From 23a1f8d44c0bca48f04fc2a2f1edafd826ce6133 Mon Sep 17 00:00:00 2001 From: Sara Sharon Date: Tue, 8 Dec 2015 16:04:31 +0200 Subject: mac80211: process and save VHT MU-MIMO group frame The Group ID Management frame is an Action frame of category VHT. It is transmitted by the AP to assign or change the user position of a STA for one or more group IDs. Process and save the group membership data. Notify underlying driver of changes. Signed-off-by: Sara Sharon Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- include/net/mac80211.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 7c30faff245f..8da483b2c067 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -298,6 +298,7 @@ struct ieee80211_vif_chanctx_switch { * note that this is only called when it changes after the channel * context had been assigned. * @BSS_CHANGED_OCB: OCB join status changed + * @BSS_CHANGED_MU_GROUPS: VHT MU-MIMO group id or user position changed */ enum ieee80211_bss_change { BSS_CHANGED_ASSOC = 1<<0, @@ -323,6 +324,7 @@ enum ieee80211_bss_change { BSS_CHANGED_BEACON_INFO = 1<<20, BSS_CHANGED_BANDWIDTH = 1<<21, BSS_CHANGED_OCB = 1<<22, + BSS_CHANGED_MU_GROUPS = 1<<23, /* when adding here, make sure to change ieee80211_reconfig */ }; @@ -435,6 +437,19 @@ struct ieee80211_event { } u; }; +/** + * struct ieee80211_mu_group_data - STA's VHT MU-MIMO group data + * + * This structure describes the group id data of VHT MU-MIMO + * + * @membership: 64 bits array - a bit is set if station is member of the group + * @position: 2 bits per group id indicating the position in the group + */ +struct ieee80211_mu_group_data { + u8 membership[WLAN_MEMBERSHIP_LEN]; + u8 position[WLAN_USER_POSITION_LEN]; +}; + /** * struct ieee80211_bss_conf - holds the BSS's changing parameters * @@ -477,6 +492,7 @@ struct ieee80211_event { * @enable_beacon: whether beaconing should be enabled or not * @chandef: Channel definition for this BSS -- the hardware might be * configured a higher bandwidth than this BSS uses, for example. + * @mu_group: VHT MU-MIMO group membership data * @ht_operation_mode: HT operation mode like in &struct ieee80211_ht_operation. * This field is only valid when the channel is a wide HT/VHT channel. * Note that with TDLS this can be the case (channel is HT, protection must @@ -535,6 +551,7 @@ struct ieee80211_bss_conf { s32 cqm_rssi_thold; u32 cqm_rssi_hyst; struct cfg80211_chan_def chandef; + struct ieee80211_mu_group_data mu_group; __be32 arp_addr_list[IEEE80211_BSS_ARP_ADDR_LIST_LEN]; int arp_addr_cnt; bool qos; -- cgit v1.2.3-71-gd317 From f9cfa5f354b11e56cd8f019c12e14a42585586cd Mon Sep 17 00:00:00 2001 From: Sara Sharon Date: Tue, 8 Dec 2015 16:04:33 +0200 Subject: mac80211: add flag for duplication check Add an option for driver to check for packet duplication by itself. This is needed for example by the iwlwifi driver which parallelizes the RX path and does the duplication check per queue. Signed-off-by: Sara Sharon Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- include/net/mac80211.h | 2 +- net/mac80211/rx.c | 3 +++ 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 8da483b2c067..ecab934dc8d9 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1063,7 +1063,7 @@ enum mac80211_rx_flags { RX_FLAG_HT_GF = BIT(13), RX_FLAG_AMPDU_DETAILS = BIT(14), RX_FLAG_PN_VALIDATED = BIT(15), - /* bit 16 free */ + RX_FLAG_DUP_VALIDATED = BIT(16), RX_FLAG_AMPDU_LAST_KNOWN = BIT(17), RX_FLAG_AMPDU_IS_LAST = BIT(18), RX_FLAG_AMPDU_DELIM_CRC_ERROR = BIT(19), diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index a5668b54015f..fe675d76f29c 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1099,6 +1099,9 @@ ieee80211_rx_h_check_dup(struct ieee80211_rx_data *rx) struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)rx->skb->data; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb); + if (status->flag & RX_FLAG_DUP_VALIDATED) + return RX_CONTINUE; + /* * Drop duplicate 802.11 retransmissions * (IEEE 802.11-2012: 9.3.2.10 "Duplicate detection and recovery") -- cgit v1.2.3-71-gd317 From fad471860c097844432c7cf5d3ae6a0a059c2bdc Mon Sep 17 00:00:00 2001 From: Sara Sharon Date: Tue, 8 Dec 2015 16:04:34 +0200 Subject: mac80211: pass RX aggregation window size to driver Currently mac80211 does not inform the driver of the window size when starting an RX aggregation session. To enable managing the reorder buffer in the driver or hardware the window size is needed. Signed-off-by: Sara Sharon Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- include/net/mac80211.h | 8 +++++--- net/mac80211/agg-rx.c | 2 +- 2 files changed, 6 insertions(+), 4 deletions(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index ecab934dc8d9..a990338a766e 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -3047,9 +3047,11 @@ enum ieee80211_reconfig_type { * ieee80211_ampdu_mlme_action. Starting sequence number (@ssn) * is the first frame we expect to perform the action on. Notice * that TX/RX_STOP can pass NULL for this parameter. - * The @buf_size parameter is only valid when the action is set to - * %IEEE80211_AMPDU_TX_OPERATIONAL and indicates the peer's reorder - * buffer size (number of subframes) for this session -- the driver + * The @buf_size parameter is valid only when the action is set to + * %IEEE80211_AMPDU_RX_START or %IEEE80211_AMPDU_TX_OPERATIONAL and + * indicates the reorder buffer size (number of subframes) for this + * session. + * When the action is set to %IEEE80211_AMPDU_TX_OPERATIONAL the driver * may neither send aggregates containing more subframes than this * nor send aggregates in a way that lost frames would exceed the * buffer size. If just limiting the aggregate size, this would be diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 10ad4ac1fa0b..78672737fe3e 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -323,7 +323,7 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta, __skb_queue_head_init(&tid_agg_rx->reorder_buf[i]); ret = drv_ampdu_action(local, sta->sdata, IEEE80211_AMPDU_RX_START, - &sta->sta, tid, &start_seq_num, 0, false); + &sta->sta, tid, &start_seq_num, buf_size, false); ht_dbg(sta->sdata, "Rx A-MPDU request on %pM tid %d result %d\n", sta->sta.addr, tid, ret); if (ret) { -- cgit v1.2.3-71-gd317 From 4352a4d7f6bfd0aed0276a13fa4993db35714db4 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 8 Dec 2015 16:04:35 +0200 Subject: mac80211: document status.freq restrictions It's not always necessary to set the status.freq field, for example when this would be an expensive calculation. It must be set for all management frames (as they might be reported to userspace), but for data frames it's not really required. Document this. Signed-off-by: Johannes Berg --- include/net/mac80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index a990338a766e..bdee1cc19c7e 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1108,6 +1108,8 @@ enum mac80211_rx_vht_flags { * it but can store it and pass it back to the driver for synchronisation * @band: the active band when this frame was received * @freq: frequency the radio was tuned to when receiving this frame, in MHz + * This field must be set for management frames, but isn't strictly needed + * for data (other) frames - for those it only affects radiotap reporting. * @signal: signal strength when receiving this frame, either in dBm, in dB or * unspecified depending on the hardware capabilities flags * @IEEE80211_HW_SIGNAL_* -- cgit v1.2.3-71-gd317 From 50ea05efaf3bed7dd34bcc2635a8b3f53bd0ccc1 Mon Sep 17 00:00:00 2001 From: Sara Sharon Date: Wed, 30 Dec 2015 16:06:04 +0200 Subject: mac80211: pass block ack session timeout to to driver Currently mac80211 does not inform the driver of the session block ack timeout when starting a rx aggregation session. Drivers that manage the reorder buffer need to know this parameter. Seeing that there are now too many arguments for the drv_ampdu_action() function, wrap them inside a structure. Signed-off-by: Sara Sharon Signed-off-by: Johannes Berg --- drivers/net/wireless/ath/ath10k/mac.c | 7 +-- drivers/net/wireless/ath/ath9k/htc_drv_main.c | 7 +-- drivers/net/wireless/ath/ath9k/main.c | 8 ++-- drivers/net/wireless/ath/carl9170/main.c | 8 ++-- drivers/net/wireless/ath/wcn36xx/main.c | 8 ++-- .../broadcom/brcm80211/brcmsmac/mac80211_if.c | 8 ++-- drivers/net/wireless/intel/iwlegacy/4965-mac.c | 8 ++-- drivers/net/wireless/intel/iwlegacy/4965.h | 4 +- drivers/net/wireless/intel/iwlwifi/dvm/mac80211.c | 9 ++-- drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 9 ++-- drivers/net/wireless/mac80211_hwsim.c | 8 ++-- drivers/net/wireless/marvell/mwl8k.c | 10 ++-- drivers/net/wireless/mediatek/mt7601u/main.c | 8 ++-- drivers/net/wireless/ralink/rt2x00/rt2800lib.c | 7 +-- drivers/net/wireless/ralink/rt2x00/rt2800lib.h | 4 +- drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.c | 6 +-- drivers/net/wireless/realtek/rtlwifi/core.c | 8 ++-- drivers/net/wireless/rsi/rsi_91x_mac80211.c | 19 +++----- drivers/net/wireless/st/cw1200/sta.c | 4 +- drivers/net/wireless/st/cw1200/sta.h | 4 +- drivers/net/wireless/ti/wlcore/main.c | 8 ++-- include/net/mac80211.h | 44 ++++++++++++------ net/mac80211/agg-rx.c | 25 ++++++++-- net/mac80211/agg-tx.c | 53 ++++++++++++++-------- net/mac80211/driver-ops.c | 10 ++-- net/mac80211/driver-ops.h | 4 +- net/mac80211/trace.h | 43 ++++++++++-------- 27 files changed, 202 insertions(+), 139 deletions(-) (limited to 'include/net') diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c index 6146a293601a..368de5e5a04f 100644 --- a/drivers/net/wireless/ath/ath10k/mac.c +++ b/drivers/net/wireless/ath/ath10k/mac.c @@ -6366,12 +6366,13 @@ static u64 ath10k_get_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif) static int ath10k_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size, bool amsdu) + struct ieee80211_ampdu_params *params) { struct ath10k *ar = hw->priv; struct ath10k_vif *arvif = ath10k_vif_to_arvif(vif); + struct ieee80211_sta *sta = params->sta; + enum ieee80211_ampdu_mlme_action action = params->action; + u16 tid = params->tid; ath10k_dbg(ar, ATH10K_DBG_MAC, "mac ampdu vdev_id %i sta %pM tid %hu action %d\n", arvif->vdev_id, sta->addr, tid, action); diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_main.c b/drivers/net/wireless/ath/ath9k/htc_drv_main.c index fe1fd1a5ae15..639294a9e34d 100644 --- a/drivers/net/wireless/ath/ath9k/htc_drv_main.c +++ b/drivers/net/wireless/ath/ath9k/htc_drv_main.c @@ -1657,13 +1657,14 @@ static void ath9k_htc_reset_tsf(struct ieee80211_hw *hw, static int ath9k_htc_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, - u16 tid, u16 *ssn, u8 buf_size, bool amsdu) + struct ieee80211_ampdu_params *params) { struct ath9k_htc_priv *priv = hw->priv; struct ath9k_htc_sta *ista; int ret = 0; + struct ieee80211_sta *sta = params->sta; + enum ieee80211_ampdu_mlme_action action = params->action; + u16 tid = params->tid; mutex_lock(&priv->mutex); ath9k_htc_ps_wakeup(priv); diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c index c1b33fdcca08..cf58a304e9f0 100644 --- a/drivers/net/wireless/ath/ath9k/main.c +++ b/drivers/net/wireless/ath/ath9k/main.c @@ -1864,14 +1864,16 @@ static void ath9k_reset_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif) static int ath9k_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, - u16 tid, u16 *ssn, u8 buf_size, bool amsdu) + struct ieee80211_ampdu_params *params) { struct ath_softc *sc = hw->priv; struct ath_common *common = ath9k_hw_common(sc->sc_ah); bool flush = false; int ret = 0; + struct ieee80211_sta *sta = params->sta; + enum ieee80211_ampdu_mlme_action action = params->action; + u16 tid = params->tid; + u16 *ssn = ¶ms->ssn; mutex_lock(&sc->mutex); diff --git a/drivers/net/wireless/ath/carl9170/main.c b/drivers/net/wireless/ath/carl9170/main.c index 19d3d64416bf..4d1527a2e292 100644 --- a/drivers/net/wireless/ath/carl9170/main.c +++ b/drivers/net/wireless/ath/carl9170/main.c @@ -1413,10 +1413,12 @@ static void carl9170_ampdu_work(struct work_struct *work) static int carl9170_op_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, - u16 tid, u16 *ssn, u8 buf_size, bool amsdu) + struct ieee80211_ampdu_params *params) { + struct ieee80211_sta *sta = params->sta; + enum ieee80211_ampdu_mlme_action action = params->action; + u16 tid = params->tid; + u16 *ssn = ¶ms->ssn; struct ar9170 *ar = hw->priv; struct carl9170_sta_info *sta_info = (void *) sta->drv_priv; struct carl9170_sta_tid *tid_info; diff --git a/drivers/net/wireless/ath/wcn36xx/main.c b/drivers/net/wireless/ath/wcn36xx/main.c index 7c169abdbafe..a27279c2c695 100644 --- a/drivers/net/wireless/ath/wcn36xx/main.c +++ b/drivers/net/wireless/ath/wcn36xx/main.c @@ -857,12 +857,14 @@ static int wcn36xx_resume(struct ieee80211_hw *hw) static int wcn36xx_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size, bool amsdu) + struct ieee80211_ampdu_params *params) { struct wcn36xx *wcn = hw->priv; struct wcn36xx_sta *sta_priv = NULL; + struct ieee80211_sta *sta = params->sta; + enum ieee80211_ampdu_mlme_action action = params->action; + u16 tid = params->tid; + u16 *ssn = ¶ms->ssn; wcn36xx_dbg(WCN36XX_DBG_MAC, "mac ampdu action action %d tid %d\n", action, tid); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c index bec2dc1ca2e4..61ae2768132a 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c @@ -818,13 +818,15 @@ brcms_ops_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif, static int brcms_ops_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size, bool amsdu) + struct ieee80211_ampdu_params *params) { struct brcms_info *wl = hw->priv; struct scb *scb = &wl->wlc->pri_scb; int status; + struct ieee80211_sta *sta = params->sta; + enum ieee80211_ampdu_mlme_action action = params->action; + u16 tid = params->tid; + u8 buf_size = params->buf_size; if (WARN_ON(scb->magic != SCB_MAGIC)) return -EIDRM; diff --git a/drivers/net/wireless/intel/iwlegacy/4965-mac.c b/drivers/net/wireless/intel/iwlegacy/4965-mac.c index fd38aa0763e4..b75f4ef3cdc7 100644 --- a/drivers/net/wireless/intel/iwlegacy/4965-mac.c +++ b/drivers/net/wireless/intel/iwlegacy/4965-mac.c @@ -5982,12 +5982,14 @@ il4965_mac_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, int il4965_mac_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 * ssn, - u8 buf_size, bool amsdu) + struct ieee80211_ampdu_params *params) { struct il_priv *il = hw->priv; int ret = -EINVAL; + struct ieee80211_sta *sta = params->sta; + enum ieee80211_ampdu_mlme_action action = params->action; + u16 tid = params->tid; + u16 *ssn = ¶ms->ssn; D_HT("A-MPDU action on addr %pM tid %d\n", sta->addr, tid); diff --git a/drivers/net/wireless/intel/iwlegacy/4965.h b/drivers/net/wireless/intel/iwlegacy/4965.h index 8ab8706f9422..e432715e02d8 100644 --- a/drivers/net/wireless/intel/iwlegacy/4965.h +++ b/drivers/net/wireless/intel/iwlegacy/4965.h @@ -182,9 +182,7 @@ void il4965_mac_update_tkip_key(struct ieee80211_hw *hw, struct ieee80211_sta *sta, u32 iv32, u16 *phase1key); int il4965_mac_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 * ssn, - u8 buf_size, bool amsdu); + struct ieee80211_ampdu_params *params); int il4965_mac_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta); void diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/dvm/mac80211.c index 29ea1c6705b4..151721e4040c 100644 --- a/drivers/net/wireless/intel/iwlwifi/dvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/dvm/mac80211.c @@ -732,12 +732,15 @@ static inline bool iwl_enable_tx_ampdu(const struct iwl_cfg *cfg) static int iwlagn_mac_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size, bool amsdu) + struct ieee80211_ampdu_params *params) { struct iwl_priv *priv = IWL_MAC80211_GET_DVM(hw); int ret = -EINVAL; + struct ieee80211_sta *sta = params->sta; + enum ieee80211_ampdu_mlme_action action = params->action; + u16 tid = params->tid; + u16 *ssn = ¶ms->ssn; + u8 buf_size = params->buf_size; struct iwl_station_priv *sta_priv = (void *) sta->drv_priv; IWL_DEBUG_HT(priv, "A-MPDU action on addr %pM tid %d\n", diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index d70a1716f3e0..1bd3f0b700d3 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -837,13 +837,16 @@ iwl_mvm_ampdu_check_trigger(struct iwl_mvm *mvm, struct ieee80211_vif *vif, static int iwl_mvm_mac_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, - u16 *ssn, u8 buf_size, bool amsdu) + struct ieee80211_ampdu_params *params) { struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw); int ret; bool tx_agg_ref = false; + struct ieee80211_sta *sta = params->sta; + enum ieee80211_ampdu_mlme_action action = params->action; + u16 tid = params->tid; + u16 *ssn = ¶ms->ssn; + u8 buf_size = params->buf_size; IWL_DEBUG_HT(mvm, "A-MPDU action on addr %pM tid %d: action %d\n", sta->addr, tid, action); diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index c32889a1e39c..e31a94fd6135 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -1845,10 +1845,12 @@ static int mac80211_hwsim_testmode_cmd(struct ieee80211_hw *hw, static int mac80211_hwsim_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size, bool amsdu) + struct ieee80211_ampdu_params *params) { + struct ieee80211_sta *sta = params->sta; + enum ieee80211_ampdu_mlme_action action = params->action; + u16 tid = params->tid; + switch (action) { case IEEE80211_AMPDU_TX_START: ieee80211_start_tx_ba_cb_irqsafe(vif, sta->addr, tid); diff --git a/drivers/net/wireless/marvell/mwl8k.c b/drivers/net/wireless/marvell/mwl8k.c index 30e3aaae32e2..088429d0a634 100644 --- a/drivers/net/wireless/marvell/mwl8k.c +++ b/drivers/net/wireless/marvell/mwl8k.c @@ -5421,11 +5421,13 @@ static int mwl8k_get_survey(struct ieee80211_hw *hw, int idx, static int mwl8k_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size, bool amsdu) + struct ieee80211_ampdu_params *params) { - + struct ieee80211_sta *sta = params->sta; + enum ieee80211_ampdu_mlme_action action = params->action; + u16 tid = params->tid; + u16 *ssn = ¶ms->ssn; + u8 buf_size = params->buf_size; int i, rc = 0; struct mwl8k_priv *priv = hw->priv; struct mwl8k_ampdu_stream *stream; diff --git a/drivers/net/wireless/mediatek/mt7601u/main.c b/drivers/net/wireless/mediatek/mt7601u/main.c index f715eee39851..e70dd9523911 100644 --- a/drivers/net/wireless/mediatek/mt7601u/main.c +++ b/drivers/net/wireless/mediatek/mt7601u/main.c @@ -334,11 +334,13 @@ static int mt7601u_set_rts_threshold(struct ieee80211_hw *hw, u32 value) static int mt76_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn, u8 buf_size, - bool amsdu) + struct ieee80211_ampdu_params *params) { struct mt7601u_dev *dev = hw->priv; + struct ieee80211_sta *sta = params->sta; + enum ieee80211_ampdu_mlme_action action = params->action; + u16 tid = params->tid; + u16 *ssn = ¶ms->ssn; struct mt76_sta *msta = (struct mt76_sta *) sta->drv_priv; WARN_ON(msta->wcid.idx > GROUP_WCID(0)); diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c index 9733b31a780d..69c1c09687a3 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c @@ -7935,10 +7935,11 @@ u64 rt2800_get_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif) EXPORT_SYMBOL_GPL(rt2800_get_tsf); int rt2800_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size, bool amsdu) + struct ieee80211_ampdu_params *params) { + struct ieee80211_sta *sta = params->sta; + enum ieee80211_ampdu_mlme_action action = params->action; + u16 tid = params->tid; struct rt2x00_sta *sta_priv = (struct rt2x00_sta *)sta->drv_priv; int ret = 0; diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800lib.h b/drivers/net/wireless/ralink/rt2x00/rt2800lib.h index 440790b92b19..83f1a44fb9b4 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2800lib.h +++ b/drivers/net/wireless/ralink/rt2x00/rt2800lib.h @@ -218,9 +218,7 @@ int rt2800_conf_tx(struct ieee80211_hw *hw, const struct ieee80211_tx_queue_params *params); u64 rt2800_get_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif); int rt2800_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size, bool amsdu); + struct ieee80211_ampdu_params *params); int rt2800_get_survey(struct ieee80211_hw *hw, int idx, struct survey_info *survey); void rt2800_disable_wpdma(struct rt2x00_dev *rt2x00dev); diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.c index 6aed923a709a..7d820c395375 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.c @@ -5375,13 +5375,13 @@ static int rtl8xxxu_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, static int rtl8xxxu_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn, u8 buf_size, - bool amsdu) + struct ieee80211_ampdu_params *params) { struct rtl8xxxu_priv *priv = hw->priv; struct device *dev = &priv->udev->dev; u8 ampdu_factor, ampdu_density; + struct ieee80211_sta *sta = params->sta; + enum ieee80211_ampdu_mlme_action action = params->action; switch (action) { case IEEE80211_AMPDU_TX_START: diff --git a/drivers/net/wireless/realtek/rtlwifi/core.c b/drivers/net/wireless/realtek/rtlwifi/core.c index 4ae421ef30d9..f2507610314b 100644 --- a/drivers/net/wireless/realtek/rtlwifi/core.c +++ b/drivers/net/wireless/realtek/rtlwifi/core.c @@ -1371,11 +1371,13 @@ static void rtl_op_sta_notify(struct ieee80211_hw *hw, static int rtl_op_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size, bool amsdu) + struct ieee80211_ampdu_params *params) { struct rtl_priv *rtlpriv = rtl_priv(hw); + struct ieee80211_sta *sta = params->sta; + enum ieee80211_ampdu_mlme_action action = params->action; + u16 tid = params->tid; + u16 *ssn = ¶ms->ssn; switch (action) { case IEEE80211_AMPDU_TX_START: diff --git a/drivers/net/wireless/rsi/rsi_91x_mac80211.c b/drivers/net/wireless/rsi/rsi_91x_mac80211.c index b5bcc933a2a6..4df992de7d07 100644 --- a/drivers/net/wireless/rsi/rsi_91x_mac80211.c +++ b/drivers/net/wireless/rsi/rsi_91x_mac80211.c @@ -659,29 +659,24 @@ static int rsi_mac80211_set_key(struct ieee80211_hw *hw, * informs the f/w regarding this. * @hw: Pointer to the ieee80211_hw structure. * @vif: Pointer to the ieee80211_vif structure. - * @action: ieee80211_ampdu_mlme_action enum. - * @sta: Pointer to the ieee80211_sta structure. - * @tid: Traffic identifier. - * @ssn: Pointer to ssn value. - * @buf_size: Buffer size (for kernel version > 2.6.38). - * @amsdu: is AMSDU in AMPDU allowed + * @params: Pointer to A-MPDU action parameters * * Return: status: 0 on success, negative error code on failure. */ static int rsi_mac80211_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, - unsigned short tid, - unsigned short *ssn, - unsigned char buf_size, - bool amsdu) + struct ieee80211_ampdu_params *params) { int status = -EOPNOTSUPP; struct rsi_hw *adapter = hw->priv; struct rsi_common *common = adapter->priv; u16 seq_no = 0; u8 ii = 0; + struct ieee80211_sta *sta = params->sta; + enum ieee80211_ampdu_mlme_action action = params->action; + u16 tid = params->tid; + u16 *ssn = ¶ms->ssn; + u8 buf_size = params->buf_size; for (ii = 0; ii < RSI_MAX_VIFS; ii++) { if (vif == adapter->vifs[ii]) diff --git a/drivers/net/wireless/st/cw1200/sta.c b/drivers/net/wireless/st/cw1200/sta.c index 06321c799c90..d0ddcde6c695 100644 --- a/drivers/net/wireless/st/cw1200/sta.c +++ b/drivers/net/wireless/st/cw1200/sta.c @@ -2129,9 +2129,7 @@ void cw1200_mcast_timeout(unsigned long arg) int cw1200_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size, bool amsdu) + struct ieee80211_ampdu_params *params) { /* Aggregation is implemented fully in firmware, * including block ack negotiation. Do not allow diff --git a/drivers/net/wireless/st/cw1200/sta.h b/drivers/net/wireless/st/cw1200/sta.h index bebb3379017f..a0bacaa39b31 100644 --- a/drivers/net/wireless/st/cw1200/sta.h +++ b/drivers/net/wireless/st/cw1200/sta.h @@ -109,9 +109,7 @@ void cw1200_bss_info_changed(struct ieee80211_hw *dev, u32 changed); int cw1200_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size, bool amsdu); + struct ieee80211_ampdu_params *params); void cw1200_suspend_resume(struct cw1200_common *priv, struct wsm_suspend_resume *arg); diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c index d1109c4f0f0d..45662cf3169f 100644 --- a/drivers/net/wireless/ti/wlcore/main.c +++ b/drivers/net/wireless/ti/wlcore/main.c @@ -5187,14 +5187,16 @@ out: static int wl1271_op_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size, bool amsdu) + struct ieee80211_ampdu_params *params) { struct wl1271 *wl = hw->priv; struct wl12xx_vif *wlvif = wl12xx_vif_to_data(vif); int ret; u8 hlid, *ba_bitmap; + struct ieee80211_sta *sta = params->sta; + enum ieee80211_ampdu_mlme_action action = params->action; + u16 tid = params->tid; + u16 *ssn = ¶ms->ssn; wl1271_debug(DEBUG_MAC80211, "mac80211 ampdu action %d tid %d", action, tid); diff --git a/include/net/mac80211.h b/include/net/mac80211.h index bdee1cc19c7e..6c9c559394b0 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2702,6 +2702,33 @@ enum ieee80211_ampdu_mlme_action { IEEE80211_AMPDU_TX_OPERATIONAL, }; +/** + * struct ieee80211_ampdu_params - AMPDU action parameters + * + * @action: the ampdu action, value from %ieee80211_ampdu_mlme_action. + * @sta: peer of this AMPDU session + * @tid: tid of the BA session + * @ssn: start sequence number of the session. TX/RX_STOP can pass 0. When + * action is set to %IEEE80211_AMPDU_RX_START the driver passes back the + * actual ssn value used to start the session and writes the value here. + * @buf_size: reorder buffer size (number of subframes). Valid only when the + * action is set to %IEEE80211_AMPDU_RX_START or + * %IEEE80211_AMPDU_TX_OPERATIONAL + * @amsdu: indicates the peer's ability to receive A-MSDU within A-MPDU. + * valid when the action is set to %IEEE80211_AMPDU_TX_OPERATIONAL + * @timeout: BA session timeout. Valid only when the action is set to + * %IEEE80211_AMPDU_RX_START + */ +struct ieee80211_ampdu_params { + enum ieee80211_ampdu_mlme_action action; + struct ieee80211_sta *sta; + u16 tid; + u16 ssn; + u8 buf_size; + bool amsdu; + u16 timeout; +}; + /** * enum ieee80211_frame_release_type - frame release reason * @IEEE80211_FRAME_RELEASE_PSPOLL: frame released for PS-Poll @@ -3046,15 +3073,9 @@ enum ieee80211_reconfig_type { * @ampdu_action: Perform a certain A-MPDU action * The RA/TID combination determines the destination and TID we want * the ampdu action to be performed for. The action is defined through - * ieee80211_ampdu_mlme_action. Starting sequence number (@ssn) - * is the first frame we expect to perform the action on. Notice - * that TX/RX_STOP can pass NULL for this parameter. - * The @buf_size parameter is valid only when the action is set to - * %IEEE80211_AMPDU_RX_START or %IEEE80211_AMPDU_TX_OPERATIONAL and - * indicates the reorder buffer size (number of subframes) for this - * session. + * ieee80211_ampdu_mlme_action. * When the action is set to %IEEE80211_AMPDU_TX_OPERATIONAL the driver - * may neither send aggregates containing more subframes than this + * may neither send aggregates containing more subframes than @buf_size * nor send aggregates in a way that lost frames would exceed the * buffer size. If just limiting the aggregate size, this would be * possible with a buf_size of 8: @@ -3065,9 +3086,6 @@ enum ieee80211_reconfig_type { * buffer size of 8. Correct ways to retransmit #1 would be: * - TX: 1 or 18 or 81 * Even "189" would be wrong since 1 could be lost again. - * The @amsdu parameter is valid when the action is set to - * %IEEE80211_AMPDU_TX_OPERATIONAL and indicates the peer's ability - * to receive A-MSDU within A-MPDU. * * Returns a negative error code on failure. * The callback can sleep. @@ -3409,9 +3427,7 @@ struct ieee80211_ops { int (*tx_last_beacon)(struct ieee80211_hw *hw); int (*ampdu_action)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size, bool amsdu); + struct ieee80211_ampdu_params *params); int (*get_survey)(struct ieee80211_hw *hw, int idx, struct survey_info *survey); void (*rfkill_poll)(struct ieee80211_hw *hw); diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 78672737fe3e..ec80db7c955c 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -7,6 +7,7 @@ * Copyright 2006-2007 Jiri Benc * Copyright 2007, Michael Wu * Copyright 2007-2010, Intel Corporation + * Copyright(c) 2015 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -61,6 +62,14 @@ void ___ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid, { struct ieee80211_local *local = sta->local; struct tid_ampdu_rx *tid_rx; + struct ieee80211_ampdu_params params = { + .sta = &sta->sta, + .action = IEEE80211_AMPDU_RX_STOP, + .tid = tid, + .amsdu = false, + .timeout = 0, + .ssn = 0, + }; lockdep_assert_held(&sta->ampdu_mlme.mtx); @@ -78,8 +87,7 @@ void ___ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid, initiator == WLAN_BACK_RECIPIENT ? "recipient" : "inititator", (int)reason); - if (drv_ampdu_action(local, sta->sdata, IEEE80211_AMPDU_RX_STOP, - &sta->sta, tid, NULL, 0, false)) + if (drv_ampdu_action(local, sta->sdata, ¶ms)) sdata_info(sta->sdata, "HW problem - can not stop rx aggregation for %pM tid %d\n", sta->sta.addr, tid); @@ -237,6 +245,15 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta, { struct ieee80211_local *local = sta->sdata->local; struct tid_ampdu_rx *tid_agg_rx; + struct ieee80211_ampdu_params params = { + .sta = &sta->sta, + .action = IEEE80211_AMPDU_RX_START, + .tid = tid, + .amsdu = false, + .timeout = timeout, + .ssn = start_seq_num, + }; + int i, ret = -EOPNOTSUPP; u16 status = WLAN_STATUS_REQUEST_DECLINED; @@ -275,6 +292,7 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta, /* make sure the size doesn't exceed the maximum supported by the hw */ if (buf_size > local->hw.max_rx_aggregation_subframes) buf_size = local->hw.max_rx_aggregation_subframes; + params.buf_size = buf_size; /* examine state machine */ mutex_lock(&sta->ampdu_mlme.mtx); @@ -322,8 +340,7 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta, for (i = 0; i < buf_size; i++) __skb_queue_head_init(&tid_agg_rx->reorder_buf[i]); - ret = drv_ampdu_action(local, sta->sdata, IEEE80211_AMPDU_RX_START, - &sta->sta, tid, &start_seq_num, buf_size, false); + ret = drv_ampdu_action(local, sta->sdata, ¶ms); ht_dbg(sta->sdata, "Rx A-MPDU request on %pM tid %d result %d\n", sta->sta.addr, tid, ret); if (ret) { diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index ff757181b0a8..4932e9f243a2 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -7,6 +7,7 @@ * Copyright 2006-2007 Jiri Benc * Copyright 2007, Michael Wu * Copyright 2007-2010, Intel Corporation + * Copyright(c) 2015 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -295,7 +296,14 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, { struct ieee80211_local *local = sta->local; struct tid_ampdu_tx *tid_tx; - enum ieee80211_ampdu_mlme_action action; + struct ieee80211_ampdu_params params = { + .sta = &sta->sta, + .tid = tid, + .buf_size = 0, + .amsdu = false, + .timeout = 0, + .ssn = 0, + }; int ret; lockdep_assert_held(&sta->ampdu_mlme.mtx); @@ -304,10 +312,10 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, case AGG_STOP_DECLINED: case AGG_STOP_LOCAL_REQUEST: case AGG_STOP_PEER_REQUEST: - action = IEEE80211_AMPDU_TX_STOP_CONT; + params.action = IEEE80211_AMPDU_TX_STOP_CONT; break; case AGG_STOP_DESTROY_STA: - action = IEEE80211_AMPDU_TX_STOP_FLUSH; + params.action = IEEE80211_AMPDU_TX_STOP_FLUSH; break; default: WARN_ON_ONCE(1); @@ -330,9 +338,8 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, spin_unlock_bh(&sta->lock); if (reason != AGG_STOP_DESTROY_STA) return -EALREADY; - ret = drv_ampdu_action(local, sta->sdata, - IEEE80211_AMPDU_TX_STOP_FLUSH_CONT, - &sta->sta, tid, NULL, 0, false); + params.action = IEEE80211_AMPDU_TX_STOP_FLUSH_CONT; + ret = drv_ampdu_action(local, sta->sdata, ¶ms); WARN_ON_ONCE(ret); return 0; } @@ -381,8 +388,7 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, WLAN_BACK_INITIATOR; tid_tx->tx_stop = reason == AGG_STOP_LOCAL_REQUEST; - ret = drv_ampdu_action(local, sta->sdata, action, - &sta->sta, tid, NULL, 0, false); + ret = drv_ampdu_action(local, sta->sdata, ¶ms); /* HW shall not deny going back to legacy */ if (WARN_ON(ret)) { @@ -445,7 +451,14 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) struct tid_ampdu_tx *tid_tx; struct ieee80211_local *local = sta->local; struct ieee80211_sub_if_data *sdata = sta->sdata; - u16 start_seq_num; + struct ieee80211_ampdu_params params = { + .sta = &sta->sta, + .action = IEEE80211_AMPDU_TX_START, + .tid = tid, + .buf_size = 0, + .amsdu = false, + .timeout = 0, + }; int ret; tid_tx = rcu_dereference_protected_tid_tx(sta, tid); @@ -467,10 +480,8 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) */ synchronize_net(); - start_seq_num = sta->tid_seq[tid] >> 4; - - ret = drv_ampdu_action(local, sdata, IEEE80211_AMPDU_TX_START, - &sta->sta, tid, &start_seq_num, 0, false); + params.ssn = sta->tid_seq[tid] >> 4; + ret = drv_ampdu_action(local, sdata, ¶ms); if (ret) { ht_dbg(sdata, "BA request denied - HW unavailable for %pM tid %d\n", @@ -499,7 +510,7 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) /* send AddBA request */ ieee80211_send_addba_request(sdata, sta->sta.addr, tid, - tid_tx->dialog_token, start_seq_num, + tid_tx->dialog_token, params.ssn, IEEE80211_MAX_AMPDU_BUF, tid_tx->timeout); } @@ -684,18 +695,24 @@ static void ieee80211_agg_tx_operational(struct ieee80211_local *local, struct sta_info *sta, u16 tid) { struct tid_ampdu_tx *tid_tx; + struct ieee80211_ampdu_params params = { + .sta = &sta->sta, + .action = IEEE80211_AMPDU_TX_OPERATIONAL, + .tid = tid, + .timeout = 0, + .ssn = 0, + }; lockdep_assert_held(&sta->ampdu_mlme.mtx); tid_tx = rcu_dereference_protected_tid_tx(sta, tid); + params.buf_size = tid_tx->buf_size; + params.amsdu = tid_tx->amsdu; ht_dbg(sta->sdata, "Aggregation is on for %pM tid %d\n", sta->sta.addr, tid); - drv_ampdu_action(local, sta->sdata, - IEEE80211_AMPDU_TX_OPERATIONAL, - &sta->sta, tid, NULL, tid_tx->buf_size, - tid_tx->amsdu); + drv_ampdu_action(local, sta->sdata, ¶ms); /* * synchronize with TX path, while splicing the TX path diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c index ca1fe5576103..c258f1041d33 100644 --- a/net/mac80211/driver-ops.c +++ b/net/mac80211/driver-ops.c @@ -284,9 +284,7 @@ int drv_switch_vif_chanctx(struct ieee80211_local *local, int drv_ampdu_action(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, - u16 *ssn, u8 buf_size, bool amsdu) + struct ieee80211_ampdu_params *params) { int ret = -EOPNOTSUPP; @@ -296,12 +294,10 @@ int drv_ampdu_action(struct ieee80211_local *local, if (!check_sdata_in_driver(sdata)) return -EIO; - trace_drv_ampdu_action(local, sdata, action, sta, tid, - ssn, buf_size, amsdu); + trace_drv_ampdu_action(local, sdata, params); if (local->ops->ampdu_action) - ret = local->ops->ampdu_action(&local->hw, &sdata->vif, action, - sta, tid, ssn, buf_size, amsdu); + ret = local->ops->ampdu_action(&local->hw, &sdata->vif, params); trace_drv_return_int(local, ret); diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 154ce4b13406..18b0d65baff0 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -585,9 +585,7 @@ static inline int drv_tx_last_beacon(struct ieee80211_local *local) int drv_ampdu_action(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, - u16 *ssn, u8 buf_size, bool amsdu); + struct ieee80211_ampdu_params *params); static inline int drv_get_survey(struct ieee80211_local *local, int idx, struct survey_info *survey) diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index a6b4442776a0..2b0a17ee907a 100644 --- a/net/mac80211/trace.h +++ b/net/mac80211/trace.h @@ -80,7 +80,23 @@ #define KEY_PR_FMT " cipher:0x%x, flags=%#x, keyidx=%d, hw_key_idx=%d" #define KEY_PR_ARG __entry->cipher, __entry->flags, __entry->keyidx, __entry->hw_key_idx - +#define AMPDU_ACTION_ENTRY __field(enum ieee80211_ampdu_mlme_action, \ + ieee80211_ampdu_mlme_action) \ + STA_ENTRY \ + __field(u16, tid) \ + __field(u16, ssn) \ + __field(u8, buf_size) \ + __field(bool, amsdu) \ + __field(u16, timeout) +#define AMPDU_ACTION_ASSIGN STA_NAMED_ASSIGN(params->sta); \ + __entry->tid = params->tid; \ + __entry->ssn = params->ssn; \ + __entry->buf_size = params->buf_size; \ + __entry->amsdu = params->amsdu; \ + __entry->timeout = params->timeout; +#define AMPDU_ACTION_PR_FMT STA_PR_FMT " tid %d, ssn %d, buf_size %u, amsdu %d, timeout %d" +#define AMPDU_ACTION_PR_ARG STA_PR_ARG, __entry->tid, __entry->ssn, \ + __entry->buf_size, __entry->amsdu, __entry->timeout /* * Tracing for driver callbacks. @@ -970,38 +986,25 @@ DEFINE_EVENT(local_only_evt, drv_tx_last_beacon, TRACE_EVENT(drv_ampdu_action, TP_PROTO(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, - u16 *ssn, u8 buf_size, bool amsdu), + struct ieee80211_ampdu_params *params), - TP_ARGS(local, sdata, action, sta, tid, ssn, buf_size, amsdu), + TP_ARGS(local, sdata, params), TP_STRUCT__entry( LOCAL_ENTRY - STA_ENTRY - __field(u32, action) - __field(u16, tid) - __field(u16, ssn) - __field(u8, buf_size) - __field(bool, amsdu) VIF_ENTRY + AMPDU_ACTION_ENTRY ), TP_fast_assign( LOCAL_ASSIGN; VIF_ASSIGN; - STA_ASSIGN; - __entry->action = action; - __entry->tid = tid; - __entry->ssn = ssn ? *ssn : 0; - __entry->buf_size = buf_size; - __entry->amsdu = amsdu; + AMPDU_ACTION_ASSIGN; ), TP_printk( - LOCAL_PR_FMT VIF_PR_FMT STA_PR_FMT " action:%d tid:%d buf:%d amsdu:%d", - LOCAL_PR_ARG, VIF_PR_ARG, STA_PR_ARG, __entry->action, - __entry->tid, __entry->buf_size, __entry->amsdu + LOCAL_PR_FMT VIF_PR_FMT AMPDU_ACTION_PR_FMT, + LOCAL_PR_ARG, VIF_PR_ARG, AMPDU_ACTION_PR_ARG ) ); -- cgit v1.2.3-71-gd317 From 61d2bcae99f66a640b3dd9632180209143fb5512 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 1 Feb 2016 21:03:07 -0800 Subject: tcp: fastopen: accept data/FIN present in SYNACK message RFC 7413 (TCP Fast Open) 4.2.2 states that the SYNACK message MAY include data and/or FIN This patch adds support for the client side : If we receive a SYNACK with payload or FIN, queue the skb instead of ignoring it. Since we already support the same for SYN, we refactor the existing code and reuse it. Note we need to clone the skb, so this operation might fail under memory pressure. Sara Dickinson pointed out FreeBSD server Fast Open implementation was planned to generate such SYNACK in the future. The server side might be implemented on linux later. Reported-by: Sara Dickinson Signed-off-by: Eric Dumazet Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Signed-off-by: David S. Miller --- include/net/tcp.h | 1 + net/ipv4/tcp_fastopen.c | 64 ++++++++++++++++++++++++++----------------------- net/ipv4/tcp_input.c | 3 +++ 3 files changed, 38 insertions(+), 30 deletions(-) (limited to 'include/net') diff --git a/include/net/tcp.h b/include/net/tcp.h index f6f8f032c73e..27f4c733116d 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1437,6 +1437,7 @@ void tcp_free_fastopen_req(struct tcp_sock *tp); extern struct tcp_fastopen_context __rcu *tcp_fastopen_ctx; int tcp_fastopen_reset_cipher(void *key, unsigned int len); +void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb); struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct tcp_fastopen_cookie *foc, diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 55be6ac70cff..467d3e985411 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -124,6 +124,35 @@ static bool tcp_fastopen_cookie_gen(struct request_sock *req, return false; } + +/* If an incoming SYN or SYNACK frame contains a payload and/or FIN, + * queue this additional data / FIN. + */ +void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (TCP_SKB_CB(skb)->end_seq == tp->rcv_nxt) + return; + + skb = skb_clone(skb, GFP_ATOMIC); + if (!skb) + return; + + skb_dst_drop(skb); + __skb_pull(skb, tcp_hdrlen(skb)); + skb_set_owner_r(skb, sk); + + tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq; + __skb_queue_tail(&sk->sk_receive_queue, skb); + tp->syn_data_acked = 1; + + /* u64_stats_update_begin(&tp->syncp) not needed here, + * as we certainly are not changing upper 32bit value (0) + */ + tp->bytes_received = skb->len; +} + static struct sock *tcp_fastopen_create_child(struct sock *sk, struct sk_buff *skb, struct dst_entry *dst, @@ -132,7 +161,6 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, struct tcp_sock *tp; struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; struct sock *child; - u32 end_seq; bool own_req; req->num_retrans = 0; @@ -178,35 +206,11 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, tcp_init_metrics(child); tcp_init_buffer_space(child); - /* Queue the data carried in the SYN packet. - * We used to play tricky games with skb_get(). - * With lockless listener, it is a dead end. - * Do not think about it. - * - * XXX (TFO) - we honor a zero-payload TFO request for now, - * (any reason not to?) but no need to queue the skb since - * there is no data. How about SYN+FIN? - */ - end_seq = TCP_SKB_CB(skb)->end_seq; - if (end_seq != TCP_SKB_CB(skb)->seq + 1) { - struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); - - if (likely(skb2)) { - skb_dst_drop(skb2); - __skb_pull(skb2, tcp_hdrlen(skb)); - skb_set_owner_r(skb2, child); - __skb_queue_tail(&child->sk_receive_queue, skb2); - tp->syn_data_acked = 1; - - /* u64_stats_update_begin(&tp->syncp) not needed here, - * as we certainly are not changing upper 32bit value (0) - */ - tp->bytes_received = end_seq - TCP_SKB_CB(skb)->seq - 1; - } else { - end_seq = TCP_SKB_CB(skb)->seq + 1; - } - } - tcp_rsk(req)->rcv_nxt = tp->rcv_nxt = end_seq; + tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; + + tcp_fastopen_add_skb(child, skb); + + tcp_rsk(req)->rcv_nxt = tp->rcv_nxt; /* tcp_conn_request() is sending the SYNACK, * and queues the child into listener accept queue. */ diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 1c2a73406261..4add3eb40e58 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5509,6 +5509,9 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, tp->syn_data_acked = tp->syn_data; if (tp->syn_data_acked) NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVE); + + tcp_fastopen_add_skb(sk, synack); + return false; } -- cgit v1.2.3-71-gd317 From e3e17b773bfe45462b7f3fae20c550025975cb13 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 6 Feb 2016 11:16:28 -0800 Subject: tcp: fastopen: call tcp_fin() if FIN present in SYNACK When we acknowledge a FIN, it is not enough to ack the sequence number and queue the skb into receive queue. We also have to call tcp_fin() to properly update socket state and send proper poll() notifications. It seems we also had the problem if we received a SYN packet with the FIN flag set, but it does not seem an urgent issue, as no known implementation can do that. Fixes: 61d2bcae99f6 ("tcp: fastopen: accept data/FIN present in SYNACK message") Signed-off-by: Eric Dumazet Cc: Yuchung Cheng Cc: Neal Cardwell Signed-off-by: David S. Miller --- include/net/tcp.h | 1 + net/ipv4/tcp_fastopen.c | 3 +++ net/ipv4/tcp_input.c | 2 +- 3 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/tcp.h b/include/net/tcp.h index 27f4c733116d..479d535609fd 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -568,6 +568,7 @@ void tcp_rearm_rto(struct sock *sk); void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req); void tcp_reset(struct sock *sk); void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb); +void tcp_fin(struct sock *sk); /* tcp_timer.c */ void tcp_init_xmit_timers(struct sock *); diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 6a6e11e54bae..fdb286ddba04 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -154,6 +154,9 @@ void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb) * as we certainly are not changing upper 32bit value (0) */ tp->bytes_received = skb->len; + + if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) + tcp_fin(sk); } static struct sock *tcp_fastopen_create_child(struct sock *sk, diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 4add3eb40e58..8194a250a01e 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3995,7 +3995,7 @@ void tcp_reset(struct sock *sk) * * If we are in FINWAIT-2, a received FIN moves us to TIME-WAIT. */ -static void tcp_fin(struct sock *sk) +void tcp_fin(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); -- cgit v1.2.3-71-gd317 From 0e715d6fbd2a4a1dcd215d6d51091346e6a3d3fa Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Tue, 2 Feb 2016 18:09:11 +0100 Subject: vxlan: cleanup types include/net/vxlan.h is a kernel header, no need to prefix fixed size types with double underscore. Signed-off-by: Jiri Benc Signed-off-by: David S. Miller --- include/net/vxlan.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/net') diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 0fb86442544b..5c64250619c5 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -30,15 +30,15 @@ * [0] https://tools.ietf.org/html/draft-smith-vxlan-group-policy */ struct vxlanhdr_gbp { - __u8 vx_flags; + u8 vx_flags; #ifdef __LITTLE_ENDIAN_BITFIELD - __u8 reserved_flags1:3, + u8 reserved_flags1:3, policy_applied:1, reserved_flags2:2, dont_learn:1, reserved_flags3:1; #elif defined(__BIG_ENDIAN_BITFIELD) - __u8 reserved_flags1:1, + u8 reserved_flags1:1, dont_learn:1, reserved_flags2:2, policy_applied:1, @@ -138,10 +138,10 @@ struct vxlan_config { int remote_ifindex; int mtu; __be16 dst_port; - __u16 port_min; - __u16 port_max; - __u8 tos; - __u8 ttl; + u16 port_min; + u16 port_max; + u8 tos; + u8 ttl; u32 flags; unsigned long age_interval; unsigned int addrmax; -- cgit v1.2.3-71-gd317 From 427bc465bf9fcdab749f6997ff7a4eecaef4ca40 Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Tue, 2 Feb 2016 18:09:12 +0100 Subject: vxlan: remove duplicated macros VNI_HASH_BITS and VNI_HASH_SIZE are defined twice. Remove the extra definitions. Signed-off-by: Jiri Benc Signed-off-by: David S. Miller --- include/net/vxlan.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/net') diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 5c64250619c5..234bf1ef2737 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -9,9 +9,6 @@ #include #include -#define VNI_HASH_BITS 10 -#define VNI_HASH_SIZE (1< Date: Tue, 2 Feb 2016 18:09:13 +0100 Subject: vxlan: restructure vxlan.h definitions RCO and GBP are VXLAN extensions, not specified in RFC 7348. Because of that, they need to be explicitly enabled when creating vxlan interface. By default, those extensions are not used and plain VXLAN header is sent and received. Reflect this in vxlan.h: first, the plain VXLAN header is defined. Following it, RCO is documented and defined, and likewise for GBP. Signed-off-by: Jiri Benc Signed-off-by: David S. Miller --- include/net/vxlan.h | 104 +++++++++++++++++++++++++++++++--------------------- 1 file changed, 63 insertions(+), 41 deletions(-) (limited to 'include/net') diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 234bf1ef2737..25bd919c9ef0 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -9,14 +9,71 @@ #include #include +/* VXLAN protocol (RFC 7348) header: + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * |R|R|R|R|I|R|R|R| Reserved | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | VXLAN Network Identifier (VNI) | Reserved | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * + * I = VXLAN Network Identifier (VNI) present. + */ +struct vxlanhdr { + __be32 vx_flags; + __be32 vx_vni; +}; + +/* VXLAN header flags. */ +#define VXLAN_HF_VNI BIT(27) + +#define VXLAN_N_VID (1u << 24) +#define VXLAN_VID_MASK (VXLAN_N_VID - 1) +#define VXLAN_VNI_MASK (VXLAN_VID_MASK << 8) +#define VXLAN_HLEN (sizeof(struct udphdr) + sizeof(struct vxlanhdr)) + +#define VNI_HASH_BITS 10 +#define VNI_HASH_SIZE (1<mark mapping @@ -59,44 +119,6 @@ struct vxlanhdr_gbp { #define VXLAN_GBP_POLICY_APPLIED (BIT(3) << 16) #define VXLAN_GBP_ID_MASK (0xFFFF) -/* VXLAN protocol header: - * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - * |G|R|R|R|I|R|R|C| Reserved | - * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - * | VXLAN Network Identifier (VNI) | Reserved | - * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - * - * G = 1 Group Policy (VXLAN-GBP) - * I = 1 VXLAN Network Identifier (VNI) present - * C = 1 Remote checksum offload (RCO) - */ -struct vxlanhdr { - __be32 vx_flags; - __be32 vx_vni; -}; - -/* VXLAN header flags. */ -#define VXLAN_HF_RCO BIT(21) -#define VXLAN_HF_VNI BIT(27) -#define VXLAN_HF_GBP BIT(31) - -/* Remote checksum offload header option */ -#define VXLAN_RCO_MASK 0x7f /* Last byte of vni field */ -#define VXLAN_RCO_UDP 0x80 /* Indicate UDP RCO (TCP when not set *) */ -#define VXLAN_RCO_SHIFT 1 /* Left shift of start */ -#define VXLAN_RCO_SHIFT_MASK ((1 << VXLAN_RCO_SHIFT) - 1) -#define VXLAN_MAX_REMCSUM_START (VXLAN_RCO_MASK << VXLAN_RCO_SHIFT) - -#define VXLAN_N_VID (1u << 24) -#define VXLAN_VID_MASK (VXLAN_N_VID - 1) -#define VXLAN_VNI_MASK (VXLAN_VID_MASK << 8) -#define VXLAN_HLEN (sizeof(struct udphdr) + sizeof(struct vxlanhdr)) - -#define VNI_HASH_BITS 10 -#define VNI_HASH_SIZE (1< Date: Wed, 3 Feb 2016 09:46:49 +0200 Subject: ipv4: Namespaceify tcp syn retries sysctl knob Signed-off-by: Nikolay Borisov Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 2 ++ include/net/tcp.h | 1 - net/ipv4/sysctl_net_ipv4.c | 18 +++++++++--------- net/ipv4/tcp.c | 3 ++- net/ipv4/tcp_ipv4.c | 2 ++ net/ipv4/tcp_timer.c | 4 ++-- 6 files changed, 17 insertions(+), 13 deletions(-) (limited to 'include/net') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 2b7907a35568..b7b5bd64df35 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -98,6 +98,8 @@ struct netns_ipv4 { int sysctl_tcp_keepalive_probes; int sysctl_tcp_keepalive_intvl; + int sysctl_tcp_syn_retries; + struct ping_group_range ping_group_range; atomic_t dev_addr_genid; diff --git a/include/net/tcp.h b/include/net/tcp.h index 479d535609fd..825485c7cc1a 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -240,7 +240,6 @@ extern int sysctl_tcp_timestamps; extern int sysctl_tcp_window_scaling; extern int sysctl_tcp_sack; extern int sysctl_tcp_fin_timeout; -extern int sysctl_tcp_syn_retries; extern int sysctl_tcp_synack_retries; extern int sysctl_tcp_retries1; extern int sysctl_tcp_retries2; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 4d367b4139a3..ae9dd8823134 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -291,15 +291,6 @@ static struct ctl_table ipv4_table[] = { .extra1 = &ip_ttl_min, .extra2 = &ip_ttl_max, }, - { - .procname = "tcp_syn_retries", - .data = &sysctl_tcp_syn_retries, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &tcp_syn_retries_min, - .extra2 = &tcp_syn_retries_max - }, { .procname = "tcp_synack_retries", .data = &sysctl_tcp_synack_retries, @@ -960,6 +951,15 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, + { + .procname = "tcp_syn_retries", + .data = &init_net.ipv4.sysctl_tcp_syn_retries, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &tcp_syn_retries_min, + .extra2 = &tcp_syn_retries_max + }, { } }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index c5075779e017..3dbb3637bb4b 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2731,6 +2731,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level, { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); + struct net *net = sock_net(sk); int val, len; if (get_user(len, optlen)) @@ -2765,7 +2766,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level, val = keepalive_probes(tp); break; case TCP_SYNCNT: - val = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries; + val = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries; break; case TCP_LINGER2: val = tp->linger2; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a4d523709ab3..f7464852aaa1 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2388,6 +2388,8 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_keepalive_probes = TCP_KEEPALIVE_PROBES; net->ipv4.sysctl_tcp_keepalive_intvl = TCP_KEEPALIVE_INTVL; + net->ipv4.sysctl_tcp_syn_retries = TCP_SYN_RETRIES; + return 0; fail: tcp_sk_exit(net); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index a4730a28b220..c5d51f530c65 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -22,7 +22,6 @@ #include #include -int sysctl_tcp_syn_retries __read_mostly = TCP_SYN_RETRIES; int sysctl_tcp_synack_retries __read_mostly = TCP_SYNACK_RETRIES; int sysctl_tcp_retries1 __read_mostly = TCP_RETR1; int sysctl_tcp_retries2 __read_mostly = TCP_RETR2; @@ -157,6 +156,7 @@ static int tcp_write_timeout(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); + struct net *net = sock_net(sk); int retry_until; bool do_reset, syn_set = false; @@ -169,7 +169,7 @@ static int tcp_write_timeout(struct sock *sk) NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVEFAIL); } - retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries; + retry_until = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries; syn_set = true; } else { if (retransmits_timed_out(sk, sysctl_tcp_retries1, 0, 0)) { -- cgit v1.2.3-71-gd317 From 7c083ecb3ba4583a625d5ff9655d1a819e374493 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Wed, 3 Feb 2016 09:46:50 +0200 Subject: ipv4: Namespaceify tcp synack retries sysctl knob Signed-off-by: Nikolay Borisov Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 1 + include/net/tcp.h | 1 - net/ipv4/inet_connection_sock.c | 7 ++----- net/ipv4/sysctl_net_ipv4.c | 14 +++++++------- net/ipv4/tcp_ipv4.c | 1 + net/ipv4/tcp_timer.c | 3 +-- 6 files changed, 12 insertions(+), 15 deletions(-) (limited to 'include/net') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index b7b5bd64df35..9e83084ab8c1 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -99,6 +99,7 @@ struct netns_ipv4 { int sysctl_tcp_keepalive_intvl; int sysctl_tcp_syn_retries; + int sysctl_tcp_synack_retries; struct ping_group_range ping_group_range; diff --git a/include/net/tcp.h b/include/net/tcp.h index 825485c7cc1a..05659e860039 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -240,7 +240,6 @@ extern int sysctl_tcp_timestamps; extern int sysctl_tcp_window_scaling; extern int sysctl_tcp_sack; extern int sysctl_tcp_fin_timeout; -extern int sysctl_tcp_synack_retries; extern int sysctl_tcp_retries1; extern int sysctl_tcp_retries2; extern int sysctl_tcp_orphan_retries; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 46b9c887bede..9b17c1792dce 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -482,10 +482,6 @@ EXPORT_SYMBOL_GPL(inet_csk_route_child_sock); #define AF_INET_FAMILY(fam) true #endif -/* Only thing we need from tcp.h */ -extern int sysctl_tcp_synack_retries; - - /* Decide when to expire the request and when to resend SYN-ACK */ static inline void syn_ack_recalc(struct request_sock *req, const int thresh, const int max_retries, @@ -557,6 +553,7 @@ static void reqsk_timer_handler(unsigned long data) { struct request_sock *req = (struct request_sock *)data; struct sock *sk_listener = req->rsk_listener; + struct net *net = sock_net(sk_listener); struct inet_connection_sock *icsk = inet_csk(sk_listener); struct request_sock_queue *queue = &icsk->icsk_accept_queue; int qlen, expire = 0, resend = 0; @@ -566,7 +563,7 @@ static void reqsk_timer_handler(unsigned long data) if (sk_state_load(sk_listener) != TCP_LISTEN) goto drop; - max_retries = icsk->icsk_syn_retries ? : sysctl_tcp_synack_retries; + max_retries = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_synack_retries; thresh = max_retries; /* Normally all the openreqs are young and become mature * (i.e. converted to established socket) for first timeout. diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index ae9dd8823134..bb682e36d8b7 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -291,13 +291,6 @@ static struct ctl_table ipv4_table[] = { .extra1 = &ip_ttl_min, .extra2 = &ip_ttl_max, }, - { - .procname = "tcp_synack_retries", - .data = &sysctl_tcp_synack_retries, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, { .procname = "tcp_max_orphans", .data = &sysctl_tcp_max_orphans, @@ -960,6 +953,13 @@ static struct ctl_table ipv4_net_table[] = { .extra1 = &tcp_syn_retries_min, .extra2 = &tcp_syn_retries_max }, + { + .procname = "tcp_synack_retries", + .data = &init_net.ipv4.sysctl_tcp_synack_retries, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { } }; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index f7464852aaa1..3146279695b9 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2389,6 +2389,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_keepalive_intvl = TCP_KEEPALIVE_INTVL; net->ipv4.sysctl_tcp_syn_retries = TCP_SYN_RETRIES; + net->ipv4.sysctl_tcp_synack_retries = TCP_SYNACK_RETRIES; return 0; fail: diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index c5d51f530c65..ca25fdf0c525 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -22,7 +22,6 @@ #include #include -int sysctl_tcp_synack_retries __read_mostly = TCP_SYNACK_RETRIES; int sysctl_tcp_retries1 __read_mostly = TCP_RETR1; int sysctl_tcp_retries2 __read_mostly = TCP_RETR2; int sysctl_tcp_orphan_retries __read_mostly; @@ -332,7 +331,7 @@ static void tcp_fastopen_synack_timer(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); int max_retries = icsk->icsk_syn_retries ? : - sysctl_tcp_synack_retries + 1; /* add one more retry for fastopen */ + sock_net(sk)->ipv4.sysctl_tcp_synack_retries + 1; /* add one more retry for fastopen */ struct request_sock *req; req = tcp_sk(sk)->fastopen_rsk; -- cgit v1.2.3-71-gd317 From 12ed8244ed8b31b023ea6d2851fd8b15f2999e9b Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Wed, 3 Feb 2016 09:46:51 +0200 Subject: ipv4: Namespaceify tcp syncookies sysctl knob Signed-off-by: Nikolay Borisov Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 2 ++ include/net/tcp.h | 1 - net/ipv4/syncookies.c | 4 +--- net/ipv4/sysctl_net_ipv4.c | 18 +++++++++--------- net/ipv4/tcp_input.c | 10 ++++++---- net/ipv4/tcp_ipv4.c | 3 ++- net/ipv4/tcp_minisocks.c | 3 --- net/ipv6/syncookies.c | 2 +- 8 files changed, 21 insertions(+), 22 deletions(-) (limited to 'include/net') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 9e83084ab8c1..ac000fccdf0f 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -101,6 +101,8 @@ struct netns_ipv4 { int sysctl_tcp_syn_retries; int sysctl_tcp_synack_retries; + int sysctl_tcp_syncookies; + struct ping_group_range ping_group_range; atomic_t dev_addr_genid; diff --git a/include/net/tcp.h b/include/net/tcp.h index 05659e860039..1fb23b70d237 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -243,7 +243,6 @@ extern int sysctl_tcp_fin_timeout; extern int sysctl_tcp_retries1; extern int sysctl_tcp_retries2; extern int sysctl_tcp_orphan_retries; -extern int sysctl_tcp_syncookies; extern int sysctl_tcp_fastopen; extern int sysctl_tcp_retrans_collapse; extern int sysctl_tcp_stdurg; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 643a86c49020..ba0dcffada3b 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -19,8 +19,6 @@ #include #include -extern int sysctl_tcp_syncookies; - static u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS] __read_mostly; #define COOKIEBITS 24 /* Upper bits store count */ @@ -307,7 +305,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) __u8 rcv_wscale; struct flowi4 fl4; - if (!sysctl_tcp_syncookies || !th->ack || th->rst) + if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies || !th->ack || th->rst) goto out; if (tcp_synq_no_recent_overflow(sk)) diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index bb682e36d8b7..d80142570a8d 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -341,15 +341,6 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, -#ifdef CONFIG_SYN_COOKIES - { - .procname = "tcp_syncookies", - .data = &sysctl_tcp_syncookies, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, -#endif { .procname = "tcp_fastopen", .data = &sysctl_tcp_fastopen, @@ -960,6 +951,15 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, +#ifdef CONFIG_SYN_COOKIES + { + .procname = "tcp_syncookies", + .data = &init_net.ipv4.sysctl_tcp_syncookies, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, +#endif { } }; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 596c1cb6759a..b17aba42a368 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6163,9 +6163,10 @@ static bool tcp_syn_flood_action(const struct sock *sk, struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; const char *msg = "Dropping request"; bool want_cookie = false; + struct net *net = sock_net(sk); #ifdef CONFIG_SYN_COOKIES - if (sysctl_tcp_syncookies) { + if (net->ipv4.sysctl_tcp_syncookies) { msg = "Sending cookies"; want_cookie = true; NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDOCOOKIES); @@ -6174,7 +6175,7 @@ static bool tcp_syn_flood_action(const struct sock *sk, NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDROP); if (!queue->synflood_warned && - sysctl_tcp_syncookies != 2 && + net->ipv4.sysctl_tcp_syncookies != 2 && xchg(&queue->synflood_warned, 1) == 0) pr_info("%s: Possible SYN flooding on port %d. %s. Check SNMP counters.\n", proto, ntohs(tcp_hdr(skb)->dest), msg); @@ -6207,6 +6208,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, __u32 isn = TCP_SKB_CB(skb)->tcp_tw_isn; struct tcp_options_received tmp_opt; struct tcp_sock *tp = tcp_sk(sk); + struct net *net = sock_net(sk); struct sock *fastopen_sk = NULL; struct dst_entry *dst = NULL; struct request_sock *req; @@ -6217,7 +6219,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, * limitations, they conserve resources and peer is * evidently real one. */ - if ((sysctl_tcp_syncookies == 2 || + if ((net->ipv4.sysctl_tcp_syncookies == 2 || inet_csk_reqsk_queue_is_full(sk)) && !isn) { want_cookie = tcp_syn_flood_action(sk, skb, rsk_ops->slab_name); if (!want_cookie) @@ -6283,7 +6285,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, } } /* Kill the following clause, if you dislike this way. */ - else if (!sysctl_tcp_syncookies && + else if (!net->ipv4.sysctl_tcp_syncookies && (sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) < (sysctl_max_syn_backlog >> 2)) && !tcp_peer_is_proven(req, dst, false, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 3146279695b9..98313d10a2e0 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -860,7 +860,6 @@ static void tcp_v4_reqsk_destructor(struct request_sock *req) kfree(inet_rsk(req)->opt); } - #ifdef CONFIG_TCP_MD5SIG /* * RFC2385 MD5 checksumming requires a mapping of @@ -2391,6 +2390,8 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_syn_retries = TCP_SYN_RETRIES; net->ipv4.sysctl_tcp_synack_retries = TCP_SYNACK_RETRIES; + net->ipv4.sysctl_tcp_syncookies = 0; + return 0; fail: tcp_sk_exit(net); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 75632a925824..fadd8b978951 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -27,9 +27,6 @@ #include #include -int sysctl_tcp_syncookies __read_mostly = 1; -EXPORT_SYMBOL(sysctl_tcp_syncookies); - int sysctl_tcp_abort_on_overflow __read_mostly; struct inet_timewait_death_row tcp_death_row = { diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 2906ef20795e..0e393ff7f5d0 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -148,7 +148,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) struct dst_entry *dst; __u8 rcv_wscale; - if (!sysctl_tcp_syncookies || !th->ack || th->rst) + if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies || !th->ack || th->rst) goto out; if (tcp_synq_no_recent_overflow(sk)) -- cgit v1.2.3-71-gd317 From 1043e25ff96a1efc7bd34d11f5f32203a28a3bd7 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Wed, 3 Feb 2016 09:46:52 +0200 Subject: ipv4: Namespaceify tcp reordering sysctl knob Signed-off-by: Nikolay Borisov Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 2 +- include/net/tcp.h | 4 +++- net/ipv4/sysctl_net_ipv4.c | 14 +++++++------- net/ipv4/tcp.c | 2 +- net/ipv4/tcp_input.c | 12 ++++++------ net/ipv4/tcp_ipv4.c | 2 +- net/ipv4/tcp_metrics.c | 3 ++- 7 files changed, 21 insertions(+), 18 deletions(-) (limited to 'include/net') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index ac000fccdf0f..eb4cd0a3c296 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -100,8 +100,8 @@ struct netns_ipv4 { int sysctl_tcp_syn_retries; int sysctl_tcp_synack_retries; - int sysctl_tcp_syncookies; + int sysctl_tcp_reordering; struct ping_group_range ping_group_range; diff --git a/include/net/tcp.h b/include/net/tcp.h index 1fb23b70d237..7e9a147cabae 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -961,9 +961,11 @@ static inline void tcp_enable_fack(struct tcp_sock *tp) */ static inline void tcp_enable_early_retrans(struct tcp_sock *tp) { + struct net *net = sock_net((struct sock *)tp); + tp->do_early_retrans = sysctl_tcp_early_retrans && sysctl_tcp_early_retrans < 4 && !sysctl_tcp_thin_dupack && - sysctl_tcp_reordering == 3; + net->ipv4.sysctl_tcp_reordering == 3; } static inline void tcp_disable_early_retrans(struct tcp_sock *tp) diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index d80142570a8d..7cd20570588f 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -455,13 +455,6 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { - .procname = "tcp_reordering", - .data = &sysctl_tcp_reordering, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, { .procname = "tcp_max_reordering", .data = &sysctl_tcp_max_reordering, @@ -960,6 +953,13 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_dointvec }, #endif + { + .procname = "tcp_reordering", + .data = &init_net.ipv4.sysctl_tcp_reordering, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { } }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 3dbb3637bb4b..f4db6b04cdb4 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -406,7 +406,7 @@ void tcp_init_sock(struct sock *sk) tp->mss_cache = TCP_MSS_DEFAULT; u64_stats_init(&tp->syncp); - tp->reordering = sysctl_tcp_reordering; + tp->reordering = sock_net(sk)->ipv4.sysctl_tcp_reordering; tcp_enable_early_retrans(tp); tcp_assign_congestion_control(sk); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index b17aba42a368..5ee6fe0d152d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -80,9 +80,7 @@ int sysctl_tcp_timestamps __read_mostly = 1; int sysctl_tcp_window_scaling __read_mostly = 1; int sysctl_tcp_sack __read_mostly = 1; int sysctl_tcp_fack __read_mostly = 1; -int sysctl_tcp_reordering __read_mostly = TCP_FASTRETRANS_THRESH; int sysctl_tcp_max_reordering __read_mostly = 300; -EXPORT_SYMBOL(sysctl_tcp_reordering); int sysctl_tcp_dsack __read_mostly = 1; int sysctl_tcp_app_win __read_mostly = 31; int sysctl_tcp_adv_win_scale __read_mostly = 1; @@ -1883,6 +1881,7 @@ void tcp_enter_loss(struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); + struct net *net = sock_net(sk); struct sk_buff *skb; bool new_recovery = icsk->icsk_ca_state < TCP_CA_Recovery; bool is_reneg; /* is receiver reneging on SACKs? */ @@ -1933,9 +1932,9 @@ void tcp_enter_loss(struct sock *sk) * suggests that the degree of reordering is over-estimated. */ if (icsk->icsk_ca_state <= TCP_CA_Disorder && - tp->sacked_out >= sysctl_tcp_reordering) + tp->sacked_out >= net->ipv4.sysctl_tcp_reordering) tp->reordering = min_t(unsigned int, tp->reordering, - sysctl_tcp_reordering); + net->ipv4.sysctl_tcp_reordering); tcp_set_ca_state(sk, TCP_CA_Loss); tp->high_seq = tp->snd_nxt; tcp_ecn_queue_cwr(tp); @@ -2119,6 +2118,7 @@ static bool tcp_time_to_recover(struct sock *sk, int flag) { struct tcp_sock *tp = tcp_sk(sk); __u32 packets_out; + int tcp_reordering = sock_net(sk)->ipv4.sysctl_tcp_reordering; /* Trick#1: The loss is proven. */ if (tp->lost_out) @@ -2133,7 +2133,7 @@ static bool tcp_time_to_recover(struct sock *sk, int flag) */ packets_out = tp->packets_out; if (packets_out <= tp->reordering && - tp->sacked_out >= max_t(__u32, packets_out/2, sysctl_tcp_reordering) && + tp->sacked_out >= max_t(__u32, packets_out/2, tcp_reordering) && !tcp_may_send_now(sk)) { /* We have nothing to send. This connection is limited * either by receiver window or by application. @@ -3317,7 +3317,7 @@ static inline bool tcp_may_raise_cwnd(const struct sock *sk, const int flag) * new SACK or ECE mark may first advance cwnd here and later reduce * cwnd in tcp_fastretrans_alert() based on more states. */ - if (tcp_sk(sk)->reordering > sysctl_tcp_reordering) + if (tcp_sk(sk)->reordering > sock_net(sk)->ipv4.sysctl_tcp_reordering) return flag & FLAG_FORWARD_PROGRESS; return flag & FLAG_DATA_ACKED; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 98313d10a2e0..10dfc8b5c0f8 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2389,8 +2389,8 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_syn_retries = TCP_SYN_RETRIES; net->ipv4.sysctl_tcp_synack_retries = TCP_SYNACK_RETRIES; - net->ipv4.sysctl_tcp_syncookies = 0; + net->ipv4.sysctl_tcp_reordering = TCP_FASTRETRANS_THRESH; return 0; fail: diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index c8cbc2b4b792..c26241f3057b 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -369,6 +369,7 @@ void tcp_update_metrics(struct sock *sk) const struct inet_connection_sock *icsk = inet_csk(sk); struct dst_entry *dst = __sk_dst_get(sk); struct tcp_sock *tp = tcp_sk(sk); + struct net *net = sock_net(sk); struct tcp_metrics_block *tm; unsigned long rtt; u32 val; @@ -473,7 +474,7 @@ void tcp_update_metrics(struct sock *sk) if (!tcp_metric_locked(tm, TCP_METRIC_REORDERING)) { val = tcp_metric_get(tm, TCP_METRIC_REORDERING); if (val < tp->reordering && - tp->reordering != sysctl_tcp_reordering) + tp->reordering != net->ipv4.sysctl_tcp_reordering) tcp_metric_set(tm, TCP_METRIC_REORDERING, tp->reordering); } -- cgit v1.2.3-71-gd317 From ae5c3f406cffe15ffd2aa544961b7cd027468d46 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Wed, 3 Feb 2016 09:46:53 +0200 Subject: ipv4: Namespaceify tcp_retries1 sysctl knob Signed-off-by: Nikolay Borisov Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 1 + include/net/tcp.h | 1 - net/ipv4/sysctl_net_ipv4.c | 16 ++++++++-------- net/ipv4/tcp_ipv4.c | 1 + net/ipv4/tcp_timer.c | 8 ++++---- 5 files changed, 14 insertions(+), 13 deletions(-) (limited to 'include/net') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index eb4cd0a3c296..dee6ba647461 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -102,6 +102,7 @@ struct netns_ipv4 { int sysctl_tcp_synack_retries; int sysctl_tcp_syncookies; int sysctl_tcp_reordering; + int sysctl_tcp_retries1; struct ping_group_range ping_group_range; diff --git a/include/net/tcp.h b/include/net/tcp.h index 7e9a147cabae..da96b9af3e5f 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -240,7 +240,6 @@ extern int sysctl_tcp_timestamps; extern int sysctl_tcp_window_scaling; extern int sysctl_tcp_sack; extern int sysctl_tcp_fin_timeout; -extern int sysctl_tcp_retries1; extern int sysctl_tcp_retries2; extern int sysctl_tcp_orphan_retries; extern int sysctl_tcp_fastopen; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 7cd20570588f..52853c6dc929 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -319,14 +319,6 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, - { - .procname = "tcp_retries1", - .data = &sysctl_tcp_retries1, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra2 = &tcp_retr1_max - }, { .procname = "tcp_retries2", .data = &sysctl_tcp_retries2, @@ -960,6 +952,14 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "tcp_retries1", + .data = &init_net.ipv4.sysctl_tcp_retries1, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra2 = &tcp_retr1_max + }, { } }; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 10dfc8b5c0f8..57fe3c6bfb30 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2391,6 +2391,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_synack_retries = TCP_SYNACK_RETRIES; net->ipv4.sysctl_tcp_syncookies = 0; net->ipv4.sysctl_tcp_reordering = TCP_FASTRETRANS_THRESH; + net->ipv4.sysctl_tcp_retries1 = TCP_RETR1; return 0; fail: diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index ca25fdf0c525..6694e33149b9 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -22,7 +22,6 @@ #include #include -int sysctl_tcp_retries1 __read_mostly = TCP_RETR1; int sysctl_tcp_retries2 __read_mostly = TCP_RETR2; int sysctl_tcp_orphan_retries __read_mostly; int sysctl_tcp_thin_linear_timeouts __read_mostly; @@ -171,7 +170,7 @@ static int tcp_write_timeout(struct sock *sk) retry_until = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries; syn_set = true; } else { - if (retransmits_timed_out(sk, sysctl_tcp_retries1, 0, 0)) { + if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1, 0, 0)) { /* Some middle-boxes may black-hole Fast Open _after_ * the handshake. Therefore we conservatively disable * Fast Open on this path on recurring timeouts with @@ -180,7 +179,7 @@ static int tcp_write_timeout(struct sock *sk) if (tp->syn_data_acked && tp->bytes_acked <= tp->rx_opt.mss_clamp) { tcp_fastopen_cache_set(sk, 0, NULL, true, 0); - if (icsk->icsk_retransmits == sysctl_tcp_retries1) + if (icsk->icsk_retransmits == net->ipv4.sysctl_tcp_retries1) NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVEFAIL); } @@ -359,6 +358,7 @@ static void tcp_fastopen_synack_timer(struct sock *sk) void tcp_retransmit_timer(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); + struct net *net = sock_net(sk); struct inet_connection_sock *icsk = inet_csk(sk); if (tp->fastopen_rsk) { @@ -489,7 +489,7 @@ out_reset_timer: icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX); } inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, icsk->icsk_rto, TCP_RTO_MAX); - if (retransmits_timed_out(sk, sysctl_tcp_retries1 + 1, 0, 0)) + if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1 + 1, 0, 0)) __sk_dst_reset(sk); out:; -- cgit v1.2.3-71-gd317 From c6214a97c86c660de4f7ddb8eed925192e646161 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Wed, 3 Feb 2016 09:46:54 +0200 Subject: ipv4: Namespaceify tcp_retries2 sysctl knob Signed-off-by: Nikolay Borisov Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 1 + include/net/tcp.h | 1 - net/ipv4/sysctl_net_ipv4.c | 14 +++++++------- net/ipv4/tcp_ipv4.c | 1 + net/ipv4/tcp_output.c | 3 ++- net/ipv4/tcp_timer.c | 5 ++--- 6 files changed, 13 insertions(+), 12 deletions(-) (limited to 'include/net') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index dee6ba647461..d92c8e5d0fbc 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -103,6 +103,7 @@ struct netns_ipv4 { int sysctl_tcp_syncookies; int sysctl_tcp_reordering; int sysctl_tcp_retries1; + int sysctl_tcp_retries2; struct ping_group_range ping_group_range; diff --git a/include/net/tcp.h b/include/net/tcp.h index da96b9af3e5f..a786cfa6301b 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -240,7 +240,6 @@ extern int sysctl_tcp_timestamps; extern int sysctl_tcp_window_scaling; extern int sysctl_tcp_sack; extern int sysctl_tcp_fin_timeout; -extern int sysctl_tcp_retries2; extern int sysctl_tcp_orphan_retries; extern int sysctl_tcp_fastopen; extern int sysctl_tcp_retrans_collapse; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 52853c6dc929..8e339d43619c 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -319,13 +319,6 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, - { - .procname = "tcp_retries2", - .data = &sysctl_tcp_retries2, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, { .procname = "tcp_fin_timeout", .data = &sysctl_tcp_fin_timeout, @@ -960,6 +953,13 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_dointvec_minmax, .extra2 = &tcp_retr1_max }, + { + .procname = "tcp_retries2", + .data = &init_net.ipv4.sysctl_tcp_retries2, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { } }; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 57fe3c6bfb30..0710e6108a5e 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2392,6 +2392,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_syncookies = 0; net->ipv4.sysctl_tcp_reordering = TCP_FASTRETRANS_THRESH; net->ipv4.sysctl_tcp_retries1 = TCP_RETR1; + net->ipv4.sysctl_tcp_retries2 = TCP_RETR2; return 0; fail: diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index fda379cd600d..7beb3f688b7a 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3476,6 +3476,7 @@ void tcp_send_probe0(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); + struct net *net = sock_net(sk); unsigned long probe_max; int err; @@ -3489,7 +3490,7 @@ void tcp_send_probe0(struct sock *sk) } if (err <= 0) { - if (icsk->icsk_backoff < sysctl_tcp_retries2) + if (icsk->icsk_backoff < net->ipv4.sysctl_tcp_retries2) icsk->icsk_backoff++; icsk->icsk_probes_out++; probe_max = TCP_RTO_MAX; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 6694e33149b9..09f4e0297e56 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -22,7 +22,6 @@ #include #include -int sysctl_tcp_retries2 __read_mostly = TCP_RETR2; int sysctl_tcp_orphan_retries __read_mostly; int sysctl_tcp_thin_linear_timeouts __read_mostly; @@ -189,7 +188,7 @@ static int tcp_write_timeout(struct sock *sk) dst_negative_advice(sk); } - retry_until = sysctl_tcp_retries2; + retry_until = net->ipv4.sysctl_tcp_retries2; if (sock_flag(sk, SOCK_DEAD)) { const bool alive = icsk->icsk_rto < TCP_RTO_MAX; @@ -303,7 +302,7 @@ static void tcp_probe_timer(struct sock *sk) (s32)(tcp_time_stamp - start_ts) > icsk->icsk_user_timeout) goto abort; - max_probes = sysctl_tcp_retries2; + max_probes = sock_net(sk)->ipv4.sysctl_tcp_retries2; if (sock_flag(sk, SOCK_DEAD)) { const bool alive = inet_csk_rto_backoff(icsk, TCP_RTO_MAX) < TCP_RTO_MAX; -- cgit v1.2.3-71-gd317 From c402d9beffb6141ab2e4d2ad8be71128803a28ca Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Wed, 3 Feb 2016 09:46:55 +0200 Subject: ipv4: Namespaceify tcp_orphan_retries sysctl knob Signed-off-by: Nikolay Borisov Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 1 + include/net/tcp.h | 1 - net/ipv4/sysctl_net_ipv4.c | 14 +++++++------- net/ipv4/tcp_ipv4.c | 1 + net/ipv4/tcp_timer.c | 3 +-- 5 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include/net') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index d92c8e5d0fbc..080230321985 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -104,6 +104,7 @@ struct netns_ipv4 { int sysctl_tcp_reordering; int sysctl_tcp_retries1; int sysctl_tcp_retries2; + int sysctl_tcp_orphan_retries; struct ping_group_range ping_group_range; diff --git a/include/net/tcp.h b/include/net/tcp.h index a786cfa6301b..71f840b89c76 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -240,7 +240,6 @@ extern int sysctl_tcp_timestamps; extern int sysctl_tcp_window_scaling; extern int sysctl_tcp_sack; extern int sysctl_tcp_fin_timeout; -extern int sysctl_tcp_orphan_retries; extern int sysctl_tcp_fastopen; extern int sysctl_tcp_retrans_collapse; extern int sysctl_tcp_stdurg; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 8e339d43619c..b7af6336985f 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -419,13 +419,6 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { - .procname = "tcp_orphan_retries", - .data = &sysctl_tcp_orphan_retries, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, { .procname = "tcp_fack", .data = &sysctl_tcp_fack, @@ -960,6 +953,13 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "tcp_orphan_retries", + .data = &init_net.ipv4.sysctl_tcp_orphan_retries, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { } }; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 0710e6108a5e..1240dd62eee1 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2393,6 +2393,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_reordering = TCP_FASTRETRANS_THRESH; net->ipv4.sysctl_tcp_retries1 = TCP_RETR1; net->ipv4.sysctl_tcp_retries2 = TCP_RETR2; + net->ipv4.sysctl_tcp_orphan_retries = 0; return 0; fail: diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 09f4e0297e56..49bc474f8e35 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -22,7 +22,6 @@ #include #include -int sysctl_tcp_orphan_retries __read_mostly; int sysctl_tcp_thin_linear_timeouts __read_mostly; static void tcp_write_err(struct sock *sk) @@ -78,7 +77,7 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset) /* Calculate maximal number or retries on an orphaned socket. */ static int tcp_orphan_retries(struct sock *sk, bool alive) { - int retries = sysctl_tcp_orphan_retries; /* May be zero. */ + int retries = sock_net(sk)->ipv4.sysctl_tcp_orphan_retries; /* May be zero. */ /* We know from an ICMP that something is wrong. */ if (sk->sk_err_soft && !alive) -- cgit v1.2.3-71-gd317 From 1e579caa18b96f9eb18f4f5416658cd15f37c062 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Wed, 3 Feb 2016 09:46:56 +0200 Subject: ipv4: Namespaceify tcp_fin_timeout sysctl knob Signed-off-by: Nikolay Borisov Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 1 + include/net/tcp.h | 3 +-- net/ipv4/sysctl_net_ipv4.c | 14 +++++++------- net/ipv4/tcp.c | 7 +++---- net/ipv4/tcp_ipv4.c | 1 + 5 files changed, 13 insertions(+), 13 deletions(-) (limited to 'include/net') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 080230321985..de5ff4385e84 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -105,6 +105,7 @@ struct netns_ipv4 { int sysctl_tcp_retries1; int sysctl_tcp_retries2; int sysctl_tcp_orphan_retries; + int sysctl_tcp_fin_timeout; struct ping_group_range ping_group_range; diff --git a/include/net/tcp.h b/include/net/tcp.h index 71f840b89c76..3f160c2e6960 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -239,7 +239,6 @@ extern struct inet_timewait_death_row tcp_death_row; extern int sysctl_tcp_timestamps; extern int sysctl_tcp_window_scaling; extern int sysctl_tcp_sack; -extern int sysctl_tcp_fin_timeout; extern int sysctl_tcp_fastopen; extern int sysctl_tcp_retrans_collapse; extern int sysctl_tcp_stdurg; @@ -1249,7 +1248,7 @@ static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp) static inline int tcp_fin_time(const struct sock *sk) { - int fin_timeout = tcp_sk(sk)->linger2 ? : sysctl_tcp_fin_timeout; + int fin_timeout = tcp_sk(sk)->linger2 ? : sock_net(sk)->ipv4.sysctl_tcp_fin_timeout; const int rto = inet_csk(sk)->icsk_rto; if (fin_timeout < (rto << 2) - (rto >> 1)) diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index b7af6336985f..8bd335a2cba8 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -319,13 +319,6 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, - { - .procname = "tcp_fin_timeout", - .data = &sysctl_tcp_fin_timeout, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, { .procname = "tcp_fastopen", .data = &sysctl_tcp_fastopen, @@ -960,6 +953,13 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "tcp_fin_timeout", + .data = &init_net.ipv4.sysctl_tcp_fin_timeout, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, { } }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index f4db6b04cdb4..014f18e2f7b3 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -282,8 +282,6 @@ #include #include -int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT; - int sysctl_tcp_min_tso_segs __read_mostly = 2; int sysctl_tcp_autocorking __read_mostly = 1; @@ -2330,6 +2328,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); + struct net *net = sock_net(sk); int val; int err = 0; @@ -2526,7 +2525,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, case TCP_LINGER2: if (val < 0) tp->linger2 = -1; - else if (val > sysctl_tcp_fin_timeout / HZ) + else if (val > net->ipv4.sysctl_tcp_fin_timeout / HZ) tp->linger2 = 0; else tp->linger2 = val * HZ; @@ -2771,7 +2770,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level, case TCP_LINGER2: val = tp->linger2; if (val >= 0) - val = (val ? : sysctl_tcp_fin_timeout) / HZ; + val = (val ? : net->ipv4.sysctl_tcp_fin_timeout) / HZ; break; case TCP_DEFER_ACCEPT: val = retrans_to_secs(icsk->icsk_accept_queue.rskq_defer_accept, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 1240dd62eee1..36c83c28d9c9 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2394,6 +2394,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_retries1 = TCP_RETR1; net->ipv4.sysctl_tcp_retries2 = TCP_RETR2; net->ipv4.sysctl_tcp_orphan_retries = 0; + net->ipv4.sysctl_tcp_fin_timeout = TCP_FIN_TIMEOUT; return 0; fail: -- cgit v1.2.3-71-gd317 From 4979f2d9f7262b9b180bc83de8d70f7a7721c085 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Wed, 3 Feb 2016 09:46:57 +0200 Subject: ipv4: Namespaceify tcp_notsent_lowat sysctl knob Signed-off-by: Nikolay Borisov Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 1 + include/net/tcp.h | 4 ++-- net/ipv4/sysctl_net_ipv4.c | 14 +++++++------- net/ipv4/tcp_ipv4.c | 1 + net/ipv4/tcp_output.c | 3 --- 5 files changed, 11 insertions(+), 12 deletions(-) (limited to 'include/net') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index de5ff4385e84..4d6ec3f6fafe 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -106,6 +106,7 @@ struct netns_ipv4 { int sysctl_tcp_retries2; int sysctl_tcp_orphan_retries; int sysctl_tcp_fin_timeout; + unsigned int sysctl_tcp_notsent_lowat; struct ping_group_range ping_group_range; diff --git a/include/net/tcp.h b/include/net/tcp.h index 3f160c2e6960..9b2cb0c8d876 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -267,7 +267,6 @@ extern int sysctl_tcp_thin_dupack; extern int sysctl_tcp_early_retrans; extern int sysctl_tcp_limit_output_bytes; extern int sysctl_tcp_challenge_ack_limit; -extern unsigned int sysctl_tcp_notsent_lowat; extern int sysctl_tcp_min_tso_segs; extern int sysctl_tcp_min_rtt_wlen; extern int sysctl_tcp_autocorking; @@ -1682,7 +1681,8 @@ void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr); static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp) { - return tp->notsent_lowat ?: sysctl_tcp_notsent_lowat; + struct net *net = sock_net((struct sock *)tp); + return tp->notsent_lowat ?: net->ipv4.sysctl_tcp_notsent_lowat; } static inline bool tcp_stream_memory_free(const struct sock *sk) diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 8bd335a2cba8..44bb59824267 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -455,13 +455,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec_minmax, .extra1 = &one, }, - { - .procname = "tcp_notsent_lowat", - .data = &sysctl_tcp_notsent_lowat, - .maxlen = sizeof(sysctl_tcp_notsent_lowat), - .mode = 0644, - .proc_handler = proc_dointvec, - }, { .procname = "tcp_rmem", .data = &sysctl_tcp_rmem, @@ -960,6 +953,13 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, + { + .procname = "tcp_notsent_lowat", + .data = &init_net.ipv4.sysctl_tcp_notsent_lowat, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, { } }; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 36c83c28d9c9..11ae706f53a1 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2395,6 +2395,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_retries2 = TCP_RETR2; net->ipv4.sysctl_tcp_orphan_retries = 0; net->ipv4.sysctl_tcp_fin_timeout = TCP_FIN_TIMEOUT; + net->ipv4.sysctl_tcp_notsent_lowat = UINT_MAX; return 0; fail: diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 7beb3f688b7a..7d2c7a400456 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -62,9 +62,6 @@ int sysctl_tcp_tso_win_divisor __read_mostly = 3; /* By default, RFC2861 behavior. */ int sysctl_tcp_slow_start_after_idle __read_mostly = 1; -unsigned int sysctl_tcp_notsent_lowat __read_mostly = UINT_MAX; -EXPORT_SYMBOL(sysctl_tcp_notsent_lowat); - static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, int push_one, gfp_t gfp); -- cgit v1.2.3-71-gd317 From 5ee14e6d336f1daacf5ba73e831029c5ab7ae329 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Wed, 3 Feb 2016 13:17:01 +0100 Subject: bonding: 3ad: apply ad_actor settings changes immediately Currently the bonding allows to set ad_actor_system and prio while the bond device is down, but these are actually applied only if there aren't any slaves yet (applied to bond device when first slave shows up, and to slaves at 3ad bind time). After this patch changes are applied immediately and the new values can be used/seen after the bond's upped so it's not necessary anymore to release all and enslave again to see the changes. CC: Jay Vosburgh CC: Veaceslav Falico CC: Andy Gospodarek Signed-off-by: Nikolay Aleksandrov Signed-off-by: Jay Vosburgh Signed-off-by: David S. Miller --- drivers/net/bonding/bond_3ad.c | 40 +++++++++++++++++++++++++++++++++++--- drivers/net/bonding/bond_options.c | 4 ++++ include/net/bond_3ad.h | 1 + 3 files changed, 42 insertions(+), 3 deletions(-) (limited to 'include/net') diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index 4cbb8b27a891..ee94056dbb2e 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -357,6 +357,14 @@ static u8 __get_duplex(struct port *port) return retval; } +static void __ad_actor_update_port(struct port *port) +{ + const struct bonding *bond = bond_get_bond_by_slave(port->slave); + + port->actor_system = BOND_AD_INFO(bond).system.sys_mac_addr; + port->actor_system_priority = BOND_AD_INFO(bond).system.sys_priority; +} + /* Conversions */ /** @@ -1963,9 +1971,7 @@ void bond_3ad_bind_slave(struct slave *slave) port->actor_admin_port_key = bond->params.ad_user_port_key << 6; ad_update_actor_keys(port, false); /* actor system is the bond's system */ - port->actor_system = BOND_AD_INFO(bond).system.sys_mac_addr; - port->actor_system_priority = - BOND_AD_INFO(bond).system.sys_priority; + __ad_actor_update_port(port); /* tx timer(to verify that no more than MAX_TX_IN_SECOND * lacpdu's are sent in one second) */ @@ -2147,6 +2153,34 @@ out: spin_unlock_bh(&bond->mode_lock); } +/** + * bond_3ad_update_ad_actor_settings - reflect change of actor settings to ports + * @bond: bonding struct to work on + * + * If an ad_actor setting gets changed we need to update the individual port + * settings so the bond device will use the new values when it gets upped. + */ +void bond_3ad_update_ad_actor_settings(struct bonding *bond) +{ + struct list_head *iter; + struct slave *slave; + + ASSERT_RTNL(); + + BOND_AD_INFO(bond).system.sys_priority = bond->params.ad_actor_sys_prio; + if (is_zero_ether_addr(bond->params.ad_actor_system)) + BOND_AD_INFO(bond).system.sys_mac_addr = + *((struct mac_addr *)bond->dev->dev_addr); + else + BOND_AD_INFO(bond).system.sys_mac_addr = + *((struct mac_addr *)bond->params.ad_actor_system); + + spin_lock_bh(&bond->mode_lock); + bond_for_each_slave(bond, slave, iter) + __ad_actor_update_port(&(SLAVE_AD_INFO(slave)->port)); + spin_unlock_bh(&bond->mode_lock); +} + /** * bond_3ad_state_machine_handler - handle state machines timeout * @bond: bonding struct to work on diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 55e93b6b6d21..ed0bdae64f5e 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -1392,6 +1392,8 @@ static int bond_option_ad_actor_sys_prio_set(struct bonding *bond, newval->value); bond->params.ad_actor_sys_prio = newval->value; + bond_3ad_update_ad_actor_settings(bond); + return 0; } @@ -1418,6 +1420,8 @@ static int bond_option_ad_actor_system_set(struct bonding *bond, netdev_info(bond->dev, "Setting ad_actor_system to %pM\n", mac); ether_addr_copy(bond->params.ad_actor_system, mac); + bond_3ad_update_ad_actor_settings(bond); + return 0; err: diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h index f1fbc3b11962..f358ad5e4214 100644 --- a/include/net/bond_3ad.h +++ b/include/net/bond_3ad.h @@ -306,5 +306,6 @@ int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond, struct slave *slave); int bond_3ad_set_carrier(struct bonding *bond); void bond_3ad_update_lacp_rate(struct bonding *bond); +void bond_3ad_update_ad_actor_settings(struct bonding *bond); #endif /* _NET_BOND_3AD_H */ -- cgit v1.2.3-71-gd317 From 086c653f5862591a9cfe2386f5650d03adacc33a Mon Sep 17 00:00:00 2001 From: Craig Gallek Date: Wed, 10 Feb 2016 11:50:35 -0500 Subject: sock: struct proto hash function may error In order to support fast reuseport lookups in TCP, the hash function defined in struct proto must be capable of returning an error code. This patch changes the function signature of all related hash functions to return an integer and handles or propagates this return value at all call sites. Signed-off-by: Craig Gallek Signed-off-by: David S. Miller --- include/net/inet_hashtables.h | 2 +- include/net/phonet/phonet.h | 2 +- include/net/ping.h | 2 +- include/net/raw.h | 2 +- include/net/sock.h | 6 +++--- include/net/udp.h | 3 ++- net/ieee802154/socket.c | 17 +++++++++++++---- net/ipv4/af_inet.c | 9 ++++++--- net/ipv4/inet_connection_sock.c | 8 +++++--- net/ipv4/inet_hashtables.c | 4 +++- net/ipv4/ping.c | 4 +++- net/ipv4/raw.c | 4 +++- net/ipv6/af_inet6.c | 6 +++++- net/phonet/socket.c | 6 ++++-- net/sctp/socket.c | 3 ++- 15 files changed, 53 insertions(+), 25 deletions(-) (limited to 'include/net') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index de2e3ade6102..554440e7f83d 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -208,7 +208,7 @@ void inet_hashinfo_init(struct inet_hashinfo *h); bool inet_ehash_insert(struct sock *sk, struct sock *osk); bool inet_ehash_nolisten(struct sock *sk, struct sock *osk); void __inet_hash(struct sock *sk, struct sock *osk); -void inet_hash(struct sock *sk); +int inet_hash(struct sock *sk); void inet_unhash(struct sock *sk); struct sock *__inet_lookup_listener(struct net *net, diff --git a/include/net/phonet/phonet.h b/include/net/phonet/phonet.h index 68e509750caa..039cc29cb4a8 100644 --- a/include/net/phonet/phonet.h +++ b/include/net/phonet/phonet.h @@ -51,7 +51,7 @@ void pn_sock_init(void); struct sock *pn_find_sock_by_sa(struct net *net, const struct sockaddr_pn *sa); void pn_deliver_sock_broadcast(struct net *net, struct sk_buff *skb); void phonet_get_local_port_range(int *min, int *max); -void pn_sock_hash(struct sock *sk); +int pn_sock_hash(struct sock *sk); void pn_sock_unhash(struct sock *sk); int pn_sock_get_port(struct sock *sk, unsigned short sport); diff --git a/include/net/ping.h b/include/net/ping.h index ac80cb45e630..5fd7cc244833 100644 --- a/include/net/ping.h +++ b/include/net/ping.h @@ -65,7 +65,7 @@ struct pingfakehdr { }; int ping_get_port(struct sock *sk, unsigned short ident); -void ping_hash(struct sock *sk); +int ping_hash(struct sock *sk); void ping_unhash(struct sock *sk); int ping_init_sock(struct sock *sk); diff --git a/include/net/raw.h b/include/net/raw.h index 6a40c6562dd2..3e789008394d 100644 --- a/include/net/raw.h +++ b/include/net/raw.h @@ -57,7 +57,7 @@ int raw_seq_open(struct inode *ino, struct file *file, #endif -void raw_hash_sk(struct sock *sk); +int raw_hash_sk(struct sock *sk); void raw_unhash_sk(struct sock *sk); struct raw_sock { diff --git a/include/net/sock.h b/include/net/sock.h index f5ea148853e2..255d3e03727b 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -984,7 +984,7 @@ struct proto { void (*release_cb)(struct sock *sk); /* Keeping track of sk's, looking them up, and port selection methods. */ - void (*hash)(struct sock *sk); + int (*hash)(struct sock *sk); void (*unhash)(struct sock *sk); void (*rehash)(struct sock *sk); int (*get_port)(struct sock *sk, unsigned short snum); @@ -1194,10 +1194,10 @@ static inline void sock_prot_inuse_add(struct net *net, struct proto *prot, /* With per-bucket locks this operation is not-atomic, so that * this version is not worse. */ -static inline void __sk_prot_rehash(struct sock *sk) +static inline int __sk_prot_rehash(struct sock *sk) { sk->sk_prot->unhash(sk); - sk->sk_prot->hash(sk); + return sk->sk_prot->hash(sk); } void sk_prot_clear_portaddr_nulls(struct sock *sk, int size); diff --git a/include/net/udp.h b/include/net/udp.h index 2842541e28e7..92927f729ac8 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -177,9 +177,10 @@ static inline struct udphdr *udp_gro_udphdr(struct sk_buff *skb) } /* hash routines shared between UDPv4/6 and UDP-Litev4/6 */ -static inline void udp_lib_hash(struct sock *sk) +static inline int udp_lib_hash(struct sock *sk) { BUG(); + return 0; } void udp_lib_unhash(struct sock *sk); diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c index a548be247e15..e0bd013a1e5e 100644 --- a/net/ieee802154/socket.c +++ b/net/ieee802154/socket.c @@ -182,12 +182,14 @@ static int ieee802154_sock_ioctl(struct socket *sock, unsigned int cmd, static HLIST_HEAD(raw_head); static DEFINE_RWLOCK(raw_lock); -static void raw_hash(struct sock *sk) +static int raw_hash(struct sock *sk) { write_lock_bh(&raw_lock); sk_add_node(sk, &raw_head); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); write_unlock_bh(&raw_lock); + + return 0; } static void raw_unhash(struct sock *sk) @@ -462,12 +464,14 @@ static inline struct dgram_sock *dgram_sk(const struct sock *sk) return container_of(sk, struct dgram_sock, sk); } -static void dgram_hash(struct sock *sk) +static int dgram_hash(struct sock *sk) { write_lock_bh(&dgram_lock); sk_add_node(sk, &dgram_head); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); write_unlock_bh(&dgram_lock); + + return 0; } static void dgram_unhash(struct sock *sk) @@ -1026,8 +1030,13 @@ static int ieee802154_create(struct net *net, struct socket *sock, /* Checksums on by default */ sock_set_flag(sk, SOCK_ZAPPED); - if (sk->sk_prot->hash) - sk->sk_prot->hash(sk); + if (sk->sk_prot->hash) { + rc = sk->sk_prot->hash(sk); + if (rc) { + sk_common_release(sk); + goto out; + } + } if (sk->sk_prot->init) { rc = sk->sk_prot->init(sk); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 5c5db6636704..eade66db214e 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -370,7 +370,11 @@ lookup_protocol: */ inet->inet_sport = htons(inet->inet_num); /* Add to protocol hash chains. */ - sk->sk_prot->hash(sk); + err = sk->sk_prot->hash(sk); + if (err) { + sk_common_release(sk); + goto out; + } } if (sk->sk_prot->init) { @@ -1142,8 +1146,7 @@ static int inet_sk_reselect_saddr(struct sock *sk) * Besides that, it does not check for connection * uniqueness. Wait for troubles. */ - __sk_prot_rehash(sk); - return 0; + return __sk_prot_rehash(sk); } int inet_sk_rebuild_header(struct sock *sk) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 9b17c1792dce..12c8d389dc18 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -734,6 +734,7 @@ int inet_csk_listen_start(struct sock *sk, int backlog) { struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet = inet_sk(sk); + int err = -EADDRINUSE; reqsk_queue_alloc(&icsk->icsk_accept_queue); @@ -751,13 +752,14 @@ int inet_csk_listen_start(struct sock *sk, int backlog) inet->inet_sport = htons(inet->inet_num); sk_dst_reset(sk); - sk->sk_prot->hash(sk); + err = sk->sk_prot->hash(sk); - return 0; + if (likely(!err)) + return 0; } sk->sk_state = TCP_CLOSE; - return -EADDRINUSE; + return err; } EXPORT_SYMBOL_GPL(inet_csk_listen_start); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index ccc5980797fc..b6023b7baae0 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -468,13 +468,15 @@ void __inet_hash(struct sock *sk, struct sock *osk) } EXPORT_SYMBOL(__inet_hash); -void inet_hash(struct sock *sk) +int inet_hash(struct sock *sk) { if (sk->sk_state != TCP_CLOSE) { local_bh_disable(); __inet_hash(sk, NULL); local_bh_enable(); } + + return 0; } EXPORT_SYMBOL_GPL(inet_hash); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index c117b21b937d..f6f93fc2c61f 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -145,10 +145,12 @@ fail: } EXPORT_SYMBOL_GPL(ping_get_port); -void ping_hash(struct sock *sk) +int ping_hash(struct sock *sk) { pr_debug("ping_hash(sk->port=%u)\n", inet_sk(sk)->inet_num); BUG(); /* "Please do not press this button again." */ + + return 0; } void ping_unhash(struct sock *sk) diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index bc35f1842512..d6352515d738 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -93,7 +93,7 @@ static struct raw_hashinfo raw_v4_hashinfo = { .lock = __RW_LOCK_UNLOCKED(raw_v4_hashinfo.lock), }; -void raw_hash_sk(struct sock *sk) +int raw_hash_sk(struct sock *sk) { struct raw_hashinfo *h = sk->sk_prot->h.raw_hash; struct hlist_head *head; @@ -104,6 +104,8 @@ void raw_hash_sk(struct sock *sk) sk_add_node(sk, head); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); write_unlock_bh(&h->lock); + + return 0; } EXPORT_SYMBOL_GPL(raw_hash_sk); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 9f5137cd604e..b11c37cfd67c 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -235,7 +235,11 @@ lookup_protocol: * creation time automatically shares. */ inet->inet_sport = htons(inet->inet_num); - sk->sk_prot->hash(sk); + err = sk->sk_prot->hash(sk); + if (err) { + sk_common_release(sk); + goto out; + } } if (sk->sk_prot->init) { err = sk->sk_prot->init(sk); diff --git a/net/phonet/socket.c b/net/phonet/socket.c index d575ef4e9aa6..ffd5f2297584 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -140,13 +140,15 @@ void pn_deliver_sock_broadcast(struct net *net, struct sk_buff *skb) rcu_read_unlock(); } -void pn_sock_hash(struct sock *sk) +int pn_sock_hash(struct sock *sk) { struct hlist_head *hlist = pn_hash_list(pn_sk(sk)->sobject); mutex_lock(&pnsocks.lock); sk_add_node_rcu(sk, hlist); mutex_unlock(&pnsocks.lock); + + return 0; } EXPORT_SYMBOL(pn_sock_hash); @@ -200,7 +202,7 @@ static int pn_socket_bind(struct socket *sock, struct sockaddr *addr, int len) pn->resource = spn->spn_resource; /* Enable RX on the socket */ - sk->sk_prot->hash(sk); + err = sk->sk_prot->hash(sk); out_port: mutex_unlock(&port_mutex); out: diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 5ca2ebfe0be8..6427b9d1197e 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -6101,9 +6101,10 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname, return retval; } -static void sctp_hash(struct sock *sk) +static int sctp_hash(struct sock *sk) { /* STUB */ + return 0; } static void sctp_unhash(struct sock *sk) -- cgit v1.2.3-71-gd317 From 496611d7b5eaf59c03440c8f2def1d9988ad2459 Mon Sep 17 00:00:00 2001 From: Craig Gallek Date: Wed, 10 Feb 2016 11:50:36 -0500 Subject: inet: create IPv6-equivalent inet_hash function In order to support fast lookups for TCP sockets with SO_REUSEPORT, the function that adds sockets to the listening hash set needs to be able to check receive address equality. Since this equality check is different for IPv4 and IPv6, we will need two different socket hashing functions. This patch adds inet6_hash identical to the existing inet_hash function and updates the appropriate references. A following patch will differentiate the two by passing different comparison functions to __inet_hash. Additionally, in order to use the IPv6 address equality function from inet6_hashtables (which is compiled as a built-in object when IPv6 is enabled) it also needs to be in a built-in object file as well. This moves ipv6_rcv_saddr_equal into inet_hashtables to accomplish this. Signed-off-by: Craig Gallek Signed-off-by: David S. Miller --- include/net/inet6_hashtables.h | 2 ++ net/dccp/ipv6.c | 2 +- net/ipv6/inet6_hashtables.c | 56 ++++++++++++++++++++++++++++++++++++++++++ net/ipv6/tcp_ipv6.c | 2 +- net/ipv6/udp.c | 44 +-------------------------------- net/l2tp/l2tp_ip6.c | 3 ++- 6 files changed, 63 insertions(+), 46 deletions(-) (limited to 'include/net') diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index 7ff588ca6817..b3c28a9dfbf1 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -96,6 +96,8 @@ struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const __be16 dport, const int dif); + +int inet6_hash(struct sock *sk); #endif /* IS_ENABLED(CONFIG_IPV6) */ #define INET6_MATCH(__sk, __net, __saddr, __daddr, __ports, __dif) \ diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 9c6d0508e63a..90a8269b28d0 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -993,7 +993,7 @@ static struct proto dccp_v6_prot = { .sendmsg = dccp_sendmsg, .recvmsg = dccp_recvmsg, .backlog_rcv = dccp_v6_do_rcv, - .hash = inet_hash, + .hash = inet6_hash, .unhash = inet_unhash, .accept = inet_csk_accept, .get_port = inet_csk_get_port, diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 21ace5a2bf7c..072653dd9c98 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -274,3 +274,59 @@ int inet6_hash_connect(struct inet_timewait_death_row *death_row, __inet6_check_established); } EXPORT_SYMBOL_GPL(inet6_hash_connect); + +int inet6_hash(struct sock *sk) +{ + if (sk->sk_state != TCP_CLOSE) { + local_bh_disable(); + __inet_hash(sk, NULL); + local_bh_enable(); + } + + return 0; +} +EXPORT_SYMBOL_GPL(inet6_hash); + +/* match_wildcard == true: IPV6_ADDR_ANY equals to any IPv6 addresses if IPv6 + * only, and any IPv4 addresses if not IPv6 only + * match_wildcard == false: addresses must be exactly the same, i.e. + * IPV6_ADDR_ANY only equals to IPV6_ADDR_ANY, + * and 0.0.0.0 equals to 0.0.0.0 only + */ +int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2, + bool match_wildcard) +{ + const struct in6_addr *sk2_rcv_saddr6 = inet6_rcv_saddr(sk2); + int sk2_ipv6only = inet_v6_ipv6only(sk2); + int addr_type = ipv6_addr_type(&sk->sk_v6_rcv_saddr); + int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED; + + /* if both are mapped, treat as IPv4 */ + if (addr_type == IPV6_ADDR_MAPPED && addr_type2 == IPV6_ADDR_MAPPED) { + if (!sk2_ipv6only) { + if (sk->sk_rcv_saddr == sk2->sk_rcv_saddr) + return 1; + if (!sk->sk_rcv_saddr || !sk2->sk_rcv_saddr) + return match_wildcard; + } + return 0; + } + + if (addr_type == IPV6_ADDR_ANY && addr_type2 == IPV6_ADDR_ANY) + return 1; + + if (addr_type2 == IPV6_ADDR_ANY && match_wildcard && + !(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED)) + return 1; + + if (addr_type == IPV6_ADDR_ANY && match_wildcard && + !(ipv6_only_sock(sk) && addr_type2 == IPV6_ADDR_MAPPED)) + return 1; + + if (sk2_rcv_saddr6 && + ipv6_addr_equal(&sk->sk_v6_rcv_saddr, sk2_rcv_saddr6)) + return 1; + + return 0; +} +EXPORT_SYMBOL_GPL(ipv6_rcv_saddr_equal); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 006396e31cb0..d72bcfb326d8 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1865,7 +1865,7 @@ struct proto tcpv6_prot = { .sendpage = tcp_sendpage, .backlog_rcv = tcp_v6_do_rcv, .release_cb = tcp_release_cb, - .hash = inet_hash, + .hash = inet6_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, .enter_memory_pressure = tcp_enter_memory_pressure, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 22e28a44e3c8..ac4e7e03dded 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -37,6 +37,7 @@ #include #include +#include #include #include #include @@ -77,49 +78,6 @@ static u32 udp6_ehashfn(const struct net *net, udp_ipv6_hash_secret + net_hash_mix(net)); } -/* match_wildcard == true: IPV6_ADDR_ANY equals to any IPv6 addresses if IPv6 - * only, and any IPv4 addresses if not IPv6 only - * match_wildcard == false: addresses must be exactly the same, i.e. - * IPV6_ADDR_ANY only equals to IPV6_ADDR_ANY, - * and 0.0.0.0 equals to 0.0.0.0 only - */ -int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2, - bool match_wildcard) -{ - const struct in6_addr *sk2_rcv_saddr6 = inet6_rcv_saddr(sk2); - int sk2_ipv6only = inet_v6_ipv6only(sk2); - int addr_type = ipv6_addr_type(&sk->sk_v6_rcv_saddr); - int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED; - - /* if both are mapped, treat as IPv4 */ - if (addr_type == IPV6_ADDR_MAPPED && addr_type2 == IPV6_ADDR_MAPPED) { - if (!sk2_ipv6only) { - if (sk->sk_rcv_saddr == sk2->sk_rcv_saddr) - return 1; - if (!sk->sk_rcv_saddr || !sk2->sk_rcv_saddr) - return match_wildcard; - } - return 0; - } - - if (addr_type == IPV6_ADDR_ANY && addr_type2 == IPV6_ADDR_ANY) - return 1; - - if (addr_type2 == IPV6_ADDR_ANY && match_wildcard && - !(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED)) - return 1; - - if (addr_type == IPV6_ADDR_ANY && match_wildcard && - !(ipv6_only_sock(sk) && addr_type2 == IPV6_ADDR_MAPPED)) - return 1; - - if (sk2_rcv_saddr6 && - ipv6_addr_equal(&sk->sk_v6_rcv_saddr, sk2_rcv_saddr6)) - return 1; - - return 0; -} - static u32 udp6_portaddr_hash(const struct net *net, const struct in6_addr *addr6, unsigned int port) diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index a2c8747d2936..6b54ff3ff4cb 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -718,7 +719,7 @@ static struct proto l2tp_ip6_prot = { .sendmsg = l2tp_ip6_sendmsg, .recvmsg = l2tp_ip6_recvmsg, .backlog_rcv = l2tp_ip6_backlog_recv, - .hash = inet_hash, + .hash = inet6_hash, .unhash = inet_unhash, .obj_size = sizeof(struct l2tp_ip6_sock), #ifdef CONFIG_COMPAT -- cgit v1.2.3-71-gd317 From a583636a83ea383fd07517e5a7a2eedbc5d90fb1 Mon Sep 17 00:00:00 2001 From: Craig Gallek Date: Wed, 10 Feb 2016 11:50:38 -0500 Subject: inet: refactor inet[6]_lookup functions to take skb This is a preliminary step to allow fast socket lookup of SO_REUSEPORT groups. Doing so with a BPF filter will require access to the skb in question. This change plumbs the skb (and offset to payload data) through the call stack to the listening socket lookup implementations where it will be used in a following patch. Signed-off-by: Craig Gallek Signed-off-by: David S. Miller --- include/net/addrconf.h | 2 ++ include/net/inet6_hashtables.h | 11 +++++++---- include/net/inet_hashtables.h | 18 ++++++++++++------ net/dccp/ipv4.c | 2 +- net/dccp/ipv6.c | 2 +- net/ipv4/inet_diag.c | 6 +++--- net/ipv4/inet_hashtables.c | 1 + net/ipv4/tcp_ipv4.c | 10 ++++++---- net/ipv6/inet6_hashtables.c | 8 ++++++-- net/ipv6/tcp_ipv6.c | 8 +++++--- net/netfilter/xt_TPROXY.c | 31 ++++++++++++++++++++----------- net/netfilter/xt_socket.c | 28 +++++++++++++++++++++------- 12 files changed, 85 insertions(+), 42 deletions(-) (limited to 'include/net') diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 47f52d3cd8df..730d856683e5 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -87,6 +87,8 @@ int __ipv6_get_lladdr(struct inet6_dev *idev, struct in6_addr *addr, u32 banned_flags); int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr, u32 banned_flags); +int ipv4_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2, + bool match_wildcard); int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2, bool match_wildcard); void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr); diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index b3c28a9dfbf1..28332bdac333 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -53,6 +53,7 @@ struct sock *__inet6_lookup_established(struct net *net, struct sock *inet6_lookup_listener(struct net *net, struct inet_hashinfo *hashinfo, + struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, @@ -60,6 +61,7 @@ struct sock *inet6_lookup_listener(struct net *net, static inline struct sock *__inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, + struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, @@ -71,12 +73,12 @@ static inline struct sock *__inet6_lookup(struct net *net, if (sk) return sk; - return inet6_lookup_listener(net, hashinfo, saddr, sport, + return inet6_lookup_listener(net, hashinfo, skb, doff, saddr, sport, daddr, hnum, dif); } static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo, - struct sk_buff *skb, + struct sk_buff *skb, int doff, const __be16 sport, const __be16 dport, int iif) @@ -86,13 +88,14 @@ static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo, if (sk) return sk; - return __inet6_lookup(dev_net(skb_dst(skb)->dev), hashinfo, - &ipv6_hdr(skb)->saddr, sport, + return __inet6_lookup(dev_net(skb_dst(skb)->dev), hashinfo, skb, + doff, &ipv6_hdr(skb)->saddr, sport, &ipv6_hdr(skb)->daddr, ntohs(dport), iif); } struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, + struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const __be16 dport, const int dif); diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 554440e7f83d..82403390af58 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -213,6 +213,7 @@ void inet_unhash(struct sock *sk); struct sock *__inet_lookup_listener(struct net *net, struct inet_hashinfo *hashinfo, + struct sk_buff *skb, int doff, const __be32 saddr, const __be16 sport, const __be32 daddr, const unsigned short hnum, @@ -220,10 +221,11 @@ struct sock *__inet_lookup_listener(struct net *net, static inline struct sock *inet_lookup_listener(struct net *net, struct inet_hashinfo *hashinfo, + struct sk_buff *skb, int doff, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif) { - return __inet_lookup_listener(net, hashinfo, saddr, sport, + return __inet_lookup_listener(net, hashinfo, skb, doff, saddr, sport, daddr, ntohs(dport), dif); } @@ -299,6 +301,7 @@ static inline struct sock * static inline struct sock *__inet_lookup(struct net *net, struct inet_hashinfo *hashinfo, + struct sk_buff *skb, int doff, const __be32 saddr, const __be16 sport, const __be32 daddr, const __be16 dport, const int dif) @@ -307,12 +310,13 @@ static inline struct sock *__inet_lookup(struct net *net, struct sock *sk = __inet_lookup_established(net, hashinfo, saddr, sport, daddr, hnum, dif); - return sk ? : __inet_lookup_listener(net, hashinfo, saddr, sport, - daddr, hnum, dif); + return sk ? : __inet_lookup_listener(net, hashinfo, skb, doff, saddr, + sport, daddr, hnum, dif); } static inline struct sock *inet_lookup(struct net *net, struct inet_hashinfo *hashinfo, + struct sk_buff *skb, int doff, const __be32 saddr, const __be16 sport, const __be32 daddr, const __be16 dport, const int dif) @@ -320,7 +324,8 @@ static inline struct sock *inet_lookup(struct net *net, struct sock *sk; local_bh_disable(); - sk = __inet_lookup(net, hashinfo, saddr, sport, daddr, dport, dif); + sk = __inet_lookup(net, hashinfo, skb, doff, saddr, sport, daddr, + dport, dif); local_bh_enable(); return sk; @@ -328,6 +333,7 @@ static inline struct sock *inet_lookup(struct net *net, static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo, struct sk_buff *skb, + int doff, const __be16 sport, const __be16 dport) { @@ -337,8 +343,8 @@ static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo, if (sk) return sk; else - return __inet_lookup(dev_net(skb_dst(skb)->dev), hashinfo, - iph->saddr, sport, + return __inet_lookup(dev_net(skb_dst(skb)->dev), hashinfo, skb, + doff, iph->saddr, sport, iph->daddr, dport, inet_iif(skb)); } diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 5684e14932bd..1e0c600c83ae 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -802,7 +802,7 @@ static int dccp_v4_rcv(struct sk_buff *skb) } lookup: - sk = __inet_lookup_skb(&dccp_hashinfo, skb, + sk = __inet_lookup_skb(&dccp_hashinfo, skb, __dccp_hdr_len(dh), dh->dccph_sport, dh->dccph_dport); if (!sk) { dccp_pr_debug("failed to look up flow ID in table and " diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 90a8269b28d0..45cbe85f0940 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -668,7 +668,7 @@ static int dccp_v6_rcv(struct sk_buff *skb) DCCP_SKB_CB(skb)->dccpd_ack_seq = dccp_hdr_ack_seq(skb); lookup: - sk = __inet6_lookup_skb(&dccp_hashinfo, skb, + sk = __inet6_lookup_skb(&dccp_hashinfo, skb, __dccp_hdr_len(dh), dh->dccph_sport, dh->dccph_dport, inet6_iif(skb)); if (!sk) { diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 6029157a19ed..50c0d96b8441 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -357,18 +357,18 @@ struct sock *inet_diag_find_one_icsk(struct net *net, struct sock *sk; if (req->sdiag_family == AF_INET) - sk = inet_lookup(net, hashinfo, req->id.idiag_dst[0], + sk = inet_lookup(net, hashinfo, NULL, 0, req->id.idiag_dst[0], req->id.idiag_dport, req->id.idiag_src[0], req->id.idiag_sport, req->id.idiag_if); #if IS_ENABLED(CONFIG_IPV6) else if (req->sdiag_family == AF_INET6) { if (ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_dst) && ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_src)) - sk = inet_lookup(net, hashinfo, req->id.idiag_dst[3], + sk = inet_lookup(net, hashinfo, NULL, 0, req->id.idiag_dst[3], req->id.idiag_dport, req->id.idiag_src[3], req->id.idiag_sport, req->id.idiag_if); else - sk = inet6_lookup(net, hashinfo, + sk = inet6_lookup(net, hashinfo, NULL, 0, (struct in6_addr *)req->id.idiag_dst, req->id.idiag_dport, (struct in6_addr *)req->id.idiag_src, diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index b6023b7baae0..5e4290b83255 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -205,6 +205,7 @@ static inline int compute_score(struct sock *sk, struct net *net, struct sock *__inet_lookup_listener(struct net *net, struct inet_hashinfo *hashinfo, + struct sk_buff *skb, int doff, const __be32 saddr, __be16 sport, const __be32 daddr, const unsigned short hnum, const int dif) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 0d381fa164f8..3f872a6bc274 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -637,8 +637,8 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) * Incoming packet is checked with md5 hash with finding key, * no RST generated if md5 hash doesn't match. */ - sk1 = __inet_lookup_listener(net, - &tcp_hashinfo, ip_hdr(skb)->saddr, + sk1 = __inet_lookup_listener(net, &tcp_hashinfo, NULL, 0, + ip_hdr(skb)->saddr, th->source, ip_hdr(skb)->daddr, ntohs(th->source), inet_iif(skb)); /* don't send rst if it can't find key */ @@ -1581,7 +1581,8 @@ int tcp_v4_rcv(struct sk_buff *skb) TCP_SKB_CB(skb)->sacked = 0; lookup: - sk = __inet_lookup_skb(&tcp_hashinfo, skb, th->source, th->dest); + sk = __inet_lookup_skb(&tcp_hashinfo, skb, __tcp_hdrlen(th), th->source, + th->dest); if (!sk) goto no_tcp_socket; @@ -1695,7 +1696,8 @@ do_time_wait: switch (tcp_timewait_state_process(inet_twsk(sk), skb, th)) { case TCP_TW_SYN: { struct sock *sk2 = inet_lookup_listener(dev_net(skb->dev), - &tcp_hashinfo, + &tcp_hashinfo, skb, + __tcp_hdrlen(th), iph->saddr, th->source, iph->daddr, th->dest, inet_iif(skb)); diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 072653dd9c98..004345d26808 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -121,7 +121,9 @@ static inline int compute_score(struct sock *sk, struct net *net, } struct sock *inet6_lookup_listener(struct net *net, - struct inet_hashinfo *hashinfo, const struct in6_addr *saddr, + struct inet_hashinfo *hashinfo, + struct sk_buff *skb, int doff, + const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const unsigned short hnum, const int dif) { @@ -177,6 +179,7 @@ begin: EXPORT_SYMBOL_GPL(inet6_lookup_listener); struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, + struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const __be16 dport, const int dif) @@ -184,7 +187,8 @@ struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, struct sock *sk; local_bh_disable(); - sk = __inet6_lookup(net, hashinfo, saddr, sport, daddr, ntohs(dport), dif); + sk = __inet6_lookup(net, hashinfo, skb, doff, saddr, sport, daddr, + ntohs(dport), dif); local_bh_enable(); return sk; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index d72bcfb326d8..9977b6f19f2a 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -866,7 +866,8 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) * no RST generated if md5 hash doesn't match. */ sk1 = inet6_lookup_listener(dev_net(skb_dst(skb)->dev), - &tcp_hashinfo, &ipv6h->saddr, + &tcp_hashinfo, NULL, 0, + &ipv6h->saddr, th->source, &ipv6h->daddr, ntohs(th->source), tcp_v6_iif(skb)); if (!sk1) @@ -1375,8 +1376,8 @@ static int tcp_v6_rcv(struct sk_buff *skb) hdr = ipv6_hdr(skb); lookup: - sk = __inet6_lookup_skb(&tcp_hashinfo, skb, th->source, th->dest, - inet6_iif(skb)); + sk = __inet6_lookup_skb(&tcp_hashinfo, skb, __tcp_hdrlen(th), + th->source, th->dest, inet6_iif(skb)); if (!sk) goto no_tcp_socket; @@ -1500,6 +1501,7 @@ do_time_wait: struct sock *sk2; sk2 = inet6_lookup_listener(dev_net(skb->dev), &tcp_hashinfo, + skb, __tcp_hdrlen(th), &ipv6_hdr(skb)->saddr, th->source, &ipv6_hdr(skb)->daddr, ntohs(th->dest), tcp_v6_iif(skb)); diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index 3ab591e73ec0..7f4414d26a66 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -105,19 +105,24 @@ tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr) * belonging to established connections going through that one. */ static inline struct sock * -nf_tproxy_get_sock_v4(struct net *net, const u8 protocol, +nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp, + const u8 protocol, const __be32 saddr, const __be32 daddr, const __be16 sport, const __be16 dport, const struct net_device *in, const enum nf_tproxy_lookup_t lookup_type) { struct sock *sk; + struct tcphdr *tcph; switch (protocol) { case IPPROTO_TCP: switch (lookup_type) { case NFT_LOOKUP_LISTENER: - sk = inet_lookup_listener(net, &tcp_hashinfo, + tcph = hp; + sk = inet_lookup_listener(net, &tcp_hashinfo, skb, + ip_hdrlen(skb) + + __tcp_hdrlen(tcph), saddr, sport, daddr, dport, in->ifindex); @@ -169,19 +174,23 @@ nf_tproxy_get_sock_v4(struct net *net, const u8 protocol, #ifdef XT_TPROXY_HAVE_IPV6 static inline struct sock * -nf_tproxy_get_sock_v6(struct net *net, const u8 protocol, +nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp, + const u8 protocol, const struct in6_addr *saddr, const struct in6_addr *daddr, const __be16 sport, const __be16 dport, const struct net_device *in, const enum nf_tproxy_lookup_t lookup_type) { struct sock *sk; + struct tcphdr *tcph; switch (protocol) { case IPPROTO_TCP: switch (lookup_type) { case NFT_LOOKUP_LISTENER: - sk = inet6_lookup_listener(net, &tcp_hashinfo, + tcph = hp; + sk = inet6_lookup_listener(net, &tcp_hashinfo, skb, + thoff + __tcp_hdrlen(tcph), saddr, sport, daddr, ntohs(dport), in->ifindex); @@ -267,7 +276,7 @@ tproxy_handle_time_wait4(struct net *net, struct sk_buff *skb, * to a listener socket if there's one */ struct sock *sk2; - sk2 = nf_tproxy_get_sock_v4(net, iph->protocol, + sk2 = nf_tproxy_get_sock_v4(net, skb, hp, iph->protocol, iph->saddr, laddr ? laddr : iph->daddr, hp->source, lport ? lport : hp->dest, skb->dev, NFT_LOOKUP_LISTENER); @@ -305,7 +314,7 @@ tproxy_tg4(struct net *net, struct sk_buff *skb, __be32 laddr, __be16 lport, * addresses, this happens if the redirect already happened * and the current packet belongs to an already established * connection */ - sk = nf_tproxy_get_sock_v4(net, iph->protocol, + sk = nf_tproxy_get_sock_v4(net, skb, hp, iph->protocol, iph->saddr, iph->daddr, hp->source, hp->dest, skb->dev, NFT_LOOKUP_ESTABLISHED); @@ -321,7 +330,7 @@ tproxy_tg4(struct net *net, struct sk_buff *skb, __be32 laddr, __be16 lport, else if (!sk) /* no, there's no established connection, check if * there's a listener on the redirected addr/port */ - sk = nf_tproxy_get_sock_v4(net, iph->protocol, + sk = nf_tproxy_get_sock_v4(net, skb, hp, iph->protocol, iph->saddr, laddr, hp->source, lport, skb->dev, NFT_LOOKUP_LISTENER); @@ -429,7 +438,7 @@ tproxy_handle_time_wait6(struct sk_buff *skb, int tproto, int thoff, * to a listener socket if there's one */ struct sock *sk2; - sk2 = nf_tproxy_get_sock_v6(par->net, tproto, + sk2 = nf_tproxy_get_sock_v6(par->net, skb, thoff, hp, tproto, &iph->saddr, tproxy_laddr6(skb, &tgi->laddr.in6, &iph->daddr), hp->source, @@ -472,7 +481,7 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par) * addresses, this happens if the redirect already happened * and the current packet belongs to an already established * connection */ - sk = nf_tproxy_get_sock_v6(par->net, tproto, + sk = nf_tproxy_get_sock_v6(par->net, skb, thoff, hp, tproto, &iph->saddr, &iph->daddr, hp->source, hp->dest, par->in, NFT_LOOKUP_ESTABLISHED); @@ -487,8 +496,8 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par) else if (!sk) /* no there's no established connection, check if * there's a listener on the redirected addr/port */ - sk = nf_tproxy_get_sock_v6(par->net, tproto, - &iph->saddr, laddr, + sk = nf_tproxy_get_sock_v6(par->net, skb, thoff, hp, + tproto, &iph->saddr, laddr, hp->source, lport, par->in, NFT_LOOKUP_LISTENER); diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 2ec08f04b816..49d14ecad444 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -112,14 +112,15 @@ extract_icmp4_fields(const struct sk_buff *skb, * box. */ static struct sock * -xt_socket_get_sock_v4(struct net *net, const u8 protocol, +xt_socket_get_sock_v4(struct net *net, struct sk_buff *skb, const int doff, + const u8 protocol, const __be32 saddr, const __be32 daddr, const __be16 sport, const __be16 dport, const struct net_device *in) { switch (protocol) { case IPPROTO_TCP: - return __inet_lookup(net, &tcp_hashinfo, + return __inet_lookup(net, &tcp_hashinfo, skb, doff, saddr, sport, daddr, dport, in->ifindex); case IPPROTO_UDP: @@ -148,6 +149,8 @@ static struct sock *xt_socket_lookup_slow_v4(struct net *net, const struct net_device *indev) { const struct iphdr *iph = ip_hdr(skb); + struct sk_buff *data_skb = NULL; + int doff = 0; __be32 uninitialized_var(daddr), uninitialized_var(saddr); __be16 uninitialized_var(dport), uninitialized_var(sport); u8 uninitialized_var(protocol); @@ -169,6 +172,10 @@ static struct sock *xt_socket_lookup_slow_v4(struct net *net, sport = hp->source; daddr = iph->daddr; dport = hp->dest; + data_skb = (struct sk_buff *)skb; + doff = iph->protocol == IPPROTO_TCP ? + ip_hdrlen(skb) + __tcp_hdrlen((struct tcphdr *)hp) : + ip_hdrlen(skb) + sizeof(*hp); } else if (iph->protocol == IPPROTO_ICMP) { if (extract_icmp4_fields(skb, &protocol, &saddr, &daddr, @@ -198,8 +205,8 @@ static struct sock *xt_socket_lookup_slow_v4(struct net *net, } #endif - return xt_socket_get_sock_v4(net, protocol, saddr, daddr, - sport, dport, indev); + return xt_socket_get_sock_v4(net, data_skb, doff, protocol, saddr, + daddr, sport, dport, indev); } static bool @@ -318,14 +325,15 @@ extract_icmp6_fields(const struct sk_buff *skb, } static struct sock * -xt_socket_get_sock_v6(struct net *net, const u8 protocol, +xt_socket_get_sock_v6(struct net *net, struct sk_buff *skb, int doff, + const u8 protocol, const struct in6_addr *saddr, const struct in6_addr *daddr, const __be16 sport, const __be16 dport, const struct net_device *in) { switch (protocol) { case IPPROTO_TCP: - return inet6_lookup(net, &tcp_hashinfo, + return inet6_lookup(net, &tcp_hashinfo, skb, doff, saddr, sport, daddr, dport, in->ifindex); case IPPROTO_UDP: @@ -343,6 +351,8 @@ static struct sock *xt_socket_lookup_slow_v6(struct net *net, __be16 uninitialized_var(dport), uninitialized_var(sport); const struct in6_addr *daddr = NULL, *saddr = NULL; struct ipv6hdr *iph = ipv6_hdr(skb); + struct sk_buff *data_skb = NULL; + int doff = 0; int thoff = 0, tproto; tproto = ipv6_find_hdr(skb, &thoff, -1, NULL, NULL); @@ -362,6 +372,10 @@ static struct sock *xt_socket_lookup_slow_v6(struct net *net, sport = hp->source; daddr = &iph->daddr; dport = hp->dest; + data_skb = (struct sk_buff *)skb; + doff = tproto == IPPROTO_TCP ? + thoff + __tcp_hdrlen((struct tcphdr *)hp) : + thoff + sizeof(*hp); } else if (tproto == IPPROTO_ICMPV6) { struct ipv6hdr ipv6_var; @@ -373,7 +387,7 @@ static struct sock *xt_socket_lookup_slow_v6(struct net *net, return NULL; } - return xt_socket_get_sock_v6(net, tproto, saddr, daddr, + return xt_socket_get_sock_v6(net, data_skb, doff, tproto, saddr, daddr, sport, dport, indev); } -- cgit v1.2.3-71-gd317 From c125e80b88687b25b321795457309eaaee4bf270 Mon Sep 17 00:00:00 2001 From: Craig Gallek Date: Wed, 10 Feb 2016 11:50:40 -0500 Subject: soreuseport: fast reuseport TCP socket selection This change extends the fast SO_REUSEPORT socket lookup implemented for UDP to TCP. Listener sockets with SO_REUSEPORT and the same receive address are additionally added to an array for faster random access. This means that only a single socket from the group must be found in the listener list before any socket in the group can be used to receive a packet. Previously, every socket in the group needed to be considered before handing off the incoming packet. This feature also exposes the ability to use a BPF program when selecting a socket from a reuseport group. Signed-off-by: Craig Gallek Signed-off-by: David S. Miller --- include/net/inet_hashtables.h | 5 +++- net/ipv4/inet_connection_sock.c | 14 ++++++--- net/ipv4/inet_hashtables.c | 64 +++++++++++++++++++++++++++++++++++++--- net/ipv4/udp.c | 4 +-- net/ipv6/inet6_connection_sock.c | 2 ++ net/ipv6/inet6_hashtables.c | 16 +++++++++- 6 files changed, 93 insertions(+), 12 deletions(-) (limited to 'include/net') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 82403390af58..50f635c2c536 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -207,7 +207,10 @@ void inet_hashinfo_init(struct inet_hashinfo *h); bool inet_ehash_insert(struct sock *sk, struct sock *osk); bool inet_ehash_nolisten(struct sock *sk, struct sock *osk); -void __inet_hash(struct sock *sk, struct sock *osk); +int __inet_hash(struct sock *sk, struct sock *osk, + int (*saddr_same)(const struct sock *sk1, + const struct sock *sk2, + bool match_wildcard)); int inet_hash(struct sock *sk); void inet_unhash(struct sock *sk); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 12c8d389dc18..c16a2e6273d9 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -24,6 +24,7 @@ #include #include #include +#include #ifdef INET_CSK_DEBUG const char inet_csk_timer_bug_msg[] = "inet_csk BUG: unknown timer value\n"; @@ -67,7 +68,8 @@ int inet_csk_bind_conflict(const struct sock *sk, if ((!reuse || !sk2->sk_reuse || sk2->sk_state == TCP_LISTEN) && (!reuseport || !sk2->sk_reuseport || - (sk2->sk_state != TCP_TIME_WAIT && + rcu_access_pointer(sk->sk_reuseport_cb) || + (sk2->sk_state != TCP_TIME_WAIT && !uid_eq(uid, sock_i_uid(sk2))))) { if (!sk2->sk_rcv_saddr || !sk->sk_rcv_saddr || @@ -132,6 +134,7 @@ again: sk->sk_state != TCP_LISTEN) || (tb->fastreuseport > 0 && sk->sk_reuseport && + !rcu_access_pointer(sk->sk_reuseport_cb) && uid_eq(tb->fastuid, uid))) && (tb->num_owners < smallest_size || smallest_size == -1)) { smallest_size = tb->num_owners; @@ -193,15 +196,18 @@ tb_found: if (((tb->fastreuse > 0 && sk->sk_reuse && sk->sk_state != TCP_LISTEN) || (tb->fastreuseport > 0 && - sk->sk_reuseport && uid_eq(tb->fastuid, uid))) && - smallest_size == -1) { + sk->sk_reuseport && + !rcu_access_pointer(sk->sk_reuseport_cb) && + uid_eq(tb->fastuid, uid))) && smallest_size == -1) { goto success; } else { ret = 1; if (inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, true)) { if (((sk->sk_reuse && sk->sk_state != TCP_LISTEN) || (tb->fastreuseport > 0 && - sk->sk_reuseport && uid_eq(tb->fastuid, uid))) && + sk->sk_reuseport && + !rcu_access_pointer(sk->sk_reuseport_cb) && + uid_eq(tb->fastuid, uid))) && smallest_size != -1 && --attempts >= 0) { spin_unlock(&head->lock); goto again; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 5e4290b83255..c0f9942de924 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -20,10 +20,12 @@ #include #include +#include #include #include #include #include +#include static u32 inet_ehashfn(const struct net *net, const __be32 laddr, const __u16 lport, const __be32 faddr, @@ -215,6 +217,7 @@ struct sock *__inet_lookup_listener(struct net *net, unsigned int hash = inet_lhashfn(net, hnum); struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash]; int score, hiscore, matches = 0, reuseport = 0; + bool select_ok = true; u32 phash = 0; rcu_read_lock(); @@ -230,6 +233,15 @@ begin: if (reuseport) { phash = inet_ehashfn(net, daddr, hnum, saddr, sport); + if (select_ok) { + struct sock *sk2; + sk2 = reuseport_select_sock(sk, phash, + skb, doff); + if (sk2) { + result = sk2; + goto found; + } + } matches = 1; } } else if (score == hiscore && reuseport) { @@ -247,11 +259,13 @@ begin: if (get_nulls_value(node) != hash + LISTENING_NULLS_BASE) goto begin; if (result) { +found: if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt))) result = NULL; else if (unlikely(compute_score(result, net, hnum, daddr, dif) < hiscore)) { sock_put(result); + select_ok = false; goto begin; } } @@ -450,34 +464,74 @@ bool inet_ehash_nolisten(struct sock *sk, struct sock *osk) } EXPORT_SYMBOL_GPL(inet_ehash_nolisten); -void __inet_hash(struct sock *sk, struct sock *osk) +static int inet_reuseport_add_sock(struct sock *sk, + struct inet_listen_hashbucket *ilb, + int (*saddr_same)(const struct sock *sk1, + const struct sock *sk2, + bool match_wildcard)) +{ + struct sock *sk2; + struct hlist_nulls_node *node; + kuid_t uid = sock_i_uid(sk); + + sk_nulls_for_each_rcu(sk2, node, &ilb->head) { + if (sk2 != sk && + sk2->sk_family == sk->sk_family && + ipv6_only_sock(sk2) == ipv6_only_sock(sk) && + sk2->sk_bound_dev_if == sk->sk_bound_dev_if && + sk2->sk_reuseport && uid_eq(uid, sock_i_uid(sk2)) && + saddr_same(sk, sk2, false)) + return reuseport_add_sock(sk, sk2); + } + + /* Initial allocation may have already happened via setsockopt */ + if (!rcu_access_pointer(sk->sk_reuseport_cb)) + return reuseport_alloc(sk); + return 0; +} + +int __inet_hash(struct sock *sk, struct sock *osk, + int (*saddr_same)(const struct sock *sk1, + const struct sock *sk2, + bool match_wildcard)) { struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; struct inet_listen_hashbucket *ilb; + int err = 0; if (sk->sk_state != TCP_LISTEN) { inet_ehash_nolisten(sk, osk); - return; + return 0; } WARN_ON(!sk_unhashed(sk)); ilb = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)]; spin_lock(&ilb->lock); + if (sk->sk_reuseport) { + err = inet_reuseport_add_sock(sk, ilb, saddr_same); + if (err) + goto unlock; + } __sk_nulls_add_node_rcu(sk, &ilb->head); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); +unlock: spin_unlock(&ilb->lock); + + return err; } EXPORT_SYMBOL(__inet_hash); int inet_hash(struct sock *sk) { + int err = 0; + if (sk->sk_state != TCP_CLOSE) { local_bh_disable(); - __inet_hash(sk, NULL); + err = __inet_hash(sk, NULL, ipv4_rcv_saddr_equal); local_bh_enable(); } - return 0; + return err; } EXPORT_SYMBOL_GPL(inet_hash); @@ -496,6 +550,8 @@ void inet_unhash(struct sock *sk) lock = inet_ehash_lockp(hashinfo, sk->sk_hash); spin_lock_bh(lock); + if (rcu_access_pointer(sk->sk_reuseport_cb)) + reuseport_detach_sock(sk); done = __sk_nulls_del_node_init_rcu(sk); if (done) sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index be0b21852b13..ac3cedb25a9f 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -356,8 +356,8 @@ EXPORT_SYMBOL(udp_lib_get_port); * match_wildcard == false: addresses must be exactly the same, i.e. * 0.0.0.0 only equals to 0.0.0.0 */ -static int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2, - bool match_wildcard) +int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2, + bool match_wildcard) { struct inet_sock *inet1 = inet_sk(sk1), *inet2 = inet_sk(sk2); diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 36c3f0155010..532c3ef282c5 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -26,6 +26,7 @@ #include #include #include +#include int inet6_csk_bind_conflict(const struct sock *sk, const struct inet_bind_bucket *tb, bool relax) @@ -48,6 +49,7 @@ int inet6_csk_bind_conflict(const struct sock *sk, if ((!reuse || !sk2->sk_reuse || sk2->sk_state == TCP_LISTEN) && (!reuseport || !sk2->sk_reuseport || + rcu_access_pointer(sk->sk_reuseport_cb) || (sk2->sk_state != TCP_TIME_WAIT && !uid_eq(uid, sock_i_uid((struct sock *)sk2))))) { diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 004345d26808..70f2628be6fa 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -17,11 +17,13 @@ #include #include +#include #include #include #include #include #include +#include u32 inet6_ehashfn(const struct net *net, const struct in6_addr *laddr, const u16 lport, @@ -131,6 +133,7 @@ struct sock *inet6_lookup_listener(struct net *net, const struct hlist_nulls_node *node; struct sock *result; int score, hiscore, matches = 0, reuseport = 0; + bool select_ok = true; u32 phash = 0; unsigned int hash = inet_lhashfn(net, hnum); struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash]; @@ -148,6 +151,15 @@ begin: if (reuseport) { phash = inet6_ehashfn(net, daddr, hnum, saddr, sport); + if (select_ok) { + struct sock *sk2; + sk2 = reuseport_select_sock(sk, phash, + skb, doff); + if (sk2) { + result = sk2; + goto found; + } + } matches = 1; } } else if (score == hiscore && reuseport) { @@ -165,11 +177,13 @@ begin: if (get_nulls_value(node) != hash + LISTENING_NULLS_BASE) goto begin; if (result) { +found: if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt))) result = NULL; else if (unlikely(compute_score(result, net, hnum, daddr, dif) < hiscore)) { sock_put(result); + select_ok = false; goto begin; } } @@ -283,7 +297,7 @@ int inet6_hash(struct sock *sk) { if (sk->sk_state != TCP_CLOSE) { local_bh_disable(); - __inet_hash(sk, NULL); + __inet_hash(sk, NULL, ipv6_rcv_saddr_equal); local_bh_enable(); } -- cgit v1.2.3-71-gd317 From 815c52700746cdcc0874a33390bac334a4b90107 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Mon, 8 Feb 2016 23:29:21 +0200 Subject: igmp: Namespaceify igmp_max_memberships sysctl knob Signed-off-by: Nikolay Borisov Signed-off-by: David S. Miller --- include/linux/igmp.h | 1 - include/net/netns/ipv4.h | 2 ++ net/ipv4/igmp.c | 4 +--- net/ipv4/sysctl_net_ipv4.c | 14 +++++++------- net/ipv4/tcp_ipv4.c | 2 ++ 5 files changed, 12 insertions(+), 11 deletions(-) (limited to 'include/net') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 9c9de11549a7..57d6d06ce0b3 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -38,7 +38,6 @@ static inline struct igmpv3_query * } extern int sysctl_igmp_llm_reports; -extern int sysctl_igmp_max_memberships; extern int sysctl_igmp_max_msf; extern int sysctl_igmp_qrv; diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 4d6ec3f6fafe..759cf624eec2 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -108,6 +108,8 @@ struct netns_ipv4 { int sysctl_tcp_fin_timeout; unsigned int sysctl_tcp_notsent_lowat; + int sysctl_igmp_max_memberships; + struct ping_group_range ping_group_range; atomic_t dev_addr_genid; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 05e4cba14162..5b86257c9d6b 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -107,7 +107,6 @@ #include #endif -#define IP_MAX_MEMBERSHIPS 20 #define IP_MAX_MSF 10 /* IGMP reports for link-local multicast groups are enabled by default */ @@ -1727,7 +1726,6 @@ static struct in_device *ip_mc_find_dev(struct net *net, struct ip_mreqn *imr) /* * Join a socket to a group */ -int sysctl_igmp_max_memberships __read_mostly = IP_MAX_MEMBERSHIPS; int sysctl_igmp_max_msf __read_mostly = IP_MAX_MSF; #ifdef CONFIG_IP_MULTICAST int sysctl_igmp_qrv __read_mostly = IGMP_QUERY_ROBUSTNESS_VARIABLE; @@ -2074,7 +2072,7 @@ int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr) count++; } err = -ENOBUFS; - if (count >= sysctl_igmp_max_memberships) + if (count >= net->ipv4.sysctl_igmp_max_memberships) goto done; iml = sock_kmalloc(sk, sizeof(*iml), GFP_KERNEL); if (!iml) diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 44bb59824267..6ea3dbb96db4 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -367,13 +367,6 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, - { - .procname = "igmp_max_memberships", - .data = &sysctl_igmp_max_memberships, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, { .procname = "igmp_max_msf", .data = &sysctl_igmp_max_msf, @@ -871,6 +864,13 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "igmp_max_memberships", + .data = &init_net.ipv4.sysctl_igmp_max_memberships, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { .procname = "tcp_keepalive_time", .data = &init_net.ipv4.sysctl_tcp_keepalive_time, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 3f872a6bc274..4b203789900b 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2399,6 +2399,8 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_fin_timeout = TCP_FIN_TIMEOUT; net->ipv4.sysctl_tcp_notsent_lowat = UINT_MAX; + net->ipv4.sysctl_igmp_max_memberships = 20; + return 0; fail: tcp_sk_exit(net); -- cgit v1.2.3-71-gd317 From 166b6b2d6f01be67a83b87ab5c91350a68b17115 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Mon, 8 Feb 2016 23:29:22 +0200 Subject: igmp: Namespaceify igmp_max_msf sysctl knob Signed-off-by: Nikolay Borisov Signed-off-by: David S. Miller --- include/linux/igmp.h | 1 - include/net/netns/ipv4.h | 1 + net/ipv4/igmp.c | 5 +---- net/ipv4/ip_sockglue.c | 5 +++-- net/ipv4/sysctl_net_ipv4.c | 14 +++++++------- net/ipv4/tcp_ipv4.c | 1 + 6 files changed, 13 insertions(+), 14 deletions(-) (limited to 'include/net') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 57d6d06ce0b3..a91ec9f575e7 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -38,7 +38,6 @@ static inline struct igmpv3_query * } extern int sysctl_igmp_llm_reports; -extern int sysctl_igmp_max_msf; extern int sysctl_igmp_qrv; struct ip_sf_socklist { diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 759cf624eec2..522a2cfe1ad9 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -109,6 +109,7 @@ struct netns_ipv4 { unsigned int sysctl_tcp_notsent_lowat; int sysctl_igmp_max_memberships; + int sysctl_igmp_max_msf; struct ping_group_range ping_group_range; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 5b86257c9d6b..6da2e467b63c 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -107,8 +107,6 @@ #include #endif -#define IP_MAX_MSF 10 - /* IGMP reports for link-local multicast groups are enabled by default */ int sysctl_igmp_llm_reports __read_mostly = 1; @@ -1726,7 +1724,6 @@ static struct in_device *ip_mc_find_dev(struct net *net, struct ip_mreqn *imr) /* * Join a socket to a group */ -int sysctl_igmp_max_msf __read_mostly = IP_MAX_MSF; #ifdef CONFIG_IP_MULTICAST int sysctl_igmp_qrv __read_mostly = IGMP_QUERY_ROBUSTNESS_VARIABLE; #endif @@ -2244,7 +2241,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct } /* else, add a new source to the filter */ - if (psl && psl->sl_count >= sysctl_igmp_max_msf) { + if (psl && psl->sl_count >= net->ipv4.sysctl_igmp_max_msf) { err = -ENOBUFS; goto done; } diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 5f73a7c03e27..92808f147ef5 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -571,6 +571,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen) { struct inet_sock *inet = inet_sk(sk); + struct net *net = sock_net(sk); int val = 0, err; bool needs_rtnl = setsockopt_needs_rtnl(optname); @@ -910,7 +911,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, } /* numsrc >= (1G-4) overflow in 32 bits */ if (msf->imsf_numsrc >= 0x3ffffffcU || - msf->imsf_numsrc > sysctl_igmp_max_msf) { + msf->imsf_numsrc > net->ipv4.sysctl_igmp_max_msf) { kfree(msf); err = -ENOBUFS; break; @@ -1065,7 +1066,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, /* numsrc >= (4G-140)/128 overflow in 32 bits */ if (gsf->gf_numsrc >= 0x1ffffff || - gsf->gf_numsrc > sysctl_igmp_max_msf) { + gsf->gf_numsrc > net->ipv4.sysctl_igmp_max_msf) { err = -ENOBUFS; goto mc_msf_out; } diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 6ea3dbb96db4..225659a02cf2 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -367,13 +367,6 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, - { - .procname = "igmp_max_msf", - .data = &sysctl_igmp_max_msf, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, #ifdef CONFIG_IP_MULTICAST { .procname = "igmp_qrv", @@ -871,6 +864,13 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "igmp_max_msf", + .data = &init_net.ipv4.sysctl_igmp_max_msf, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { .procname = "tcp_keepalive_time", .data = &init_net.ipv4.sysctl_tcp_keepalive_time, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 4b203789900b..055d8a9a0c61 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2400,6 +2400,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_notsent_lowat = UINT_MAX; net->ipv4.sysctl_igmp_max_memberships = 20; + net->ipv4.sysctl_igmp_max_msf = 10; return 0; fail: -- cgit v1.2.3-71-gd317 From 87a8a2ae65b7721893c7922f963502be8fa01c94 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Tue, 9 Feb 2016 00:13:50 +0200 Subject: igmp: Namespaceify igmp_llm_reports sysctl knob This was initially introduced in df2cf4a78e488d26 ("IGMP: Inhibit reports for local multicast groups") by defining the sysctl in the ipv4_net_table array, however it was never implemented to be namespace aware. Fix this by changing the code accordingly. Signed-off-by: David S. Miller --- include/linux/igmp.h | 1 - include/net/netns/ipv4.h | 1 + net/ipv4/igmp.c | 26 +++++++++++++++----------- net/ipv4/sysctl_net_ipv4.c | 2 +- net/ipv4/tcp_ipv4.c | 2 ++ 5 files changed, 19 insertions(+), 13 deletions(-) (limited to 'include/net') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index a91ec9f575e7..c683f4bf642b 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -37,7 +37,6 @@ static inline struct igmpv3_query * return (struct igmpv3_query *)skb_transport_header(skb); } -extern int sysctl_igmp_llm_reports; extern int sysctl_igmp_qrv; struct ip_sf_socklist { diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 522a2cfe1ad9..cbbf8115e8a7 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -110,6 +110,7 @@ struct netns_ipv4 { int sysctl_igmp_max_memberships; int sysctl_igmp_max_msf; + int sysctl_igmp_llm_reports; struct ping_group_range ping_group_range; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 6da2e467b63c..2e22ee0efc98 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -107,9 +107,6 @@ #include #endif -/* IGMP reports for link-local multicast groups are enabled by default */ -int sysctl_igmp_llm_reports __read_mostly = 1; - #ifdef CONFIG_IP_MULTICAST /* Parameter names and values are taken from igmp-v2-06 draft */ @@ -430,6 +427,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted) { struct net_device *dev = pmc->interface->dev; + struct net *net = dev_net(dev); struct igmpv3_report *pih; struct igmpv3_grec *pgr = NULL; struct ip_sf_list *psf, *psf_next, *psf_prev, **psf_list; @@ -437,7 +435,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, if (pmc->multiaddr == IGMP_ALL_HOSTS) return skb; - if (ipv4_is_local_multicast(pmc->multiaddr) && !sysctl_igmp_llm_reports) + if (ipv4_is_local_multicast(pmc->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports) return skb; isquery = type == IGMPV3_MODE_IS_INCLUDE || @@ -540,6 +538,7 @@ empty_source: static int igmpv3_send_report(struct in_device *in_dev, struct ip_mc_list *pmc) { struct sk_buff *skb = NULL; + struct net *net = dev_net(in_dev->dev); int type; if (!pmc) { @@ -548,7 +547,7 @@ static int igmpv3_send_report(struct in_device *in_dev, struct ip_mc_list *pmc) if (pmc->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(pmc->multiaddr) && - !sysctl_igmp_llm_reports) + !net->ipv4.sysctl_igmp_llm_reports) continue; spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) @@ -684,7 +683,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, if (type == IGMPV3_HOST_MEMBERSHIP_REPORT) return igmpv3_send_report(in_dev, pmc); - if (ipv4_is_local_multicast(group) && !sysctl_igmp_llm_reports) + if (ipv4_is_local_multicast(group) && !net->ipv4.sysctl_igmp_llm_reports) return 0; if (type == IGMP_HOST_LEAVE_MESSAGE) @@ -855,12 +854,13 @@ static int igmp_marksources(struct ip_mc_list *pmc, int nsrcs, __be32 *srcs) static bool igmp_heard_report(struct in_device *in_dev, __be32 group) { struct ip_mc_list *im; + struct net *net = dev_net(in_dev->dev); /* Timers are only set for non-local groups */ if (group == IGMP_ALL_HOSTS) return false; - if (ipv4_is_local_multicast(group) && !sysctl_igmp_llm_reports) + if (ipv4_is_local_multicast(group) && !net->ipv4.sysctl_igmp_llm_reports) return false; rcu_read_lock(); @@ -884,6 +884,7 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, __be32 group = ih->group; int max_delay; int mark = 0; + struct net *net = dev_net(in_dev->dev); if (len == 8) { @@ -969,7 +970,7 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, if (im->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(im->multiaddr) && - !sysctl_igmp_llm_reports) + !net->ipv4.sysctl_igmp_llm_reports) continue; spin_lock_bh(&im->lock); if (im->tm_running) @@ -1184,6 +1185,7 @@ static void igmp_group_dropped(struct ip_mc_list *im) { struct in_device *in_dev = im->interface; #ifdef CONFIG_IP_MULTICAST + struct net *net = dev_net(in_dev->dev); int reporter; #endif @@ -1195,7 +1197,7 @@ static void igmp_group_dropped(struct ip_mc_list *im) #ifdef CONFIG_IP_MULTICAST if (im->multiaddr == IGMP_ALL_HOSTS) return; - if (ipv4_is_local_multicast(im->multiaddr) && !sysctl_igmp_llm_reports) + if (ipv4_is_local_multicast(im->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports) return; reporter = im->reporter; @@ -1220,6 +1222,7 @@ static void igmp_group_dropped(struct ip_mc_list *im) static void igmp_group_added(struct ip_mc_list *im) { struct in_device *in_dev = im->interface; + struct net *net = dev_net(in_dev->dev); if (im->loaded == 0) { im->loaded = 1; @@ -1229,7 +1232,7 @@ static void igmp_group_added(struct ip_mc_list *im) #ifdef CONFIG_IP_MULTICAST if (im->multiaddr == IGMP_ALL_HOSTS) return; - if (ipv4_is_local_multicast(im->multiaddr) && !sysctl_igmp_llm_reports) + if (ipv4_is_local_multicast(im->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports) return; if (in_dev->dead) @@ -1530,6 +1533,7 @@ static void ip_mc_rejoin_groups(struct in_device *in_dev) #ifdef CONFIG_IP_MULTICAST struct ip_mc_list *im; int type; + struct net *net = dev_net(in_dev->dev); ASSERT_RTNL(); @@ -1537,7 +1541,7 @@ static void ip_mc_rejoin_groups(struct in_device *in_dev) if (im->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(im->multiaddr) && - !sysctl_igmp_llm_reports) + !net->ipv4.sysctl_igmp_llm_reports) continue; /* a failover is happening and switches diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 225659a02cf2..fc40fa1303d3 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -852,7 +852,7 @@ static struct ctl_table ipv4_net_table[] = { }, { .procname = "igmp_link_local_mcast_reports", - .data = &sysctl_igmp_llm_reports, + .data = &init_net.ipv4.sysctl_igmp_llm_reports, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 055d8a9a0c61..6c3c1d5232c6 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2401,6 +2401,8 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_igmp_max_memberships = 20; net->ipv4.sysctl_igmp_max_msf = 10; + /* IGMP reports for link-local multicast groups are enabled by default */ + net->ipv4.sysctl_igmp_llm_reports = 1; return 0; fail: -- cgit v1.2.3-71-gd317 From 165094afcee79e4d5b6e94032a5d3be157460b4a Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Mon, 8 Feb 2016 23:29:24 +0200 Subject: igmp: Namespacify igmp_qrv sysctl knob Signed-off-by: Nikolay Borisov Signed-off-by: David S. Miller --- include/linux/igmp.h | 2 -- include/net/netns/ipv4.h | 1 + net/ipv4/igmp.c | 29 +++++++++++++++++------------ net/ipv4/sysctl_net_ipv4.c | 20 ++++++++++---------- net/ipv4/tcp_ipv4.c | 1 + 5 files changed, 29 insertions(+), 24 deletions(-) (limited to 'include/net') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index c683f4bf642b..12f6fba6d21a 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -37,8 +37,6 @@ static inline struct igmpv3_query * return (struct igmpv3_query *)skb_transport_header(skb); } -extern int sysctl_igmp_qrv; - struct ip_sf_socklist { unsigned int sl_max; unsigned int sl_count; diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index cbbf8115e8a7..848fe8056534 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -111,6 +111,7 @@ struct netns_ipv4 { int sysctl_igmp_max_memberships; int sysctl_igmp_max_msf; int sysctl_igmp_llm_reports; + int sysctl_igmp_qrv; struct ping_group_range ping_group_range; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 2e22ee0efc98..7c95335bf85e 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -762,9 +762,10 @@ static void igmp_ifc_timer_expire(unsigned long data) static void igmp_ifc_event(struct in_device *in_dev) { + struct net *net = dev_net(in_dev->dev); if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) return; - in_dev->mr_ifc_count = in_dev->mr_qrv ?: sysctl_igmp_qrv; + in_dev->mr_ifc_count = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; igmp_ifc_start_timer(in_dev, 1); } @@ -1086,6 +1087,7 @@ static void ip_mc_filter_del(struct in_device *in_dev, __be32 addr) static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im) { struct ip_mc_list *pmc; + struct net *net = dev_net(in_dev->dev); /* this is an "ip_mc_list" for convenience; only the fields below * are actually used. In particular, the refcnt and users are not @@ -1100,7 +1102,7 @@ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im) pmc->interface = im->interface; in_dev_hold(in_dev); pmc->multiaddr = im->multiaddr; - pmc->crcount = in_dev->mr_qrv ?: sysctl_igmp_qrv; + pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; pmc->sfmode = im->sfmode; if (pmc->sfmode == MCAST_INCLUDE) { struct ip_sf_list *psf; @@ -1245,7 +1247,7 @@ static void igmp_group_added(struct ip_mc_list *im) } /* else, v3 */ - im->crcount = in_dev->mr_qrv ?: sysctl_igmp_qrv; + im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; igmp_ifc_event(in_dev); #endif } @@ -1314,6 +1316,7 @@ static void ip_mc_hash_remove(struct in_device *in_dev, void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) { struct ip_mc_list *im; + struct net *net = dev_net(in_dev->dev); ASSERT_RTNL(); @@ -1340,7 +1343,7 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) spin_lock_init(&im->lock); #ifdef CONFIG_IP_MULTICAST setup_timer(&im->timer, igmp_timer_expire, (unsigned long)im); - im->unsolicit_count = sysctl_igmp_qrv; + im->unsolicit_count = net->ipv4.sysctl_igmp_qrv; #endif im->next_rcu = in_dev->mc_list; @@ -1640,6 +1643,7 @@ void ip_mc_down(struct in_device *in_dev) void ip_mc_init_dev(struct in_device *in_dev) { + struct net *net = dev_net(in_dev->dev); ASSERT_RTNL(); #ifdef CONFIG_IP_MULTICAST @@ -1647,7 +1651,7 @@ void ip_mc_init_dev(struct in_device *in_dev) (unsigned long)in_dev); setup_timer(&in_dev->mr_ifc_timer, igmp_ifc_timer_expire, (unsigned long)in_dev); - in_dev->mr_qrv = sysctl_igmp_qrv; + in_dev->mr_qrv = net->ipv4.sysctl_igmp_qrv; #endif spin_lock_init(&in_dev->mc_tomb_lock); @@ -1658,11 +1662,12 @@ void ip_mc_init_dev(struct in_device *in_dev) void ip_mc_up(struct in_device *in_dev) { struct ip_mc_list *pmc; + struct net *net = dev_net(in_dev->dev); ASSERT_RTNL(); #ifdef CONFIG_IP_MULTICAST - in_dev->mr_qrv = sysctl_igmp_qrv; + in_dev->mr_qrv = net->ipv4.sysctl_igmp_qrv; #endif ip_mc_inc_group(in_dev, IGMP_ALL_HOSTS); @@ -1728,9 +1733,6 @@ static struct in_device *ip_mc_find_dev(struct net *net, struct ip_mreqn *imr) /* * Join a socket to a group */ -#ifdef CONFIG_IP_MULTICAST -int sysctl_igmp_qrv __read_mostly = IGMP_QUERY_ROBUSTNESS_VARIABLE; -#endif static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, __be32 *psfsrc) @@ -1755,6 +1757,7 @@ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, if (!psf->sf_count[MCAST_INCLUDE] && !psf->sf_count[MCAST_EXCLUDE]) { #ifdef CONFIG_IP_MULTICAST struct in_device *in_dev = pmc->interface; + struct net *net = dev_net(in_dev->dev); #endif /* no more filters for this source */ @@ -1765,7 +1768,7 @@ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, #ifdef CONFIG_IP_MULTICAST if (psf->sf_oldin && !IGMP_V1_SEEN(in_dev) && !IGMP_V2_SEEN(in_dev)) { - psf->sf_crcount = in_dev->mr_qrv ?: sysctl_igmp_qrv; + psf->sf_crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; psf->sf_next = pmc->tomb; pmc->tomb = psf; rv = 1; @@ -1823,12 +1826,13 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode, pmc->sfcount[MCAST_INCLUDE]) { #ifdef CONFIG_IP_MULTICAST struct ip_sf_list *psf; + struct net *net = dev_net(in_dev->dev); #endif /* filter mode change */ pmc->sfmode = MCAST_INCLUDE; #ifdef CONFIG_IP_MULTICAST - pmc->crcount = in_dev->mr_qrv ?: sysctl_igmp_qrv; + pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; in_dev->mr_ifc_count = pmc->crcount; for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; @@ -1995,6 +1999,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, } else if (isexclude != (pmc->sfcount[MCAST_EXCLUDE] != 0)) { #ifdef CONFIG_IP_MULTICAST struct ip_sf_list *psf; + struct net *net = dev_net(pmc->interface->dev); in_dev = pmc->interface; #endif @@ -2006,7 +2011,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, #ifdef CONFIG_IP_MULTICAST /* else no filters; keep old mode for reports */ - pmc->crcount = in_dev->mr_qrv ?: sysctl_igmp_qrv; + pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; in_dev->mr_ifc_count = pmc->crcount; for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index fc40fa1303d3..b537338f5c97 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -367,16 +367,6 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, -#ifdef CONFIG_IP_MULTICAST - { - .procname = "igmp_qrv", - .data = &sysctl_igmp_qrv, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &one - }, -#endif { .procname = "inet_peer_threshold", .data = &inet_peer_threshold, @@ -871,6 +861,16 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, +#ifdef CONFIG_IP_MULTICAST + { + .procname = "igmp_qrv", + .data = &init_net.ipv4.sysctl_igmp_qrv, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one + }, +#endif { .procname = "tcp_keepalive_time", .data = &init_net.ipv4.sysctl_tcp_keepalive_time, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 6c3c1d5232c6..ba5d0146e3f0 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2403,6 +2403,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_igmp_max_msf = 10; /* IGMP reports for link-local multicast groups are enabled by default */ net->ipv4.sysctl_igmp_llm_reports = 1; + net->ipv4.sysctl_igmp_qrv = 2; return 0; fail: -- cgit v1.2.3-71-gd317 From 21e2e7f9b5fefdbf94a107a9b24d74baa5148ef3 Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Thu, 11 Feb 2016 20:50:44 +0000 Subject: net: enable LCO for udp_tunnel_handle_offloads() users The only protocol affected at present is Geneve. Signed-off-by: Edward Cree Signed-off-by: David S. Miller --- include/net/udp_tunnel.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index cca2ad3082c3..734c15662ea9 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -103,7 +103,8 @@ static inline struct sk_buff *udp_tunnel_handle_offloads(struct sk_buff *skb, { int type = udp_csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; - return iptunnel_handle_offloads(skb, udp_csum, type); + /* As we're a UDP tunnel, we support LCO, so don't need csum_help */ + return iptunnel_handle_offloads(skb, false, type); } static inline void udp_tunnel_gro_complete(struct sk_buff *skb, int nhoff) -- cgit v1.2.3-71-gd317 From 6fa79666e24d32be1b709f5269af41ed9e829e7e Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Thu, 11 Feb 2016 21:02:31 +0000 Subject: net: ip_tunnel: remove 'csum_help' argument to iptunnel_handle_offloads All users now pass false, so we can remove it, and remove the code that was conditional upon it. Signed-off-by: Edward Cree Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 2 +- include/net/ip_tunnels.h | 3 +-- include/net/udp_tunnel.h | 3 +-- net/ipv4/fou.c | 4 ++-- net/ipv4/ip_gre.c | 3 +-- net/ipv4/ip_tunnel_core.c | 18 ++++++------------ net/ipv4/ipip.c | 2 +- net/ipv6/sit.c | 4 ++-- net/netfilter/ipvs/ip_vs_xmit.c | 6 ++---- 9 files changed, 17 insertions(+), 28 deletions(-) (limited to 'include/net') diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 9f52203ac860..0a23c64379d6 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -1721,7 +1721,7 @@ static int vxlan_build_skb(struct sk_buff *skb, struct dst_entry *dst, if (WARN_ON(!skb)) return -ENOMEM; - skb = iptunnel_handle_offloads(skb, false, type); + skb = iptunnel_handle_offloads(skb, type); if (IS_ERR(skb)) return PTR_ERR(skb); diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 6db96ea0144f..bc439f32baa9 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -279,8 +279,7 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md, gfp_t flags); -struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb, bool gre_csum, - int gso_type_mask); +struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb, int gso_type_mask); static inline void iptunnel_xmit_stats(struct net_device *dev, int pkt_len) { diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index 734c15662ea9..97f5adb121a6 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -103,8 +103,7 @@ static inline struct sk_buff *udp_tunnel_handle_offloads(struct sk_buff *skb, { int type = udp_csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; - /* As we're a UDP tunnel, we support LCO, so don't need csum_help */ - return iptunnel_handle_offloads(skb, false, type); + return iptunnel_handle_offloads(skb, type); } static inline void udp_tunnel_gro_complete(struct sk_buff *skb, int nhoff) diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index dac1874a5911..88dab0c1670c 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -787,7 +787,7 @@ int fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, SKB_GSO_UDP_TUNNEL; __be16 sport; - skb = iptunnel_handle_offloads(skb, false, type); + skb = iptunnel_handle_offloads(skb, type); if (IS_ERR(skb)) return PTR_ERR(skb); @@ -820,7 +820,7 @@ int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, optlen += need_priv ? GUE_LEN_PRIV : 0; - skb = iptunnel_handle_offloads(skb, false, type); + skb = iptunnel_handle_offloads(skb, type); if (IS_ERR(skb)) return PTR_ERR(skb); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 9b31532d95f4..65748db44285 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -503,8 +503,7 @@ static void __gre_xmit(struct sk_buff *skb, struct net_device *dev, static struct sk_buff *gre_handle_offloads(struct sk_buff *skb, bool csum) { - return iptunnel_handle_offloads(skb, false, - csum ? SKB_GSO_GRE_CSUM : SKB_GSO_GRE); + return iptunnel_handle_offloads(skb, csum ? SKB_GSO_GRE_CSUM : SKB_GSO_GRE); } static struct rtable *gre_get_rt(struct sk_buff *skb, diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index d74ce93de1fe..a6e58b6141cd 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -148,7 +148,6 @@ struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md, EXPORT_SYMBOL_GPL(iptunnel_metadata_reply); struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb, - bool csum_help, int gso_type_mask) { int err; @@ -166,18 +165,13 @@ struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb, return skb; } - /* If packet is not gso and we are not offloading inner checksum, - * clear encapsulation flag. This allows setting CHECKSUM_PARTIAL - * on the outer header without confusing devices that implement - * NETIF_F_IP_CSUM with encapsulation. - */ - if (skb->ip_summed == CHECKSUM_PARTIAL && csum_help) { - skb->encapsulation = 0; - err = skb_checksum_help(skb); - if (unlikely(err)) - goto error; - } else if (skb->ip_summed != CHECKSUM_PARTIAL) { + if (skb->ip_summed != CHECKSUM_PARTIAL) { skb->ip_summed = CHECKSUM_NONE; + /* We clear encapsulation here to prevent badly-written + * drivers potentially deciding to offload an inner checksum + * if we set CHECKSUM_PARTIAL on the outer header. + * This should go away when the drivers are all fixed. + */ skb->encapsulation = 0; } diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 4044da61e747..6ec5b42fd172 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -219,7 +219,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) if (unlikely(skb->protocol != htons(ETH_P_IP))) goto tx_error; - skb = iptunnel_handle_offloads(skb, false, SKB_GSO_IPIP); + skb = iptunnel_handle_offloads(skb, SKB_GSO_IPIP); if (IS_ERR(skb)) goto out; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 2066d1c25a11..9a6b407f5840 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -911,7 +911,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, goto tx_error; } - skb = iptunnel_handle_offloads(skb, false, SKB_GSO_SIT); + skb = iptunnel_handle_offloads(skb, SKB_GSO_SIT); if (IS_ERR(skb)) { ip_rt_put(rt); goto out; @@ -1000,7 +1000,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *tiph = &tunnel->parms.iph; - skb = iptunnel_handle_offloads(skb, false, SKB_GSO_IPIP); + skb = iptunnel_handle_offloads(skb, SKB_GSO_IPIP); if (IS_ERR(skb)) goto out; diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 3264cb49b333..a3f5cd9b3c4c 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -1019,8 +1019,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, if (IS_ERR(skb)) goto tx_error; - skb = iptunnel_handle_offloads( - skb, false, __tun_gso_type_mask(AF_INET, cp->af)); + skb = iptunnel_handle_offloads(skb, __tun_gso_type_mask(AF_INET, cp->af)); if (IS_ERR(skb)) goto tx_error; @@ -1112,8 +1111,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, if (IS_ERR(skb)) goto tx_error; - skb = iptunnel_handle_offloads( - skb, false, __tun_gso_type_mask(AF_INET6, cp->af)); + skb = iptunnel_handle_offloads(skb, __tun_gso_type_mask(AF_INET6, cp->af)); if (IS_ERR(skb)) goto tx_error; -- cgit v1.2.3-71-gd317 From 911362c70df5b766c243dc297fadeaced786ffd8 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Fri, 12 Feb 2016 15:43:53 +0100 Subject: net: add dst_cache support This patch add a generic, lockless dst cache implementation. The need for lock is avoided updating the dst cache fields only in per cpu scope, and requiring that the cache manipulation functions are invoked with the local bh disabled. The refresh_ts and reset_ts fields are used to ensure the cache consistency in case of cuncurrent cache update (dst_cache_set*) and reset operation (dst_cache_reset). Consider the following scenario: CPU1: CPU2: dst_cache_reset() dst_cache_set() The dst entry set passed to dst_cache_set() should not be used for later dst cache lookup, because it's obtained using old configuration values. Since the refresh_ts is updated only on dst_cache lookup, the cached value in the above scenario will be discarded on the next lookup. Signed-off-by: Paolo Abeni Suggested-and-acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/net/dst_cache.h | 97 ++++++++++++++++++++++++++++ net/Kconfig | 4 ++ net/core/Makefile | 1 + net/core/dst_cache.c | 168 ++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 270 insertions(+) create mode 100644 include/net/dst_cache.h create mode 100644 net/core/dst_cache.c (limited to 'include/net') diff --git a/include/net/dst_cache.h b/include/net/dst_cache.h new file mode 100644 index 000000000000..151accae708b --- /dev/null +++ b/include/net/dst_cache.h @@ -0,0 +1,97 @@ +#ifndef _NET_DST_CACHE_H +#define _NET_DST_CACHE_H + +#include +#include +#if IS_ENABLED(CONFIG_IPV6) +#include +#endif + +struct dst_cache { + struct dst_cache_pcpu __percpu *cache; + unsigned long reset_ts; +}; + +/** + * dst_cache_get - perform cache lookup + * @dst_cache: the cache + * + * The caller should use dst_cache_get_ip4() if it need to retrieve the + * source address to be used when xmitting to the cached dst. + * local BH must be disabled. + */ +struct dst_entry *dst_cache_get(struct dst_cache *dst_cache); + +/** + * dst_cache_get_ip4 - perform cache lookup and fetch ipv4 source address + * @dst_cache: the cache + * @saddr: return value for the retrieved source address + * + * local BH must be disabled. + */ +struct rtable *dst_cache_get_ip4(struct dst_cache *dst_cache, __be32 *saddr); + +/** + * dst_cache_set_ip4 - store the ipv4 dst into the cache + * @dst_cache: the cache + * @dst: the entry to be cached + * @saddr: the source address to be stored inside the cache + * + * local BH must be disabled. + */ +void dst_cache_set_ip4(struct dst_cache *dst_cache, struct dst_entry *dst, + __be32 saddr); + +#if IS_ENABLED(CONFIG_IPV6) + +/** + * dst_cache_set_ip6 - store the ipv6 dst into the cache + * @dst_cache: the cache + * @dst: the entry to be cached + * @saddr: the source address to be stored inside the cache + * + * local BH must be disabled. + */ +void dst_cache_set_ip6(struct dst_cache *dst_cache, struct dst_entry *dst, + const struct in6_addr *addr); + +/** + * dst_cache_get_ip6 - perform cache lookup and fetch ipv6 source address + * @dst_cache: the cache + * @saddr: return value for the retrieved source address + * + * local BH must be disabled. + */ +struct dst_entry *dst_cache_get_ip6(struct dst_cache *dst_cache, + struct in6_addr *saddr); +#endif + +/** + * dst_cache_reset - invalidate the cache contents + * @dst_cache: the cache + * + * This do not free the cached dst to avoid races and contentions. + * the dst will be freed on later cache lookup. + */ +static inline void dst_cache_reset(struct dst_cache *dst_cache) +{ + dst_cache->reset_ts = jiffies; +} + +/** + * dst_cache_init - initialize the cache, allocating the required storage + * @dst_cache: the cache + * @gfp: allocation flags + */ +int dst_cache_init(struct dst_cache *dst_cache, gfp_t gfp); + +/** + * dst_cache_destroy - empty the cache and free the allocated storage + * @dst_cache: the cache + * + * No synchronization is enforced: it must be called only when the cache + * is unsed. + */ +void dst_cache_destroy(struct dst_cache *dst_cache); + +#endif diff --git a/net/Kconfig b/net/Kconfig index 174354618f8a..b80efecfc1a0 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -392,6 +392,10 @@ config LWTUNNEL weight tunnel endpoint. Tunnel encapsulation parameters are stored with light weight tunnel state associated with fib routes. +config DST_CACHE + bool "dst cache" + default n + endif # if NET # Used by archs to tell that they support BPF_JIT diff --git a/net/core/Makefile b/net/core/Makefile index 0b835de04de3..7a8fb8aef992 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -24,3 +24,4 @@ obj-$(CONFIG_NET_PTP_CLASSIFY) += ptp_classifier.o obj-$(CONFIG_CGROUP_NET_PRIO) += netprio_cgroup.o obj-$(CONFIG_CGROUP_NET_CLASSID) += netclassid_cgroup.o obj-$(CONFIG_LWTUNNEL) += lwtunnel.o +obj-$(CONFIG_DST_CACHE) += dst_cache.o diff --git a/net/core/dst_cache.c b/net/core/dst_cache.c new file mode 100644 index 000000000000..3938f3f38d69 --- /dev/null +++ b/net/core/dst_cache.c @@ -0,0 +1,168 @@ +/* + * net/core/dst_cache.c - dst entry cache + * + * Copyright (c) 2016 Paolo Abeni + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include +#include +#include +#include +#if IS_ENABLED(CONFIG_IPV6) +#include +#endif +#include + +struct dst_cache_pcpu { + unsigned long refresh_ts; + struct dst_entry *dst; + u32 cookie; + union { + struct in_addr in_saddr; + struct in6_addr in6_saddr; + }; +}; + +void dst_cache_per_cpu_dst_set(struct dst_cache_pcpu *dst_cache, + struct dst_entry *dst, u32 cookie) +{ + dst_release(dst_cache->dst); + if (dst) + dst_hold(dst); + + dst_cache->cookie = cookie; + dst_cache->dst = dst; +} + +struct dst_entry *dst_cache_per_cpu_get(struct dst_cache *dst_cache, + struct dst_cache_pcpu *idst) +{ + struct dst_entry *dst; + + dst = idst->dst; + if (!dst) + goto fail; + + /* the cache already hold a dst reference; it can't go away */ + dst_hold(dst); + + if (unlikely(!time_after(idst->refresh_ts, dst_cache->reset_ts) || + (dst->obsolete && !dst->ops->check(dst, idst->cookie)))) { + dst_cache_per_cpu_dst_set(idst, NULL, 0); + dst_release(dst); + goto fail; + } + return dst; + +fail: + idst->refresh_ts = jiffies; + return NULL; +} + +struct dst_entry *dst_cache_get(struct dst_cache *dst_cache) +{ + if (!dst_cache->cache) + return NULL; + + return dst_cache_per_cpu_get(dst_cache, this_cpu_ptr(dst_cache->cache)); +} +EXPORT_SYMBOL_GPL(dst_cache_get); + +struct rtable *dst_cache_get_ip4(struct dst_cache *dst_cache, __be32 *saddr) +{ + struct dst_cache_pcpu *idst; + struct dst_entry *dst; + + if (!dst_cache->cache) + return NULL; + + idst = this_cpu_ptr(dst_cache->cache); + dst = dst_cache_per_cpu_get(dst_cache, idst); + if (!dst) + return NULL; + + *saddr = idst->in_saddr.s_addr; + return container_of(dst, struct rtable, dst); +} +EXPORT_SYMBOL_GPL(dst_cache_get_ip4); + +void dst_cache_set_ip4(struct dst_cache *dst_cache, struct dst_entry *dst, + __be32 saddr) +{ + struct dst_cache_pcpu *idst; + + if (!dst_cache->cache) + return; + + idst = this_cpu_ptr(dst_cache->cache); + dst_cache_per_cpu_dst_set(idst, dst, 0); + idst->in_saddr.s_addr = saddr; +} +EXPORT_SYMBOL_GPL(dst_cache_set_ip4); + +#if IS_ENABLED(CONFIG_IPV6) +void dst_cache_set_ip6(struct dst_cache *dst_cache, struct dst_entry *dst, + const struct in6_addr *addr) +{ + struct dst_cache_pcpu *idst; + + if (!dst_cache->cache) + return; + + idst = this_cpu_ptr(dst_cache->cache); + dst_cache_per_cpu_dst_set(this_cpu_ptr(dst_cache->cache), dst, + rt6_get_cookie((struct rt6_info *)dst)); + idst->in6_saddr = *addr; +} +EXPORT_SYMBOL_GPL(dst_cache_set_ip6); + +struct dst_entry *dst_cache_get_ip6(struct dst_cache *dst_cache, + struct in6_addr *saddr) +{ + struct dst_cache_pcpu *idst; + struct dst_entry *dst; + + if (!dst_cache->cache) + return NULL; + + idst = this_cpu_ptr(dst_cache->cache); + dst = dst_cache_per_cpu_get(dst_cache, idst); + if (!dst) + return NULL; + + *saddr = idst->in6_saddr; + return dst; +} +EXPORT_SYMBOL_GPL(dst_cache_get_ip6); +#endif + +int dst_cache_init(struct dst_cache *dst_cache, gfp_t gfp) +{ + dst_cache->cache = alloc_percpu_gfp(struct dst_cache_pcpu, + gfp | __GFP_ZERO); + if (!dst_cache->cache) + return -ENOMEM; + + dst_cache_reset(dst_cache); + return 0; +} +EXPORT_SYMBOL_GPL(dst_cache_init); + +void dst_cache_destroy(struct dst_cache *dst_cache) +{ + int i; + + if (!dst_cache->cache) + return; + + for_each_possible_cpu(i) + dst_release(per_cpu_ptr(dst_cache->cache, i)->dst); + + free_percpu(dst_cache->cache); +} +EXPORT_SYMBOL_GPL(dst_cache_destroy); -- cgit v1.2.3-71-gd317 From 607f725f6f7d5ec3759fbc16224afb60e2152a5b Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Fri, 12 Feb 2016 15:43:54 +0100 Subject: net: replace dst_cache ip6_tunnel implementation with the generic one This also fix a potential race into the existing tunnel code, which could lead to the wrong dst to be permanenty cached: CPU1: CPU2: dst = ip6_route_output(...) dst_cache_reset() // no effect, // the cache is empty dst_cache_set() // the wrong dst // is permanenty stored // into the cache With the new dst implementation the above race is not possible since the first cache lookup after dst_cache_reset will fail due to the timestamp check Signed-off-by: Paolo Abeni Suggested-and-acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/net/ip6_tunnel.h | 14 +------ net/ipv6/Kconfig | 1 + net/ipv6/ip6_gre.c | 12 +++--- net/ipv6/ip6_tunnel.c | 103 +++-------------------------------------------- net/ipv6/ip6_vti.c | 2 +- 5 files changed, 16 insertions(+), 116 deletions(-) (limited to 'include/net') diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index 0d0ce0b2d870..499a707765ea 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -6,6 +6,7 @@ #include #include #include +#include #define IP6TUNNEL_ERR_TIMEO (30*HZ) @@ -33,12 +34,6 @@ struct __ip6_tnl_parm { __be32 o_key; }; -struct ip6_tnl_dst { - seqlock_t lock; - struct dst_entry __rcu *dst; - u32 cookie; -}; - /* IPv6 tunnel */ struct ip6_tnl { struct ip6_tnl __rcu *next; /* next tunnel in list */ @@ -46,7 +41,7 @@ struct ip6_tnl { struct net *net; /* netns for packet i/o */ struct __ip6_tnl_parm parms; /* tunnel configuration parameters */ struct flowi fl; /* flowi template for xmit */ - struct ip6_tnl_dst __percpu *dst_cache; /* cached dst */ + struct dst_cache dst_cache; /* cached dst */ int err_count; unsigned long err_time; @@ -66,11 +61,6 @@ struct ipv6_tlv_tnl_enc_lim { __u8 encap_limit; /* tunnel encapsulation limit */ } __packed; -struct dst_entry *ip6_tnl_dst_get(struct ip6_tnl *t); -int ip6_tnl_dst_init(struct ip6_tnl *t); -void ip6_tnl_dst_destroy(struct ip6_tnl *t); -void ip6_tnl_dst_reset(struct ip6_tnl *t); -void ip6_tnl_dst_set(struct ip6_tnl *t, struct dst_entry *dst); int ip6_tnl_rcv_ctl(struct ip6_tnl *t, const struct in6_addr *laddr, const struct in6_addr *raddr); int ip6_tnl_xmit_ctl(struct ip6_tnl *t, const struct in6_addr *laddr, diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index 40c897515ddc..11e875ffd7ac 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -207,6 +207,7 @@ config IPV6_NDISC_NODETYPE config IPV6_TUNNEL tristate "IPv6: IP-in-IPv6 tunnel (RFC2473)" select INET6_TUNNEL + select DST_CACHE ---help--- Support for IPv6-in-IPv6 and IPv4-in-IPv6 tunnels described in RFC 2473. diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index f37f18b6b40c..a94e50602813 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -360,7 +360,7 @@ static void ip6gre_tunnel_uninit(struct net_device *dev) struct ip6gre_net *ign = net_generic(t->net, ip6gre_net_id); ip6gre_tunnel_unlink(ign, t); - ip6_tnl_dst_reset(t); + dst_cache_reset(&t->dst_cache); dev_put(dev); } @@ -633,7 +633,7 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, } if (!fl6->flowi6_mark) - dst = ip6_tnl_dst_get(tunnel); + dst = dst_cache_get(&tunnel->dst_cache); if (!dst) { dst = ip6_route_output(net, NULL, fl6); @@ -702,7 +702,7 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, } if (!fl6->flowi6_mark && ndst) - ip6_tnl_dst_set(tunnel, ndst); + dst_cache_set_ip6(&tunnel->dst_cache, ndst, &fl6->saddr); skb_dst_set(skb, dst); proto = NEXTHDR_GRE; @@ -1009,7 +1009,7 @@ static int ip6gre_tnl_change(struct ip6_tnl *t, t->parms.o_key = p->o_key; t->parms.i_flags = p->i_flags; t->parms.o_flags = p->o_flags; - ip6_tnl_dst_reset(t); + dst_cache_reset(&t->dst_cache); ip6gre_tnl_link_config(t, set_mtu); return 0; } @@ -1219,7 +1219,7 @@ static void ip6gre_dev_free(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); - ip6_tnl_dst_destroy(t); + dst_cache_destroy(&t->dst_cache); free_percpu(dev->tstats); free_netdev(dev); } @@ -1257,7 +1257,7 @@ static int ip6gre_tunnel_init_common(struct net_device *dev) if (!dev->tstats) return -ENOMEM; - ret = ip6_tnl_dst_init(tunnel); + ret = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL); if (ret) { free_percpu(dev->tstats); dev->tstats = NULL; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 137fca42aaa6..3f3aabd2f07b 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -122,97 +122,6 @@ static struct net_device_stats *ip6_get_stats(struct net_device *dev) return &dev->stats; } -/* - * Locking : hash tables are protected by RCU and RTNL - */ - -static void ip6_tnl_per_cpu_dst_set(struct ip6_tnl_dst *idst, - struct dst_entry *dst) -{ - write_seqlock_bh(&idst->lock); - dst_release(rcu_dereference_protected( - idst->dst, - lockdep_is_held(&idst->lock.lock))); - if (dst) { - dst_hold(dst); - idst->cookie = rt6_get_cookie((struct rt6_info *)dst); - } else { - idst->cookie = 0; - } - rcu_assign_pointer(idst->dst, dst); - write_sequnlock_bh(&idst->lock); -} - -struct dst_entry *ip6_tnl_dst_get(struct ip6_tnl *t) -{ - struct ip6_tnl_dst *idst; - struct dst_entry *dst; - unsigned int seq; - u32 cookie; - - idst = raw_cpu_ptr(t->dst_cache); - - rcu_read_lock(); - do { - seq = read_seqbegin(&idst->lock); - dst = rcu_dereference(idst->dst); - cookie = idst->cookie; - } while (read_seqretry(&idst->lock, seq)); - - if (dst && !atomic_inc_not_zero(&dst->__refcnt)) - dst = NULL; - rcu_read_unlock(); - - if (dst && dst->obsolete && !dst->ops->check(dst, cookie)) { - ip6_tnl_per_cpu_dst_set(idst, NULL); - dst_release(dst); - dst = NULL; - } - return dst; -} -EXPORT_SYMBOL_GPL(ip6_tnl_dst_get); - -void ip6_tnl_dst_reset(struct ip6_tnl *t) -{ - int i; - - for_each_possible_cpu(i) - ip6_tnl_per_cpu_dst_set(per_cpu_ptr(t->dst_cache, i), NULL); -} -EXPORT_SYMBOL_GPL(ip6_tnl_dst_reset); - -void ip6_tnl_dst_set(struct ip6_tnl *t, struct dst_entry *dst) -{ - ip6_tnl_per_cpu_dst_set(raw_cpu_ptr(t->dst_cache), dst); - -} -EXPORT_SYMBOL_GPL(ip6_tnl_dst_set); - -void ip6_tnl_dst_destroy(struct ip6_tnl *t) -{ - if (!t->dst_cache) - return; - - ip6_tnl_dst_reset(t); - free_percpu(t->dst_cache); -} -EXPORT_SYMBOL_GPL(ip6_tnl_dst_destroy); - -int ip6_tnl_dst_init(struct ip6_tnl *t) -{ - int i; - - t->dst_cache = alloc_percpu(struct ip6_tnl_dst); - if (!t->dst_cache) - return -ENOMEM; - - for_each_possible_cpu(i) - seqlock_init(&per_cpu_ptr(t->dst_cache, i)->lock); - - return 0; -} -EXPORT_SYMBOL_GPL(ip6_tnl_dst_init); - /** * ip6_tnl_lookup - fetch tunnel matching the end-point addresses * @remote: the address of the tunnel exit-point @@ -329,7 +238,7 @@ static void ip6_dev_free(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); - ip6_tnl_dst_destroy(t); + dst_cache_destroy(&t->dst_cache); free_percpu(dev->tstats); free_netdev(dev); } @@ -462,7 +371,7 @@ ip6_tnl_dev_uninit(struct net_device *dev) RCU_INIT_POINTER(ip6n->tnls_wc[0], NULL); else ip6_tnl_unlink(ip6n, t); - ip6_tnl_dst_reset(t); + dst_cache_reset(&t->dst_cache); dev_put(dev); } @@ -1069,7 +978,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr)); neigh_release(neigh); } else if (!fl6->flowi6_mark) - dst = ip6_tnl_dst_get(t); + dst = dst_cache_get(&t->dst_cache); if (!ip6_tnl_xmit_ctl(t, &fl6->saddr, &fl6->daddr)) goto tx_err_link_failure; @@ -1133,7 +1042,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, } if (!fl6->flowi6_mark && ndst) - ip6_tnl_dst_set(t, ndst); + dst_cache_set_ip6(&t->dst_cache, ndst, &fl6->saddr); skb_dst_set(skb, dst); skb->transport_header = skb->network_header; @@ -1366,7 +1275,7 @@ ip6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p) t->parms.flowinfo = p->flowinfo; t->parms.link = p->link; t->parms.proto = p->proto; - ip6_tnl_dst_reset(t); + dst_cache_reset(&t->dst_cache); ip6_tnl_link_config(t); return 0; } @@ -1637,7 +1546,7 @@ ip6_tnl_dev_init_gen(struct net_device *dev) if (!dev->tstats) return -ENOMEM; - ret = ip6_tnl_dst_init(t); + ret = dst_cache_init(&t->dst_cache, GFP_KERNEL); if (ret) { free_percpu(dev->tstats); dev->tstats = NULL; diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 0a8610b33d79..d90a11f14040 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -640,7 +640,7 @@ vti6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p) t->parms.i_key = p->i_key; t->parms.o_key = p->o_key; t->parms.proto = p->proto; - ip6_tnl_dst_reset(t); + dst_cache_reset(&t->dst_cache); vti6_link_config(t); return 0; } -- cgit v1.2.3-71-gd317 From e09acddf873bf775b208b452a4c3a3fd26fa9427 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Fri, 12 Feb 2016 15:43:55 +0100 Subject: ip_tunnel: replace dst_cache with generic implementation The current ip_tunnel cache implementation is prone to a race that will cause the wrong dst to be cached on cuncurrent dst cache miss and ip tunnel update via netlink. Replacing with the generic implementation fix the issue. Signed-off-by: Paolo Abeni Suggested-and-acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/net/ip_tunnels.h | 9 ++---- net/ipv4/Kconfig | 1 + net/ipv4/ip_tunnel.c | 78 ++++++++---------------------------------------- net/ipv6/sit.c | 17 ++++++----- 4 files changed, 25 insertions(+), 80 deletions(-) (limited to 'include/net') diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index bc439f32baa9..fd36936d85a6 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -13,6 +13,7 @@ #include #include #include +#include #if IS_ENABLED(CONFIG_IPV6) #include @@ -85,11 +86,6 @@ struct ip_tunnel_prl_entry { struct rcu_head rcu_head; }; -struct ip_tunnel_dst { - struct dst_entry __rcu *dst; - __be32 saddr; -}; - struct metadata_dst; struct ip_tunnel { @@ -108,7 +104,7 @@ struct ip_tunnel { int tun_hlen; /* Precalculated header length */ int mlink; - struct ip_tunnel_dst __percpu *dst_cache; + struct dst_cache dst_cache; struct ip_tunnel_parm parms; @@ -247,7 +243,6 @@ int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[], int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], struct ip_tunnel_parm *p); void ip_tunnel_setup(struct net_device *dev, int net_id); -void ip_tunnel_dst_reset_all(struct ip_tunnel *t); int ip_tunnel_encap_setup(struct ip_tunnel *t, struct ip_tunnel_encap *ipencap); diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 775824720b6b..395d82754626 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -186,6 +186,7 @@ config NET_IPGRE_DEMUX config NET_IP_TUNNEL tristate + select DST_CACHE default n config NET_IPGRE diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index c7bd72e9b544..4569da7dfa88 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -68,61 +68,6 @@ static unsigned int ip_tunnel_hash(__be32 key, __be32 remote) IP_TNL_HASH_BITS); } -static void __tunnel_dst_set(struct ip_tunnel_dst *idst, - struct dst_entry *dst, __be32 saddr) -{ - struct dst_entry *old_dst; - - dst_clone(dst); - old_dst = xchg((__force struct dst_entry **)&idst->dst, dst); - dst_release(old_dst); - idst->saddr = saddr; -} - -static noinline void tunnel_dst_set(struct ip_tunnel *t, - struct dst_entry *dst, __be32 saddr) -{ - __tunnel_dst_set(raw_cpu_ptr(t->dst_cache), dst, saddr); -} - -static void tunnel_dst_reset(struct ip_tunnel *t) -{ - tunnel_dst_set(t, NULL, 0); -} - -void ip_tunnel_dst_reset_all(struct ip_tunnel *t) -{ - int i; - - for_each_possible_cpu(i) - __tunnel_dst_set(per_cpu_ptr(t->dst_cache, i), NULL, 0); -} -EXPORT_SYMBOL(ip_tunnel_dst_reset_all); - -static struct rtable *tunnel_rtable_get(struct ip_tunnel *t, - u32 cookie, __be32 *saddr) -{ - struct ip_tunnel_dst *idst; - struct dst_entry *dst; - - rcu_read_lock(); - idst = raw_cpu_ptr(t->dst_cache); - dst = rcu_dereference(idst->dst); - if (dst && !atomic_inc_not_zero(&dst->__refcnt)) - dst = NULL; - if (dst) { - if (!dst->obsolete || dst->ops->check(dst, cookie)) { - *saddr = idst->saddr; - } else { - tunnel_dst_reset(t); - dst_release(dst); - dst = NULL; - } - } - rcu_read_unlock(); - return (struct rtable *)dst; -} - static bool ip_tunnel_key_match(const struct ip_tunnel_parm *p, __be16 flags, __be32 key) { @@ -381,7 +326,8 @@ static int ip_tunnel_bind_dev(struct net_device *dev) if (!IS_ERR(rt)) { tdev = rt->dst.dev; - tunnel_dst_set(tunnel, &rt->dst, fl4.saddr); + dst_cache_set_ip4(&tunnel->dst_cache, &rt->dst, + fl4.saddr); ip_rt_put(rt); } if (dev->type != ARPHRD_ETHER) @@ -729,7 +675,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0) goto tx_error; - rt = connected ? tunnel_rtable_get(tunnel, 0, &fl4.saddr) : NULL; + rt = connected ? dst_cache_get_ip4(&tunnel->dst_cache, &fl4.saddr) : + NULL; if (!rt) { rt = ip_route_output_key(tunnel->net, &fl4); @@ -739,7 +686,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, goto tx_error; } if (connected) - tunnel_dst_set(tunnel, &rt->dst, fl4.saddr); + dst_cache_set_ip4(&tunnel->dst_cache, &rt->dst, + fl4.saddr); } if (rt->dst.dev == dev) { @@ -836,7 +784,7 @@ static void ip_tunnel_update(struct ip_tunnel_net *itn, if (set_mtu) dev->mtu = mtu; } - ip_tunnel_dst_reset_all(t); + dst_cache_reset(&t->dst_cache); netdev_state_change(dev); } @@ -961,7 +909,7 @@ static void ip_tunnel_dev_free(struct net_device *dev) struct ip_tunnel *tunnel = netdev_priv(dev); gro_cells_destroy(&tunnel->gro_cells); - free_percpu(tunnel->dst_cache); + dst_cache_destroy(&tunnel->dst_cache); free_percpu(dev->tstats); free_netdev(dev); } @@ -1155,15 +1103,15 @@ int ip_tunnel_init(struct net_device *dev) if (!dev->tstats) return -ENOMEM; - tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst); - if (!tunnel->dst_cache) { + err = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL); + if (err) { free_percpu(dev->tstats); - return -ENOMEM; + return err; } err = gro_cells_init(&tunnel->gro_cells, dev); if (err) { - free_percpu(tunnel->dst_cache); + dst_cache_destroy(&tunnel->dst_cache); free_percpu(dev->tstats); return err; } @@ -1193,7 +1141,7 @@ void ip_tunnel_uninit(struct net_device *dev) if (itn->fb_tunnel_dev != dev) ip_tunnel_del(itn, netdev_priv(dev)); - ip_tunnel_dst_reset_all(tunnel); + dst_cache_reset(&tunnel->dst_cache); } EXPORT_SYMBOL_GPL(ip_tunnel_uninit); diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 9a6b407f5840..0625ac6356b5 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -475,7 +475,7 @@ static void ipip6_tunnel_uninit(struct net_device *dev) ipip6_tunnel_unlink(sitn, tunnel); ipip6_tunnel_del_prl(tunnel, NULL); } - ip_tunnel_dst_reset_all(tunnel); + dst_cache_reset(&tunnel->dst_cache); dev_put(dev); } @@ -1093,7 +1093,7 @@ static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p) t->parms.link = p->link; ipip6_tunnel_bind_dev(t->dev); } - ip_tunnel_dst_reset_all(t); + dst_cache_reset(&t->dst_cache); netdev_state_change(t->dev); } @@ -1124,7 +1124,7 @@ static int ipip6_tunnel_update_6rd(struct ip_tunnel *t, t->ip6rd.relay_prefix = relay_prefix; t->ip6rd.prefixlen = ip6rd->prefixlen; t->ip6rd.relay_prefixlen = ip6rd->relay_prefixlen; - ip_tunnel_dst_reset_all(t); + dst_cache_reset(&t->dst_cache); netdev_state_change(t->dev); return 0; } @@ -1278,7 +1278,7 @@ ipip6_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) err = ipip6_tunnel_add_prl(t, &prl, cmd == SIOCCHGPRL); break; } - ip_tunnel_dst_reset_all(t); + dst_cache_reset(&t->dst_cache); netdev_state_change(dev); break; @@ -1339,7 +1339,7 @@ static void ipip6_dev_free(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - free_percpu(tunnel->dst_cache); + dst_cache_destroy(&tunnel->dst_cache); free_percpu(dev->tstats); free_netdev(dev); } @@ -1372,6 +1372,7 @@ static void ipip6_tunnel_setup(struct net_device *dev) static int ipip6_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); + int err; tunnel->dev = dev; tunnel->net = dev_net(dev); @@ -1382,10 +1383,10 @@ static int ipip6_tunnel_init(struct net_device *dev) if (!dev->tstats) return -ENOMEM; - tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst); - if (!tunnel->dst_cache) { + err = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL); + if (err) { free_percpu(dev->tstats); - return -ENOMEM; + return err; } return 0; -- cgit v1.2.3-71-gd317 From 0c1d70af924b966cc71e9e48920b2b635441aa50 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Fri, 12 Feb 2016 15:43:56 +0100 Subject: net: use dst_cache for vxlan device In case of UDP traffic with datagram length below MTU this give about 3% performance increase when tunneling over ipv4 and about 70% when tunneling over ipv6. Signed-off-by: Paolo Abeni Suggested-and-acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 55 +++++++++++++++++++++++++++++++++++++++++++++-------- include/net/vxlan.h | 1 + 2 files changed, 48 insertions(+), 8 deletions(-) (limited to 'include/net') diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 0a23c64379d6..ad673037bd73 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -480,6 +480,8 @@ static int vxlan_fdb_replace(struct vxlan_fdb *f, rd = list_first_entry_or_null(&f->remotes, struct vxlan_rdst, list); if (!rd) return 0; + + dst_cache_reset(&rd->dst_cache); rd->remote_ip = *ip; rd->remote_port = port; rd->remote_vni = vni; @@ -501,6 +503,12 @@ static int vxlan_fdb_append(struct vxlan_fdb *f, rd = kmalloc(sizeof(*rd), GFP_ATOMIC); if (rd == NULL) return -ENOBUFS; + + if (dst_cache_init(&rd->dst_cache, GFP_ATOMIC)) { + kfree(rd); + return -ENOBUFS; + } + rd->remote_ip = *ip; rd->remote_port = port; rd->remote_vni = vni; @@ -749,8 +757,10 @@ static void vxlan_fdb_free(struct rcu_head *head) struct vxlan_fdb *f = container_of(head, struct vxlan_fdb, rcu); struct vxlan_rdst *rd, *nd; - list_for_each_entry_safe(rd, nd, &f->remotes, list) + list_for_each_entry_safe(rd, nd, &f->remotes, list) { + dst_cache_destroy(&rd->dst_cache); kfree(rd); + } kfree(f); } @@ -1754,11 +1764,24 @@ static int vxlan_build_skb(struct sk_buff *skb, struct dst_entry *dst, static struct rtable *vxlan_get_route(struct vxlan_dev *vxlan, struct sk_buff *skb, int oif, u8 tos, - __be32 daddr, __be32 *saddr) + __be32 daddr, __be32 *saddr, + struct dst_cache *dst_cache, + struct ip_tunnel_info *info) { struct rtable *rt = NULL; + bool use_cache = false; struct flowi4 fl4; + /* when the ip_tunnel_info is availble, the tos used for lookup is + * packet independent, so we can use the cache + */ + if (dst_cache && !skb->mark && (!tos || info)) { + use_cache = true; + rt = dst_cache_get_ip4(dst_cache, saddr); + if (rt) + return rt; + } + memset(&fl4, 0, sizeof(fl4)); fl4.flowi4_oif = oif; fl4.flowi4_tos = RT_TOS(tos); @@ -1768,8 +1791,11 @@ static struct rtable *vxlan_get_route(struct vxlan_dev *vxlan, fl4.saddr = vxlan->cfg.saddr.sin.sin_addr.s_addr; rt = ip_route_output_key(vxlan->net, &fl4); - if (!IS_ERR(rt)) + if (!IS_ERR(rt)) { *saddr = fl4.saddr; + if (use_cache) + dst_cache_set_ip4(dst_cache, &rt->dst, fl4.saddr); + } return rt; } @@ -1777,12 +1803,21 @@ static struct rtable *vxlan_get_route(struct vxlan_dev *vxlan, static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan, struct sk_buff *skb, int oif, const struct in6_addr *daddr, - struct in6_addr *saddr) + struct in6_addr *saddr, + struct dst_cache *dst_cache) { + bool use_cache = false; struct dst_entry *ndst; struct flowi6 fl6; int err; + if (dst_cache && !skb->mark) { + use_cache = true; + ndst = dst_cache_get_ip6(dst_cache, saddr); + if (ndst) + return ndst; + } + memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_oif = oif; fl6.daddr = *daddr; @@ -1797,6 +1832,8 @@ static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan, return ERR_PTR(err); *saddr = fl6.saddr; + if (use_cache) + dst_cache_set_ip6(dst_cache, ndst, saddr); return ndst; } #endif @@ -1938,7 +1975,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, rt = vxlan_get_route(vxlan, skb, rdst ? rdst->remote_ifindex : 0, tos, - dst->sin.sin_addr.s_addr, &saddr); + dst->sin.sin_addr.s_addr, &saddr, + rdst ? &rdst->dst_cache : NULL, info); if (IS_ERR(rt)) { netdev_dbg(dev, "no route to %pI4\n", &dst->sin.sin_addr.s_addr); @@ -1990,7 +2028,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, ndst = vxlan6_get_route(vxlan, skb, rdst ? rdst->remote_ifindex : 0, - &dst->sin6.sin6_addr, &saddr); + &dst->sin6.sin6_addr, &saddr, + rdst ? &rdst->dst_cache : NULL); if (IS_ERR(ndst)) { netdev_dbg(dev, "no route to %pI6\n", &dst->sin6.sin6_addr); @@ -2331,7 +2370,7 @@ static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) return -EINVAL; rt = vxlan_get_route(vxlan, skb, 0, info->key.tos, info->key.u.ipv4.dst, - &info->key.u.ipv4.src); + &info->key.u.ipv4.src, NULL, info); if (IS_ERR(rt)) return PTR_ERR(rt); ip_rt_put(rt); @@ -2343,7 +2382,7 @@ static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) return -EINVAL; ndst = vxlan6_get_route(vxlan, skb, 0, &info->key.u.ipv6.dst, - &info->key.u.ipv6.src); + &info->key.u.ipv6.src, NULL); if (IS_ERR(ndst)) return PTR_ERR(ndst); dst_release(ndst); diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 25bd919c9ef0..b314e4af89c5 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -148,6 +148,7 @@ struct vxlan_rdst { u32 remote_ifindex; struct list_head list; struct rcu_head rcu; + struct dst_cache dst_cache; }; struct vxlan_config { -- cgit v1.2.3-71-gd317 From d71785ffc7e7cae3fbdc4ea8a9d05b7a1c59f7b8 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Fri, 12 Feb 2016 15:43:57 +0100 Subject: net: add dst_cache to ovs vxlan lwtunnel In case of UDP traffic with datagram length below MTU this give about 2% performance increase when tunneling over ipv4 and about 60% when tunneling over ipv6 Signed-off-by: Paolo Abeni Suggested-and-acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 15 ++++++++------- include/net/dst_metadata.h | 1 + include/net/ip_tunnels.h | 3 +++ net/core/dst.c | 10 +++++++++- net/openvswitch/Kconfig | 1 + net/openvswitch/flow_netlink.c | 6 ++++++ 6 files changed, 28 insertions(+), 8 deletions(-) (limited to 'include/net') diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index ad673037bd73..ee1206d9f8df 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -1775,7 +1775,7 @@ static struct rtable *vxlan_get_route(struct vxlan_dev *vxlan, /* when the ip_tunnel_info is availble, the tos used for lookup is * packet independent, so we can use the cache */ - if (dst_cache && !skb->mark && (!tos || info)) { + if (!skb->mark && (!tos || info)) { use_cache = true; rt = dst_cache_get_ip4(dst_cache, saddr); if (rt) @@ -1806,13 +1806,11 @@ static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan, struct in6_addr *saddr, struct dst_cache *dst_cache) { - bool use_cache = false; struct dst_entry *ndst; struct flowi6 fl6; int err; - if (dst_cache && !skb->mark) { - use_cache = true; + if (!skb->mark) { ndst = dst_cache_get_ip6(dst_cache, saddr); if (ndst) return ndst; @@ -1832,7 +1830,7 @@ static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan, return ERR_PTR(err); *saddr = fl6.saddr; - if (use_cache) + if (!skb->mark) dst_cache_set_ip6(dst_cache, ndst, saddr); return ndst; } @@ -1886,6 +1884,7 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, struct vxlan_rdst *rdst, bool did_rsc) { + struct dst_cache *dst_cache; struct ip_tunnel_info *info; struct vxlan_dev *vxlan = netdev_priv(dev); struct sock *sk; @@ -1910,6 +1909,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, dst_port = rdst->remote_port ? rdst->remote_port : vxlan->cfg.dst_port; vni = rdst->remote_vni; dst = &rdst->remote_ip; + dst_cache = &rdst->dst_cache; } else { if (!info) { WARN_ONCE(1, "%s: Missing encapsulation instructions\n", @@ -1924,6 +1924,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, else remote_ip.sin6.sin6_addr = info->key.u.ipv6.dst; dst = &remote_ip; + dst_cache = &info->dst_cache; } if (vxlan_addr_any(dst)) { @@ -1976,7 +1977,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, rt = vxlan_get_route(vxlan, skb, rdst ? rdst->remote_ifindex : 0, tos, dst->sin.sin_addr.s_addr, &saddr, - rdst ? &rdst->dst_cache : NULL, info); + dst_cache, info); if (IS_ERR(rt)) { netdev_dbg(dev, "no route to %pI4\n", &dst->sin.sin_addr.s_addr); @@ -2029,7 +2030,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, ndst = vxlan6_get_route(vxlan, skb, rdst ? rdst->remote_ifindex : 0, &dst->sin6.sin6_addr, &saddr, - rdst ? &rdst->dst_cache : NULL); + dst_cache); if (IS_ERR(ndst)) { netdev_dbg(dev, "no route to %pI6\n", &dst->sin6.sin6_addr); diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h index 30a56ab2ccfb..84b833af6882 100644 --- a/include/net/dst_metadata.h +++ b/include/net/dst_metadata.h @@ -62,6 +62,7 @@ static inline int skb_metadata_dst_cmp(const struct sk_buff *skb_a, sizeof(a->u.tun_info) + a->u.tun_info.options_len); } +void metadata_dst_free(struct metadata_dst *); struct metadata_dst *metadata_dst_alloc(u8 optslen, gfp_t flags); struct metadata_dst __percpu *metadata_dst_alloc_percpu(u8 optslen, gfp_t flags); diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index fd36936d85a6..87408ab80856 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -58,6 +58,9 @@ struct ip_tunnel_key { struct ip_tunnel_info { struct ip_tunnel_key key; +#ifdef CONFIG_DST_CACHE + struct dst_cache dst_cache; +#endif u8 options_len; u8 mode; }; diff --git a/net/core/dst.c b/net/core/dst.c index a1656e3b8d72..b5cbbe07f786 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -265,7 +265,7 @@ again: lwtstate_put(dst->lwtstate); if (dst->flags & DST_METADATA) - kfree(dst); + metadata_dst_free((struct metadata_dst *)dst); else kmem_cache_free(dst->ops->kmem_cachep, dst); @@ -395,6 +395,14 @@ struct metadata_dst *metadata_dst_alloc(u8 optslen, gfp_t flags) } EXPORT_SYMBOL_GPL(metadata_dst_alloc); +void metadata_dst_free(struct metadata_dst *md_dst) +{ +#ifdef CONFIG_DST_CACHE + dst_cache_destroy(&md_dst->u.tun_info.dst_cache); +#endif + kfree(md_dst); +} + struct metadata_dst __percpu *metadata_dst_alloc_percpu(u8 optslen, gfp_t flags) { int cpu; diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig index d143aa9f6654..cd5fd9d728a7 100644 --- a/net/openvswitch/Kconfig +++ b/net/openvswitch/Kconfig @@ -10,6 +10,7 @@ config OPENVSWITCH select LIBCRC32C select MPLS select NET_MPLS_GSO + select DST_CACHE ---help--- Open vSwitch is a multilayer Ethernet switch targeted at virtualized environments. In addition to supporting a variety of features diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index d1bd4a45ca2d..58b8efc23668 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -1959,6 +1959,12 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, if (!tun_dst) return -ENOMEM; + err = dst_cache_init(&tun_dst->u.tun_info.dst_cache, GFP_KERNEL); + if (err) { + dst_release((struct dst_entry *)tun_dst); + return err; + } + a = __add_action(sfa, OVS_KEY_ATTR_TUNNEL_INFO, NULL, sizeof(*ovs_tun), log); if (IS_ERR(a)) { -- cgit v1.2.3-71-gd317 From fa50d974d104113630d68b7d03233a6686230d0c Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Mon, 15 Feb 2016 12:11:27 +0200 Subject: ipv4: Namespaceify ip_default_ttl sysctl knob Signed-off-by: Nikolay Borisov Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 1 + include/net/route.h | 5 ++--- net/bridge/netfilter/nft_reject_bridge.c | 8 +++++--- net/ipv4/ip_output.c | 3 --- net/ipv4/ip_sockglue.c | 5 ++++- net/ipv4/netfilter/ipt_SYNPROXY.c | 3 ++- net/ipv4/proc.c | 2 +- net/ipv4/sysctl_net_ipv4.c | 20 +++++++++++--------- 8 files changed, 26 insertions(+), 21 deletions(-) (limited to 'include/net') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 848fe8056534..bc8f7f94abcb 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -80,6 +80,7 @@ struct netns_ipv4 { int sysctl_tcp_ecn; int sysctl_tcp_ecn_fallback; + int sysctl_ip_default_ttl; int sysctl_ip_no_pmtu_disc; int sysctl_ip_fwd_use_pmtu; int sysctl_ip_nonlocal_bind; diff --git a/include/net/route.h b/include/net/route.h index a3b9ef74a389..9b0a523bb428 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -329,14 +329,13 @@ static inline int inet_iif(const struct sk_buff *skb) return skb->skb_iif; } -extern int sysctl_ip_default_ttl; - static inline int ip4_dst_hoplimit(const struct dst_entry *dst) { int hoplimit = dst_metric_raw(dst, RTAX_HOPLIMIT); + struct net *net = dev_net(dst->dev); if (hoplimit == 0) - hoplimit = sysctl_ip_default_ttl; + hoplimit = net->ipv4.sysctl_ip_default_ttl; return hoplimit; } diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c index fdba3d9fbff3..adc8d7221dbb 100644 --- a/net/bridge/netfilter/nft_reject_bridge.c +++ b/net/bridge/netfilter/nft_reject_bridge.c @@ -48,6 +48,7 @@ static void nft_reject_br_send_v4_tcp_reset(struct sk_buff *oldskb, struct iphdr *niph; const struct tcphdr *oth; struct tcphdr _oth; + struct net *net = sock_net(oldskb->sk); if (!nft_bridge_iphdr_validate(oldskb)) return; @@ -63,9 +64,9 @@ static void nft_reject_br_send_v4_tcp_reset(struct sk_buff *oldskb, skb_reserve(nskb, LL_MAX_HEADER); niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_TCP, - sysctl_ip_default_ttl); + net->ipv4.sysctl_ip_default_ttl); nf_reject_ip_tcphdr_put(nskb, oldskb, oth); - niph->ttl = sysctl_ip_default_ttl; + niph->ttl = net->ipv4.sysctl_ip_default_ttl; niph->tot_len = htons(nskb->len); ip_send_check(niph); @@ -85,6 +86,7 @@ static void nft_reject_br_send_v4_unreach(struct sk_buff *oldskb, void *payload; __wsum csum; u8 proto; + struct net *net = sock_net(oldskb->sk); if (oldskb->csum_bad || !nft_bridge_iphdr_validate(oldskb)) return; @@ -119,7 +121,7 @@ static void nft_reject_br_send_v4_unreach(struct sk_buff *oldskb, skb_reserve(nskb, LL_MAX_HEADER); niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_ICMP, - sysctl_ip_default_ttl); + net->ipv4.sysctl_ip_default_ttl); skb_reset_transport_header(nskb); icmph = (struct icmphdr *)skb_put(nskb, sizeof(struct icmphdr)); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 64878efa045c..f734c42acdaf 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -79,9 +79,6 @@ #include #include -int sysctl_ip_default_ttl __read_mostly = IPDEFTTL; -EXPORT_SYMBOL(sysctl_ip_default_ttl); - static int ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int mtu, diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 92808f147ef5..3f1befc4e17b 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -1341,10 +1341,13 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, val = inet->tos; break; case IP_TTL: + { + struct net *net = sock_net(sk); val = (inet->uc_ttl == -1 ? - sysctl_ip_default_ttl : + net->ipv4.sysctl_ip_default_ttl : inet->uc_ttl); break; + } case IP_HDRINCL: val = inet->hdrincl; break; diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index 5fdc556514ba..7b8fbb352877 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -21,6 +21,7 @@ static struct iphdr * synproxy_build_ip(struct sk_buff *skb, __be32 saddr, __be32 daddr) { struct iphdr *iph; + struct net *net = sock_net(skb->sk); skb_reset_network_header(skb); iph = (struct iphdr *)skb_put(skb, sizeof(*iph)); @@ -29,7 +30,7 @@ synproxy_build_ip(struct sk_buff *skb, __be32 saddr, __be32 daddr) iph->tos = 0; iph->id = 0; iph->frag_off = htons(IP_DF); - iph->ttl = sysctl_ip_default_ttl; + iph->ttl = net->ipv4.sysctl_ip_default_ttl; iph->protocol = IPPROTO_TCP; iph->check = 0; iph->saddr = saddr; diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 3abd9d7a3adf..9f665b63a927 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -390,7 +390,7 @@ static int snmp_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "\nIp: %d %d", IPV4_DEVCONF_ALL(net, FORWARDING) ? 1 : 2, - sysctl_ip_default_ttl); + net->ipv4.sysctl_ip_default_ttl); BUILD_BUG_ON(offsetof(struct ipstats_mib, mibs) != 0); for (i = 0; snmp4_ipstats_list[i].name != NULL; i++) diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index b537338f5c97..a833a9f9e4cd 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -282,15 +282,6 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, - { - .procname = "ip_default_ttl", - .data = &sysctl_ip_default_ttl, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &ip_ttl_min, - .extra2 = &ip_ttl_max, - }, { .procname = "tcp_max_orphans", .data = &sysctl_tcp_max_orphans, @@ -752,6 +743,15 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "ip_default_ttl", + .data = &init_net.ipv4.sysctl_ip_default_ttl, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &ip_ttl_min, + .extra2 = &ip_ttl_max, + }, { .procname = "ip_local_port_range", .maxlen = sizeof(init_net.ipv4.ip_local_ports.range), @@ -988,6 +988,8 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) if (!net->ipv4.sysctl_local_reserved_ports) goto err_ports; + net->ipv4.sysctl_ip_default_ttl = IPDEFTTL; + return 0; err_ports: -- cgit v1.2.3-71-gd317 From 287b7f38fd6842e534db1783cead3843f7677b79 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Mon, 15 Feb 2016 12:11:29 +0200 Subject: ipv4: Namespacify ip_dynaddr sysctl knob Signed-off-by: Nikolay Borisov Signed-off-by: David S. Miller --- include/net/ip.h | 3 --- include/net/netns/ipv4.h | 2 ++ net/ipv4/af_inet.c | 10 ++-------- net/ipv4/sysctl_net_ipv4.c | 15 ++++++++------- 4 files changed, 12 insertions(+), 18 deletions(-) (limited to 'include/net') diff --git a/include/net/ip.h b/include/net/ip.h index 1a98f1ca1638..e3fb25d76421 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -248,9 +248,6 @@ extern int inet_peer_maxttl; /* From ip_input.c */ extern int sysctl_ip_early_demux; -/* From ip_output.c */ -extern int sysctl_ip_dynaddr; - void ipfrag_init(void); void ip_static_sysctl_init(void); diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index bc8f7f94abcb..b7e3fb2587da 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -84,6 +84,8 @@ struct netns_ipv4 { int sysctl_ip_no_pmtu_disc; int sysctl_ip_fwd_use_pmtu; int sysctl_ip_nonlocal_bind; + /* Shall we try to damage output packets if routing dev changes? */ + int sysctl_ip_dynaddr; int sysctl_fwmark_reflect; int sysctl_tcp_fwmark_accept; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index eade66db214e..209d1ed28954 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1095,12 +1095,6 @@ void inet_unregister_protosw(struct inet_protosw *p) } EXPORT_SYMBOL(inet_unregister_protosw); -/* - * Shall we try to damage output packets if routing dev changes? - */ - -int sysctl_ip_dynaddr __read_mostly; - static int inet_sk_reselect_saddr(struct sock *sk) { struct inet_sock *inet = inet_sk(sk); @@ -1131,7 +1125,7 @@ static int inet_sk_reselect_saddr(struct sock *sk) if (new_saddr == old_saddr) return 0; - if (sysctl_ip_dynaddr > 1) { + if (sock_net(sk)->ipv4.sysctl_ip_dynaddr > 1) { pr_info("%s(): shifting inet->saddr from %pI4 to %pI4\n", __func__, &old_saddr, &new_saddr); } @@ -1186,7 +1180,7 @@ int inet_sk_rebuild_header(struct sock *sk) * Other protocols have to map its equivalent state to TCP_SYN_SENT. * DCCP maps its DCCP_REQUESTING state to TCP_SYN_SENT. -acme */ - if (!sysctl_ip_dynaddr || + if (!sock_net(sk)->ipv4.sysctl_ip_dynaddr || sk->sk_state != TCP_SYN_SENT || (sk->sk_userlocks & SOCK_BINDADDR_LOCK) || (err = inet_sk_reselect_saddr(sk)) != 0) diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index a833a9f9e4cd..04ac5b763385 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -303,13 +303,6 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, - { - .procname = "ip_dynaddr", - .data = &sysctl_ip_dynaddr, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, { .procname = "tcp_fastopen", .data = &sysctl_tcp_fastopen, @@ -743,6 +736,13 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "ip_dynaddr", + .data = &init_net.ipv4.sysctl_ip_dynaddr, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { .procname = "ip_default_ttl", .data = &init_net.ipv4.sysctl_ip_default_ttl, @@ -989,6 +989,7 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) goto err_ports; net->ipv4.sysctl_ip_default_ttl = IPDEFTTL; + net->ipv4.sysctl_ip_dynaddr = 0; return 0; -- cgit v1.2.3-71-gd317 From e21145a9871aa5ae07e01926105bb8e523d64095 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Mon, 15 Feb 2016 12:11:30 +0200 Subject: ipv4: namespacify ip_early_demux sysctl knob Signed-off-by: Nikolay Borisov Signed-off-by: David S. Miller --- include/net/ip.h | 3 --- include/net/netns/ipv4.h | 1 + net/ipv4/ip_input.c | 5 +---- net/ipv4/sysctl_net_ipv4.c | 15 ++++++++------- net/ipv6/ip6_input.c | 2 +- 5 files changed, 11 insertions(+), 15 deletions(-) (limited to 'include/net') diff --git a/include/net/ip.h b/include/net/ip.h index e3fb25d76421..cbb134b2f0e4 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -245,9 +245,6 @@ extern int inet_peer_threshold; extern int inet_peer_minttl; extern int inet_peer_maxttl; -/* From ip_input.c */ -extern int sysctl_ip_early_demux; - void ipfrag_init(void); void ip_static_sysctl_init(void); diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index b7e3fb2587da..a69cde3ce460 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -86,6 +86,7 @@ struct netns_ipv4 { int sysctl_ip_nonlocal_bind; /* Shall we try to damage output packets if routing dev changes? */ int sysctl_ip_dynaddr; + int sysctl_ip_early_demux; int sysctl_fwmark_reflect; int sysctl_tcp_fwmark_accept; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 852002f64c68..e3d782746d9d 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -308,15 +308,12 @@ drop: return true; } -int sysctl_ip_early_demux __read_mostly = 1; -EXPORT_SYMBOL(sysctl_ip_early_demux); - static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { const struct iphdr *iph = ip_hdr(skb); struct rtable *rt; - if (sysctl_ip_early_demux && + if (net->ipv4.sysctl_ip_early_demux && !skb_dst(skb) && !skb->sk && !ip_is_fragment(iph)) { diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 04ac5b763385..1e1fe6086dd9 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -296,13 +296,6 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, - { - .procname = "ip_early_demux", - .data = &sysctl_ip_early_demux, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, { .procname = "tcp_fastopen", .data = &sysctl_tcp_fastopen, @@ -743,6 +736,13 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "ip_early_demux", + .data = &init_net.ipv4.sysctl_ip_early_demux, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { .procname = "ip_default_ttl", .data = &init_net.ipv4.sysctl_ip_default_ttl, @@ -990,6 +990,7 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) net->ipv4.sysctl_ip_default_ttl = IPDEFTTL; net->ipv4.sysctl_ip_dynaddr = 0; + net->ipv4.sysctl_ip_early_demux = 1; return 0; diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 31ac3c56da4b..c05c425c2389 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -49,7 +49,7 @@ int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { - if (sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) { + if (net->ipv4.sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) { const struct inet6_protocol *ipprot; ipprot = rcu_dereference(inet6_protos[ipv6_hdr(skb)->nexthdr]); -- cgit v1.2.3-71-gd317 From 0fbf4cb27e061204c8cee8e7eb2870416bdf30fd Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Mon, 15 Feb 2016 12:11:31 +0200 Subject: ipv4: namespacify ip fragment max dist sysctl knob Signed-off-by: Nikolay Borisov Signed-off-by: David S. Miller --- include/net/inet_frag.h | 1 + net/ipv4/ip_fragment.c | 25 +++++++++++++------------ 2 files changed, 14 insertions(+), 12 deletions(-) (limited to 'include/net') diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 12aac0fd6ee7..909972aa3acd 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -13,6 +13,7 @@ struct netns_frags { int timeout; int high_thresh; int low_thresh; + int max_dist; }; /** diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 187c6fcc3027..957161413335 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -54,8 +54,6 @@ * code now. If you change something here, _PLEASE_ update ipv6/reassembly.c * as well. Or notify me, at least. --ANK */ - -static int sysctl_ipfrag_max_dist __read_mostly = 64; static const char ip_frag_cache_name[] = "ip4-frags"; struct ipfrag_skb_cb @@ -150,7 +148,7 @@ static void ip4_frag_init(struct inet_frag_queue *q, const void *a) qp->daddr = arg->iph->daddr; qp->vif = arg->vif; qp->user = arg->user; - qp->peer = sysctl_ipfrag_max_dist ? + qp->peer = q->net->max_dist ? inet_getpeer_v4(net->ipv4.peers, arg->iph->saddr, arg->vif, 1) : NULL; } @@ -275,7 +273,7 @@ static struct ipq *ip_find(struct net *net, struct iphdr *iph, static int ip_frag_too_far(struct ipq *qp) { struct inet_peer *peer = qp->peer; - unsigned int max = sysctl_ipfrag_max_dist; + unsigned int max = qp->q.net->max_dist; unsigned int start, end; int rc; @@ -749,6 +747,14 @@ static struct ctl_table ip4_frags_ns_ctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, + { + .procname = "ipfrag_max_dist", + .data = &init_net.ipv4.frags.max_dist, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero + }, { } }; @@ -762,14 +768,6 @@ static struct ctl_table ip4_frags_ctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { - .procname = "ipfrag_max_dist", - .data = &sysctl_ipfrag_max_dist, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &zero - }, { } }; @@ -790,6 +788,7 @@ static int __net_init ip4_frags_ns_ctl_register(struct net *net) table[1].data = &net->ipv4.frags.low_thresh; table[1].extra2 = &net->ipv4.frags.high_thresh; table[2].data = &net->ipv4.frags.timeout; + table[3].data = &net->ipv4.frags.max_dist; /* Don't export sysctls to unprivileged users */ if (net->user_ns != &init_user_ns) @@ -865,6 +864,8 @@ static int __net_init ipv4_frags_init_net(struct net *net) */ net->ipv4.frags.timeout = IP_FRAG_TIME; + net->ipv4.frags.max_dist = 64; + res = inet_frags_init_net(&net->ipv4.frags); if (res) return res; -- cgit v1.2.3-71-gd317 From a1b7c5fd7fe98f51fbbc393ee1fc4c1cdb2f0119 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 16 Feb 2016 21:17:09 -0800 Subject: net: sched: add cls_u32 offload hooks for netdevs This patch allows netdev drivers to consume cls_u32 offloads via the ndo_setup_tc ndo op. This works aligns with how network drivers have been doing qdisc offloads for mqprio. Signed-off-by: John Fastabend Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 ++- include/net/pkt_cls.h | 34 ++++++++++++++++ net/sched/cls_u32.c | 99 ++++++++++++++++++++++++++++++++++++++++++++++- 3 files changed, 136 insertions(+), 3 deletions(-) (limited to 'include/net') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e396060f815f..47671ce04ac4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -779,17 +779,21 @@ static inline bool netdev_phys_item_id_same(struct netdev_phys_item_id *a, typedef u16 (*select_queue_fallback_t)(struct net_device *dev, struct sk_buff *skb); -/* This structure holds attributes of qdisc and classifiers +/* These structures hold the attributes of qdisc and classifiers * that are being passed to the netdevice through the setup_tc op. */ enum { TC_SETUP_MQPRIO, + TC_SETUP_CLSU32, }; +struct tc_cls_u32_offload; + struct tc_to_netdev { unsigned int type; union { u8 tc; + struct tc_cls_u32_offload *cls_u32; }; }; diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index bc49967e1a68..59789ca6e2c8 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -358,4 +358,38 @@ tcf_match_indev(struct sk_buff *skb, int ifindex) } #endif /* CONFIG_NET_CLS_IND */ +struct tc_cls_u32_knode { + struct tcf_exts *exts; + u8 fshift; + u32 handle; + u32 val; + u32 mask; + u32 link_handle; + struct tc_u32_sel *sel; +}; + +struct tc_cls_u32_hnode { + u32 handle; + u32 prio; + unsigned int divisor; +}; + +enum tc_clsu32_command { + TC_CLSU32_NEW_KNODE, + TC_CLSU32_REPLACE_KNODE, + TC_CLSU32_DELETE_KNODE, + TC_CLSU32_NEW_HNODE, + TC_CLSU32_REPLACE_HNODE, + TC_CLSU32_DELETE_HNODE, +}; + +struct tc_cls_u32_offload { + /* knode values */ + enum tc_clsu32_command command; + union { + struct tc_cls_u32_knode knode; + struct tc_cls_u32_hnode hnode; + }; +}; + #endif diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 4fbb67430ce4..d54bc942ea87 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -43,6 +43,7 @@ #include #include #include +#include struct tc_u_knode { struct tc_u_knode __rcu *next; @@ -424,6 +425,93 @@ static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key) return 0; } +static void u32_remove_hw_knode(struct tcf_proto *tp, u32 handle) +{ + struct net_device *dev = tp->q->dev_queue->dev; + struct tc_cls_u32_offload u32_offload = {0}; + struct tc_to_netdev offload; + + offload.type = TC_SETUP_CLSU32; + offload.cls_u32 = &u32_offload; + + if (dev->netdev_ops->ndo_setup_tc) { + offload.cls_u32->command = TC_CLSU32_DELETE_KNODE; + offload.cls_u32->knode.handle = handle; + dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, + tp->protocol, &offload); + } +} + +static void u32_replace_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h) +{ + struct net_device *dev = tp->q->dev_queue->dev; + struct tc_cls_u32_offload u32_offload = {0}; + struct tc_to_netdev offload; + + offload.type = TC_SETUP_CLSU32; + offload.cls_u32 = &u32_offload; + + if (dev->netdev_ops->ndo_setup_tc) { + offload.cls_u32->command = TC_CLSU32_NEW_HNODE; + offload.cls_u32->hnode.divisor = h->divisor; + offload.cls_u32->hnode.handle = h->handle; + offload.cls_u32->hnode.prio = h->prio; + + dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, + tp->protocol, &offload); + } +} + +static void u32_clear_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h) +{ + struct net_device *dev = tp->q->dev_queue->dev; + struct tc_cls_u32_offload u32_offload = {0}; + struct tc_to_netdev offload; + + offload.type = TC_SETUP_CLSU32; + offload.cls_u32 = &u32_offload; + + if (dev->netdev_ops->ndo_setup_tc) { + offload.cls_u32->command = TC_CLSU32_DELETE_HNODE; + offload.cls_u32->hnode.divisor = h->divisor; + offload.cls_u32->hnode.handle = h->handle; + offload.cls_u32->hnode.prio = h->prio; + + dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, + tp->protocol, &offload); + } +} + +static void u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n) +{ + struct net_device *dev = tp->q->dev_queue->dev; + struct tc_cls_u32_offload u32_offload = {0}; + struct tc_to_netdev offload; + + offload.type = TC_SETUP_CLSU32; + offload.cls_u32 = &u32_offload; + + if (dev->netdev_ops->ndo_setup_tc) { + offload.cls_u32->command = TC_CLSU32_REPLACE_KNODE; + offload.cls_u32->knode.handle = n->handle; + offload.cls_u32->knode.fshift = n->fshift; +#ifdef CONFIG_CLS_U32_MARK + offload.cls_u32->knode.val = n->val; + offload.cls_u32->knode.mask = n->mask; +#else + offload.cls_u32->knode.val = 0; + offload.cls_u32->knode.mask = 0; +#endif + offload.cls_u32->knode.sel = &n->sel; + offload.cls_u32->knode.exts = &n->exts; + if (n->ht_down) + offload.cls_u32->knode.link_handle = n->ht_down->handle; + + dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, + tp->protocol, &offload); + } +} + static void u32_clear_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht) { struct tc_u_knode *n; @@ -434,6 +522,7 @@ static void u32_clear_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht) RCU_INIT_POINTER(ht->ht[h], rtnl_dereference(n->next)); tcf_unbind_filter(tp, &n->res); + u32_remove_hw_knode(tp, n->handle); call_rcu(&n->rcu, u32_delete_key_freepf_rcu); } } @@ -454,6 +543,7 @@ static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht) phn; hn = &phn->next, phn = rtnl_dereference(*hn)) { if (phn == ht) { + u32_clear_hw_hnode(tp, ht); RCU_INIT_POINTER(*hn, ht->next); kfree_rcu(ht, rcu); return 0; @@ -540,8 +630,10 @@ static int u32_delete(struct tcf_proto *tp, unsigned long arg) if (ht == NULL) return 0; - if (TC_U32_KEY(ht->handle)) + if (TC_U32_KEY(ht->handle)) { + u32_remove_hw_knode(tp, ht->handle); return u32_delete_key(tp, (struct tc_u_knode *)ht); + } if (root_ht == ht) return -EINVAL; @@ -769,6 +861,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, u32_replace_knode(tp, tp_c, new); tcf_unbind_filter(tp, &n->res); call_rcu(&n->rcu, u32_delete_key_rcu); + u32_replace_hw_knode(tp, new); return 0; } @@ -795,6 +888,8 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, RCU_INIT_POINTER(ht->next, tp_c->hlist); rcu_assign_pointer(tp_c->hlist, ht); *arg = (unsigned long)ht; + + u32_replace_hw_hnode(tp, ht); return 0; } @@ -877,7 +972,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, RCU_INIT_POINTER(n->next, pins); rcu_assign_pointer(*ins, n); - + u32_replace_hw_knode(tp, n); *arg = (unsigned long)n; return 0; } -- cgit v1.2.3-71-gd317 From 3b01cf56daf96acf9b155d6201d94bc8b4de218e Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 16 Feb 2016 21:18:03 -0800 Subject: net: tc: helper functions to query action types This is a helper function drivers can use to learn if the action type is a drop action. Signed-off-by: John Fastabend Acked-by: Jiri Pirko Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/tc_act/tc_gact.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/net') diff --git a/include/net/tc_act/tc_gact.h b/include/net/tc_act/tc_gact.h index 592a6bc02b0b..04a31830711b 100644 --- a/include/net/tc_act/tc_gact.h +++ b/include/net/tc_act/tc_gact.h @@ -2,6 +2,7 @@ #define __NET_TC_GACT_H #include +#include struct tcf_gact { struct tcf_common common; @@ -15,4 +16,19 @@ struct tcf_gact { #define to_gact(a) \ container_of(a->priv, struct tcf_gact, common) +#ifdef CONFIG_NET_CLS_ACT +static inline bool is_tcf_gact_shot(const struct tc_action *a) +{ + struct tcf_gact *gact; + + if (a->ops && a->ops->type != TCA_ACT_GACT) + return false; + + gact = a->priv; + if (gact->tcf_action == TC_ACT_SHOT) + return true; + + return false; +} +#endif #endif /* __NET_TC_GACT_H */ -- cgit v1.2.3-71-gd317 From 1cd4d5c4326a7ed3bb0e346bd7d20f5057a80ae6 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 15 Feb 2016 14:28:05 +0800 Subject: sctp: remove the unused sctp_datamsg_free() Since commit 8b570dc9f7b6 ("sctp: only drop the reference on the datamsg after sending a msg") used sctp_datamsg_put in sctp_sendmsg, instead of sctp_datamsg_free, this function has no use in sctp. So we will remove it. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 1 - net/sctp/chunk.c | 13 ------------- 2 files changed, 14 deletions(-) (limited to 'include/net') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 205630bb5010..d05b56641abc 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -535,7 +535,6 @@ struct sctp_datamsg { struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *, struct sctp_sndrcvinfo *, struct iov_iter *); -void sctp_datamsg_free(struct sctp_datamsg *); void sctp_datamsg_put(struct sctp_datamsg *); void sctp_chunk_fail(struct sctp_chunk *, int error); int sctp_chunk_abandoned(struct sctp_chunk *); diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index a3380917f197..3aa43073e0b9 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -70,19 +70,6 @@ static struct sctp_datamsg *sctp_datamsg_new(gfp_t gfp) return msg; } -void sctp_datamsg_free(struct sctp_datamsg *msg) -{ - struct sctp_chunk *chunk; - - /* This doesn't have to be a _safe vairant because - * sctp_chunk_free() only drops the refs. - */ - list_for_each_entry(chunk, &msg->chunks, frag_list) - sctp_chunk_free(chunk); - - sctp_datamsg_put(msg); -} - /* Final destructruction of datamsg memory. */ static void sctp_datamsg_destroy(struct sctp_datamsg *msg) { -- cgit v1.2.3-71-gd317 From e014860e31e2a66b1a94088504360a6ebc023564 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Wed, 17 Feb 2016 14:59:30 -0800 Subject: net: pack tc_cls_u32_knode struct slighter better By packing the structure we can remove a few holes as Jamal suggests. before: struct tc_cls_u32_knode { struct tcf_exts * exts; /* 0 8 */ u8 fshift; /* 8 1 */ /* XXX 3 bytes hole, try to pack */ u32 handle; /* 12 4 */ u32 val; /* 16 4 */ u32 mask; /* 20 4 */ u32 link_handle; /* 24 4 */ /* XXX 4 bytes hole, try to pack */ struct tc_u32_sel * sel; /* 32 8 */ /* size: 40, cachelines: 1, members: 7 */ /* sum members: 33, holes: 2, sum holes: 7 */ /* last cacheline: 40 bytes */ }; after: struct tc_cls_u32_knode { struct tcf_exts * exts; /* 0 8 */ struct tc_u32_sel * sel; /* 8 8 */ u32 handle; /* 16 4 */ u32 val; /* 20 4 */ u32 mask; /* 24 4 */ u32 link_handle; /* 28 4 */ u8 fshift; /* 32 1 */ /* size: 40, cachelines: 1, members: 7 */ /* padding: 7 */ /* last cacheline: 40 bytes */ }; Suggested-by: Jamal Hadi Salim Signed-off-by: John Fastabend Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 59789ca6e2c8..2121df574262 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -360,12 +360,12 @@ tcf_match_indev(struct sk_buff *skb, int ifindex) struct tc_cls_u32_knode { struct tcf_exts *exts; - u8 fshift; + struct tc_u32_sel *sel; u32 handle; u32 val; u32 mask; u32 link_handle; - struct tc_u32_sel *sel; + u8 fshift; }; struct tc_cls_u32_hnode { -- cgit v1.2.3-71-gd317 From d4ac05ff3697e036dcb0e2e284c5f7eb77cc0966 Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Tue, 16 Feb 2016 21:58:57 +0100 Subject: vxlan: introduce vxlan_hdr Currently, pointer to the vxlan header is kept in a local variable. It has to be reloaded whenever the pskb pull operations are performed which usually happens somewhere deep in called functions. Create a vxlan_hdr function and use it to reference the vxlan header instead. Signed-off-by: Jiri Benc Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 17 +++++++---------- include/net/vxlan.h | 5 +++++ 2 files changed, 12 insertions(+), 10 deletions(-) (limited to 'include/net') diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index ee1206d9f8df..524e3b139122 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -1257,7 +1257,6 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb) { struct metadata_dst *tun_dst = NULL; struct vxlan_sock *vs; - struct vxlanhdr *vxh; u32 flags, vni; struct vxlan_metadata _md; struct vxlan_metadata *md = &_md; @@ -1266,9 +1265,8 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb) if (!pskb_may_pull(skb, VXLAN_HLEN)) goto error; - vxh = (struct vxlanhdr *)(udp_hdr(skb) + 1); - flags = ntohl(vxh->vx_flags); - vni = ntohl(vxh->vx_vni); + flags = ntohl(vxlan_hdr(skb)->vx_flags); + vni = ntohl(vxlan_hdr(skb)->vx_vni); if (flags & VXLAN_HF_VNI) { flags &= ~VXLAN_HF_VNI; @@ -1279,16 +1277,14 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb) if (iptunnel_pull_header(skb, VXLAN_HLEN, htons(ETH_P_TEB))) goto drop; - vxh = (struct vxlanhdr *)(udp_hdr(skb) + 1); vs = rcu_dereference_sk_user_data(sk); if (!vs) goto drop; if ((flags & VXLAN_HF_RCO) && (vs->flags & VXLAN_F_REMCSUM_RX)) { - vxh = vxlan_remcsum(skb, vxh, sizeof(struct vxlanhdr), vni, - !!(vs->flags & VXLAN_F_REMCSUM_NOPARTIAL)); - if (!vxh) + if (!vxlan_remcsum(skb, vxlan_hdr(skb), sizeof(struct vxlanhdr), vni, + !!(vs->flags & VXLAN_F_REMCSUM_NOPARTIAL))) goto drop; flags &= ~VXLAN_HF_RCO; @@ -1313,7 +1309,7 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb) if ((flags & VXLAN_HF_GBP) && (vs->flags & VXLAN_F_GBP)) { struct vxlanhdr_gbp *gbp; - gbp = (struct vxlanhdr_gbp *)vxh; + gbp = (struct vxlanhdr_gbp *)vxlan_hdr(skb); md->gbp = ntohs(gbp->policy_id); if (tun_dst) @@ -1351,7 +1347,8 @@ drop: bad_flags: netdev_dbg(skb->dev, "invalid vxlan flags=%#x vni=%#x\n", - ntohl(vxh->vx_flags), ntohl(vxh->vx_vni)); + ntohl(vxlan_hdr(skb)->vx_flags), + ntohl(vxlan_hdr(skb)->vx_vni)); error: if (tun_dst) diff --git a/include/net/vxlan.h b/include/net/vxlan.h index b314e4af89c5..3f38b40ec4aa 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -262,6 +262,11 @@ static inline netdev_features_t vxlan_features_check(struct sk_buff *skb, /* IPv6 header + UDP + VXLAN + Ethernet header */ #define VXLAN6_HEADROOM (40 + 8 + 8 + 14) +static inline struct vxlanhdr *vxlan_hdr(struct sk_buff *skb) +{ + return (struct vxlanhdr *)(udp_hdr(skb) + 1); +} + #if IS_ENABLED(CONFIG_VXLAN) void vxlan_get_rx_port(struct net_device *netdev); #else -- cgit v1.2.3-71-gd317 From 54bfd872bf16d40b61bd0cd9b769b2fef67dd272 Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Tue, 16 Feb 2016 21:58:58 +0100 Subject: vxlan: keep flags and vni in network byte order Prevent repeated conversions from and to network order in the fast path. To achieve this, define all flag constants in big endian order and store VNI as __be32. To prevent confusion between the actual VNI value and the VNI field from the header (which contains additional reserved byte), strictly distinguish between "vni" and "vni_field". Signed-off-by: Jiri Benc Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 115 ++++++++++++++++++++++++++-------------------------- include/net/vxlan.h | 70 +++++++++++++++++++++++++++----- 2 files changed, 116 insertions(+), 69 deletions(-) (limited to 'include/net') diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 524e3b139122..4e3d3dfe2a0e 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -197,9 +197,9 @@ static int vxlan_nla_put_addr(struct sk_buff *skb, int attr, #endif /* Virtual Network hash table head */ -static inline struct hlist_head *vni_head(struct vxlan_sock *vs, u32 id) +static inline struct hlist_head *vni_head(struct vxlan_sock *vs, __be32 vni) { - return &vs->vni_list[hash_32(id, VNI_HASH_BITS)]; + return &vs->vni_list[hash_32((__force u32)vni, VNI_HASH_BITS)]; } /* Socket hash table head */ @@ -242,12 +242,12 @@ static struct vxlan_sock *vxlan_find_sock(struct net *net, sa_family_t family, return NULL; } -static struct vxlan_dev *vxlan_vs_find_vni(struct vxlan_sock *vs, u32 id) +static struct vxlan_dev *vxlan_vs_find_vni(struct vxlan_sock *vs, __be32 vni) { struct vxlan_dev *vxlan; - hlist_for_each_entry_rcu(vxlan, vni_head(vs, id), hlist) { - if (vxlan->default_dst.remote_vni == id) + hlist_for_each_entry_rcu(vxlan, vni_head(vs, vni), hlist) { + if (vxlan->default_dst.remote_vni == vni) return vxlan; } @@ -255,7 +255,7 @@ static struct vxlan_dev *vxlan_vs_find_vni(struct vxlan_sock *vs, u32 id) } /* Look up VNI in a per net namespace table */ -static struct vxlan_dev *vxlan_find_vni(struct net *net, u32 id, +static struct vxlan_dev *vxlan_find_vni(struct net *net, __be32 vni, sa_family_t family, __be16 port, u32 flags) { @@ -265,7 +265,7 @@ static struct vxlan_dev *vxlan_find_vni(struct net *net, u32 id, if (!vs) return NULL; - return vxlan_vs_find_vni(vs, id); + return vxlan_vs_find_vni(vs, vni); } /* Fill in neighbour message in skbuff. */ @@ -315,7 +315,7 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan, nla_put_be16(skb, NDA_PORT, rdst->remote_port)) goto nla_put_failure; if (rdst->remote_vni != vxlan->default_dst.remote_vni && - nla_put_u32(skb, NDA_VNI, rdst->remote_vni)) + nla_put_u32(skb, NDA_VNI, be32_to_cpu(rdst->remote_vni))) goto nla_put_failure; if (rdst->remote_ifindex && nla_put_u32(skb, NDA_IFINDEX, rdst->remote_ifindex)) @@ -383,7 +383,7 @@ static void vxlan_ip_miss(struct net_device *dev, union vxlan_addr *ipa) }; struct vxlan_rdst remote = { .remote_ip = *ipa, /* goes to NDA_DST */ - .remote_vni = VXLAN_N_VID, + .remote_vni = cpu_to_be32(VXLAN_N_VID), }; vxlan_fdb_notify(vxlan, &f, &remote, RTM_GETNEIGH); @@ -452,7 +452,7 @@ static struct vxlan_fdb *vxlan_find_mac(struct vxlan_dev *vxlan, /* caller should hold vxlan->hash_lock */ static struct vxlan_rdst *vxlan_fdb_find_rdst(struct vxlan_fdb *f, union vxlan_addr *ip, __be16 port, - __u32 vni, __u32 ifindex) + __be32 vni, __u32 ifindex) { struct vxlan_rdst *rd; @@ -469,7 +469,8 @@ static struct vxlan_rdst *vxlan_fdb_find_rdst(struct vxlan_fdb *f, /* Replace destination of unicast mac */ static int vxlan_fdb_replace(struct vxlan_fdb *f, - union vxlan_addr *ip, __be16 port, __u32 vni, __u32 ifindex) + union vxlan_addr *ip, __be16 port, __be32 vni, + __u32 ifindex) { struct vxlan_rdst *rd; @@ -491,7 +492,7 @@ static int vxlan_fdb_replace(struct vxlan_fdb *f, /* Add/update destinations for multicast */ static int vxlan_fdb_append(struct vxlan_fdb *f, - union vxlan_addr *ip, __be16 port, __u32 vni, + union vxlan_addr *ip, __be16 port, __be32 vni, __u32 ifindex, struct vxlan_rdst **rdp) { struct vxlan_rdst *rd; @@ -523,7 +524,8 @@ static int vxlan_fdb_append(struct vxlan_fdb *f, static struct vxlanhdr *vxlan_gro_remcsum(struct sk_buff *skb, unsigned int off, struct vxlanhdr *vh, size_t hdrlen, - u32 data, struct gro_remcsum *grc, + __be32 vni_field, + struct gro_remcsum *grc, bool nopartial) { size_t start, offset; @@ -534,10 +536,8 @@ static struct vxlanhdr *vxlan_gro_remcsum(struct sk_buff *skb, if (!NAPI_GRO_CB(skb)->csum_valid) return NULL; - start = (data & VXLAN_RCO_MASK) << VXLAN_RCO_SHIFT; - offset = start + ((data & VXLAN_RCO_UDP) ? - offsetof(struct udphdr, check) : - offsetof(struct tcphdr, check)); + start = vxlan_rco_start(vni_field); + offset = start + vxlan_rco_offset(vni_field); vh = skb_gro_remcsum_process(skb, (void *)vh, off, hdrlen, start, offset, grc, nopartial); @@ -557,7 +557,7 @@ static struct sk_buff **vxlan_gro_receive(struct sk_buff **head, int flush = 1; struct vxlan_sock *vs = container_of(uoff, struct vxlan_sock, udp_offloads); - u32 flags; + __be32 flags; struct gro_remcsum grc; skb_gro_remcsum_init(&grc); @@ -573,11 +573,11 @@ static struct sk_buff **vxlan_gro_receive(struct sk_buff **head, skb_gro_postpull_rcsum(skb, vh, sizeof(struct vxlanhdr)); - flags = ntohl(vh->vx_flags); + flags = vh->vx_flags; if ((flags & VXLAN_HF_RCO) && (vs->flags & VXLAN_F_REMCSUM_RX)) { vh = vxlan_gro_remcsum(skb, off_vx, vh, sizeof(struct vxlanhdr), - ntohl(vh->vx_vni), &grc, + vh->vx_vni, &grc, !!(vs->flags & VXLAN_F_REMCSUM_NOPARTIAL)); @@ -668,7 +668,7 @@ static void vxlan_notify_del_rx_port(struct vxlan_sock *vs) static int vxlan_fdb_create(struct vxlan_dev *vxlan, const u8 *mac, union vxlan_addr *ip, __u16 state, __u16 flags, - __be16 port, __u32 vni, __u32 ifindex, + __be16 port, __be32 vni, __u32 ifindex, __u8 ndm_flags) { struct vxlan_rdst *rd = NULL; @@ -777,7 +777,8 @@ static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f) } static int vxlan_fdb_parse(struct nlattr *tb[], struct vxlan_dev *vxlan, - union vxlan_addr *ip, __be16 *port, u32 *vni, u32 *ifindex) + union vxlan_addr *ip, __be16 *port, __be32 *vni, + u32 *ifindex) { struct net *net = dev_net(vxlan->dev); int err; @@ -810,7 +811,7 @@ static int vxlan_fdb_parse(struct nlattr *tb[], struct vxlan_dev *vxlan, if (tb[NDA_VNI]) { if (nla_len(tb[NDA_VNI]) != sizeof(u32)) return -EINVAL; - *vni = nla_get_u32(tb[NDA_VNI]); + *vni = cpu_to_be32(nla_get_u32(tb[NDA_VNI])); } else { *vni = vxlan->default_dst.remote_vni; } @@ -840,7 +841,8 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], /* struct net *net = dev_net(vxlan->dev); */ union vxlan_addr ip; __be16 port; - u32 vni, ifindex; + __be32 vni; + u32 ifindex; int err; if (!(ndm->ndm_state & (NUD_PERMANENT|NUD_REACHABLE))) { @@ -877,7 +879,8 @@ static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], struct vxlan_rdst *rd = NULL; union vxlan_addr ip; __be16 port; - u32 vni, ifindex; + __be32 vni; + u32 ifindex; int err; err = vxlan_fdb_parse(tb, vxlan, &ip, &port, &vni, &ifindex); @@ -1133,17 +1136,16 @@ static int vxlan_igmp_leave(struct vxlan_dev *vxlan) } static struct vxlanhdr *vxlan_remcsum(struct sk_buff *skb, struct vxlanhdr *vh, - size_t hdrlen, u32 data, bool nopartial) + size_t hdrlen, __be32 vni_field, + bool nopartial) { size_t start, offset, plen; if (skb->remcsum_offload) return vh; - start = (data & VXLAN_RCO_MASK) << VXLAN_RCO_SHIFT; - offset = start + ((data & VXLAN_RCO_UDP) ? - offsetof(struct udphdr, check) : - offsetof(struct tcphdr, check)); + start = vxlan_rco_start(vni_field); + offset = start + vxlan_rco_offset(vni_field); plen = hdrlen + offset + sizeof(u16); @@ -1159,7 +1161,7 @@ static struct vxlanhdr *vxlan_remcsum(struct sk_buff *skb, struct vxlanhdr *vh, } static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb, - struct vxlan_metadata *md, u32 vni, + struct vxlan_metadata *md, __be32 vni, struct metadata_dst *tun_dst) { struct iphdr *oip = NULL; @@ -1257,7 +1259,7 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb) { struct metadata_dst *tun_dst = NULL; struct vxlan_sock *vs; - u32 flags, vni; + __be32 flags, vni_field; struct vxlan_metadata _md; struct vxlan_metadata *md = &_md; @@ -1265,8 +1267,8 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb) if (!pskb_may_pull(skb, VXLAN_HLEN)) goto error; - flags = ntohl(vxlan_hdr(skb)->vx_flags); - vni = ntohl(vxlan_hdr(skb)->vx_vni); + flags = vxlan_hdr(skb)->vx_flags; + vni_field = vxlan_hdr(skb)->vx_vni; if (flags & VXLAN_HF_VNI) { flags &= ~VXLAN_HF_VNI; @@ -1283,17 +1285,18 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb) goto drop; if ((flags & VXLAN_HF_RCO) && (vs->flags & VXLAN_F_REMCSUM_RX)) { - if (!vxlan_remcsum(skb, vxlan_hdr(skb), sizeof(struct vxlanhdr), vni, + if (!vxlan_remcsum(skb, vxlan_hdr(skb), sizeof(struct vxlanhdr), + vni_field, !!(vs->flags & VXLAN_F_REMCSUM_NOPARTIAL))) goto drop; flags &= ~VXLAN_HF_RCO; - vni &= VXLAN_VNI_MASK; + vni_field &= VXLAN_VNI_MASK; } if (vxlan_collect_metadata(vs)) { tun_dst = udp_tun_rx_dst(skb, vxlan_get_sk_family(vs), TUNNEL_KEY, - cpu_to_be64(vni >> 8), sizeof(*md)); + vxlan_vni(vni_field), sizeof(*md)); if (!tun_dst) goto drop; @@ -1324,7 +1327,7 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb) flags &= ~VXLAN_GBP_USED_BITS; } - if (flags || vni & ~VXLAN_VNI_MASK) { + if (flags || vni_field & ~VXLAN_VNI_MASK) { /* If there are any unprocessed flags remaining treat * this as a malformed packet. This behavior diverges from * VXLAN RFC (RFC7348) which stipulates that bits in reserved @@ -1337,7 +1340,7 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb) goto bad_flags; } - vxlan_rcv(vs, skb, md, vni >> 8, tun_dst); + vxlan_rcv(vs, skb, md, vxlan_vni(vni_field), tun_dst); return 0; drop: @@ -1680,7 +1683,7 @@ static void vxlan_build_gbp_hdr(struct vxlanhdr *vxh, u32 vxflags, return; gbp = (struct vxlanhdr_gbp *)vxh; - vxh->vx_flags |= htonl(VXLAN_HF_GBP); + vxh->vx_flags |= VXLAN_HF_GBP; if (md->gbp & VXLAN_GBP_DONT_LEARN) gbp->dont_learn = 1; @@ -1700,7 +1703,6 @@ static int vxlan_build_skb(struct sk_buff *skb, struct dst_entry *dst, int min_headroom; int err; int type = udp_sum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; - u16 hdrlen = sizeof(struct vxlanhdr); if ((vxflags & VXLAN_F_REMCSUM_TX) && skb->ip_summed == CHECKSUM_PARTIAL) { @@ -1733,18 +1735,15 @@ static int vxlan_build_skb(struct sk_buff *skb, struct dst_entry *dst, return PTR_ERR(skb); vxh = (struct vxlanhdr *) __skb_push(skb, sizeof(*vxh)); - vxh->vx_flags = htonl(VXLAN_HF_VNI); - vxh->vx_vni = vni; + vxh->vx_flags = VXLAN_HF_VNI; + vxh->vx_vni = vxlan_vni_field(vni); if (type & SKB_GSO_TUNNEL_REMCSUM) { - u32 data = (skb_checksum_start_offset(skb) - hdrlen) >> - VXLAN_RCO_SHIFT; + unsigned int start; - if (skb->csum_offset == offsetof(struct udphdr, check)) - data |= VXLAN_RCO_UDP; - - vxh->vx_vni |= htonl(data); - vxh->vx_flags |= htonl(VXLAN_HF_RCO); + start = skb_checksum_start_offset(skb) - sizeof(struct vxlanhdr); + vxh->vx_vni |= vxlan_compute_rco(start, skb->csum_offset); + vxh->vx_flags |= VXLAN_HF_RCO; if (!skb_is_gso(skb)) { skb->ip_summed = CHECKSUM_NONE; @@ -1892,7 +1891,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, struct vxlan_metadata _md; struct vxlan_metadata *md = &_md; __be16 src_port = 0, dst_port; - u32 vni; + __be32 vni; __be16 df = 0; __u8 tos, ttl; int err; @@ -1914,7 +1913,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, goto drop; } dst_port = info->key.tp_dst ? : vxlan->cfg.dst_port; - vni = be64_to_cpu(info->key.tun_id); + vni = vxlan_tun_id_to_vni(info->key.tun_id); remote_ip.sa.sa_family = ip_tunnel_info_af(info); if (remote_ip.sa.sa_family == AF_INET) remote_ip.sin.sin_addr.s_addr = info->key.u.ipv4.dst; @@ -2007,7 +2006,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, tos = ip_tunnel_ecn_encap(tos, old_iph, skb); ttl = ttl ? : ip4_dst_hoplimit(&rt->dst); err = vxlan_build_skb(skb, &rt->dst, sizeof(struct iphdr), - htonl(vni << 8), md, flags, udp_sum); + vni, md, flags, udp_sum); if (err < 0) goto xmit_tx_error; @@ -2065,7 +2064,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, ttl = ttl ? : ip6_dst_hoplimit(ndst); skb_scrub_packet(skb, xnet); err = vxlan_build_skb(skb, ndst, sizeof(struct ipv6hdr), - htonl(vni << 8), md, flags, udp_sum); + vni, md, flags, udp_sum); if (err < 0) { dst_release(ndst); return; @@ -2222,7 +2221,7 @@ static void vxlan_cleanup(unsigned long arg) static void vxlan_vs_add_dev(struct vxlan_sock *vs, struct vxlan_dev *vxlan) { struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); - __u32 vni = vxlan->default_dst.remote_vni; + __be32 vni = vxlan->default_dst.remote_vni; spin_lock(&vn->sock_lock); hlist_add_head_rcu(&vxlan->hlist, vni_head(vs, vni)); @@ -2837,7 +2836,7 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev, memset(&conf, 0, sizeof(conf)); if (data[IFLA_VXLAN_ID]) - conf.vni = nla_get_u32(data[IFLA_VXLAN_ID]); + conf.vni = cpu_to_be32(nla_get_u32(data[IFLA_VXLAN_ID])); if (data[IFLA_VXLAN_GROUP]) { conf.remote_ip.sin.sin_addr.s_addr = nla_get_in_addr(data[IFLA_VXLAN_GROUP]); @@ -2941,7 +2940,7 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev, break; case -EEXIST: - pr_info("duplicate VNI %u\n", conf.vni); + pr_info("duplicate VNI %u\n", be32_to_cpu(conf.vni)); break; } @@ -2999,7 +2998,7 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev) .high = htons(vxlan->cfg.port_max), }; - if (nla_put_u32(skb, IFLA_VXLAN_ID, dst->remote_vni)) + if (nla_put_u32(skb, IFLA_VXLAN_ID, be32_to_cpu(dst->remote_vni))) goto nla_put_failure; if (!vxlan_addr_any(&dst->remote_ip)) { diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 3f38b40ec4aa..1b85a3b40c5a 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -24,11 +24,11 @@ struct vxlanhdr { }; /* VXLAN header flags. */ -#define VXLAN_HF_VNI BIT(27) +#define VXLAN_HF_VNI cpu_to_be32(BIT(27)) #define VXLAN_N_VID (1u << 24) #define VXLAN_VID_MASK (VXLAN_N_VID - 1) -#define VXLAN_VNI_MASK (VXLAN_VID_MASK << 8) +#define VXLAN_VNI_MASK cpu_to_be32(VXLAN_VID_MASK << 8) #define VXLAN_HLEN (sizeof(struct udphdr) + sizeof(struct vxlanhdr)) #define VNI_HASH_BITS 10 @@ -55,14 +55,14 @@ struct vxlanhdr { */ /* VXLAN-RCO header flags. */ -#define VXLAN_HF_RCO BIT(21) +#define VXLAN_HF_RCO cpu_to_be32(BIT(21)) /* Remote checksum offload header option */ -#define VXLAN_RCO_MASK 0x7f /* Last byte of vni field */ -#define VXLAN_RCO_UDP 0x80 /* Indicate UDP RCO (TCP when not set *) */ -#define VXLAN_RCO_SHIFT 1 /* Left shift of start */ +#define VXLAN_RCO_MASK cpu_to_be32(0x7f) /* Last byte of vni field */ +#define VXLAN_RCO_UDP cpu_to_be32(0x80) /* Indicate UDP RCO (TCP when not set *) */ +#define VXLAN_RCO_SHIFT 1 /* Left shift of start */ #define VXLAN_RCO_SHIFT_MASK ((1 << VXLAN_RCO_SHIFT) - 1) -#define VXLAN_MAX_REMCSUM_START (VXLAN_RCO_MASK << VXLAN_RCO_SHIFT) +#define VXLAN_MAX_REMCSUM_START (0x7f << VXLAN_RCO_SHIFT) /* * VXLAN Group Based Policy Extension (VXLAN_F_GBP): @@ -105,9 +105,9 @@ struct vxlanhdr_gbp { }; /* VXLAN-GBP header flags. */ -#define VXLAN_HF_GBP BIT(31) +#define VXLAN_HF_GBP cpu_to_be32(BIT(31)) -#define VXLAN_GBP_USED_BITS (VXLAN_HF_GBP | 0xFFFFFF) +#define VXLAN_GBP_USED_BITS (VXLAN_HF_GBP | cpu_to_be32(0xFFFFFF)) /* skb->mark mapping * @@ -144,7 +144,7 @@ union vxlan_addr { struct vxlan_rdst { union vxlan_addr remote_ip; __be16 remote_port; - u32 remote_vni; + __be32 remote_vni; u32 remote_ifindex; struct list_head list; struct rcu_head rcu; @@ -154,7 +154,7 @@ struct vxlan_rdst { struct vxlan_config { union vxlan_addr remote_ip; union vxlan_addr saddr; - u32 vni; + __be32 vni; int remote_ifindex; int mtu; __be16 dst_port; @@ -267,6 +267,54 @@ static inline struct vxlanhdr *vxlan_hdr(struct sk_buff *skb) return (struct vxlanhdr *)(udp_hdr(skb) + 1); } +static inline __be32 vxlan_vni(__be32 vni_field) +{ +#if defined(__BIG_ENDIAN) + return vni_field >> 8; +#else + return (vni_field & VXLAN_VNI_MASK) << 8; +#endif +} + +static inline __be32 vxlan_vni_field(__be32 vni) +{ +#if defined(__BIG_ENDIAN) + return vni << 8; +#else + return vni >> 8; +#endif +} + +static inline __be32 vxlan_tun_id_to_vni(__be64 tun_id) +{ +#if defined(__BIG_ENDIAN) + return tun_id; +#else + return tun_id >> 32; +#endif +} + +static inline size_t vxlan_rco_start(__be32 vni_field) +{ + return be32_to_cpu(vni_field & VXLAN_RCO_MASK) << VXLAN_RCO_SHIFT; +} + +static inline size_t vxlan_rco_offset(__be32 vni_field) +{ + return (vni_field & VXLAN_RCO_UDP) ? + offsetof(struct udphdr, check) : + offsetof(struct tcphdr, check); +} + +static inline __be32 vxlan_compute_rco(unsigned int start, unsigned int offset) +{ + __be32 vni_field = cpu_to_be32(start >> VXLAN_RCO_SHIFT); + + if (offset == offsetof(struct udphdr, check)) + vni_field |= VXLAN_RCO_UDP; + return vni_field; +} + #if IS_ENABLED(CONFIG_VXLAN) void vxlan_get_rx_port(struct net_device *netdev); #else -- cgit v1.2.3-71-gd317 From 263ea09084d172cac6e40459a690babe8de8e448 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 18 Feb 2016 15:03:26 +0100 Subject: Revert "genl: Add genlmsg_new_unicast() for unicast message allocation" This reverts commit bb9b18fb55b0 ("genl: Add genlmsg_new_unicast() for unicast message allocation")'. Nothing wrong with it; its no longer needed since this was only for mmapped netlink support. Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/net/genetlink.h | 4 ---- net/netlink/genetlink.c | 21 --------------------- net/openvswitch/datapath.c | 10 +++++----- net/tipc/netlink_compat.c | 1 - 4 files changed, 5 insertions(+), 31 deletions(-) (limited to 'include/net') diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 43c0e771f417..8d4608ce8716 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -83,7 +83,6 @@ struct genl_family { * @attrs: netlink attributes * @_net: network namespace * @user_ptr: user pointers - * @dst_sk: destination socket */ struct genl_info { u32 snd_seq; @@ -94,7 +93,6 @@ struct genl_info { struct nlattr ** attrs; possible_net_t _net; void * user_ptr[2]; - struct sock * dst_sk; }; static inline struct net *genl_info_net(struct genl_info *info) @@ -188,8 +186,6 @@ int genl_unregister_family(struct genl_family *family); void genl_notify(struct genl_family *family, struct sk_buff *skb, struct genl_info *info, u32 group, gfp_t flags); -struct sk_buff *genlmsg_new_unicast(size_t payload, struct genl_info *info, - gfp_t flags); void *genlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, struct genl_family *family, int flags, u8 cmd); diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 0ffd721126e7..a09132a69869 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -462,26 +462,6 @@ int genl_unregister_family(struct genl_family *family) } EXPORT_SYMBOL(genl_unregister_family); -/** - * genlmsg_new_unicast - Allocate generic netlink message for unicast - * @payload: size of the message payload - * @info: information on destination - * @flags: the type of memory to allocate - * - * Allocates a new sk_buff large enough to cover the specified payload - * plus required Netlink headers. Will check receiving socket for - * memory mapped i/o capability and use it if enabled. Will fall back - * to non-mapped skb if message size exceeds the frame size of the ring. - */ -struct sk_buff *genlmsg_new_unicast(size_t payload, struct genl_info *info, - gfp_t flags) -{ - size_t len = nlmsg_total_size(genlmsg_total_size(payload)); - - return netlink_alloc_skb(info->dst_sk, len, info->snd_portid, flags); -} -EXPORT_SYMBOL_GPL(genlmsg_new_unicast); - /** * genlmsg_put - Add generic netlink header to netlink message * @skb: socket buffer holding the message @@ -642,7 +622,6 @@ static int genl_family_rcv_msg(struct genl_family *family, info.genlhdr = nlmsg_data(nlh); info.userhdr = nlmsg_data(nlh) + GENL_HDRLEN; info.attrs = attrbuf; - info.dst_sk = skb->sk; genl_info_net_set(&info, net); memset(&info.user_ptr, 0, sizeof(info.user_ptr)); diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 35a2659a277e..c4e8455d5d56 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -1477,7 +1477,7 @@ error: return -EMSGSIZE; } -static struct sk_buff *ovs_dp_cmd_alloc_info(struct genl_info *info) +static struct sk_buff *ovs_dp_cmd_alloc_info(void) { return genlmsg_new(ovs_dp_cmd_msg_size(), GFP_KERNEL); } @@ -1532,7 +1532,7 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) if (!a[OVS_DP_ATTR_NAME] || !a[OVS_DP_ATTR_UPCALL_PID]) goto err; - reply = ovs_dp_cmd_alloc_info(info); + reply = ovs_dp_cmd_alloc_info(); if (!reply) return -ENOMEM; @@ -1653,7 +1653,7 @@ static int ovs_dp_cmd_del(struct sk_buff *skb, struct genl_info *info) struct datapath *dp; int err; - reply = ovs_dp_cmd_alloc_info(info); + reply = ovs_dp_cmd_alloc_info(); if (!reply) return -ENOMEM; @@ -1686,7 +1686,7 @@ static int ovs_dp_cmd_set(struct sk_buff *skb, struct genl_info *info) struct datapath *dp; int err; - reply = ovs_dp_cmd_alloc_info(info); + reply = ovs_dp_cmd_alloc_info(); if (!reply) return -ENOMEM; @@ -1719,7 +1719,7 @@ static int ovs_dp_cmd_get(struct sk_buff *skb, struct genl_info *info) struct datapath *dp; int err; - reply = ovs_dp_cmd_alloc_info(info); + reply = ovs_dp_cmd_alloc_info(); if (!reply) return -ENOMEM; diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index 2c016fdefe97..de66d8f945ed 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -1104,7 +1104,6 @@ static int tipc_nl_compat_recv(struct sk_buff *skb, struct genl_info *info) req_nlh = (struct nlmsghdr *)skb->data; msg.req = nlmsg_data(req_nlh) + GENL_HDRLEN + TIPC_GENL_HDRLEN; msg.cmd = req_userhdr->cmd; - msg.dst_sk = info->dst_sk; msg.net = genl_info_net(info); if ((msg.cmd & 0xC000) && (!netlink_net_capable(skb, CAP_NET_ADMIN))) { -- cgit v1.2.3-71-gd317 From 07dabf20d9867710b90b91108b2adcd448773e25 Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Thu, 18 Feb 2016 19:19:29 +0100 Subject: vxlan: tun_id is 64bit, not 32bit The tun_id field in struct ip_tunnel_key is __be64, not __be32. We need to convert the vni to tun_id correctly. Fixes: 54bfd872bf16 ("vxlan: keep flags and vni in network byte order") Reported-by: Paolo Abeni Tested-by: Paolo Abeni Signed-off-by: Jiri Benc Acked-by: Thadeu Lima de Souza Cascardo Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 5 +++-- include/net/vxlan.h | 9 +++++++++ 2 files changed, 12 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 3a84680b5117..75bccb360599 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -1310,9 +1310,10 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb) goto drop; if (vxlan_collect_metadata(vs)) { + __be32 vni = vxlan_vni(vxlan_hdr(skb)->vx_vni); + tun_dst = udp_tun_rx_dst(skb, vxlan_get_sk_family(vs), TUNNEL_KEY, - vxlan_vni(vxlan_hdr(skb)->vx_vni), - sizeof(*md)); + vxlan_vni_to_tun_id(vni), sizeof(*md)); if (!tun_dst) goto drop; diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 1b85a3b40c5a..748083de367a 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -294,6 +294,15 @@ static inline __be32 vxlan_tun_id_to_vni(__be64 tun_id) #endif } +static inline __be64 vxlan_vni_to_tun_id(__be32 vni) +{ +#if defined(__BIG_ENDIAN) + return (__be64)vni; +#else + return (__be64)vni << 32; +#endif +} + static inline size_t vxlan_rco_start(__be32 vni_field) { return be32_to_cpu(vni_field & VXLAN_RCO_MASK) << VXLAN_RCO_SHIFT; -- cgit v1.2.3-71-gd317 From 7f290c94352e59b1d720055fce760a69a63bd0a1 Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Thu, 18 Feb 2016 11:22:52 +0100 Subject: iptunnel: scrub packet in iptunnel_pull_header Part of skb_scrub_packet was open coded in iptunnel_pull_header. Let it call skb_scrub_packet directly instead. Signed-off-by: Jiri Benc Signed-off-by: David S. Miller --- drivers/net/geneve.c | 4 ++-- drivers/net/vxlan.c | 4 ++-- include/net/ip_tunnels.h | 3 ++- net/ipv4/ip_gre.c | 2 +- net/ipv4/ip_tunnel_core.c | 8 +++----- net/ipv4/ipip.c | 2 +- net/ipv6/sit.c | 2 +- 7 files changed, 12 insertions(+), 13 deletions(-) (limited to 'include/net') diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 4ceccf871b3f..dfbe3ca687f7 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -237,7 +237,6 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs, } skb_reset_mac_header(skb); - skb_scrub_packet(skb, !net_eq(geneve->net, dev_net(geneve->dev))); skb->protocol = eth_type_trans(skb, geneve->dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); @@ -356,7 +355,8 @@ static int geneve_udp_encap_recv(struct sock *sk, struct sk_buff *skb) opts_len = geneveh->opt_len * 4; if (iptunnel_pull_header(skb, GENEVE_BASE_HLEN + opts_len, - htons(ETH_P_TEB))) + htons(ETH_P_TEB), + !net_eq(geneve->net, dev_net(geneve->dev)))) goto drop; geneve_rx(geneve, gs, skb); diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 16a176cd0dad..c963897e713d 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -1198,7 +1198,6 @@ static void vxlan_rcv(struct vxlan_dev *vxlan, struct vxlan_sock *vs, int err = 0; skb_reset_mac_header(skb); - skb_scrub_packet(skb, !net_eq(vxlan->net, dev_net(vxlan->dev))); skb->protocol = eth_type_trans(skb, vxlan->dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); @@ -1305,7 +1304,8 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb) if (!vxlan) goto drop; - if (iptunnel_pull_header(skb, VXLAN_HLEN, htons(ETH_P_TEB))) + if (iptunnel_pull_header(skb, VXLAN_HLEN, htons(ETH_P_TEB), + !net_eq(vxlan->net, dev_net(vxlan->dev)))) goto drop; if (vxlan_collect_metadata(vs)) { diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 87408ab80856..4dd616376fec 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -270,7 +270,8 @@ static inline u8 ip_tunnel_ecn_encap(u8 tos, const struct iphdr *iph, return INET_ECN_encapsulate(tos, inner); } -int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto); +int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto, + bool xnet); void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, __be32 src, __be32 dst, u8 proto, u8 tos, u8 ttl, __be16 df, bool xnet); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 917c2c1bfadd..12071e28d958 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -238,7 +238,7 @@ static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, return -EINVAL; } } - return iptunnel_pull_header(skb, hdr_len, tpi->proto); + return iptunnel_pull_header(skb, hdr_len, tpi->proto, false); } static void ipgre_err(struct sk_buff *skb, u32 info, diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index a6e58b6141cd..eaca2449a09a 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -86,7 +86,8 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, } EXPORT_SYMBOL_GPL(iptunnel_xmit); -int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto) +int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto, + bool xnet) { if (unlikely(!pskb_may_pull(skb, hdr_len))) return -ENOMEM; @@ -109,13 +110,10 @@ int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto) skb->protocol = inner_proto; } - nf_reset(skb); - secpath_reset(skb); skb_clear_hash_if_not_l4(skb); - skb_dst_drop(skb); skb->vlan_tci = 0; skb_set_queue_mapping(skb, 0); - skb->pkt_type = PACKET_HOST; + skb_scrub_packet(skb, xnet); return 0; } EXPORT_SYMBOL_GPL(iptunnel_pull_header); diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 6ec5b42fd172..ec51d02166de 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -195,7 +195,7 @@ static int ipip_rcv(struct sk_buff *skb) if (tunnel) { if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; - if (iptunnel_pull_header(skb, 0, tpi.proto)) + if (iptunnel_pull_header(skb, 0, tpi.proto, false)) goto drop; return ip_tunnel_rcv(tunnel, skb, &tpi, NULL, log_ecn_error); } diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 0625ac6356b5..f45b8ffc2840 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -740,7 +740,7 @@ static int ipip_rcv(struct sk_buff *skb) if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; - if (iptunnel_pull_header(skb, 0, tpi.proto)) + if (iptunnel_pull_header(skb, 0, tpi.proto, false)) goto drop; return ip_tunnel_rcv(tunnel, skb, &tpi, NULL, log_ecn_error); } -- cgit v1.2.3-71-gd317 From e550785c30f639b3cc6ca70c489a6463ff298453 Mon Sep 17 00:00:00 2001 From: Benjamin Poirier Date: Wed, 17 Feb 2016 16:20:33 -0800 Subject: ipv6: Annotate change of locking mechanism for np->opt follows up commit 45f6fad84cc3 ("ipv6: add complete rcu protection around np->opt") which added mixed rcu/refcount protection to np->opt. Given the current implementation of rcu_pointer_handoff(), this has no effect at runtime. Signed-off-by: Benjamin Poirier Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ipv6.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 6570f379aba2..f3c9857c645d 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -259,8 +259,12 @@ static inline struct ipv6_txoptions *txopt_get(const struct ipv6_pinfo *np) rcu_read_lock(); opt = rcu_dereference(np->opt); - if (opt && !atomic_inc_not_zero(&opt->refcnt)) - opt = NULL; + if (opt) { + if (!atomic_inc_not_zero(&opt->refcnt)) + opt = NULL; + else + opt = rcu_pointer_handoff(opt); + } rcu_read_unlock(); return opt; } -- cgit v1.2.3-71-gd317 From 745041e2aaf1d668f293aaab4b0f6ad7daa056a5 Mon Sep 17 00:00:00 2001 From: Robert Shearman Date: Fri, 19 Feb 2016 09:43:16 +0000 Subject: lwtunnel: autoload of lwt modules The lwt implementations using net devices can autoload using the existing mechanism using IFLA_INFO_KIND. However, there's no mechanism that lwt modules not using net devices can use. Therefore, add the ability to autoload modules registering lwt operations for lwt implementations not using a net device so that users don't have to manually load the modules. Only users with the CAP_NET_ADMIN capability can cause modules to be loaded, which is ensured by rtnetlink_rcv_msg rejecting non-RTM_GETxxx messages for users without this capability, and by lwtunnel_build_state not being called in response to RTM_GETxxx messages. Signed-off-by: Robert Shearman Signed-off-by: David S. Miller --- include/net/lwtunnel.h | 4 +++- net/core/lwtunnel.c | 37 +++++++++++++++++++++++++++++++++++++ 2 files changed, 40 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h index 66350ce3e955..e9f116e29c22 100644 --- a/include/net/lwtunnel.h +++ b/include/net/lwtunnel.h @@ -170,6 +170,8 @@ static inline int lwtunnel_input(struct sk_buff *skb) return -EOPNOTSUPP; } -#endif +#endif /* CONFIG_LWTUNNEL */ + +#define MODULE_ALIAS_RTNL_LWT(encap_type) MODULE_ALIAS("rtnl-lwt-" __stringify(encap_type)) #endif /* __NET_LWTUNNEL_H */ diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c index 299cfc24d888..669ecc9f884e 100644 --- a/net/core/lwtunnel.c +++ b/net/core/lwtunnel.c @@ -27,6 +27,31 @@ #include #include +#ifdef CONFIG_MODULES + +static const char *lwtunnel_encap_str(enum lwtunnel_encap_types encap_type) +{ + /* Only lwt encaps implemented without using an interface for + * the encap need to return a string here. + */ + switch (encap_type) { + case LWTUNNEL_ENCAP_MPLS: + return "MPLS"; + case LWTUNNEL_ENCAP_ILA: + return "ILA"; + case LWTUNNEL_ENCAP_IP6: + case LWTUNNEL_ENCAP_IP: + case LWTUNNEL_ENCAP_NONE: + case __LWTUNNEL_ENCAP_MAX: + /* should not have got here */ + WARN_ON(1); + break; + } + return NULL; +} + +#endif /* CONFIG_MODULES */ + struct lwtunnel_state *lwtunnel_state_alloc(int encap_len) { struct lwtunnel_state *lws; @@ -85,6 +110,18 @@ int lwtunnel_build_state(struct net_device *dev, u16 encap_type, ret = -EOPNOTSUPP; rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[encap_type]); +#ifdef CONFIG_MODULES + if (!ops) { + const char *encap_type_str = lwtunnel_encap_str(encap_type); + + if (encap_type_str) { + rcu_read_unlock(); + request_module("rtnl-lwt-%s", encap_type_str); + rcu_read_lock(); + ops = rcu_dereference(lwtun_encaps[encap_type]); + } + } +#endif if (likely(ops && ops->build_state)) ret = ops->build_state(dev, encap, family, cfg, lws); rcu_read_unlock(); -- cgit v1.2.3-71-gd317 From 6ceb31ca5f65acff299dbc3da5854d54e147b7d8 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 19 Feb 2016 11:26:31 -0800 Subject: VXLAN: Support outer IPv4 Tx checksums by default This change makes it so that if UDP CSUM is not specified we will default to enabling it. The main motivation behind this is the fact that with the use of outer checksum we can greatly improve the performance for VXLAN tunnels on devices that don't know how to parse tunnel headers. Signed-off-by: Alexander Duyck Acked-by: Tom Herbert Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 19 +++++++++---------- include/net/vxlan.h | 2 +- 2 files changed, 10 insertions(+), 11 deletions(-) (limited to 'include/net') diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index c963897e713d..2ddc642fb64f 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -1957,13 +1957,6 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, goto drop; sk = vxlan->vn4_sock->sock->sk; - if (info) { - if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT) - df = htons(IP_DF); - } else { - udp_sum = !!(flags & VXLAN_F_UDP_CSUM); - } - rt = vxlan_get_route(vxlan, skb, rdst ? rdst->remote_ifindex : 0, tos, dst->sin.sin_addr.s_addr, &saddr, @@ -1997,6 +1990,11 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, return; } + if (!info) + udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM_TX); + else if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT) + df = htons(IP_DF); + tos = ip_tunnel_ecn_encap(tos, old_iph, skb); ttl = ttl ? : ip4_dst_hoplimit(&rt->dst); err = vxlan_build_skb(skb, &rt->dst, sizeof(struct iphdr), @@ -2898,8 +2896,9 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev, if (data[IFLA_VXLAN_PORT]) conf.dst_port = nla_get_be16(data[IFLA_VXLAN_PORT]); - if (data[IFLA_VXLAN_UDP_CSUM] && nla_get_u8(data[IFLA_VXLAN_UDP_CSUM])) - conf.flags |= VXLAN_F_UDP_CSUM; + if (data[IFLA_VXLAN_UDP_CSUM] && + !nla_get_u8(data[IFLA_VXLAN_UDP_CSUM])) + conf.flags |= VXLAN_F_UDP_ZERO_CSUM_TX; if (data[IFLA_VXLAN_UDP_ZERO_CSUM6_TX] && nla_get_u8(data[IFLA_VXLAN_UDP_ZERO_CSUM6_TX])) @@ -3043,7 +3042,7 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev) nla_put_u32(skb, IFLA_VXLAN_LIMIT, vxlan->cfg.addrmax) || nla_put_be16(skb, IFLA_VXLAN_PORT, vxlan->cfg.dst_port) || nla_put_u8(skb, IFLA_VXLAN_UDP_CSUM, - !!(vxlan->flags & VXLAN_F_UDP_CSUM)) || + !(vxlan->flags & VXLAN_F_UDP_ZERO_CSUM_TX)) || nla_put_u8(skb, IFLA_VXLAN_UDP_ZERO_CSUM6_TX, !!(vxlan->flags & VXLAN_F_UDP_ZERO_CSUM6_TX)) || nla_put_u8(skb, IFLA_VXLAN_UDP_ZERO_CSUM6_RX, diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 748083de367a..6eda4ed4d78b 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -197,7 +197,7 @@ struct vxlan_dev { #define VXLAN_F_L2MISS 0x08 #define VXLAN_F_L3MISS 0x10 #define VXLAN_F_IPV6 0x20 -#define VXLAN_F_UDP_CSUM 0x40 +#define VXLAN_F_UDP_ZERO_CSUM_TX 0x40 #define VXLAN_F_UDP_ZERO_CSUM6_TX 0x80 #define VXLAN_F_UDP_ZERO_CSUM6_RX 0x100 #define VXLAN_F_REMCSUM_TX 0x200 -- cgit v1.2.3-71-gd317 From 6d5d2ee63cee7025badda3b74ae2ef7ab097acfa Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Fri, 8 Jan 2016 19:28:58 +0100 Subject: Bluetooth: add LED trigger for indicating HCI is powered up Add support for LED triggers to the Bluetooth subsystem and add kernel config symbol BT_LEDS for it. For now one trigger for indicating "HCI is powered up" is supported. Signed-off-by: Heiner Kallweit Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 3 ++ net/bluetooth/Kconfig | 9 +++++ net/bluetooth/Makefile | 1 + net/bluetooth/hci_core.c | 8 ++++ net/bluetooth/leds.c | 80 ++++++++++++++++++++++++++++++++++++++++ net/bluetooth/leds.h | 18 +++++++++ 6 files changed, 119 insertions(+) create mode 100644 net/bluetooth/leds.c create mode 100644 net/bluetooth/leds.h (limited to 'include/net') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index d4f82edb5cff..dc71473462ac 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -25,6 +25,7 @@ #ifndef __HCI_CORE_H #define __HCI_CORE_H +#include #include #include @@ -396,6 +397,8 @@ struct hci_dev { struct delayed_work rpa_expired; bdaddr_t rpa; + struct led_trigger *power_led; + int (*open)(struct hci_dev *hdev); int (*close)(struct hci_dev *hdev); int (*flush)(struct hci_dev *hdev); diff --git a/net/bluetooth/Kconfig b/net/bluetooth/Kconfig index 95d1a66ba03a..06c31b9a68b0 100644 --- a/net/bluetooth/Kconfig +++ b/net/bluetooth/Kconfig @@ -69,6 +69,15 @@ config BT_6LOWPAN help IPv6 compression over Bluetooth Low Energy. +config BT_LEDS + bool "Enable LED triggers" + depends on BT + depends on LEDS_CLASS + select LEDS_TRIGGERS + help + This option selects a few LED triggers for different + Bluetooth events. + config BT_SELFTEST bool "Bluetooth self testing support" depends on BT && DEBUG_KERNEL diff --git a/net/bluetooth/Makefile b/net/bluetooth/Makefile index 2b15ae8c1def..b3ff12eb9b6d 100644 --- a/net/bluetooth/Makefile +++ b/net/bluetooth/Makefile @@ -17,6 +17,7 @@ bluetooth-y := af_bluetooth.o hci_core.o hci_conn.o hci_event.o mgmt.o \ bluetooth-$(CONFIG_BT_BREDR) += sco.o bluetooth-$(CONFIG_BT_HS) += a2mp.o amp.o +bluetooth-$(CONFIG_BT_LEDS) += leds.o bluetooth-$(CONFIG_BT_DEBUGFS) += hci_debugfs.o bluetooth-$(CONFIG_BT_SELFTEST) += selftest.o diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 883c821a9e78..88f1ef3589d8 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -40,6 +40,7 @@ #include "hci_request.h" #include "hci_debugfs.h" #include "smp.h" +#include "leds.h" static void hci_rx_work(struct work_struct *work); static void hci_cmd_work(struct work_struct *work); @@ -1395,6 +1396,7 @@ static int hci_dev_do_open(struct hci_dev *hdev) hci_dev_set_flag(hdev, HCI_RPA_EXPIRED); set_bit(HCI_UP, &hdev->flags); hci_sock_dev_event(hdev, HCI_DEV_UP); + hci_leds_update_powered(hdev, true); if (!hci_dev_test_flag(hdev, HCI_SETUP) && !hci_dev_test_flag(hdev, HCI_CONFIG) && !hci_dev_test_flag(hdev, HCI_UNCONFIGURED) && @@ -1532,6 +1534,8 @@ int hci_dev_do_close(struct hci_dev *hdev) return 0; } + hci_leds_update_powered(hdev, false); + /* Flush RX and TX works */ flush_work(&hdev->tx_work); flush_work(&hdev->rx_work); @@ -3067,6 +3071,8 @@ int hci_register_dev(struct hci_dev *hdev) if (error < 0) goto err_wqueue; + hci_leds_init(hdev); + hdev->rfkill = rfkill_alloc(hdev->name, &hdev->dev, RFKILL_TYPE_BLUETOOTH, &hci_rfkill_ops, hdev); @@ -3128,6 +3134,8 @@ void hci_unregister_dev(struct hci_dev *hdev) id = hdev->id; + hci_leds_exit(hdev); + write_lock(&hci_dev_list_lock); list_del(&hdev->list); write_unlock(&hci_dev_list_lock); diff --git a/net/bluetooth/leds.c b/net/bluetooth/leds.c new file mode 100644 index 000000000000..ded7c88eaccc --- /dev/null +++ b/net/bluetooth/leds.c @@ -0,0 +1,80 @@ +/* + * Copyright 2015, Heiner Kallweit + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include + +#include "leds.h" + +struct hci_basic_led_trigger { + struct led_trigger led_trigger; + struct hci_dev *hdev; +}; + +#define to_hci_basic_led_trigger(arg) container_of(arg, \ + struct hci_basic_led_trigger, led_trigger) + +void hci_leds_update_powered(struct hci_dev *hdev, bool enabled) +{ + if (hdev->power_led) + led_trigger_event(hdev->power_led, + enabled ? LED_FULL : LED_OFF); +} + +static void power_activate(struct led_classdev *led_cdev) +{ + struct hci_basic_led_trigger *htrig; + bool powered; + + htrig = to_hci_basic_led_trigger(led_cdev->trigger); + powered = test_bit(HCI_UP, &htrig->hdev->flags); + + led_trigger_event(led_cdev->trigger, powered ? LED_FULL : LED_OFF); +} + +static struct led_trigger *led_allocate_basic(struct hci_dev *hdev, + void (*activate)(struct led_classdev *led_cdev), + const char *name) +{ + struct hci_basic_led_trigger *htrig; + + htrig = devm_kzalloc(&hdev->dev, sizeof(*htrig), GFP_KERNEL); + if (!htrig) + return NULL; + + htrig->hdev = hdev; + htrig->led_trigger.activate = activate; + htrig->led_trigger.name = devm_kasprintf(&hdev->dev, GFP_KERNEL, + "%s-%s", hdev->name, + name); + if (!htrig->led_trigger.name) + goto err_alloc; + + if (led_trigger_register(&htrig->led_trigger)) + goto err_register; + + return &htrig->led_trigger; + +err_register: + devm_kfree(&hdev->dev, (void *)htrig->led_trigger.name); +err_alloc: + devm_kfree(&hdev->dev, htrig); + return NULL; +} + +void hci_leds_init(struct hci_dev *hdev) +{ + /* initialize power_led */ + hdev->power_led = led_allocate_basic(hdev, power_activate, "power"); +} + +void hci_leds_exit(struct hci_dev *hdev) +{ + if (hdev->power_led) + led_trigger_unregister(hdev->power_led); +} diff --git a/net/bluetooth/leds.h b/net/bluetooth/leds.h new file mode 100644 index 000000000000..068261a4e12c --- /dev/null +++ b/net/bluetooth/leds.h @@ -0,0 +1,18 @@ +/* + * Copyright 2015, Heiner Kallweit + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#if IS_ENABLED(CONFIG_BT_LEDS) +void hci_leds_update_powered(struct hci_dev *hdev, bool enabled); +void hci_leds_init(struct hci_dev *hdev); +void hci_leds_exit(struct hci_dev *hdev); +#else +static inline void hci_leds_update_powered(struct hci_dev *hdev, + bool enabled) {} +static inline void hci_leds_init(struct hci_dev *hdev) {} +static inline void hci_leds_exit(struct hci_dev *hdev) {} +#endif -- cgit v1.2.3-71-gd317 From 07b0188adf7298bf80a9890d3e90f27e973623d3 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Fri, 19 Feb 2016 09:59:11 +0100 Subject: mac802154: fix mac header length check I got report about that sometimes the WARN_ON occurs there which should never happen. I came to the conclusion that the mac header is there but inside the headroom of skb. The skb->len information doesn't contain the information about the headroom length and skb->len is lesser than two. We check now if the skb_mac_header pointer is set and the room between mac header pointer and tail pointer. Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/net/mac802154.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/mac802154.h b/include/net/mac802154.h index da574bbdc333..2e3cdd2048d2 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -247,8 +247,9 @@ struct ieee802154_ops { */ static inline __le16 ieee802154_get_fc_from_skb(const struct sk_buff *skb) { - /* return some invalid fc on failure */ - if (unlikely(skb->len < 2)) { + /* check if we can fc at skb_mac_header of sk buffer */ + if (unlikely(!skb_mac_header_was_set(skb) || + (skb_tail_pointer(skb) - skb_mac_header(skb)) < 2)) { WARN_ON(1); return cpu_to_le16(0); } -- cgit v1.2.3-71-gd317 From 5609c185f24dffca5f6a9c127106869da150be03 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Mon, 22 Feb 2016 09:13:54 +0100 Subject: 6lowpan: iphc: add support for stateful compression This patch introduce support for IPHC stateful address compression. It will offer the context table via one debugfs entry. This debugfs has and directory for each cid entry for the context table. Inside each cid directory there exists the following files: - "active": If the entry is added or deleted. The context table is original a list implementation, this flag will indicate if the context is part of list or not. - "prefix": The ipv6 prefix. - "prefix_length": The prefix length for the prefix. - "compression": The compression flag according RFC6775. This part should be moved into sysfs after some testing time. Also the debugfs entry contains a "show" file which is a pretty-printout for the current context table information. Reviewed-by: Stefan Schmidt Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/net/6lowpan.h | 32 ++++ net/6lowpan/core.c | 39 ++++- net/6lowpan/debugfs.c | 247 ++++++++++++++++++++++++++++++ net/6lowpan/iphc.c | 414 +++++++++++++++++++++++++++++++++++++++++++------- 4 files changed, 674 insertions(+), 58 deletions(-) (limited to 'include/net') diff --git a/include/net/6lowpan.h b/include/net/6lowpan.h index 2f6a3f2233ed..da3a77d25fcb 100644 --- a/include/net/6lowpan.h +++ b/include/net/6lowpan.h @@ -75,6 +75,8 @@ #define LOWPAN_IPHC_MAX_HC_BUF_LEN (sizeof(struct ipv6hdr) + \ LOWPAN_IPHC_MAX_HEADER_LEN + \ LOWPAN_NHC_MAX_HDR_LEN) +/* SCI/DCI is 4 bit width, so we have maximum 16 entries */ +#define LOWPAN_IPHC_CTX_TABLE_SIZE (1 << 4) #define LOWPAN_DISPATCH_IPV6 0x41 /* 01000001 = 65 */ #define LOWPAN_DISPATCH_IPHC 0x60 /* 011xxxxx = ... */ @@ -98,9 +100,39 @@ enum lowpan_lltypes { LOWPAN_LLTYPE_IEEE802154, }; +enum lowpan_iphc_ctx_flags { + LOWPAN_IPHC_CTX_FLAG_ACTIVE, + LOWPAN_IPHC_CTX_FLAG_COMPRESSION, +}; + +struct lowpan_iphc_ctx { + u8 id; + struct in6_addr pfx; + u8 plen; + unsigned long flags; +}; + +struct lowpan_iphc_ctx_table { + spinlock_t lock; + const struct lowpan_iphc_ctx_ops *ops; + struct lowpan_iphc_ctx table[LOWPAN_IPHC_CTX_TABLE_SIZE]; +}; + +static inline bool lowpan_iphc_ctx_is_active(const struct lowpan_iphc_ctx *ctx) +{ + return test_bit(LOWPAN_IPHC_CTX_FLAG_ACTIVE, &ctx->flags); +} + +static inline bool +lowpan_iphc_ctx_is_compression(const struct lowpan_iphc_ctx *ctx) +{ + return test_bit(LOWPAN_IPHC_CTX_FLAG_COMPRESSION, &ctx->flags); +} + struct lowpan_priv { enum lowpan_lltypes lltype; struct dentry *iface_debugfs; + struct lowpan_iphc_ctx_table ctx; /* must be last */ u8 priv[0] __aligned(sizeof(void *)); diff --git a/net/6lowpan/core.c b/net/6lowpan/core.c index faf65baed617..34e44c0c0836 100644 --- a/net/6lowpan/core.c +++ b/net/6lowpan/core.c @@ -20,7 +20,7 @@ int lowpan_register_netdevice(struct net_device *dev, enum lowpan_lltypes lltype) { - int ret; + int i, ret; dev->addr_len = EUI64_ADDR_LEN; dev->type = ARPHRD_6LOWPAN; @@ -29,6 +29,10 @@ int lowpan_register_netdevice(struct net_device *dev, lowpan_priv(dev)->lltype = lltype; + spin_lock_init(&lowpan_priv(dev)->ctx.lock); + for (i = 0; i < LOWPAN_IPHC_CTX_TABLE_SIZE; i++) + lowpan_priv(dev)->ctx.table[i].id = i; + ret = register_netdevice(dev); if (ret < 0) return ret; @@ -68,6 +72,32 @@ void lowpan_unregister_netdev(struct net_device *dev) } EXPORT_SYMBOL(lowpan_unregister_netdev); +static int lowpan_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + int i; + + if (dev->type != ARPHRD_6LOWPAN) + return NOTIFY_DONE; + + switch (event) { + case NETDEV_DOWN: + for (i = 0; i < LOWPAN_IPHC_CTX_TABLE_SIZE; i++) + clear_bit(LOWPAN_IPHC_CTX_FLAG_ACTIVE, + &lowpan_priv(dev)->ctx.table[i].flags); + break; + default: + return NOTIFY_DONE; + } + + return NOTIFY_OK; +} + +static struct notifier_block lowpan_notifier = { + .notifier_call = lowpan_event, +}; + static int __init lowpan_module_init(void) { int ret; @@ -76,6 +106,12 @@ static int __init lowpan_module_init(void) if (ret < 0) return ret; + ret = register_netdevice_notifier(&lowpan_notifier); + if (ret < 0) { + lowpan_debugfs_exit(); + return ret; + } + request_module_nowait("ipv6"); request_module_nowait("nhc_dest"); @@ -92,6 +128,7 @@ static int __init lowpan_module_init(void) static void __exit lowpan_module_exit(void) { lowpan_debugfs_exit(); + unregister_netdevice_notifier(&lowpan_notifier); } module_init(lowpan_module_init); diff --git a/net/6lowpan/debugfs.c b/net/6lowpan/debugfs.c index 88eef84df0fc..aa49ff4ce6fd 100644 --- a/net/6lowpan/debugfs.c +++ b/net/6lowpan/debugfs.c @@ -16,19 +16,266 @@ #include "6lowpan_i.h" +#define LOWPAN_DEBUGFS_CTX_PFX_NUM_ARGS 8 + static struct dentry *lowpan_debugfs; +static int lowpan_ctx_flag_active_set(void *data, u64 val) +{ + struct lowpan_iphc_ctx *ctx = data; + + if (val != 0 && val != 1) + return -EINVAL; + + if (val) + set_bit(LOWPAN_IPHC_CTX_FLAG_ACTIVE, &ctx->flags); + else + clear_bit(LOWPAN_IPHC_CTX_FLAG_ACTIVE, &ctx->flags); + + return 0; +} + +static int lowpan_ctx_flag_active_get(void *data, u64 *val) +{ + *val = lowpan_iphc_ctx_is_active(data); + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(lowpan_ctx_flag_active_fops, + lowpan_ctx_flag_active_get, + lowpan_ctx_flag_active_set, "%llu\n"); + +static int lowpan_ctx_flag_c_set(void *data, u64 val) +{ + struct lowpan_iphc_ctx *ctx = data; + + if (val != 0 && val != 1) + return -EINVAL; + + if (val) + set_bit(LOWPAN_IPHC_CTX_FLAG_COMPRESSION, &ctx->flags); + else + clear_bit(LOWPAN_IPHC_CTX_FLAG_COMPRESSION, &ctx->flags); + + return 0; +} + +static int lowpan_ctx_flag_c_get(void *data, u64 *val) +{ + *val = lowpan_iphc_ctx_is_compression(data); + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(lowpan_ctx_flag_c_fops, lowpan_ctx_flag_c_get, + lowpan_ctx_flag_c_set, "%llu\n"); + +static int lowpan_ctx_plen_set(void *data, u64 val) +{ + struct lowpan_iphc_ctx *ctx = data; + struct lowpan_iphc_ctx_table *t = + container_of(ctx, struct lowpan_iphc_ctx_table, table[ctx->id]); + + if (val > 128) + return -EINVAL; + + spin_lock_bh(&t->lock); + ctx->plen = val; + spin_unlock_bh(&t->lock); + + return 0; +} + +static int lowpan_ctx_plen_get(void *data, u64 *val) +{ + struct lowpan_iphc_ctx *ctx = data; + struct lowpan_iphc_ctx_table *t = + container_of(ctx, struct lowpan_iphc_ctx_table, table[ctx->id]); + + spin_lock_bh(&t->lock); + *val = ctx->plen; + spin_unlock_bh(&t->lock); + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(lowpan_ctx_plen_fops, lowpan_ctx_plen_get, + lowpan_ctx_plen_set, "%llu\n"); + +static int lowpan_ctx_pfx_show(struct seq_file *file, void *offset) +{ + struct lowpan_iphc_ctx *ctx = file->private; + struct lowpan_iphc_ctx_table *t = + container_of(ctx, struct lowpan_iphc_ctx_table, table[ctx->id]); + + spin_lock_bh(&t->lock); + seq_printf(file, "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x\n", + be16_to_cpu(ctx->pfx.s6_addr16[0]), + be16_to_cpu(ctx->pfx.s6_addr16[1]), + be16_to_cpu(ctx->pfx.s6_addr16[2]), + be16_to_cpu(ctx->pfx.s6_addr16[3]), + be16_to_cpu(ctx->pfx.s6_addr16[4]), + be16_to_cpu(ctx->pfx.s6_addr16[5]), + be16_to_cpu(ctx->pfx.s6_addr16[6]), + be16_to_cpu(ctx->pfx.s6_addr16[7])); + spin_unlock_bh(&t->lock); + + return 0; +} + +static int lowpan_ctx_pfx_open(struct inode *inode, struct file *file) +{ + return single_open(file, lowpan_ctx_pfx_show, inode->i_private); +} + +static ssize_t lowpan_ctx_pfx_write(struct file *fp, + const char __user *user_buf, size_t count, + loff_t *ppos) +{ + char buf[128] = {}; + struct seq_file *file = fp->private_data; + struct lowpan_iphc_ctx *ctx = file->private; + struct lowpan_iphc_ctx_table *t = + container_of(ctx, struct lowpan_iphc_ctx_table, table[ctx->id]); + int status = count, n, i; + unsigned int addr[8]; + + if (copy_from_user(&buf, user_buf, min_t(size_t, sizeof(buf) - 1, + count))) { + status = -EFAULT; + goto out; + } + + n = sscanf(buf, "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x", + &addr[0], &addr[1], &addr[2], &addr[3], &addr[4], + &addr[5], &addr[6], &addr[7]); + if (n != LOWPAN_DEBUGFS_CTX_PFX_NUM_ARGS) { + status = -EINVAL; + goto out; + } + + spin_lock_bh(&t->lock); + for (i = 0; i < 8; i++) + ctx->pfx.s6_addr16[i] = cpu_to_be16(addr[i] & 0xffff); + spin_unlock_bh(&t->lock); + +out: + return status; +} + +const struct file_operations lowpan_ctx_pfx_fops = { + .open = lowpan_ctx_pfx_open, + .read = seq_read, + .write = lowpan_ctx_pfx_write, + .llseek = seq_lseek, + .release = single_release, +}; + +static int lowpan_dev_debugfs_ctx_init(struct net_device *dev, + struct dentry *ctx, u8 id) +{ + struct lowpan_priv *lpriv = lowpan_priv(dev); + struct dentry *dentry, *root; + char buf[32]; + + WARN_ON_ONCE(id > LOWPAN_IPHC_CTX_TABLE_SIZE); + + sprintf(buf, "%d", id); + + root = debugfs_create_dir(buf, ctx); + if (!root) + return -EINVAL; + + dentry = debugfs_create_file("active", 0644, root, + &lpriv->ctx.table[id], + &lowpan_ctx_flag_active_fops); + if (!dentry) + return -EINVAL; + + dentry = debugfs_create_file("compression", 0644, root, + &lpriv->ctx.table[id], + &lowpan_ctx_flag_c_fops); + if (!dentry) + return -EINVAL; + + dentry = debugfs_create_file("prefix", 0644, root, + &lpriv->ctx.table[id], + &lowpan_ctx_pfx_fops); + if (!dentry) + return -EINVAL; + + dentry = debugfs_create_file("prefix_len", 0644, root, + &lpriv->ctx.table[id], + &lowpan_ctx_plen_fops); + if (!dentry) + return -EINVAL; + + return 0; +} + +static int lowpan_context_show(struct seq_file *file, void *offset) +{ + struct lowpan_iphc_ctx_table *t = file->private; + int i; + + seq_printf(file, "%3s|%-43s|%c\n", "cid", "prefix", 'C'); + seq_puts(file, "-------------------------------------------------\n"); + + spin_lock_bh(&t->lock); + for (i = 0; i < LOWPAN_IPHC_CTX_TABLE_SIZE; i++) { + if (!lowpan_iphc_ctx_is_active(&t->table[i])) + continue; + + seq_printf(file, "%3d|%39pI6c/%-3d|%d\n", t->table[i].id, + &t->table[i].pfx, t->table[i].plen, + lowpan_iphc_ctx_is_compression(&t->table[i])); + } + spin_unlock_bh(&t->lock); + + return 0; +} + +static int lowpan_context_open(struct inode *inode, struct file *file) +{ + return single_open(file, lowpan_context_show, inode->i_private); +} + +const struct file_operations lowpan_context_fops = { + .open = lowpan_context_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + int lowpan_dev_debugfs_init(struct net_device *dev) { struct lowpan_priv *lpriv = lowpan_priv(dev); + struct dentry *contexts, *dentry; + int ret, i; /* creating the root */ lpriv->iface_debugfs = debugfs_create_dir(dev->name, lowpan_debugfs); if (!lpriv->iface_debugfs) goto fail; + contexts = debugfs_create_dir("contexts", lpriv->iface_debugfs); + if (!contexts) + goto remove_root; + + dentry = debugfs_create_file("show", 0644, contexts, + &lowpan_priv(dev)->ctx, + &lowpan_context_fops); + if (!dentry) + goto remove_root; + + for (i = 0; i < LOWPAN_IPHC_CTX_TABLE_SIZE; i++) { + ret = lowpan_dev_debugfs_ctx_init(dev, contexts, i); + if (ret < 0) + goto remove_root; + } + return 0; +remove_root: + lowpan_dev_debugfs_exit(dev); fail: return -EINVAL; } diff --git a/net/6lowpan/iphc.c b/net/6lowpan/iphc.c index 346b5c1a9185..d2a565cde4f4 100644 --- a/net/6lowpan/iphc.c +++ b/net/6lowpan/iphc.c @@ -56,6 +56,7 @@ /* special link-layer handling */ #include +#include "6lowpan_i.h" #include "nhc.h" /* Values of fields within the IPHC encoding first byte */ @@ -147,6 +148,9 @@ (((a)->s6_addr16[6]) == 0) && \ (((a)->s6_addr[14]) == 0)) +#define LOWPAN_IPHC_CID_DCI(cid) (cid & 0x0f) +#define LOWPAN_IPHC_CID_SCI(cid) ((cid & 0xf0) >> 4) + static inline void iphc_uncompress_eui64_lladdr(struct in6_addr *ipaddr, const void *lladdr) { @@ -195,6 +199,98 @@ static inline void iphc_uncompress_802154_lladdr(struct in6_addr *ipaddr, } } +static struct lowpan_iphc_ctx * +lowpan_iphc_ctx_get_by_id(const struct net_device *dev, u8 id) +{ + struct lowpan_iphc_ctx *ret = &lowpan_priv(dev)->ctx.table[id]; + + if (!lowpan_iphc_ctx_is_active(ret)) + return NULL; + + return ret; +} + +static struct lowpan_iphc_ctx * +lowpan_iphc_ctx_get_by_addr(const struct net_device *dev, + const struct in6_addr *addr) +{ + struct lowpan_iphc_ctx *table = lowpan_priv(dev)->ctx.table; + struct lowpan_iphc_ctx *ret = NULL; + struct in6_addr addr_pfx; + u8 addr_plen; + int i; + + for (i = 0; i < LOWPAN_IPHC_CTX_TABLE_SIZE; i++) { + /* Check if context is valid. A context that is not valid + * MUST NOT be used for compression. + */ + if (!lowpan_iphc_ctx_is_active(&table[i]) || + !lowpan_iphc_ctx_is_compression(&table[i])) + continue; + + ipv6_addr_prefix(&addr_pfx, addr, table[i].plen); + + /* if prefix len < 64, the remaining bits until 64th bit is + * zero. Otherwise we use table[i]->plen. + */ + if (table[i].plen < 64) + addr_plen = 64; + else + addr_plen = table[i].plen; + + if (ipv6_prefix_equal(&addr_pfx, &table[i].pfx, addr_plen)) { + /* remember first match */ + if (!ret) { + ret = &table[i]; + continue; + } + + /* get the context with longest prefix len */ + if (table[i].plen > ret->plen) + ret = &table[i]; + } + } + + return ret; +} + +static struct lowpan_iphc_ctx * +lowpan_iphc_ctx_get_by_mcast_addr(const struct net_device *dev, + const struct in6_addr *addr) +{ + struct lowpan_iphc_ctx *table = lowpan_priv(dev)->ctx.table; + struct lowpan_iphc_ctx *ret = NULL; + struct in6_addr addr_mcast, network_pfx = {}; + int i; + + /* init mcast address with */ + memcpy(&addr_mcast, addr, sizeof(*addr)); + + for (i = 0; i < LOWPAN_IPHC_CTX_TABLE_SIZE; i++) { + /* Check if context is valid. A context that is not valid + * MUST NOT be used for compression. + */ + if (!lowpan_iphc_ctx_is_active(&table[i]) || + !lowpan_iphc_ctx_is_compression(&table[i])) + continue; + + /* setting plen */ + addr_mcast.s6_addr[3] = table[i].plen; + /* get network prefix to copy into multicast address */ + ipv6_addr_prefix(&network_pfx, &table[i].pfx, + table[i].plen); + /* setting network prefix */ + memcpy(&addr_mcast.s6_addr[4], &network_pfx, 8); + + if (ipv6_addr_equal(addr, &addr_mcast)) { + ret = &table[i]; + break; + } + } + + return ret; +} + /* Uncompress address function for source and * destination address(non-multicast). * @@ -259,30 +355,59 @@ static int uncompress_addr(struct sk_buff *skb, const struct net_device *dev, /* Uncompress address function for source context * based address(non-multicast). */ -static int uncompress_context_based_src_addr(struct sk_buff *skb, - struct in6_addr *ipaddr, - u8 address_mode) +static int uncompress_ctx_addr(struct sk_buff *skb, + const struct net_device *dev, + const struct lowpan_iphc_ctx *ctx, + struct in6_addr *ipaddr, u8 address_mode, + const void *lladdr) { + bool fail; + switch (address_mode) { - case LOWPAN_IPHC_SAM_00: - /* unspec address :: + /* SAM and DAM are the same here */ + case LOWPAN_IPHC_DAM_00: + fail = false; + /* SAM_00 -> unspec address :: * Do nothing, address is already :: + * + * DAM 00 -> reserved should never occur. */ break; case LOWPAN_IPHC_SAM_01: - /* TODO */ + case LOWPAN_IPHC_DAM_01: + fail = lowpan_fetch_skb(skb, &ipaddr->s6_addr[8], 8); + ipv6_addr_prefix_copy(ipaddr, &ctx->pfx, ctx->plen); + break; case LOWPAN_IPHC_SAM_10: - /* TODO */ + case LOWPAN_IPHC_DAM_10: + ipaddr->s6_addr[11] = 0xFF; + ipaddr->s6_addr[12] = 0xFE; + fail = lowpan_fetch_skb(skb, &ipaddr->s6_addr[14], 2); + ipv6_addr_prefix_copy(ipaddr, &ctx->pfx, ctx->plen); + break; case LOWPAN_IPHC_SAM_11: - /* TODO */ - netdev_warn(skb->dev, "SAM value 0x%x not supported\n", - address_mode); - return -EINVAL; + case LOWPAN_IPHC_DAM_11: + fail = false; + switch (lowpan_priv(dev)->lltype) { + case LOWPAN_LLTYPE_IEEE802154: + iphc_uncompress_802154_lladdr(ipaddr, lladdr); + break; + default: + iphc_uncompress_eui64_lladdr(ipaddr, lladdr); + break; + } + ipv6_addr_prefix_copy(ipaddr, &ctx->pfx, ctx->plen); + break; default: pr_debug("Invalid sam value: 0x%x\n", address_mode); return -EINVAL; } + if (fail) { + pr_debug("Failed to fetch skb data\n"); + return -EIO; + } + raw_dump_inline(NULL, "Reconstructed context based ipv6 src addr is", ipaddr->s6_addr, 16); @@ -346,6 +471,30 @@ static int lowpan_uncompress_multicast_daddr(struct sk_buff *skb, return 0; } +static int lowpan_uncompress_multicast_ctx_daddr(struct sk_buff *skb, + struct lowpan_iphc_ctx *ctx, + struct in6_addr *ipaddr, + u8 address_mode) +{ + struct in6_addr network_pfx = {}; + bool fail; + + ipaddr->s6_addr[0] = 0xFF; + fail = lowpan_fetch_skb(skb, &ipaddr->s6_addr[1], 2); + fail |= lowpan_fetch_skb(skb, &ipaddr->s6_addr[12], 4); + if (fail < 0) + return -EIO; + + /* take prefix_len and network prefix from the context */ + ipaddr->s6_addr[3] = ctx->plen; + /* get network prefix to copy into multicast address */ + ipv6_addr_prefix(&network_pfx, &ctx->pfx, ctx->plen); + /* setting network prefix */ + memcpy(&ipaddr->s6_addr[4], &network_pfx, 8); + + return 0; +} + /* get the ecn values from iphc tf format and set it to ipv6hdr */ static inline void lowpan_iphc_tf_set_ecn(struct ipv6hdr *hdr, const u8 *tf) { @@ -459,7 +608,8 @@ int lowpan_header_decompress(struct sk_buff *skb, const struct net_device *dev, const void *daddr, const void *saddr) { struct ipv6hdr hdr = {}; - u8 iphc0, iphc1; + struct lowpan_iphc_ctx *ci; + u8 iphc0, iphc1, cid = 0; int err; raw_dump_table(__func__, "raw skb data dump uncompressed", @@ -469,12 +619,14 @@ int lowpan_header_decompress(struct sk_buff *skb, const struct net_device *dev, lowpan_fetch_skb(skb, &iphc1, sizeof(iphc1))) return -EINVAL; - /* another if the CID flag is set */ - if (iphc1 & LOWPAN_IPHC_CID) - return -ENOTSUPP; - hdr.version = 6; + /* default CID = 0, another if the CID flag is set */ + if (iphc1 & LOWPAN_IPHC_CID) { + if (lowpan_fetch_skb(skb, &cid, sizeof(cid))) + return -EINVAL; + } + err = lowpan_iphc_tf_decompress(skb, &hdr, iphc0 & LOWPAN_IPHC_TF_MASK); if (err < 0) @@ -500,10 +652,17 @@ int lowpan_header_decompress(struct sk_buff *skb, const struct net_device *dev, } if (iphc1 & LOWPAN_IPHC_SAC) { - /* Source address context based uncompression */ + spin_lock_bh(&lowpan_priv(dev)->ctx.lock); + ci = lowpan_iphc_ctx_get_by_id(dev, LOWPAN_IPHC_CID_SCI(cid)); + if (!ci) { + spin_unlock_bh(&lowpan_priv(dev)->ctx.lock); + return -EINVAL; + } + pr_debug("SAC bit is set. Handle context based source address.\n"); - err = uncompress_context_based_src_addr(skb, &hdr.saddr, - iphc1 & LOWPAN_IPHC_SAM_MASK); + err = uncompress_ctx_addr(skb, dev, ci, &hdr.saddr, + iphc1 & LOWPAN_IPHC_SAM_MASK, saddr); + spin_unlock_bh(&lowpan_priv(dev)->ctx.lock); } else { /* Source address uncompression */ pr_debug("source address stateless compression\n"); @@ -515,27 +674,52 @@ int lowpan_header_decompress(struct sk_buff *skb, const struct net_device *dev, if (err) return -EINVAL; - /* check for Multicast Compression */ - if (iphc1 & LOWPAN_IPHC_M) { - if (iphc1 & LOWPAN_IPHC_DAC) { - pr_debug("dest: context-based mcast compression\n"); - /* TODO: implement this */ - } else { - err = lowpan_uncompress_multicast_daddr(skb, &hdr.daddr, - iphc1 & LOWPAN_IPHC_DAM_MASK); + switch (iphc1 & (LOWPAN_IPHC_M | LOWPAN_IPHC_DAC)) { + case LOWPAN_IPHC_M | LOWPAN_IPHC_DAC: + spin_lock_bh(&lowpan_priv(dev)->ctx.lock); + ci = lowpan_iphc_ctx_get_by_id(dev, LOWPAN_IPHC_CID_DCI(cid)); + if (!ci) { + spin_unlock_bh(&lowpan_priv(dev)->ctx.lock); + return -EINVAL; + } - if (err) - return -EINVAL; + /* multicast with context */ + pr_debug("dest: context-based mcast compression\n"); + err = lowpan_uncompress_multicast_ctx_daddr(skb, ci, + &hdr.daddr, + iphc1 & LOWPAN_IPHC_DAM_MASK); + spin_unlock_bh(&lowpan_priv(dev)->ctx.lock); + break; + case LOWPAN_IPHC_M: + /* multicast */ + err = lowpan_uncompress_multicast_daddr(skb, &hdr.daddr, + iphc1 & LOWPAN_IPHC_DAM_MASK); + break; + case LOWPAN_IPHC_DAC: + spin_lock_bh(&lowpan_priv(dev)->ctx.lock); + ci = lowpan_iphc_ctx_get_by_id(dev, LOWPAN_IPHC_CID_DCI(cid)); + if (!ci) { + spin_unlock_bh(&lowpan_priv(dev)->ctx.lock); + return -EINVAL; } - } else { + + /* Destination address context based uncompression */ + pr_debug("DAC bit is set. Handle context based destination address.\n"); + err = uncompress_ctx_addr(skb, dev, ci, &hdr.daddr, + iphc1 & LOWPAN_IPHC_DAM_MASK, daddr); + spin_unlock_bh(&lowpan_priv(dev)->ctx.lock); + break; + default: err = uncompress_addr(skb, dev, &hdr.daddr, iphc1 & LOWPAN_IPHC_DAM_MASK, daddr); pr_debug("dest: stateless compression mode %d dest %pI6c\n", iphc1 & LOWPAN_IPHC_DAM_MASK, &hdr.daddr); - if (err) - return -EINVAL; + break; } + if (err) + return -EINVAL; + /* Next header data uncompression */ if (iphc0 & LOWPAN_IPHC_NH) { err = lowpan_nhc_do_uncompression(skb, dev, &hdr); @@ -585,6 +769,58 @@ static const u8 lowpan_iphc_dam_to_sam_value[] = { [LOWPAN_IPHC_DAM_11] = LOWPAN_IPHC_SAM_11, }; +static u8 lowpan_compress_ctx_addr(u8 **hc_ptr, const struct in6_addr *ipaddr, + const struct lowpan_iphc_ctx *ctx, + const unsigned char *lladdr, bool sam) +{ + struct in6_addr tmp = {}; + u8 dam; + + /* check for SAM/DAM = 11 */ + memcpy(&tmp.s6_addr[8], lladdr, 8); + /* second bit-flip (Universe/Local) is done according RFC2464 */ + tmp.s6_addr[8] ^= 0x02; + /* context information are always used */ + ipv6_addr_prefix_copy(&tmp, &ctx->pfx, ctx->plen); + if (ipv6_addr_equal(&tmp, ipaddr)) { + dam = LOWPAN_IPHC_DAM_11; + goto out; + } + + memset(&tmp, 0, sizeof(tmp)); + /* check for SAM/DAM = 01 */ + tmp.s6_addr[11] = 0xFF; + tmp.s6_addr[12] = 0xFE; + memcpy(&tmp.s6_addr[14], &ipaddr->s6_addr[14], 2); + /* context information are always used */ + ipv6_addr_prefix_copy(&tmp, &ctx->pfx, ctx->plen); + if (ipv6_addr_equal(&tmp, ipaddr)) { + lowpan_push_hc_data(hc_ptr, &ipaddr->s6_addr[14], 2); + dam = LOWPAN_IPHC_DAM_10; + goto out; + } + + memset(&tmp, 0, sizeof(tmp)); + /* check for SAM/DAM = 10, should always match */ + memcpy(&tmp.s6_addr[8], &ipaddr->s6_addr[8], 8); + /* context information are always used */ + ipv6_addr_prefix_copy(&tmp, &ctx->pfx, ctx->plen); + if (ipv6_addr_equal(&tmp, ipaddr)) { + lowpan_push_hc_data(hc_ptr, &ipaddr->s6_addr[8], 8); + dam = LOWPAN_IPHC_DAM_01; + goto out; + } + + WARN_ON_ONCE("context found but no address mode matched\n"); + return -EINVAL; +out: + + if (sam) + return lowpan_iphc_dam_to_sam_value[dam]; + else + return dam; +} + static u8 lowpan_compress_addr_64(u8 **hc_ptr, const struct in6_addr *ipaddr, const unsigned char *lladdr, bool sam) { @@ -708,6 +944,21 @@ static u8 lowpan_iphc_tf_compress(u8 **hc_ptr, const struct ipv6hdr *hdr) return val; } +static u8 lowpan_iphc_mcast_ctx_addr_compress(u8 **hc_ptr, + const struct lowpan_iphc_ctx *ctx, + const struct in6_addr *ipaddr) +{ + u8 data[6]; + + /* flags/scope, reserved (RIID) */ + memcpy(data, &ipaddr->s6_addr[1], 2); + /* group ID */ + memcpy(&data[1], &ipaddr->s6_addr[11], 4); + lowpan_push_hc_data(hc_ptr, data, 6); + + return LOWPAN_IPHC_DAM_00; +} + static u8 lowpan_iphc_mcast_addr_compress(u8 **hc_ptr, const struct in6_addr *ipaddr) { @@ -742,10 +993,11 @@ static u8 lowpan_iphc_mcast_addr_compress(u8 **hc_ptr, int lowpan_header_compress(struct sk_buff *skb, const struct net_device *dev, const void *daddr, const void *saddr) { - u8 iphc0, iphc1, *hc_ptr; + u8 iphc0, iphc1, *hc_ptr, cid = 0; struct ipv6hdr *hdr; u8 head[LOWPAN_IPHC_MAX_HC_BUF_LEN] = {}; - int ret, addr_type; + struct lowpan_iphc_ctx *dci, *sci, dci_entry, sci_entry; + int ret, ipv6_daddr_type, ipv6_saddr_type; if (skb->protocol != htons(ETH_P_IPV6)) return -EINVAL; @@ -769,14 +1021,38 @@ int lowpan_header_compress(struct sk_buff *skb, const struct net_device *dev, iphc0 = LOWPAN_DISPATCH_IPHC; iphc1 = 0; - /* TODO: context lookup */ - raw_dump_inline(__func__, "saddr", saddr, EUI64_ADDR_LEN); raw_dump_inline(__func__, "daddr", daddr, EUI64_ADDR_LEN); raw_dump_table(__func__, "sending raw skb network uncompressed packet", skb->data, skb->len); + ipv6_daddr_type = ipv6_addr_type(&hdr->daddr); + spin_lock_bh(&lowpan_priv(dev)->ctx.lock); + if (ipv6_daddr_type & IPV6_ADDR_MULTICAST) + dci = lowpan_iphc_ctx_get_by_mcast_addr(dev, &hdr->daddr); + else + dci = lowpan_iphc_ctx_get_by_addr(dev, &hdr->daddr); + if (dci) { + memcpy(&dci_entry, dci, sizeof(*dci)); + cid |= dci->id; + } + spin_unlock_bh(&lowpan_priv(dev)->ctx.lock); + + spin_lock_bh(&lowpan_priv(dev)->ctx.lock); + sci = lowpan_iphc_ctx_get_by_addr(dev, &hdr->saddr); + if (sci) { + memcpy(&sci_entry, sci, sizeof(*sci)); + cid |= (sci->id << 4); + } + spin_unlock_bh(&lowpan_priv(dev)->ctx.lock); + + /* if cid is zero it will be compressed */ + if (cid) { + iphc1 |= LOWPAN_IPHC_CID; + lowpan_push_hc_data(&hc_ptr, &cid, sizeof(cid)); + } + /* Traffic Class, Flow Label compression */ iphc0 |= lowpan_iphc_tf_compress(&hc_ptr, hdr); @@ -813,39 +1089,63 @@ int lowpan_header_compress(struct sk_buff *skb, const struct net_device *dev, sizeof(hdr->hop_limit)); } - addr_type = ipv6_addr_type(&hdr->saddr); + ipv6_saddr_type = ipv6_addr_type(&hdr->saddr); /* source address compression */ - if (addr_type == IPV6_ADDR_ANY) { + if (ipv6_saddr_type == IPV6_ADDR_ANY) { pr_debug("source address is unspecified, setting SAC\n"); iphc1 |= LOWPAN_IPHC_SAC; } else { - if (addr_type & IPV6_ADDR_LINKLOCAL) { - iphc1 |= lowpan_compress_addr_64(&hc_ptr, &hdr->saddr, - saddr, true); - pr_debug("source address unicast link-local %pI6c iphc1 0x%02x\n", - &hdr->saddr, iphc1); + if (sci) { + iphc1 |= lowpan_compress_ctx_addr(&hc_ptr, &hdr->saddr, + &sci_entry, saddr, + true); + iphc1 |= LOWPAN_IPHC_SAC; } else { - pr_debug("send the full source address\n"); - lowpan_push_hc_data(&hc_ptr, hdr->saddr.s6_addr, 16); + if (ipv6_saddr_type & IPV6_ADDR_LINKLOCAL) { + iphc1 |= lowpan_compress_addr_64(&hc_ptr, + &hdr->saddr, + saddr, true); + pr_debug("source address unicast link-local %pI6c iphc1 0x%02x\n", + &hdr->saddr, iphc1); + } else { + pr_debug("send the full source address\n"); + lowpan_push_hc_data(&hc_ptr, + hdr->saddr.s6_addr, 16); + } } } - addr_type = ipv6_addr_type(&hdr->daddr); /* destination address compression */ - if (addr_type & IPV6_ADDR_MULTICAST) { + if (ipv6_daddr_type & IPV6_ADDR_MULTICAST) { pr_debug("destination address is multicast: "); - iphc1 |= LOWPAN_IPHC_M; - iphc1 |= lowpan_iphc_mcast_addr_compress(&hc_ptr, &hdr->daddr); + if (dci) { + iphc1 |= lowpan_iphc_mcast_ctx_addr_compress(&hc_ptr, + &dci_entry, + &hdr->daddr); + } else { + iphc1 |= LOWPAN_IPHC_M; + iphc1 |= lowpan_iphc_mcast_addr_compress(&hc_ptr, + &hdr->daddr); + } } else { - if (addr_type & IPV6_ADDR_LINKLOCAL) { - /* TODO: context lookup */ - iphc1 |= lowpan_compress_addr_64(&hc_ptr, &hdr->daddr, - daddr, false); - pr_debug("dest address unicast link-local %pI6c " - "iphc1 0x%02x\n", &hdr->daddr, iphc1); + if (dci) { + iphc1 |= lowpan_compress_ctx_addr(&hc_ptr, &hdr->daddr, + &dci_entry, daddr, + false); + iphc1 |= LOWPAN_IPHC_DAC; } else { - pr_debug("dest address unicast %pI6c\n", &hdr->daddr); - lowpan_push_hc_data(&hc_ptr, hdr->daddr.s6_addr, 16); + if (ipv6_daddr_type & IPV6_ADDR_LINKLOCAL) { + iphc1 |= lowpan_compress_addr_64(&hc_ptr, + &hdr->daddr, + daddr, false); + pr_debug("dest address unicast link-local %pI6c iphc1 0x%02x\n", + &hdr->daddr, iphc1); + } else { + pr_debug("dest address unicast %pI6c\n", + &hdr->daddr); + lowpan_push_hc_data(&hc_ptr, + hdr->daddr.s6_addr, 16); + } } } -- cgit v1.2.3-71-gd317 From a6692754d61a6b3735803783f394880805675f99 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Fri, 12 Feb 2016 12:09:39 -0500 Subject: net: dsa: pass bridge down to drivers Some DSA drivers may or may not support multiple software bridges on top of an hardware switch. It is more convenient for them to access the bridge's net_device for finer configuration. Removing the need to craft and access a bitmask also simplifies the code. This patch changes the signature of bridge related functions, update DSA drivers, and removes dsa_slave_br_port_mask. Signed-off-by: Vivien Didelot Tested-by: Florian Fainelli Signed-off-by: David S. Miller --- Documentation/networking/dsa/dsa.txt | 7 ++----- drivers/net/dsa/bcm_sf2.c | 12 +++++++----- drivers/net/dsa/bcm_sf2.h | 2 ++ drivers/net/dsa/mv88e6xxx.c | 13 +++++++++++-- drivers/net/dsa/mv88e6xxx.h | 6 ++++-- include/net/dsa.h | 5 ++--- net/dsa/slave.c | 31 ++----------------------------- 7 files changed, 30 insertions(+), 46 deletions(-) (limited to 'include/net') diff --git a/Documentation/networking/dsa/dsa.txt b/Documentation/networking/dsa/dsa.txt index aa9c1f9313cd..ebf21530471f 100644 --- a/Documentation/networking/dsa/dsa.txt +++ b/Documentation/networking/dsa/dsa.txt @@ -524,17 +524,14 @@ Bridge layer - port_join_bridge: bridge layer function invoked when a given switch port is added to a bridge, this function should be doing the necessary at the switch level to permit the joining port from being added to the relevant logical - domain for it to ingress/egress traffic with other members of the bridge. DSA - does nothing but calculate a bitmask of switch ports currently members of the - specified bridge being requested the join + domain for it to ingress/egress traffic with other members of the bridge. - port_leave_bridge: bridge layer function invoked when a given switch port is removed from a bridge, this function should be doing the necessary at the switch level to deny the leaving port from ingress/egress traffic from the remaining bridge members. When the port leaves the bridge, it should be aged out at the switch hardware for the switch to (re) learn MAC addresses behind - this port. DSA calculates the bitmask of ports still members of the bridge - being left + this port. - port_stp_update: bridge layer function invoked when a given switch port STP state is computed by the bridge layer and should be propagated to switch diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 6f946fedbb77..3f627598f277 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -483,16 +483,17 @@ static int bcm_sf2_sw_fast_age_port(struct dsa_switch *ds, int port) } static int bcm_sf2_sw_br_join(struct dsa_switch *ds, int port, - u32 br_port_mask) + struct net_device *bridge) { struct bcm_sf2_priv *priv = ds_to_priv(ds); unsigned int i; u32 reg, p_ctl; + priv->port_sts[port].bridge_dev = bridge; p_ctl = core_readl(priv, CORE_PORT_VLAN_CTL_PORT(port)); for (i = 0; i < priv->hw_params.num_ports; i++) { - if (!((1 << i) & br_port_mask)) + if (priv->port_sts[i].bridge_dev != bridge) continue; /* Add this local port to the remote port VLAN control @@ -515,10 +516,10 @@ static int bcm_sf2_sw_br_join(struct dsa_switch *ds, int port, return 0; } -static int bcm_sf2_sw_br_leave(struct dsa_switch *ds, int port, - u32 br_port_mask) +static int bcm_sf2_sw_br_leave(struct dsa_switch *ds, int port) { struct bcm_sf2_priv *priv = ds_to_priv(ds); + struct net_device *bridge = priv->port_sts[port].bridge_dev; unsigned int i; u32 reg, p_ctl; @@ -526,7 +527,7 @@ static int bcm_sf2_sw_br_leave(struct dsa_switch *ds, int port, for (i = 0; i < priv->hw_params.num_ports; i++) { /* Don't touch the remaining ports */ - if (!((1 << i) & br_port_mask)) + if (priv->port_sts[i].bridge_dev != bridge) continue; reg = core_readl(priv, CORE_PORT_VLAN_CTL_PORT(i)); @@ -541,6 +542,7 @@ static int bcm_sf2_sw_br_leave(struct dsa_switch *ds, int port, core_writel(priv, p_ctl, CORE_PORT_VLAN_CTL_PORT(port)); priv->port_sts[port].vlan_ctl_mask = p_ctl; + priv->port_sts[port].bridge_dev = NULL; return 0; } diff --git a/drivers/net/dsa/bcm_sf2.h b/drivers/net/dsa/bcm_sf2.h index 6bba1c98d764..200b1f5fdb56 100644 --- a/drivers/net/dsa/bcm_sf2.h +++ b/drivers/net/dsa/bcm_sf2.h @@ -50,6 +50,8 @@ struct bcm_sf2_port_status { struct ethtool_eee eee; u32 vlan_ctl_mask; + + struct net_device *bridge_dev; }; struct bcm_sf2_arl_entry { diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c index b0e00edb302e..2e515e8a95fe 100644 --- a/drivers/net/dsa/mv88e6xxx.c +++ b/drivers/net/dsa/mv88e6xxx.c @@ -1889,13 +1889,22 @@ unlock: return err; } -int mv88e6xxx_port_bridge_join(struct dsa_switch *ds, int port, u32 members) +int mv88e6xxx_port_bridge_join(struct dsa_switch *ds, int port, + struct net_device *bridge) { + struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); + + ps->ports[port].bridge_dev = bridge; + return 0; } -int mv88e6xxx_port_bridge_leave(struct dsa_switch *ds, int port, u32 members) +int mv88e6xxx_port_bridge_leave(struct dsa_switch *ds, int port) { + struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); + + ps->ports[port].bridge_dev = NULL; + return 0; } diff --git a/drivers/net/dsa/mv88e6xxx.h b/drivers/net/dsa/mv88e6xxx.h index 63a6f587e9e8..260b4918e427 100644 --- a/drivers/net/dsa/mv88e6xxx.h +++ b/drivers/net/dsa/mv88e6xxx.h @@ -380,6 +380,7 @@ struct mv88e6xxx_vtu_stu_entry { }; struct mv88e6xxx_priv_port { + struct net_device *bridge_dev; u8 state; }; @@ -481,8 +482,9 @@ int mv88e6xxx_phy_write_indirect(struct dsa_switch *ds, int addr, int regnum, int mv88e6xxx_get_eee(struct dsa_switch *ds, int port, struct ethtool_eee *e); int mv88e6xxx_set_eee(struct dsa_switch *ds, int port, struct phy_device *phydev, struct ethtool_eee *e); -int mv88e6xxx_port_bridge_join(struct dsa_switch *ds, int port, u32 members); -int mv88e6xxx_port_bridge_leave(struct dsa_switch *ds, int port, u32 members); +int mv88e6xxx_port_bridge_join(struct dsa_switch *ds, int port, + struct net_device *bridge); +int mv88e6xxx_port_bridge_leave(struct dsa_switch *ds, int port); int mv88e6xxx_port_stp_update(struct dsa_switch *ds, int port, u8 state); int mv88e6xxx_port_vlan_prepare(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan, diff --git a/include/net/dsa.h b/include/net/dsa.h index 26a0e86e611e..1c845d7bf0b2 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -297,9 +297,8 @@ struct dsa_switch_driver { * Bridge integration */ int (*port_join_bridge)(struct dsa_switch *ds, int port, - u32 br_port_mask); - int (*port_leave_bridge)(struct dsa_switch *ds, int port, - u32 br_port_mask); + struct net_device *bridge); + int (*port_leave_bridge)(struct dsa_switch *ds, int port); int (*port_stp_update)(struct dsa_switch *ds, int port, u8 state); diff --git a/net/dsa/slave.c b/net/dsa/slave.c index ab24521beb4d..ab515df5f493 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -385,31 +385,6 @@ static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) return -EOPNOTSUPP; } -/* Return a bitmask of all ports being currently bridged within a given bridge - * device. Note that on leave, the mask will still return the bitmask of ports - * currently bridged, prior to port removal, and this is exactly what we want. - */ -static u32 dsa_slave_br_port_mask(struct dsa_switch *ds, - struct net_device *bridge) -{ - struct dsa_slave_priv *p; - unsigned int port; - u32 mask = 0; - - for (port = 0; port < DSA_MAX_PORTS; port++) { - if (!dsa_is_port_initialized(ds, port)) - continue; - - p = netdev_priv(ds->ports[port]); - - if (ds->ports[port]->priv_flags & IFF_BRIDGE_PORT && - p->bridge_dev == bridge) - mask |= 1 << port; - } - - return mask; -} - static int dsa_slave_stp_update(struct net_device *dev, u8 state) { struct dsa_slave_priv *p = netdev_priv(dev); @@ -533,8 +508,7 @@ static int dsa_slave_bridge_port_join(struct net_device *dev, p->bridge_dev = br; if (ds->drv->port_join_bridge) - ret = ds->drv->port_join_bridge(ds, p->port, - dsa_slave_br_port_mask(ds, br)); + ret = ds->drv->port_join_bridge(ds, p->port, br); return ret; } @@ -547,8 +521,7 @@ static int dsa_slave_bridge_port_leave(struct net_device *dev) if (ds->drv->port_leave_bridge) - ret = ds->drv->port_leave_bridge(ds, p->port, - dsa_slave_br_port_mask(ds, p->bridge_dev)); + ret = ds->drv->port_leave_bridge(ds, p->port); p->bridge_dev = NULL; -- cgit v1.2.3-71-gd317 From 412a6d800c7380c1b87c11080c7da905c27cfea8 Mon Sep 17 00:00:00 2001 From: Sara Sharon Date: Tue, 8 Dec 2015 19:09:05 +0200 Subject: mac80211: support hw managing reorder logic Enable driver to manage the reordering logic itself. This is needed for example for the iwlwifi driver that will support hardware assisted reordering. Signed-off-by: Sara Sharon Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- include/net/mac80211.h | 6 ++++++ net/mac80211/agg-rx.c | 24 ++++++++++++++++++++++-- net/mac80211/debugfs.c | 1 + net/mac80211/sta_info.h | 21 ++++++++++++--------- 4 files changed, 41 insertions(+), 11 deletions(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 6c9c559394b0..ee6305a52251 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1929,6 +1929,11 @@ struct ieee80211_txq { * by just its MAC address; this prevents, for example, the same station * from connecting to two virtual AP interfaces at the same time. * + * @IEEE80211_HW_SUPPORTS_REORDERING_BUFFER: Hardware (or driver) manages the + * reordering buffer internally, guaranteeing mac80211 receives frames in + * order and does not need to manage its own reorder buffer or BA session + * timeout. + * * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ enum ieee80211_hw_flags { @@ -1965,6 +1970,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_SUPPORTS_AMSDU_IN_AMPDU, IEEE80211_HW_BEACON_TX_STATUS, IEEE80211_HW_NEEDS_UNIQUE_STA_ADDR, + IEEE80211_HW_SUPPORTS_REORDERING_BUFFER, /* keep last, obviously */ NUM_IEEE80211_HW_FLAGS diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index ec80db7c955c..2ab54791281d 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -76,10 +76,11 @@ void ___ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid, tid_rx = rcu_dereference_protected(sta->ampdu_mlme.tid_rx[tid], lockdep_is_held(&sta->ampdu_mlme.mtx)); - if (!tid_rx) + if (!test_bit(tid, sta->ampdu_mlme.agg_session_valid)) return; RCU_INIT_POINTER(sta->ampdu_mlme.tid_rx[tid], NULL); + __clear_bit(tid, sta->ampdu_mlme.agg_session_valid); ht_dbg(sta->sdata, "Rx BA session stop requested for %pM tid %u %s reason: %d\n", @@ -97,6 +98,13 @@ void ___ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid, ieee80211_send_delba(sta->sdata, sta->sta.addr, tid, WLAN_BACK_RECIPIENT, reason); + /* + * return here in case tid_rx is not assigned - which will happen if + * IEEE80211_HW_SUPPORTS_REORDERING_BUFFER is set. + */ + if (!tid_rx) + return; + del_timer_sync(&tid_rx->session_timer); /* make sure ieee80211_sta_reorder_release() doesn't re-arm the timer */ @@ -297,7 +305,7 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta, /* examine state machine */ mutex_lock(&sta->ampdu_mlme.mtx); - if (sta->ampdu_mlme.tid_rx[tid]) { + if (test_bit(tid, sta->ampdu_mlme.agg_session_valid)) { ht_dbg_ratelimited(sta->sdata, "unexpected AddBA Req from %pM on tid %u\n", sta->sta.addr, tid); @@ -308,6 +316,16 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta, false); } + if (ieee80211_hw_check(&local->hw, SUPPORTS_REORDERING_BUFFER)) { + ret = drv_ampdu_action(local, sta->sdata, ¶ms); + ht_dbg(sta->sdata, + "Rx A-MPDU request on %pM tid %d result %d\n", + sta->sta.addr, tid, ret); + if (!ret) + status = WLAN_STATUS_SUCCESS; + goto end; + } + /* prepare A-MPDU MLME for Rx aggregation */ tid_agg_rx = kmalloc(sizeof(struct tid_ampdu_rx), GFP_KERNEL); if (!tid_agg_rx) @@ -369,6 +387,8 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta, } end: + if (status == WLAN_STATUS_SUCCESS) + __set_bit(tid, sta->ampdu_mlme.agg_session_valid); mutex_unlock(&sta->ampdu_mlme.mtx); end_no_lock: diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index abbdff03ce92..e433d0c97e86 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -126,6 +126,7 @@ static const char *hw_flag_names[NUM_IEEE80211_HW_FLAGS + 1] = { FLAG(SUPPORTS_AMSDU_IN_AMPDU), FLAG(BEACON_TX_STATUS), FLAG(NEEDS_UNIQUE_STA_ADDR), + FLAG(SUPPORTS_REORDERING_BUFFER), /* keep last for the build bug below */ (void *)0x1 diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index d6051629ed15..f4d38994ecee 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -1,6 +1,7 @@ /* * Copyright 2002-2005, Devicescape Software, Inc. * Copyright 2013-2014 Intel Mobile Communications GmbH + * Copyright(c) 2015 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -212,20 +213,21 @@ struct tid_ampdu_rx { /** * struct sta_ampdu_mlme - STA aggregation information. * + * @mtx: mutex to protect all TX data (except non-NULL assignments + * to tid_tx[idx], which are protected by the sta spinlock) + * tid_start_tx is also protected by sta->lock. * @tid_rx: aggregation info for Rx per TID -- RCU protected - * @tid_tx: aggregation info for Tx per TID - * @tid_start_tx: sessions where start was requested - * @addba_req_num: number of times addBA request has been sent. - * @last_addba_req_time: timestamp of the last addBA request. - * @dialog_token_allocator: dialog token enumerator for each new session; - * @work: work struct for starting/stopping aggregation * @tid_rx_timer_expired: bitmap indicating on which TIDs the * RX timer expired until the work for it runs * @tid_rx_stop_requested: bitmap indicating which BA sessions per TID the * driver requested to close until the work for it runs - * @mtx: mutex to protect all TX data (except non-NULL assignments - * to tid_tx[idx], which are protected by the sta spinlock) - * tid_start_tx is also protected by sta->lock. + * @agg_session_valid: bitmap indicating which TID has a rx BA session open on + * @work: work struct for starting/stopping aggregation + * @tid_tx: aggregation info for Tx per TID + * @tid_start_tx: sessions where start was requested + * @last_addba_req_time: timestamp of the last addBA request. + * @addba_req_num: number of times addBA request has been sent. + * @dialog_token_allocator: dialog token enumerator for each new session; */ struct sta_ampdu_mlme { struct mutex mtx; @@ -233,6 +235,7 @@ struct sta_ampdu_mlme { struct tid_ampdu_rx __rcu *tid_rx[IEEE80211_NUM_TIDS]; unsigned long tid_rx_timer_expired[BITS_TO_LONGS(IEEE80211_NUM_TIDS)]; unsigned long tid_rx_stop_requested[BITS_TO_LONGS(IEEE80211_NUM_TIDS)]; + unsigned long agg_session_valid[BITS_TO_LONGS(IEEE80211_NUM_TIDS)]; /* tx */ struct work_struct work; struct tid_ampdu_tx __rcu *tid_tx[IEEE80211_NUM_TIDS]; -- cgit v1.2.3-71-gd317 From 178830481eee5eea147a1c8fab67a96e09d80345 Mon Sep 17 00:00:00 2001 From: Grzegorz Bajorski Date: Fri, 11 Dec 2015 14:39:46 +0100 Subject: mac80211: allow drivers to report (non-)monitor frames Some drivers offload some frames internally (e.g. AddBa). Reporting such frames to mac80211 would only confuse MLME. However it would be useful to be able to pass such frames to monitor interfaces for sniffing purposes, e.g. when running AP + monitor. To do that allow drivers to tell mac80211 whether a given frame should be: - processed but not delivered to any monitor vif - not processed but delievered to monitor vifs only Signed-off-by: Grzegorz Bajorski Signed-off-by: Johannes Berg --- include/net/mac80211.h | 11 +++++++++++ net/mac80211/rx.c | 5 +++-- 2 files changed, 14 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index ee6305a52251..5910085af9e6 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1031,6 +1031,14 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) * @RX_FLAG_AMPDU_DELIM_CRC_KNOWN: The delimiter CRC field is known (the CRC * is stored in the @ampdu_delimiter_crc field) * @RX_FLAG_LDPC: LDPC was used + * @RX_FLAG_ONLY_MONITOR: Report frame only to monitor interfaces without + * processing it in any regular way. + * This is useful if drivers offload some frames but still want to report + * them for sniffing purposes. + * @RX_FLAG_SKIP_MONITOR: Process and report frame to all interfaces except + * monitor interfaces. + * This is useful if drivers offload some frames but still want to report + * them for sniffing purposes. * @RX_FLAG_STBC_MASK: STBC 2 bit bitmask. 1 - Nss=1, 2 - Nss=2, 3 - Nss=3 * @RX_FLAG_10MHZ: 10 MHz (half channel) was used * @RX_FLAG_5MHZ: 5 MHz (quarter channel) was used @@ -1071,6 +1079,8 @@ enum mac80211_rx_flags { RX_FLAG_MACTIME_END = BIT(21), RX_FLAG_VHT = BIT(22), RX_FLAG_LDPC = BIT(23), + RX_FLAG_ONLY_MONITOR = BIT(24), + RX_FLAG_SKIP_MONITOR = BIT(25), RX_FLAG_STBC_MASK = BIT(26) | BIT(27), RX_FLAG_10MHZ = BIT(28), RX_FLAG_5MHZ = BIT(29), @@ -1089,6 +1099,7 @@ enum mac80211_rx_flags { * @RX_VHT_FLAG_160MHZ: 160 MHz was used * @RX_VHT_FLAG_BF: packet was beamformed */ + enum mac80211_rx_vht_flags { RX_VHT_FLAG_80MHZ = BIT(0), RX_VHT_FLAG_160MHZ = BIT(1), diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index fe675d76f29c..ae993edfdecf 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -122,7 +122,8 @@ static inline bool should_drop_frame(struct sk_buff *skb, int present_fcs_len, hdr = (void *)(skb->data + rtap_vendor_space); if (status->flag & (RX_FLAG_FAILED_FCS_CRC | - RX_FLAG_FAILED_PLCP_CRC)) + RX_FLAG_FAILED_PLCP_CRC | + RX_FLAG_ONLY_MONITOR)) return true; if (unlikely(skb->len < 16 + present_fcs_len + rtap_vendor_space)) @@ -507,7 +508,7 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb, return NULL; } - if (!local->monitors) { + if (!local->monitors || (status->flag & RX_FLAG_SKIP_MONITOR)) { if (should_drop_frame(origskb, present_fcs_len, rtap_vendor_space)) { dev_kfree_skb(origskb); -- cgit v1.2.3-71-gd317 From 506bcfa8abebdbcebdc17b03e96e38dc0b8ce765 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Sun, 13 Dec 2015 15:41:05 +0200 Subject: mac80211: limit the A-MSDU Tx based on peer's capabilities In VHT, the specification allows to limit the number of MSDUs in an A-MSDU in the Extended Capabilities IE. There is also a limitation on the byte size in the VHT IE. In HT, the only limitation is on the byte size. Parse the capabilities from the peer and make them available to the driver. In HT, there is another limitation when a BA agreement is active: the byte size can't be greater than 4095. This is not enforced here. Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 19 +++++++++++++++++++ include/net/mac80211.h | 14 ++++++++++++++ net/mac80211/cfg.c | 29 +++++++++++++++++++++++++++++ net/mac80211/ht.c | 5 +++++ net/mac80211/vht.c | 17 +++++++++++++++++ 5 files changed, 84 insertions(+) (limited to 'include/net') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index d9ddb89533a7..3b1f6cef9513 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -163,6 +163,14 @@ static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2) /* 30 byte 4 addr hdr, 2 byte QoS, 2304 byte MSDU, 12 byte crypt, 4 byte FCS */ #define IEEE80211_MAX_FRAME_LEN 2352 +/* Maximal size of an A-MSDU */ +#define IEEE80211_MAX_MPDU_LEN_HT_3839 3839 +#define IEEE80211_MAX_MPDU_LEN_HT_7935 7935 + +#define IEEE80211_MAX_MPDU_LEN_VHT_3895 3895 +#define IEEE80211_MAX_MPDU_LEN_VHT_7991 7991 +#define IEEE80211_MAX_MPDU_LEN_VHT_11454 11454 + #define IEEE80211_MAX_SSID_LEN 32 #define IEEE80211_MAX_MESH_ID_LEN 32 @@ -1505,6 +1513,7 @@ struct ieee80211_vht_operation { #define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895 0x00000000 #define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991 0x00000001 #define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454 0x00000002 +#define IEEE80211_VHT_CAP_MAX_MPDU_MASK 0x00000003 #define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ 0x00000004 #define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ 0x00000008 #define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK 0x0000000C @@ -2086,6 +2095,16 @@ enum ieee80211_tdls_actioncode { #define WLAN_EXT_CAPA8_TDLS_WIDE_BW_ENABLED BIT(5) #define WLAN_EXT_CAPA8_OPMODE_NOTIF BIT(6) +/* Defines the maximal number of MSDUs in an A-MSDU. */ +#define WLAN_EXT_CAPA8_MAX_MSDU_IN_AMSDU_LSB BIT(7) +#define WLAN_EXT_CAPA9_MAX_MSDU_IN_AMSDU_MSB BIT(0) + +/* + * Fine Timing Measurement Initiator - bit 71 of @WLAN_EID_EXT_CAPABILITY + * information element + */ +#define WLAN_EXT_CAPA9_FTM_INITIATOR BIT(7) + /* TDLS specific payload type in the LLC/SNAP header */ #define WLAN_TDLS_SNAP_RFTYPE 0x2 diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 5910085af9e6..df5698ed8052 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1714,6 +1714,18 @@ struct ieee80211_sta_rates { * @tdls_initiator: indicates the STA is an initiator of the TDLS link. Only * valid if the STA is a TDLS peer in the first place. * @mfp: indicates whether the STA uses management frame protection or not. + * @max_amsdu_subframes: indicates the maximal number of MSDUs in a single + * A-MSDU. Taken from the Extended Capabilities element. 0 means + * unlimited. + * @max_amsdu_len: indicates the maximal length of an A-MSDU in bytes. This + * field is always valid for packets with a VHT preamble. For packets + * with a HT preamble, additional limits apply: + * + If the skb is transmitted as part of a BA agreement, the + * A-MSDU maximal size is min(max_amsdu_len, 4065) bytes. + * + If the skb is not part of a BA aggreement, the A-MSDU maximal + * size is min(max_amsdu_len, 7935) bytes. + * Both additional HT limits must be enforced by the low level driver. + * This is defined by the spec (IEEE 802.11-2012 section 8.3.2.2 NOTE 2). * @txq: per-TID data TX queues (if driver uses the TXQ abstraction) */ struct ieee80211_sta { @@ -1732,6 +1744,8 @@ struct ieee80211_sta { bool tdls; bool tdls_initiator; bool mfp; + u8 max_amsdu_subframes; + u16 max_amsdu_len; struct ieee80211_txq *txq[IEEE80211_NUM_TIDS]; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 166a29fe6c35..66d22de93c8d 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1131,6 +1131,34 @@ static int sta_apply_parameters(struct ieee80211_local *local, sta->sta.max_sp = params->max_sp; } + /* The sender might not have sent the last bit, consider it to be 0 */ + if (params->ext_capab_len >= 8) { + u8 val = (params->ext_capab[7] & + WLAN_EXT_CAPA8_MAX_MSDU_IN_AMSDU_LSB) >> 7; + + /* we did get all the bits, take the MSB as well */ + if (params->ext_capab_len >= 9) { + u8 val_msb = params->ext_capab[8] & + WLAN_EXT_CAPA9_MAX_MSDU_IN_AMSDU_MSB; + val_msb <<= 1; + val |= val_msb; + } + + switch (val) { + case 1: + sta->sta.max_amsdu_subframes = 32; + break; + case 2: + sta->sta.max_amsdu_subframes = 16; + break; + case 3: + sta->sta.max_amsdu_subframes = 8; + break; + default: + sta->sta.max_amsdu_subframes = 0; + } + } + /* * cfg80211 validates this (1-2007) and allows setting the AID * only when creating a new station entry @@ -1160,6 +1188,7 @@ static int sta_apply_parameters(struct ieee80211_local *local, ieee80211_ht_cap_ie_to_sta_ht_cap(sdata, sband, params->ht_capa, sta); + /* VHT can override some HT caps such as the A-MSDU max length */ if (params->vht_capa) ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband, params->vht_capa, sta); diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index 7a76ce639d58..f4a528773563 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -230,6 +230,11 @@ bool ieee80211_ht_cap_ie_to_sta_ht_cap(struct ieee80211_sub_if_data *sdata, /* set Rx highest rate */ ht_cap.mcs.rx_highest = ht_cap_ie->mcs.rx_highest; + if (ht_cap.cap & IEEE80211_HT_CAP_MAX_AMSDU) + sta->sta.max_amsdu_len = IEEE80211_MAX_MPDU_LEN_HT_7935; + else + sta->sta.max_amsdu_len = IEEE80211_MAX_MPDU_LEN_HT_3839; + apply: changed = memcmp(&sta->sta.ht_cap, &ht_cap, sizeof(ht_cap)); diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index 050de08bf82e..204cf9ad3019 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -281,6 +281,23 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, } sta->sta.bandwidth = ieee80211_sta_cur_vht_bw(sta); + + /* If HT IE reported 3839 bytes only, stay with that size. */ + if (sta->sta.max_amsdu_len == IEEE80211_MAX_MPDU_LEN_HT_3839) + return; + + switch (vht_cap->cap & IEEE80211_VHT_CAP_MAX_MPDU_MASK) { + case IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454: + sta->sta.max_amsdu_len = IEEE80211_MAX_MPDU_LEN_VHT_11454; + break; + case IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991: + sta->sta.max_amsdu_len = IEEE80211_MAX_MPDU_LEN_VHT_7991; + break; + case IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895: + default: + sta->sta.max_amsdu_len = IEEE80211_MAX_MPDU_LEN_VHT_3895; + break; + } } enum ieee80211_sta_rx_bandwidth ieee80211_sta_cap_rx_bw(struct sta_info *sta) -- cgit v1.2.3-71-gd317 From 538dc9045251d3d6b5c0216a5c61c32bd9cedac9 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Thu, 24 Dec 2015 00:33:26 -0800 Subject: mac80211: Make addr const in SET_IEEE80211_PERM_ADDR() Make the addr parameter const in SET_IEEE80211_PERM_ADDR() to save clients from having to cast away a const qualifier. Signed-off-by: Bjorn Andersson Signed-off-by: Johannes Berg --- include/net/mac80211.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index df5698ed8052..566df20dc957 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2217,7 +2217,7 @@ static inline void SET_IEEE80211_DEV(struct ieee80211_hw *hw, struct device *dev * @hw: the &struct ieee80211_hw to set the MAC address for * @addr: the address to set */ -static inline void SET_IEEE80211_PERM_ADDR(struct ieee80211_hw *hw, u8 *addr) +static inline void SET_IEEE80211_PERM_ADDR(struct ieee80211_hw *hw, const u8 *addr) { memcpy(hw->wiphy->perm_addr, addr, ETH_ALEN); } -- cgit v1.2.3-71-gd317 From f4a0f0c5264e72d9279fbf9cf48a061526e8f788 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 25 Jan 2016 15:46:34 +0200 Subject: mac80211: add RX_FLAG_MACTIME_PLCP_START The timestamp given by iwlwifi is at the beginning of the frame over the air, at (or during) the SYNC field. Allow such timestamps to be given to mac80211, at least (for now) for frames with non-HT/VHT preambles. Signed-off-by: Johannes Berg --- include/net/mac80211.h | 3 +++ net/mac80211/ieee80211_i.h | 8 +++++++- net/mac80211/util.c | 14 +++++++++++++- 3 files changed, 23 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 566df20dc957..31337f81ec03 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1010,6 +1010,8 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) * @RX_FLAG_MACTIME_END: The timestamp passed in the RX status (@mactime * field) is valid and contains the time the last symbol of the MPDU * (including FCS) was received. + * @RX_FLAG_MACTIME_PLCP_START: The timestamp passed in the RX status (@mactime + * field) is valid and contains the time the SYNC preamble was received. * @RX_FLAG_SHORTPRE: Short preamble was used for this frame * @RX_FLAG_HT: HT MCS was used and rate_idx is MCS index * @RX_FLAG_VHT: VHT MCS was used and rate_index is MCS index @@ -1058,6 +1060,7 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) enum mac80211_rx_flags { RX_FLAG_MMIC_ERROR = BIT(0), RX_FLAG_DECRYPTED = BIT(1), + RX_FLAG_MACTIME_PLCP_START = BIT(2), RX_FLAG_MMIC_STRIPPED = BIT(3), RX_FLAG_IV_STRIPPED = BIT(4), RX_FLAG_FAILED_FCS_CRC = BIT(5), diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 9934447a8b9a..a29f61dc9c06 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1466,7 +1466,13 @@ ieee80211_have_rx_timestamp(struct ieee80211_rx_status *status) { WARN_ON_ONCE(status->flag & RX_FLAG_MACTIME_START && status->flag & RX_FLAG_MACTIME_END); - return status->flag & (RX_FLAG_MACTIME_START | RX_FLAG_MACTIME_END); + if (status->flag & (RX_FLAG_MACTIME_START | RX_FLAG_MACTIME_END)) + return true; + /* can't handle HT/VHT preamble yet */ + if (status->flag & RX_FLAG_MACTIME_PLCP_START && + !(status->flag & (RX_FLAG_HT | RX_FLAG_VHT))) + return true; + return false; } u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local, diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 7d0479e31674..fb90d9c5df59 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -4,7 +4,7 @@ * Copyright 2006-2007 Jiri Benc * Copyright 2007 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH - * Copyright (C) 2015 Intel Deutschland GmbH + * Copyright (C) 2015-2016 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -2671,6 +2671,18 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local, sband = local->hw.wiphy->bands[status->band]; bitrate = sband->bitrates[status->rate_idx].bitrate; ri.legacy = DIV_ROUND_UP(bitrate, (1 << shift)); + + if (status->flag & RX_FLAG_MACTIME_PLCP_START) { + /* TODO: handle HT/VHT preambles */ + if (status->band == IEEE80211_BAND_5GHZ) { + ts += 20 << shift; + mpdu_offset += 2; + } else if (status->flag & RX_FLAG_SHORTPRE) { + ts += 96; + } else { + ts += 192; + } + } } rate = cfg80211_calculate_bitrate(&ri); -- cgit v1.2.3-71-gd317 From dfdfc2beb0dd7e3a067d2eeacb4623cb48e77658 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Tue, 26 Jan 2016 17:11:13 +0100 Subject: mac80211: Parse legacy and HT rate in injected frames Drivers/devices without their own rate control algorithm can get the information what rates they should use from either the radiotap header of injected frames or from the rate control algorithm. But the parsing of the legacy rate information from the radiotap header was removed in commit e6a9854b05c1 ("mac80211/drivers: rewrite the rate control API"). The removal of this feature heavily reduced the usefulness of frame injection when wanting to simulate specific transmission behavior. Having rate parsing together with MCS rates and retry support allows a fine grained selection of the tx behavior of injected frames for these kind of tests. Signed-off-by: Sven Eckelmann Cc: Simon Wunderlich Signed-off-by: Johannes Berg --- Documentation/networking/mac80211-injection.txt | 17 ++++++ include/net/mac80211.h | 2 + net/mac80211/tx.c | 72 ++++++++++++++++++++++++- 3 files changed, 89 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/Documentation/networking/mac80211-injection.txt b/Documentation/networking/mac80211-injection.txt index 3a930072b161..ec8f934c2eb2 100644 --- a/Documentation/networking/mac80211-injection.txt +++ b/Documentation/networking/mac80211-injection.txt @@ -28,6 +28,23 @@ radiotap headers and used to control injection: IEEE80211_RADIOTAP_F_TX_NOACK: frame should be sent without waiting for an ACK even if it is a unicast frame + * IEEE80211_RADIOTAP_RATE + + legacy rate for the transmission (only for devices without own rate control) + + * IEEE80211_RADIOTAP_MCS + + HT rate for the transmission (only for devices without own rate control). + Also some flags are parsed + + IEEE80211_TX_RC_SHORT_GI: use short guard interval + IEEE80211_TX_RC_40_MHZ_WIDTH: send in HT40 mode + + * IEEE80211_RADIOTAP_DATA_RETRIES + + number of retries when either IEEE80211_RADIOTAP_RATE or + IEEE80211_RADIOTAP_MCS was used + The injection code can also skip all other currently defined radiotap fields facilitating replay of captured radiotap headers directly. diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 31337f81ec03..dbcd69a6bfda 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -708,12 +708,14 @@ enum mac80211_tx_info_flags { * protocol frame (e.g. EAP) * @IEEE80211_TX_CTRL_PS_RESPONSE: This frame is a response to a poll * frame (PS-Poll or uAPSD). + * @IEEE80211_TX_CTRL_RATE_INJECT: This frame is injected with rate information * * These flags are used in tx_info->control.flags. */ enum mac80211_tx_control_flags { IEEE80211_TX_CTRL_PORT_CTRL_PROTO = BIT(0), IEEE80211_TX_CTRL_PS_RESPONSE = BIT(1), + IEEE80211_TX_CTRL_RATE_INJECT = BIT(2), }; /* diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 3311ce0f3d6c..723cd7aa8953 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -710,6 +710,10 @@ ieee80211_tx_h_rate_ctrl(struct ieee80211_tx_data *tx) info->control.short_preamble = txrc.short_preamble; + /* don't ask rate control when rate already injected via radiotap */ + if (info->control.flags & IEEE80211_TX_CTRL_RATE_INJECT) + return TX_CONTINUE; + if (tx->sta) assoc = test_sta_flag(tx->sta, WLAN_STA_ASSOC); @@ -1665,15 +1669,24 @@ void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, ieee80211_tx(sdata, sta, skb, false); } -static bool ieee80211_parse_tx_radiotap(struct sk_buff *skb) +static bool ieee80211_parse_tx_radiotap(struct ieee80211_local *local, + struct sk_buff *skb) { struct ieee80211_radiotap_iterator iterator; struct ieee80211_radiotap_header *rthdr = (struct ieee80211_radiotap_header *) skb->data; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + struct ieee80211_supported_band *sband = + local->hw.wiphy->bands[info->band]; int ret = ieee80211_radiotap_iterator_init(&iterator, rthdr, skb->len, NULL); u16 txflags; + u16 rate = 0; + bool rate_found = false; + u8 rate_retries = 0; + u16 rate_flags = 0; + u8 mcs_known, mcs_flags; + int i; info->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT | IEEE80211_TX_CTL_DONTFRAG; @@ -1724,6 +1737,35 @@ static bool ieee80211_parse_tx_radiotap(struct sk_buff *skb) info->flags |= IEEE80211_TX_CTL_NO_ACK; break; + case IEEE80211_RADIOTAP_RATE: + rate = *iterator.this_arg; + rate_flags = 0; + rate_found = true; + break; + + case IEEE80211_RADIOTAP_DATA_RETRIES: + rate_retries = *iterator.this_arg; + break; + + case IEEE80211_RADIOTAP_MCS: + mcs_known = iterator.this_arg[0]; + mcs_flags = iterator.this_arg[1]; + if (!(mcs_known & IEEE80211_RADIOTAP_MCS_HAVE_MCS)) + break; + + rate_found = true; + rate = iterator.this_arg[2]; + rate_flags = IEEE80211_TX_RC_MCS; + + if (mcs_known & IEEE80211_RADIOTAP_MCS_HAVE_GI && + mcs_flags & IEEE80211_RADIOTAP_MCS_SGI) + rate_flags |= IEEE80211_TX_RC_SHORT_GI; + + if (mcs_known & IEEE80211_RADIOTAP_MCS_HAVE_BW && + mcs_flags & IEEE80211_RADIOTAP_MCS_BW_40) + rate_flags |= IEEE80211_TX_RC_40_MHZ_WIDTH; + break; + /* * Please update the file * Documentation/networking/mac80211-injection.txt @@ -1738,6 +1780,32 @@ static bool ieee80211_parse_tx_radiotap(struct sk_buff *skb) if (ret != -ENOENT) /* ie, if we didn't simply run out of fields */ return false; + if (rate_found) { + info->control.flags |= IEEE80211_TX_CTRL_RATE_INJECT; + + for (i = 0; i < IEEE80211_TX_MAX_RATES; i++) { + info->control.rates[i].idx = -1; + info->control.rates[i].flags = 0; + info->control.rates[i].count = 0; + } + + if (rate_flags & IEEE80211_TX_RC_MCS) { + info->control.rates[0].idx = rate; + } else { + for (i = 0; i < sband->n_bitrates; i++) { + if (rate * 5 != sband->bitrates[i].bitrate) + continue; + + info->control.rates[0].idx = i; + break; + } + } + + info->control.rates[0].flags = rate_flags; + info->control.rates[0].count = min_t(u8, rate_retries + 1, + local->hw.max_rate_tries); + } + /* * remove the radiotap header * iterator->_max_length was sanity-checked against @@ -1819,7 +1887,7 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, IEEE80211_TX_CTL_INJECTED; /* process and remove the injection radiotap header */ - if (!ieee80211_parse_tx_radiotap(skb)) + if (!ieee80211_parse_tx_radiotap(local, skb)) goto fail; rcu_read_lock(); -- cgit v1.2.3-71-gd317 From f2ac7e301ae6397669ff3f79e691942a9b5d2f39 Mon Sep 17 00:00:00 2001 From: Michal Kazior Date: Wed, 27 Jan 2016 15:26:12 +0100 Subject: mac80211: expose txq queue depth and size to drivers This will allow drivers to make more educated decisions whether to defer transmission or not. Relying on wake_tx_queue() call count implicitly was not possible because it could be called without queued frame count actually changing on software tx aggregation start/stop code paths. It was also not possible to know how long byte-wise queue was without dequeueing. Signed-off-by: Michal Kazior Signed-off-by: Johannes Berg --- include/net/mac80211.h | 15 +++++++++++++++ net/mac80211/ieee80211_i.h | 1 + net/mac80211/iface.c | 1 + net/mac80211/sta_info.c | 1 + net/mac80211/tx.c | 8 +++++++- net/mac80211/util.c | 14 ++++++++++++++ 6 files changed, 39 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index dbcd69a6bfda..fd35fc4d7127 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -5596,4 +5596,19 @@ void ieee80211_unreserve_tid(struct ieee80211_sta *sta, u8 tid); */ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw, struct ieee80211_txq *txq); + +/** + * ieee80211_txq_get_depth - get pending frame/byte count of given txq + * + * The values are not guaranteed to be coherent with regard to each other, i.e. + * txq state can change half-way of this function and the caller may end up + * with "new" frame_cnt and "old" byte_cnt or vice-versa. + * + * @txq: pointer obtained from station or virtual interface + * @frame_cnt: pointer to store frame count + * @byte_cnt: pointer to store byte count + */ +void ieee80211_txq_get_depth(struct ieee80211_txq *txq, + unsigned long *frame_cnt, + unsigned long *byte_cnt); #endif /* MAC80211_H */ diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index a29f61dc9c06..a96f8c0461f6 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -804,6 +804,7 @@ enum txq_info_flags { struct txq_info { struct sk_buff_head queue; unsigned long flags; + unsigned long byte_cnt; /* keep last! */ struct ieee80211_txq txq; diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 0451f120746e..453b4e741780 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -979,6 +979,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, spin_lock_bh(&txqi->queue.lock); ieee80211_purge_tx_queue(&local->hw, &txqi->queue); + txqi->byte_cnt = 0; spin_unlock_bh(&txqi->queue.lock); atomic_set(&sdata->txqs_len[txqi->txq.ac], 0); diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index b28e7a220d56..5894c0a1c01f 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -116,6 +116,7 @@ static void __cleanup_single_sta(struct sta_info *sta) ieee80211_purge_tx_queue(&local->hw, &txqi->queue); atomic_sub(n, &sdata->txqs_len[txqi->txq.ac]); + txqi->byte_cnt = 0; } } diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 723cd7aa8953..a5aa275d0434 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1270,7 +1270,11 @@ static void ieee80211_drv_tx(struct ieee80211_local *local, if (atomic_read(&sdata->txqs_len[ac]) >= local->hw.txq_ac_max_pending) netif_stop_subqueue(sdata->dev, ac); - skb_queue_tail(&txqi->queue, skb); + spin_lock_bh(&txqi->queue.lock); + txqi->byte_cnt += skb->len; + __skb_queue_tail(&txqi->queue, skb); + spin_unlock_bh(&txqi->queue.lock); + drv_wake_tx_queue(local, txqi); return; @@ -1298,6 +1302,8 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw, if (!skb) goto out; + txqi->byte_cnt -= skb->len; + atomic_dec(&sdata->txqs_len[ac]); if (__netif_subqueue_stopped(sdata->dev, ac)) ieee80211_propagate_queue_wake(local, sdata->vif.hw_queue[ac]); diff --git a/net/mac80211/util.c b/net/mac80211/util.c index fb90d9c5df59..091f3dd62ad1 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -3368,3 +3368,17 @@ void ieee80211_init_tx_queue(struct ieee80211_sub_if_data *sdata, txqi->txq.ac = IEEE80211_AC_BE; } } + +void ieee80211_txq_get_depth(struct ieee80211_txq *txq, + unsigned long *frame_cnt, + unsigned long *byte_cnt) +{ + struct txq_info *txqi = to_txq_info(txq); + + if (frame_cnt) + *frame_cnt = txqi->queue.qlen; + + if (byte_cnt) + *byte_cnt = txqi->byte_cnt; +} +EXPORT_SYMBOL(ieee80211_txq_get_depth); -- cgit v1.2.3-71-gd317 From 06470f7468c8b6c95e72ebda803a61a99f4ee446 Mon Sep 17 00:00:00 2001 From: Sara Sharon Date: Thu, 28 Jan 2016 16:19:25 +0200 Subject: mac80211: add API to allow filtering frames in BA sessions If any frames are dropped that are part of a BA session, the reorder buffer will "indefinitely" (until the timeout) wait for them to come in (or a BAR moving the window) and won't release frames after them. This means it isn't possible to filter frames within a BA session in firmware. Introduce an API function that allows such filtering. Calling this function will move the BA window forward to the new SSN, and allows marking frames after the SSN as having been filtered, so any future reordering activity will release frames while skipping the holes. Signed-off-by: Sara Sharon Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- include/net/mac80211.h | 20 +++++++++++- net/mac80211/agg-rx.c | 1 + net/mac80211/rx.c | 84 +++++++++++++++++++++++++++++++++++++++++++++++++ net/mac80211/sta_info.h | 3 ++ 4 files changed, 107 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index fd35fc4d7127..57147749ae42 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -5,7 +5,7 @@ * Copyright 2006-2007 Jiri Benc * Copyright 2007-2010 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH - * Copyright (C) 2015 Intel Deutschland GmbH + * Copyright (C) 2015 - 2016 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -5193,6 +5193,24 @@ void ieee80211_remain_on_channel_expired(struct ieee80211_hw *hw); void ieee80211_stop_rx_ba_session(struct ieee80211_vif *vif, u16 ba_rx_bitmap, const u8 *addr); +/** + * ieee80211_mark_rx_ba_filtered_frames - move RX BA window and mark filtered + * @pubsta: station struct + * @tid: the session's TID + * @ssn: starting sequence number of the bitmap, all frames before this are + * assumed to be out of the window after the call + * @filtered: bitmap of filtered frames, BIT(0) is the @ssn entry etc. + * @received_mpdus: number of received mpdus in firmware + * + * This function moves the BA window and releases all frames before @ssn, and + * marks frames marked in the bitmap as having been filtered. Afterwards, it + * checks if any frames in the window starting from @ssn can now be released + * (in case they were only waiting for frames that were filtered.) + */ +void ieee80211_mark_rx_ba_filtered_frames(struct ieee80211_sta *pubsta, u8 tid, + u16 ssn, u64 filtered, + u16 received_mpdus); + /** * ieee80211_send_bar - send a BlockAckReq frame * diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 2ab54791281d..1b8a5caa221e 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -376,6 +376,7 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta, tid_agg_rx->timeout = timeout; tid_agg_rx->stored_mpdu_num = 0; tid_agg_rx->auto_seq = auto_seq; + tid_agg_rx->reorder_buf_filtered = 0; status = WLAN_STATUS_SUCCESS; /* activate it for RX */ diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 1153871b570f..9fb7074f0280 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include @@ -806,6 +807,9 @@ static inline bool ieee80211_rx_reorder_ready(struct tid_ampdu_rx *tid_agg_rx, struct sk_buff *tail = skb_peek_tail(frames); struct ieee80211_rx_status *status; + if (tid_agg_rx->reorder_buf_filtered & BIT_ULL(index)) + return true; + if (!tail) return false; @@ -844,6 +848,7 @@ static void ieee80211_release_reorder_frame(struct ieee80211_sub_if_data *sdata, } no_frame: + tid_agg_rx->reorder_buf_filtered &= ~BIT_ULL(index); tid_agg_rx->head_seq_num = ieee80211_sn_inc(tid_agg_rx->head_seq_num); } @@ -3300,6 +3305,85 @@ void ieee80211_release_reorder_timeout(struct sta_info *sta, int tid) ieee80211_rx_handlers(&rx, &frames); } +void ieee80211_mark_rx_ba_filtered_frames(struct ieee80211_sta *pubsta, u8 tid, + u16 ssn, u64 filtered, + u16 received_mpdus) +{ + struct sta_info *sta; + struct tid_ampdu_rx *tid_agg_rx; + struct sk_buff_head frames; + struct ieee80211_rx_data rx = { + /* This is OK -- must be QoS data frame */ + .security_idx = tid, + .seqno_idx = tid, + }; + int i, diff; + + if (WARN_ON(!pubsta || tid >= IEEE80211_NUM_TIDS)) + return; + + __skb_queue_head_init(&frames); + + sta = container_of(pubsta, struct sta_info, sta); + + rx.sta = sta; + rx.sdata = sta->sdata; + rx.local = sta->local; + + rcu_read_lock(); + tid_agg_rx = rcu_dereference(sta->ampdu_mlme.tid_rx[tid]); + if (!tid_agg_rx) + goto out; + + spin_lock_bh(&tid_agg_rx->reorder_lock); + + if (received_mpdus >= IEEE80211_SN_MODULO >> 1) { + int release; + + /* release all frames in the reorder buffer */ + release = (tid_agg_rx->head_seq_num + tid_agg_rx->buf_size) % + IEEE80211_SN_MODULO; + ieee80211_release_reorder_frames(sta->sdata, tid_agg_rx, + release, &frames); + /* update ssn to match received ssn */ + tid_agg_rx->head_seq_num = ssn; + } else { + ieee80211_release_reorder_frames(sta->sdata, tid_agg_rx, ssn, + &frames); + } + + /* handle the case that received ssn is behind the mac ssn. + * it can be tid_agg_rx->buf_size behind and still be valid */ + diff = (tid_agg_rx->head_seq_num - ssn) & IEEE80211_SN_MASK; + if (diff >= tid_agg_rx->buf_size) { + tid_agg_rx->reorder_buf_filtered = 0; + goto release; + } + filtered = filtered >> diff; + ssn += diff; + + /* update bitmap */ + for (i = 0; i < tid_agg_rx->buf_size; i++) { + int index = (ssn + i) % tid_agg_rx->buf_size; + + tid_agg_rx->reorder_buf_filtered &= ~BIT_ULL(index); + if (filtered & BIT_ULL(i)) + tid_agg_rx->reorder_buf_filtered |= BIT_ULL(index); + } + + /* now process also frames that the filter marking released */ + ieee80211_sta_reorder_release(sta->sdata, tid_agg_rx, &frames); + +release: + spin_unlock_bh(&tid_agg_rx->reorder_lock); + + ieee80211_rx_handlers(&rx, &frames); + + out: + rcu_read_unlock(); +} +EXPORT_SYMBOL(ieee80211_mark_rx_ba_filtered_frames); + /* main receive path */ static bool ieee80211_accept_frame(struct ieee80211_rx_data *rx) diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index f4d38994ecee..053f5c4fa495 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -168,6 +168,8 @@ struct tid_ampdu_tx { * * @reorder_buf: buffer to reorder incoming aggregated MPDUs. An MPDU may be an * A-MSDU with individually reported subframes. + * @reorder_buf_filtered: bitmap indicating where there are filtered frames in + * the reorder buffer that should be ignored when releasing frames * @reorder_time: jiffies when skb was added * @session_timer: check if peer keeps Tx-ing on the TID (by timeout value) * @reorder_timer: releases expired frames from the reorder buffer. @@ -195,6 +197,7 @@ struct tid_ampdu_tx { struct tid_ampdu_rx { struct rcu_head rcu_head; spinlock_t reorder_lock; + u64 reorder_buf_filtered; struct sk_buff_head *reorder_buf; unsigned long *reorder_time; struct timer_list session_timer; -- cgit v1.2.3-71-gd317 From 34d505193bd10668acf1caba02d2f66bddc23fea Mon Sep 17 00:00:00 2001 From: Lior David Date: Thu, 28 Jan 2016 10:58:25 +0200 Subject: cfg80211: basic support for PBSS network type PBSS (Personal Basic Service Set) is a new BSS type for DMG networks. It is similar to infrastructure BSS, having an AP-like entity called PCP (PBSS Control Point), but it has few differences. PBSS support is mandatory for 11ad devices. Add support for PBSS by introducing a new PBSS flag attribute. The PBSS flag is used in the START_AP command to request starting a PCP instead of an AP, and in the CONNECT command to request connecting to a PCP instead of an AP. Signed-off-by: Lior David Signed-off-by: Johannes Berg --- drivers/net/wireless/ath/wil6210/cfg80211.c | 10 ++++++++++ include/net/cfg80211.h | 8 ++++++++ include/uapi/linux/nl80211.h | 6 ++++++ net/wireless/nl80211.c | 11 +++++++++++ net/wireless/sme.c | 9 ++++++--- 5 files changed, 41 insertions(+), 3 deletions(-) (limited to 'include/net') diff --git a/drivers/net/wireless/ath/wil6210/cfg80211.c b/drivers/net/wireless/ath/wil6210/cfg80211.c index 20d07ef679e8..1f231cd08138 100644 --- a/drivers/net/wireless/ath/wil6210/cfg80211.c +++ b/drivers/net/wireless/ath/wil6210/cfg80211.c @@ -422,6 +422,11 @@ static int wil_cfg80211_connect(struct wiphy *wiphy, if (sme->privacy && !rsn_eid) wil_info(wil, "WSC connection\n"); + if (sme->pbss) { + wil_err(wil, "connect - PBSS not yet supported\n"); + return -EOPNOTSUPP; + } + bss = cfg80211_get_bss(wiphy, sme->channel, sme->bssid, sme->ssid, sme->ssid_len, IEEE80211_BSS_TYPE_ESS, IEEE80211_PRIVACY_ANY); @@ -870,6 +875,11 @@ static int wil_cfg80211_start_ap(struct wiphy *wiphy, return -EINVAL; } + if (info->pbss) { + wil_err(wil, "AP: PBSS not yet supported\n"); + return -EOPNOTSUPP; + } + switch (info->hidden_ssid) { case NL80211_HIDDEN_SSID_NOT_IN_USE: hidden_ssid = WMI_HIDDEN_SSID_DISABLED; diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 9bcaaf7cd15a..9e1b24c29f0c 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -712,6 +712,8 @@ struct cfg80211_acl_data { * @p2p_opp_ps: P2P opportunistic PS * @acl: ACL configuration used by the drivers which has support for * MAC address based access control + * @pbss: If set, start as a PCP instead of AP. Relevant for DMG + * networks. */ struct cfg80211_ap_settings { struct cfg80211_chan_def chandef; @@ -730,6 +732,7 @@ struct cfg80211_ap_settings { u8 p2p_ctwindow; bool p2p_opp_ps; const struct cfg80211_acl_data *acl; + bool pbss; }; /** @@ -1888,6 +1891,8 @@ struct cfg80211_ibss_params { * @ht_capa_mask: The bits of ht_capa which are to be used. * @vht_capa: VHT Capability overrides * @vht_capa_mask: The bits of vht_capa which are to be used. + * @pbss: if set, connect to a PCP instead of AP. Valid for DMG + * networks. */ struct cfg80211_connect_params { struct ieee80211_channel *channel; @@ -1910,6 +1915,7 @@ struct cfg80211_connect_params { struct ieee80211_ht_cap ht_capa_mask; struct ieee80211_vht_cap vht_capa; struct ieee80211_vht_cap vht_capa_mask; + bool pbss; }; /** @@ -3489,6 +3495,7 @@ struct cfg80211_cached_keys; * registered for unexpected class 3 frames (AP mode) * @conn: (private) cfg80211 software SME connection state machine data * @connect_keys: (private) keys to set after connection is established + * @conn_bss_type: connecting/connected BSS type * @ibss_fixed: (private) IBSS is using fixed BSSID * @ibss_dfs_possible: (private) IBSS may change to a DFS channel * @event_list: (private) list for internal event processing @@ -3519,6 +3526,7 @@ struct wireless_dev { u8 ssid_len, mesh_id_len, mesh_id_up_len; struct cfg80211_conn *conn; struct cfg80211_cached_keys *connect_keys; + enum ieee80211_bss_type conn_bss_type; struct list_head event_list; spinlock_t event_lock; diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 5b7b5ebe7ca8..7758969a2a8e 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1789,6 +1789,10 @@ enum nl80211_commands { * thus it must not specify the number of iterations, only the interval * between scans. The scan plans are executed sequentially. * Each scan plan is a nested attribute of &enum nl80211_sched_scan_plan. + * @NL80211_ATTR_PBSS: flag attribute. If set it means operate + * in a PBSS. Specified in %NL80211_CMD_CONNECT to request + * connecting to a PCP, and in %NL80211_CMD_START_AP to start + * a PCP instead of AP. Relevant for DMG networks only. * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined @@ -2164,6 +2168,8 @@ enum nl80211_attrs { NL80211_ATTR_MAX_SCAN_PLAN_ITERATIONS, NL80211_ATTR_SCHED_SCAN_PLANS, + NL80211_ATTR_PBSS, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index d4786f2802aa..268cb493f6a5 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -401,6 +401,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_NETNS_FD] = { .type = NLA_U32 }, [NL80211_ATTR_SCHED_SCAN_DELAY] = { .type = NLA_U32 }, [NL80211_ATTR_REG_INDOOR] = { .type = NLA_FLAG }, + [NL80211_ATTR_PBSS] = { .type = NLA_FLAG }, }; /* policy for the key attributes */ @@ -3461,6 +3462,10 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) return PTR_ERR(params.acl); } + params.pbss = nla_get_flag(info->attrs[NL80211_ATTR_PBSS]); + if (params.pbss && !rdev->wiphy.bands[IEEE80211_BAND_60GHZ]) + return -EOPNOTSUPP; + wdev_lock(wdev); err = rdev_start_ap(rdev, dev, ¶ms); if (!err) { @@ -7980,6 +7985,12 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info) connect.flags |= ASSOC_REQ_USE_RRM; } + connect.pbss = nla_get_flag(info->attrs[NL80211_ATTR_PBSS]); + if (connect.pbss && !rdev->wiphy.bands[IEEE80211_BAND_60GHZ]) { + kzfree(connkeys); + return -EOPNOTSUPP; + } + wdev_lock(dev->ieee80211_ptr); err = cfg80211_connect(rdev, dev, &connect, connkeys, NULL); wdev_unlock(dev->ieee80211_ptr); diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 8020b5b094d4..79bd3a171caa 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -264,7 +264,7 @@ static struct cfg80211_bss *cfg80211_get_conn_bss(struct wireless_dev *wdev) wdev->conn->params.bssid, wdev->conn->params.ssid, wdev->conn->params.ssid_len, - IEEE80211_BSS_TYPE_ESS, + wdev->conn_bss_type, IEEE80211_PRIVACY(wdev->conn->params.privacy)); if (!bss) return NULL; @@ -687,7 +687,7 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid, WARN_ON_ONCE(!wiphy_to_rdev(wdev->wiphy)->ops->connect); bss = cfg80211_get_bss(wdev->wiphy, NULL, bssid, wdev->ssid, wdev->ssid_len, - IEEE80211_BSS_TYPE_ESS, + wdev->conn_bss_type, IEEE80211_PRIVACY_ANY); if (bss) cfg80211_hold_bss(bss_from_pub(bss)); @@ -846,7 +846,7 @@ void cfg80211_roamed(struct net_device *dev, bss = cfg80211_get_bss(wdev->wiphy, channel, bssid, wdev->ssid, wdev->ssid_len, - IEEE80211_BSS_TYPE_ESS, IEEE80211_PRIVACY_ANY); + wdev->conn_bss_type, IEEE80211_PRIVACY_ANY); if (WARN_ON(!bss)) return; @@ -1017,6 +1017,9 @@ int cfg80211_connect(struct cfg80211_registered_device *rdev, memcpy(wdev->ssid, connect->ssid, connect->ssid_len); wdev->ssid_len = connect->ssid_len; + wdev->conn_bss_type = connect->pbss ? IEEE80211_BSS_TYPE_PBSS : + IEEE80211_BSS_TYPE_ESS; + if (!rdev->ops->connect) err = cfg80211_sme_connect(wdev, connect, prev_bssid); else -- cgit v1.2.3-71-gd317 From f8079d43cf0f1f0171606e75fcef6fe17bb183f2 Mon Sep 17 00:00:00 2001 From: Eliad Peller Date: Sun, 14 Feb 2016 13:56:35 +0200 Subject: mac80211: move TKIP TX IVs to public part of key struct Some drivers/devices might want to set the IVs by themselves (and still let mac80211 generate MMIC). Specifically, this is needed when the device does offloading at certain times, and the driver has to make sure that the IVs of new tx frames (from the host) are synchronized with IVs that were potentially used during the offloading. Similarly to CCMP, move the TX IVs of TKIP keys to the public part of the key struct, and export a function to add the IV right into the crypto header. The public tx_pn field is defined as atomic64, so define TKIP_PN_TO_IV16/32 helper macros to convert it to iv16/32 when needed. Since the iv32 used for the p1k cache is taken directly from the frame, we can safely remove iv16/32 from being protected by tkip.txlock. Signed-off-by: Eliad Peller Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- include/net/mac80211.h | 23 ++++++++++++++++++++--- net/mac80211/cfg.c | 5 +++-- net/mac80211/debugfs_key.c | 5 +++-- net/mac80211/key.c | 9 +++++---- net/mac80211/key.h | 10 +++++++--- net/mac80211/tkip.c | 36 ++++++++++++++++++------------------ net/mac80211/tkip.h | 2 -- net/mac80211/wpa.c | 11 ++++------- 8 files changed, 60 insertions(+), 41 deletions(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 57147749ae42..15879b49baad 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1521,9 +1521,8 @@ enum ieee80211_key_flags { * wants to be given when a frame is transmitted and needs to be * encrypted in hardware. * @cipher: The key's cipher suite selector. - * @tx_pn: PN used for TX on non-TKIP keys, may be used by the driver - * as well if it needs to do software PN assignment by itself - * (e.g. due to TSO) + * @tx_pn: PN used for TX keys, may be used by the driver as well if it + * needs to do software PN assignment by itself (e.g. due to TSO) * @flags: key flags, see &enum ieee80211_key_flags. * @keyidx: the key index (0-3) * @keylen: key material length @@ -1549,6 +1548,9 @@ struct ieee80211_key_conf { #define IEEE80211_MAX_PN_LEN 16 +#define TKIP_PN_TO_IV16(pn) ((u16)(pn & 0xffff)) +#define TKIP_PN_TO_IV32(pn) ((u32)((pn >> 16) & 0xffffffff)) + /** * struct ieee80211_key_seq - key sequence counter * @@ -4446,6 +4448,21 @@ void ieee80211_get_tkip_rx_p1k(struct ieee80211_key_conf *keyconf, void ieee80211_get_tkip_p2k(struct ieee80211_key_conf *keyconf, struct sk_buff *skb, u8 *p2k); +/** + * ieee80211_tkip_add_iv - write TKIP IV and Ext. IV to pos + * + * @pos: start of crypto header + * @keyconf: the parameter passed with the set key + * @pn: PN to add + * + * Returns: pointer to the octet following IVs (i.e. beginning of + * the packet payload) + * + * This function writes the tkip IV value to pos (which should + * point to the crypto header) + */ +u8 *ieee80211_tkip_add_iv(u8 *pos, struct ieee80211_key_conf *keyconf, u64 pn); + /** * ieee80211_get_key_tx_seq - get key TX sequence counter * diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 66d22de93c8d..fe1704c4e8fb 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -339,8 +339,9 @@ static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev, switch (key->conf.cipher) { case WLAN_CIPHER_SUITE_TKIP: - iv32 = key->u.tkip.tx.iv32; - iv16 = key->u.tkip.tx.iv16; + pn64 = atomic64_read(&key->conf.tx_pn); + iv32 = TKIP_PN_TO_IV32(pn64); + iv16 = TKIP_PN_TO_IV16(pn64); if (key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE && !(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV)) { diff --git a/net/mac80211/debugfs_key.c b/net/mac80211/debugfs_key.c index 7961e7d0b61e..a2ef95f16f11 100644 --- a/net/mac80211/debugfs_key.c +++ b/net/mac80211/debugfs_key.c @@ -132,9 +132,10 @@ static ssize_t key_tx_spec_read(struct file *file, char __user *userbuf, len = scnprintf(buf, sizeof(buf), "\n"); break; case WLAN_CIPHER_SUITE_TKIP: + pn = atomic64_read(&key->conf.tx_pn); len = scnprintf(buf, sizeof(buf), "%08x %04x\n", - key->u.tkip.tx.iv32, - key->u.tkip.tx.iv16); + TKIP_PN_TO_IV32(pn), + TKIP_PN_TO_IV16(pn)); break; case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 5e5bc599da4c..f9c4cb9c6e06 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -945,8 +945,9 @@ void ieee80211_get_key_tx_seq(struct ieee80211_key_conf *keyconf, switch (key->conf.cipher) { case WLAN_CIPHER_SUITE_TKIP: - seq->tkip.iv32 = key->u.tkip.tx.iv32; - seq->tkip.iv16 = key->u.tkip.tx.iv16; + pn64 = atomic64_read(&key->conf.tx_pn); + seq->tkip.iv32 = TKIP_PN_TO_IV32(pn64); + seq->tkip.iv16 = TKIP_PN_TO_IV16(pn64); break; case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: @@ -1039,8 +1040,8 @@ void ieee80211_set_key_tx_seq(struct ieee80211_key_conf *keyconf, switch (key->conf.cipher) { case WLAN_CIPHER_SUITE_TKIP: - key->u.tkip.tx.iv32 = seq->tkip.iv32; - key->u.tkip.tx.iv16 = seq->tkip.iv16; + pn64 = (u64)seq->tkip.iv16 | ((u64)seq->tkip.iv32 << 16); + atomic64_set(&key->conf.tx_pn, pn64); break; case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: diff --git a/net/mac80211/key.h b/net/mac80211/key.h index 9951ef06323e..4aa20cef0859 100644 --- a/net/mac80211/key.h +++ b/net/mac80211/key.h @@ -44,13 +44,17 @@ enum ieee80211_internal_tkip_state { }; struct tkip_ctx { - u32 iv32; /* current iv32 */ - u16 iv16; /* current iv16 */ u16 p1k[5]; /* p1k cache */ u32 p1k_iv32; /* iv32 for which p1k computed */ enum ieee80211_internal_tkip_state state; }; +struct tkip_ctx_rx { + struct tkip_ctx ctx; + u32 iv32; /* current iv32 */ + u16 iv16; /* current iv16 */ +}; + struct ieee80211_key { struct ieee80211_local *local; struct ieee80211_sub_if_data *sdata; @@ -71,7 +75,7 @@ struct ieee80211_key { struct tkip_ctx tx; /* last received RSC */ - struct tkip_ctx rx[IEEE80211_NUM_TIDS]; + struct tkip_ctx_rx rx[IEEE80211_NUM_TIDS]; /* number of mic failures */ u32 mic_failures; diff --git a/net/mac80211/tkip.c b/net/mac80211/tkip.c index 0ae207771a58..b3622823bad2 100644 --- a/net/mac80211/tkip.c +++ b/net/mac80211/tkip.c @@ -1,6 +1,7 @@ /* * Copyright 2002-2004, Instant802 Networks, Inc. * Copyright 2005, Devicescape Software, Inc. + * Copyright (C) 2016 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -142,15 +143,14 @@ static void tkip_mixing_phase2(const u8 *tk, struct tkip_ctx *ctx, /* Add TKIP IV and Ext. IV at @pos. @iv0, @iv1, and @iv2 are the first octets * of the IV. Returns pointer to the octet following IVs (i.e., beginning of * the packet payload). */ -u8 *ieee80211_tkip_add_iv(u8 *pos, struct ieee80211_key *key) +u8 *ieee80211_tkip_add_iv(u8 *pos, struct ieee80211_key_conf *keyconf, u64 pn) { - lockdep_assert_held(&key->u.tkip.txlock); - - pos = write_tkip_iv(pos, key->u.tkip.tx.iv16); - *pos++ = (key->conf.keyidx << 6) | (1 << 5) /* Ext IV */; - put_unaligned_le32(key->u.tkip.tx.iv32, pos); + pos = write_tkip_iv(pos, TKIP_PN_TO_IV16(pn)); + *pos++ = (keyconf->keyidx << 6) | (1 << 5) /* Ext IV */; + put_unaligned_le32(TKIP_PN_TO_IV32(pn), pos); return pos + 4; } +EXPORT_SYMBOL_GPL(ieee80211_tkip_add_iv); static void ieee80211_compute_tkip_p1k(struct ieee80211_key *key, u32 iv32) { @@ -250,6 +250,7 @@ int ieee80211_tkip_decrypt_data(struct crypto_cipher *tfm, u8 rc4key[16], keyid, *pos = payload; int res; const u8 *tk = &key->conf.key[NL80211_TKIP_DATA_OFFSET_ENCR_KEY]; + struct tkip_ctx_rx *rx_ctx = &key->u.tkip.rx[queue]; if (payload_len < 12) return -1; @@ -265,37 +266,36 @@ int ieee80211_tkip_decrypt_data(struct crypto_cipher *tfm, if ((keyid >> 6) != key->conf.keyidx) return TKIP_DECRYPT_INVALID_KEYIDX; - if (key->u.tkip.rx[queue].state != TKIP_STATE_NOT_INIT && - (iv32 < key->u.tkip.rx[queue].iv32 || - (iv32 == key->u.tkip.rx[queue].iv32 && - iv16 <= key->u.tkip.rx[queue].iv16))) + if (rx_ctx->ctx.state != TKIP_STATE_NOT_INIT && + (iv32 < rx_ctx->iv32 || + (iv32 == rx_ctx->iv32 && iv16 <= rx_ctx->iv16))) return TKIP_DECRYPT_REPLAY; if (only_iv) { res = TKIP_DECRYPT_OK; - key->u.tkip.rx[queue].state = TKIP_STATE_PHASE1_HW_UPLOADED; + rx_ctx->ctx.state = TKIP_STATE_PHASE1_HW_UPLOADED; goto done; } - if (key->u.tkip.rx[queue].state == TKIP_STATE_NOT_INIT || - key->u.tkip.rx[queue].iv32 != iv32) { + if (rx_ctx->ctx.state == TKIP_STATE_NOT_INIT || + rx_ctx->iv32 != iv32) { /* IV16 wrapped around - perform TKIP phase 1 */ - tkip_mixing_phase1(tk, &key->u.tkip.rx[queue], ta, iv32); + tkip_mixing_phase1(tk, &rx_ctx->ctx, ta, iv32); } if (key->local->ops->update_tkip_key && key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE && - key->u.tkip.rx[queue].state != TKIP_STATE_PHASE1_HW_UPLOADED) { + rx_ctx->ctx.state != TKIP_STATE_PHASE1_HW_UPLOADED) { struct ieee80211_sub_if_data *sdata = key->sdata; if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) sdata = container_of(key->sdata->bss, struct ieee80211_sub_if_data, u.ap); drv_update_tkip_key(key->local, sdata, &key->conf, key->sta, - iv32, key->u.tkip.rx[queue].p1k); - key->u.tkip.rx[queue].state = TKIP_STATE_PHASE1_HW_UPLOADED; + iv32, rx_ctx->ctx.p1k); + rx_ctx->ctx.state = TKIP_STATE_PHASE1_HW_UPLOADED; } - tkip_mixing_phase2(tk, &key->u.tkip.rx[queue], iv16, rc4key); + tkip_mixing_phase2(tk, &rx_ctx->ctx, iv16, rc4key); res = ieee80211_wep_decrypt_data(tfm, rc4key, 16, pos, payload_len - 12); done: diff --git a/net/mac80211/tkip.h b/net/mac80211/tkip.h index e3ecb659b90a..a1bcbfbefe7c 100644 --- a/net/mac80211/tkip.h +++ b/net/mac80211/tkip.h @@ -13,8 +13,6 @@ #include #include "key.h" -u8 *ieee80211_tkip_add_iv(u8 *pos, struct ieee80211_key *key); - int ieee80211_tkip_encrypt_data(struct crypto_cipher *tfm, struct ieee80211_key *key, struct sk_buff *skb, diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index d824c38971ed..18848258adde 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -1,6 +1,7 @@ /* * Copyright 2002-2004, Instant802 Networks, Inc. * Copyright 2008, Jouni Malinen + * Copyright (C) 2016 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -183,7 +184,6 @@ mic_fail_no_key: return RX_DROP_UNUSABLE; } - static int tkip_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; @@ -191,6 +191,7 @@ static int tkip_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb) struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); unsigned int hdrlen; int len, tail; + u64 pn; u8 *pos; if (info->control.hw_key && @@ -222,12 +223,8 @@ static int tkip_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb) return 0; /* Increase IV for the frame */ - spin_lock(&key->u.tkip.txlock); - key->u.tkip.tx.iv16++; - if (key->u.tkip.tx.iv16 == 0) - key->u.tkip.tx.iv32++; - pos = ieee80211_tkip_add_iv(pos, key); - spin_unlock(&key->u.tkip.txlock); + pn = atomic64_inc_return(&key->conf.tx_pn); + pos = ieee80211_tkip_add_iv(pos, &key->conf, pn); /* hwaccel - with software IV */ if (info->control.hw_key) -- cgit v1.2.3-71-gd317 From ca48ebbc7ea7e82e3ae4b55aacead0cdb54ff008 Mon Sep 17 00:00:00 2001 From: Eliad Peller Date: Mon, 15 Feb 2016 12:34:10 +0200 Subject: mac80211: remove ieee80211_get_key_tx_seq/ieee80211_set_key_tx_seq Since the PNs of all the tx keys are now tracked in the public part of the key struct (with atomic counter), we no longer need these functions. dvm and vt665{5,6} are currently the only users of these functions, so update them accordingly. Signed-off-by: Eliad Peller Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/dvm/lib.c | 20 +++---- drivers/staging/vt6655/rxtx.c | 12 ++-- drivers/staging/vt6656/rxtx.c | 12 ++-- include/net/mac80211.h | 34 ----------- net/mac80211/key.c | 87 ---------------------------- 5 files changed, 24 insertions(+), 141 deletions(-) (limited to 'include/net') diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/lib.c b/drivers/net/wireless/intel/iwlwifi/dvm/lib.c index 4841be2aa499..1799469268ea 100644 --- a/drivers/net/wireless/intel/iwlwifi/dvm/lib.c +++ b/drivers/net/wireless/intel/iwlwifi/dvm/lib.c @@ -943,14 +943,16 @@ static void iwlagn_wowlan_program_keys(struct ieee80211_hw *hw, switch (key->cipher) { case WLAN_CIPHER_SUITE_TKIP: if (sta) { + u64 pn64; + tkip_sc = data->rsc_tsc->all_tsc_rsc.tkip.unicast_rsc; tkip_tx_sc = &data->rsc_tsc->all_tsc_rsc.tkip.tsc; rx_p1ks = data->tkip->rx_uni; - ieee80211_get_key_tx_seq(key, &seq); - tkip_tx_sc->iv16 = cpu_to_le16(seq.tkip.iv16); - tkip_tx_sc->iv32 = cpu_to_le32(seq.tkip.iv32); + pn64 = atomic64_read(&key->tx_pn); + tkip_tx_sc->iv16 = cpu_to_le16(TKIP_PN_TO_IV16(pn64)); + tkip_tx_sc->iv32 = cpu_to_le32(TKIP_PN_TO_IV32(pn64)); ieee80211_get_tkip_p1k_iv(key, seq.tkip.iv32, p1k); iwlagn_convert_p1k(p1k, data->tkip->tx.p1k); @@ -996,19 +998,13 @@ static void iwlagn_wowlan_program_keys(struct ieee80211_hw *hw, break; case WLAN_CIPHER_SUITE_CCMP: if (sta) { - u8 *pn = seq.ccmp.pn; + u64 pn64; aes_sc = data->rsc_tsc->all_tsc_rsc.aes.unicast_rsc; aes_tx_sc = &data->rsc_tsc->all_tsc_rsc.aes.tsc; - ieee80211_get_key_tx_seq(key, &seq); - aes_tx_sc->pn = cpu_to_le64( - (u64)pn[5] | - ((u64)pn[4] << 8) | - ((u64)pn[3] << 16) | - ((u64)pn[2] << 24) | - ((u64)pn[1] << 32) | - ((u64)pn[0] << 40)); + pn64 = atomic64_read(&key->tx_pn); + aes_tx_sc->pn = cpu_to_le64(pn64); } else aes_sc = data->rsc_tsc->all_tsc_rsc.aes.multicast_rsc; diff --git a/drivers/staging/vt6655/rxtx.c b/drivers/staging/vt6655/rxtx.c index b668db6a45fb..1a2dda09b69d 100644 --- a/drivers/staging/vt6655/rxtx.c +++ b/drivers/staging/vt6655/rxtx.c @@ -1210,7 +1210,7 @@ static void vnt_fill_txkey(struct ieee80211_hdr *hdr, u8 *key_buffer, struct sk_buff *skb, u16 payload_len, struct vnt_mic_hdr *mic_hdr) { - struct ieee80211_key_seq seq; + u64 pn64; u8 *iv = ((u8 *)hdr + ieee80211_get_hdrlen_from_skb(skb)); /* strip header and icv len from payload */ @@ -1243,9 +1243,13 @@ static void vnt_fill_txkey(struct ieee80211_hdr *hdr, u8 *key_buffer, mic_hdr->payload_len = cpu_to_be16(payload_len); ether_addr_copy(mic_hdr->mic_addr2, hdr->addr2); - ieee80211_get_key_tx_seq(tx_key, &seq); - - memcpy(mic_hdr->ccmp_pn, seq.ccmp.pn, IEEE80211_CCMP_PN_LEN); + pn64 = atomic64_read(&tx_key->tx_pn); + mic_hdr->ccmp_pn[5] = pn64; + mic_hdr->ccmp_pn[4] = pn64 >> 8; + mic_hdr->ccmp_pn[3] = pn64 >> 16; + mic_hdr->ccmp_pn[2] = pn64 >> 24; + mic_hdr->ccmp_pn[1] = pn64 >> 32; + mic_hdr->ccmp_pn[0] = pn64 >> 40; if (ieee80211_has_a4(hdr->frame_control)) mic_hdr->hlen = cpu_to_be16(28); diff --git a/drivers/staging/vt6656/rxtx.c b/drivers/staging/vt6656/rxtx.c index efb54f53b4f9..76378d225b46 100644 --- a/drivers/staging/vt6656/rxtx.c +++ b/drivers/staging/vt6656/rxtx.c @@ -719,7 +719,7 @@ static void vnt_fill_txkey(struct vnt_usb_send_context *tx_context, u16 payload_len, struct vnt_mic_hdr *mic_hdr) { struct ieee80211_hdr *hdr = tx_context->hdr; - struct ieee80211_key_seq seq; + u64 pn64; u8 *iv = ((u8 *)hdr + ieee80211_get_hdrlen_from_skb(skb)); /* strip header and icv len from payload */ @@ -752,9 +752,13 @@ static void vnt_fill_txkey(struct vnt_usb_send_context *tx_context, mic_hdr->payload_len = cpu_to_be16(payload_len); ether_addr_copy(mic_hdr->mic_addr2, hdr->addr2); - ieee80211_get_key_tx_seq(tx_key, &seq); - - memcpy(mic_hdr->ccmp_pn, seq.ccmp.pn, IEEE80211_CCMP_PN_LEN); + pn64 = atomic64_read(&tx_key->tx_pn); + mic_hdr->ccmp_pn[5] = pn64; + mic_hdr->ccmp_pn[4] = pn64 >> 8; + mic_hdr->ccmp_pn[3] = pn64 >> 16; + mic_hdr->ccmp_pn[2] = pn64 >> 24; + mic_hdr->ccmp_pn[1] = pn64 >> 32; + mic_hdr->ccmp_pn[0] = pn64 >> 40; if (ieee80211_has_a4(hdr->frame_control)) mic_hdr->hlen = cpu_to_be16(28); diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 15879b49baad..66155d3ad7e6 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -4463,23 +4463,6 @@ void ieee80211_get_tkip_p2k(struct ieee80211_key_conf *keyconf, */ u8 *ieee80211_tkip_add_iv(u8 *pos, struct ieee80211_key_conf *keyconf, u64 pn); -/** - * ieee80211_get_key_tx_seq - get key TX sequence counter - * - * @keyconf: the parameter passed with the set key - * @seq: buffer to receive the sequence data - * - * This function allows a driver to retrieve the current TX IV/PN - * for the given key. It must not be called if IV generation is - * offloaded to the device. - * - * Note that this function may only be called when no TX processing - * can be done concurrently, for example when queues are stopped - * and the stop has been synchronized. - */ -void ieee80211_get_key_tx_seq(struct ieee80211_key_conf *keyconf, - struct ieee80211_key_seq *seq); - /** * ieee80211_get_key_rx_seq - get key RX sequence counter * @@ -4499,23 +4482,6 @@ void ieee80211_get_key_tx_seq(struct ieee80211_key_conf *keyconf, void ieee80211_get_key_rx_seq(struct ieee80211_key_conf *keyconf, int tid, struct ieee80211_key_seq *seq); -/** - * ieee80211_set_key_tx_seq - set key TX sequence counter - * - * @keyconf: the parameter passed with the set key - * @seq: new sequence data - * - * This function allows a driver to set the current TX IV/PNs for the - * given key. This is useful when resuming from WoWLAN sleep and the - * device may have transmitted frames using the PTK, e.g. replies to - * ARP requests. - * - * Note that this function may only be called when no TX processing - * can be done concurrently. - */ -void ieee80211_set_key_tx_seq(struct ieee80211_key_conf *keyconf, - struct ieee80211_key_seq *seq); - /** * ieee80211_set_key_rx_seq - set key RX sequence counter * diff --git a/net/mac80211/key.c b/net/mac80211/key.c index f9c4cb9c6e06..3df7b0392d30 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -932,51 +932,6 @@ void ieee80211_gtk_rekey_notify(struct ieee80211_vif *vif, const u8 *bssid, } EXPORT_SYMBOL_GPL(ieee80211_gtk_rekey_notify); -void ieee80211_get_key_tx_seq(struct ieee80211_key_conf *keyconf, - struct ieee80211_key_seq *seq) -{ - struct ieee80211_key *key; - u64 pn64; - - if (WARN_ON(!(keyconf->flags & IEEE80211_KEY_FLAG_GENERATE_IV))) - return; - - key = container_of(keyconf, struct ieee80211_key, conf); - - switch (key->conf.cipher) { - case WLAN_CIPHER_SUITE_TKIP: - pn64 = atomic64_read(&key->conf.tx_pn); - seq->tkip.iv32 = TKIP_PN_TO_IV32(pn64); - seq->tkip.iv16 = TKIP_PN_TO_IV16(pn64); - break; - case WLAN_CIPHER_SUITE_CCMP: - case WLAN_CIPHER_SUITE_CCMP_256: - case WLAN_CIPHER_SUITE_AES_CMAC: - case WLAN_CIPHER_SUITE_BIP_CMAC_256: - BUILD_BUG_ON(offsetof(typeof(*seq), ccmp) != - offsetof(typeof(*seq), aes_cmac)); - case WLAN_CIPHER_SUITE_BIP_GMAC_128: - case WLAN_CIPHER_SUITE_BIP_GMAC_256: - BUILD_BUG_ON(offsetof(typeof(*seq), ccmp) != - offsetof(typeof(*seq), aes_gmac)); - case WLAN_CIPHER_SUITE_GCMP: - case WLAN_CIPHER_SUITE_GCMP_256: - BUILD_BUG_ON(offsetof(typeof(*seq), ccmp) != - offsetof(typeof(*seq), gcmp)); - pn64 = atomic64_read(&key->conf.tx_pn); - seq->ccmp.pn[5] = pn64; - seq->ccmp.pn[4] = pn64 >> 8; - seq->ccmp.pn[3] = pn64 >> 16; - seq->ccmp.pn[2] = pn64 >> 24; - seq->ccmp.pn[1] = pn64 >> 32; - seq->ccmp.pn[0] = pn64 >> 40; - break; - default: - WARN_ON(1); - } -} -EXPORT_SYMBOL(ieee80211_get_key_tx_seq); - void ieee80211_get_key_rx_seq(struct ieee80211_key_conf *keyconf, int tid, struct ieee80211_key_seq *seq) { @@ -1030,48 +985,6 @@ void ieee80211_get_key_rx_seq(struct ieee80211_key_conf *keyconf, } EXPORT_SYMBOL(ieee80211_get_key_rx_seq); -void ieee80211_set_key_tx_seq(struct ieee80211_key_conf *keyconf, - struct ieee80211_key_seq *seq) -{ - struct ieee80211_key *key; - u64 pn64; - - key = container_of(keyconf, struct ieee80211_key, conf); - - switch (key->conf.cipher) { - case WLAN_CIPHER_SUITE_TKIP: - pn64 = (u64)seq->tkip.iv16 | ((u64)seq->tkip.iv32 << 16); - atomic64_set(&key->conf.tx_pn, pn64); - break; - case WLAN_CIPHER_SUITE_CCMP: - case WLAN_CIPHER_SUITE_CCMP_256: - case WLAN_CIPHER_SUITE_AES_CMAC: - case WLAN_CIPHER_SUITE_BIP_CMAC_256: - BUILD_BUG_ON(offsetof(typeof(*seq), ccmp) != - offsetof(typeof(*seq), aes_cmac)); - case WLAN_CIPHER_SUITE_BIP_GMAC_128: - case WLAN_CIPHER_SUITE_BIP_GMAC_256: - BUILD_BUG_ON(offsetof(typeof(*seq), ccmp) != - offsetof(typeof(*seq), aes_gmac)); - case WLAN_CIPHER_SUITE_GCMP: - case WLAN_CIPHER_SUITE_GCMP_256: - BUILD_BUG_ON(offsetof(typeof(*seq), ccmp) != - offsetof(typeof(*seq), gcmp)); - pn64 = (u64)seq->ccmp.pn[5] | - ((u64)seq->ccmp.pn[4] << 8) | - ((u64)seq->ccmp.pn[3] << 16) | - ((u64)seq->ccmp.pn[2] << 24) | - ((u64)seq->ccmp.pn[1] << 32) | - ((u64)seq->ccmp.pn[0] << 40); - atomic64_set(&key->conf.tx_pn, pn64); - break; - default: - WARN_ON(1); - break; - } -} -EXPORT_SYMBOL_GPL(ieee80211_set_key_tx_seq); - void ieee80211_set_key_rx_seq(struct ieee80211_key_conf *keyconf, int tid, struct ieee80211_key_seq *seq) { -- cgit v1.2.3-71-gd317 From 65554d07adfc22bb9e14f6df8c609a646f869a74 Mon Sep 17 00:00:00 2001 From: Sara Sharon Date: Tue, 16 Feb 2016 12:48:17 +0200 Subject: mac80211: provide interface to driver to set VHT MU-MIMO data Provide an interface to the lower level driver to set the VHT MU-MIMO data. This is needed for example when there is an update of the group data during low power state, where the management frame will not be passed to the host at all. Signed-off-by: Sara Sharon Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- include/net/mac80211.h | 15 +++++++++++++++ net/mac80211/vht.c | 16 +++++++++++++++- 2 files changed, 30 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 66155d3ad7e6..23f2a5ecf669 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -5445,6 +5445,21 @@ ieee80211_vif_type_p2p(struct ieee80211_vif *vif) return ieee80211_iftype_p2p(vif->type, vif->p2p); } +/** + * ieee80211_update_mu_groups - set the VHT MU-MIMO groud data + * + * @vif: the specified virtual interface + * @membership: 64 bits array - a bit is set if station is member of the group + * @position: 2 bits per group id indicating the position in the group + * + * Note: This function assumes that the given vif is valid and the position and + * membership data is of the correct size and are in the same byte order as the + * matching GroupId management frame. + * Calls to this function need to be serialized with RX path. + */ +void ieee80211_update_mu_groups(struct ieee80211_vif *vif, + const u8 *membership, const u8 *position); + void ieee80211_enable_rssi_reports(struct ieee80211_vif *vif, int rssi_min_thold, int rssi_max_thold); diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index 341d192cea52..f8f161179b5d 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -2,7 +2,7 @@ * VHT handling * * Portions of this file - * Copyright(c) 2015 Intel Deutschland GmbH + * Copyright(c) 2015 - 2016 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -469,6 +469,20 @@ void ieee80211_process_mu_groups(struct ieee80211_sub_if_data *sdata, ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_MU_GROUPS); } +void ieee80211_update_mu_groups(struct ieee80211_vif *vif, + const u8 *membership, const u8 *position) +{ + struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + struct ieee80211_bss_conf *bss_conf = &sdata->vif.bss_conf; + + if (WARN_ON_ONCE(!(sdata->flags & IEEE80211_SDATA_MU_MIMO_OWNER))) + return; + + memcpy(bss_conf->mu_group.membership, membership, WLAN_MEMBERSHIP_LEN); + memcpy(bss_conf->mu_group.position, position, WLAN_USER_POSITION_LEN); +} +EXPORT_SYMBOL_GPL(ieee80211_update_mu_groups); + void ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, u8 opmode, enum ieee80211_band band) -- cgit v1.2.3-71-gd317 From b5a33d52595f0cb153f09bf45a5dcd66a7418dbb Mon Sep 17 00:00:00 2001 From: Sara Sharon Date: Tue, 16 Feb 2016 12:48:18 +0200 Subject: mac80211: move MU_MIMO_OWNER flag to ieee80211_vif Drivers may need to track which vif is using VHT MU-MIMO. Move the flag indicationg the ownership of MU_MIMO to ieee80211_vif. Signed-off-by: Sara Sharon Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- include/net/mac80211.h | 2 ++ net/mac80211/ieee80211_i.h | 2 -- net/mac80211/mlme.c | 11 ++++++----- net/mac80211/util.c | 2 +- net/mac80211/vht.c | 7 +++---- 5 files changed, 12 insertions(+), 12 deletions(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 23f2a5ecf669..0c09da34b67a 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1382,6 +1382,7 @@ enum ieee80211_vif_flags { * @csa_active: marks whether a channel switch is going on. Internally it is * write-protected by sdata_lock and local->mtx so holding either is fine * for read access. + * @mu_mimo_owner: indicates interface owns MU-MIMO capability * @driver_flags: flags/capabilities the driver has for this interface, * these need to be set (or cleared) when the interface is added * or, if supported by the driver, the interface type is changed @@ -1408,6 +1409,7 @@ struct ieee80211_vif { u8 addr[ETH_ALEN]; bool p2p; bool csa_active; + bool mu_mimo_owner; u8 cab_queue; u8 hw_queue[IEEE80211_NUM_ACS]; diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index a49c10361f1c..1630975c89f1 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -716,7 +716,6 @@ struct ieee80211_if_mesh { * back to wireless media and to the local net stack. * @IEEE80211_SDATA_DISCONNECT_RESUME: Disconnect after resume. * @IEEE80211_SDATA_IN_DRIVER: indicates interface was added to driver - * @IEEE80211_SDATA_MU_MIMO_OWNER: indicates interface owns MU-MIMO capability */ enum ieee80211_sub_if_data_flags { IEEE80211_SDATA_ALLMULTI = BIT(0), @@ -724,7 +723,6 @@ enum ieee80211_sub_if_data_flags { IEEE80211_SDATA_DONT_BRIDGE_PACKETS = BIT(3), IEEE80211_SDATA_DISCONNECT_RESUME = BIT(4), IEEE80211_SDATA_IN_DRIVER = BIT(5), - IEEE80211_SDATA_MU_MIMO_OWNER = BIT(6), }; /** diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 857089de475f..f41625bcd879 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -6,7 +6,7 @@ * Copyright 2006-2007 Jiri Benc * Copyright 2007, Michael Wu * Copyright 2013-2014 Intel Mobile Communications GmbH - * Copyright (C) 2015 Intel Deutschland GmbH + * Copyright (C) 2015 - 2016 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -559,7 +559,7 @@ static void ieee80211_add_vht_ie(struct ieee80211_sub_if_data *sdata, struct ieee80211_sub_if_data *other; list_for_each_entry_rcu(other, &local->interfaces, list) { - if (other->flags & IEEE80211_SDATA_MU_MIMO_OWNER) { + if (other->vif.mu_mimo_owner) { disable_mu_mimo = true; break; } @@ -567,7 +567,7 @@ static void ieee80211_add_vht_ie(struct ieee80211_sub_if_data *sdata, if (disable_mu_mimo) cap &= ~IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE; else - sdata->flags |= IEEE80211_SDATA_MU_MIMO_OWNER; + sdata->vif.mu_mimo_owner = true; } mask = IEEE80211_VHT_CAP_BEAMFORMEE_STS_MASK; @@ -2052,7 +2052,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, memset(sdata->vif.bss_conf.mu_group.position, 0, sizeof(sdata->vif.bss_conf.mu_group.position)); changed |= BSS_CHANGED_MU_GROUPS; - sdata->flags &= ~IEEE80211_SDATA_MU_MIMO_OWNER; + sdata->vif.mu_mimo_owner = false; sdata->ap_power_level = IEEE80211_UNSET_POWER_LEVEL; @@ -2509,7 +2509,8 @@ static void ieee80211_destroy_assoc_data(struct ieee80211_sub_if_data *sdata, eth_zero_addr(sdata->u.mgd.bssid); ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BSSID); sdata->u.mgd.flags = 0; - sdata->flags &= ~IEEE80211_SDATA_MU_MIMO_OWNER; + sdata->vif.mu_mimo_owner = false; + mutex_lock(&sdata->local->mtx); ieee80211_vif_release_channel(sdata); mutex_unlock(&sdata->local->mtx); diff --git a/net/mac80211/util.c b/net/mac80211/util.c index f1e5b76eda70..89f71799df84 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1928,7 +1928,7 @@ int ieee80211_reconfig(struct ieee80211_local *local) BSS_CHANGED_IDLE | BSS_CHANGED_TXPOWER; - if (sdata->flags & IEEE80211_SDATA_MU_MIMO_OWNER) + if (sdata->vif.mu_mimo_owner) changed |= BSS_CHANGED_MU_GROUPS; switch (sdata->vif.type) { diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index f8f161179b5d..89e04d55aa18 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -450,7 +450,7 @@ void ieee80211_process_mu_groups(struct ieee80211_sub_if_data *sdata, { struct ieee80211_bss_conf *bss_conf = &sdata->vif.bss_conf; - if (!(sdata->flags & IEEE80211_SDATA_MU_MIMO_OWNER)) + if (!sdata->vif.mu_mimo_owner) return; if (!memcmp(mgmt->u.action.u.vht_group_notif.position, @@ -472,10 +472,9 @@ void ieee80211_process_mu_groups(struct ieee80211_sub_if_data *sdata, void ieee80211_update_mu_groups(struct ieee80211_vif *vif, const u8 *membership, const u8 *position) { - struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); - struct ieee80211_bss_conf *bss_conf = &sdata->vif.bss_conf; + struct ieee80211_bss_conf *bss_conf = &vif->bss_conf; - if (WARN_ON_ONCE(!(sdata->flags & IEEE80211_SDATA_MU_MIMO_OWNER))) + if (WARN_ON_ONCE(!vif->mu_mimo_owner)) return; memcpy(bss_conf->mu_group.membership, membership, WLAN_MEMBERSHIP_LEN); -- cgit v1.2.3-71-gd317 From 1d4150c02c5709fdfd80f10368a31867de35e72e Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Mon, 22 Feb 2016 15:57:52 -0800 Subject: net_sched: prepare tcf_hashinfo_destroy() for netns support We only release the memory of the hashtable itself, not its entries inside. This is not a problem yet since we only call it in module release path, and module is refcount'ed by actions. This would be a problem after we move the per module hinfo into per netns in the latter patch. Cc: Jamal Hadi Salim Signed-off-by: Cong Wang Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/act_api.h | 5 ----- net/sched/act_api.c | 32 +++++++++++++++++++++++++++++--- 2 files changed, 29 insertions(+), 8 deletions(-) (limited to 'include/net') diff --git a/include/net/act_api.h b/include/net/act_api.h index 9d446f136607..8c4e3ff723fb 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -65,11 +65,6 @@ static inline int tcf_hashinfo_init(struct tcf_hashinfo *hf, unsigned int mask) return 0; } -static inline void tcf_hashinfo_destroy(struct tcf_hashinfo *hf) -{ - kfree(hf->htab); -} - /* Update lastuse only if needed, to avoid dirtying a cache line. * We use a temp variable to avoid fetching jiffies twice. */ diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 06e7c4a37245..acafaf7434fc 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -69,7 +69,7 @@ int __tcf_hash_release(struct tc_action *a, bool bind, bool strict) if (a->ops->cleanup) a->ops->cleanup(a, bind); tcf_hash_destroy(a); - ret = 1; + ret = ACT_P_DELETED; } } @@ -302,6 +302,32 @@ void tcf_hash_insert(struct tc_action *a) } EXPORT_SYMBOL(tcf_hash_insert); +static void tcf_hashinfo_destroy(const struct tc_action_ops *ops) +{ + struct tcf_hashinfo *hinfo = ops->hinfo; + struct tc_action a = { + .ops = ops, + }; + int i; + + for (i = 0; i < hinfo->hmask + 1; i++) { + struct tcf_common *p; + struct hlist_node *n; + + hlist_for_each_entry_safe(p, n, &hinfo->htab[i], tcfc_head) { + int ret; + + a.priv = p; + ret = __tcf_hash_release(&a, false, true); + if (ret == ACT_P_DELETED) + module_put(ops->owner); + else if (ret < 0) + return; + } + } + kfree(hinfo->htab); +} + static LIST_HEAD(act_base); static DEFINE_RWLOCK(act_mod_lock); @@ -333,7 +359,7 @@ int tcf_register_action(struct tc_action_ops *act, unsigned int mask) list_for_each_entry(a, &act_base, head) { if (act->type == a->type || (strcmp(act->kind, a->kind) == 0)) { write_unlock(&act_mod_lock); - tcf_hashinfo_destroy(act->hinfo); + tcf_hashinfo_destroy(act); kfree(act->hinfo); return -EEXIST; } @@ -353,7 +379,7 @@ int tcf_unregister_action(struct tc_action_ops *act) list_for_each_entry(a, &act_base, head) { if (a == act) { list_del(&act->head); - tcf_hashinfo_destroy(act->hinfo); + tcf_hashinfo_destroy(act); kfree(act->hinfo); err = 0; break; -- cgit v1.2.3-71-gd317 From ddf97ccdd7cb7e00daba465a5c947b8d941dc2a4 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Mon, 22 Feb 2016 15:57:53 -0800 Subject: net_sched: add network namespace support for tc actions Currently tc actions are stored in a per-module hashtable, therefore are visible to all network namespaces. This is probably the last part of the tc subsystem which is not aware of netns now. This patch makes them per-netns, several tc action API's need to be adjusted for this. The tc action API code is ugly due to historical reasons, we need to refactor that code in the future. Cc: Jamal Hadi Salim Signed-off-by: Cong Wang Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/act_api.h | 58 ++++++++++++++++++---- net/sched/act_api.c | 113 +++++++++++++++++++++-------------------- net/sched/act_bpf.c | 52 +++++++++++++++++-- net/sched/act_connmark.c | 54 +++++++++++++++++--- net/sched/act_csum.c | 59 +++++++++++++++++++--- net/sched/act_gact.c | 55 +++++++++++++++++--- net/sched/act_ipt.c | 127 ++++++++++++++++++++++++++++++++++++++++++----- net/sched/act_mirred.c | 54 +++++++++++++++++--- net/sched/act_nat.c | 54 +++++++++++++++++--- net/sched/act_pedit.c | 54 +++++++++++++++++--- net/sched/act_police.c | 52 +++++++++++++++---- net/sched/act_simple.c | 55 +++++++++++++++++--- net/sched/act_skbedit.c | 54 +++++++++++++++++--- net/sched/act_vlan.c | 54 +++++++++++++++++--- 14 files changed, 746 insertions(+), 149 deletions(-) (limited to 'include/net') diff --git a/include/net/act_api.h b/include/net/act_api.h index 8c4e3ff723fb..342be6c5ab5c 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -7,6 +7,8 @@ #include #include +#include +#include struct tcf_common { struct hlist_node tcfc_head; @@ -87,31 +89,65 @@ struct tc_action { __u32 type; /* for backward compat(TCA_OLD_COMPAT) */ __u32 order; struct list_head list; + struct tcf_hashinfo *hinfo; }; struct tc_action_ops { struct list_head head; - struct tcf_hashinfo *hinfo; char kind[IFNAMSIZ]; __u32 type; /* TBD to match kind */ struct module *owner; int (*act)(struct sk_buff *, const struct tc_action *, struct tcf_result *); int (*dump)(struct sk_buff *, struct tc_action *, int, int); void (*cleanup)(struct tc_action *, int bind); - int (*lookup)(struct tc_action *, u32); + int (*lookup)(struct net *, struct tc_action *, u32); int (*init)(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action *act, int ovr, int bind); - int (*walk)(struct sk_buff *, struct netlink_callback *, int, struct tc_action *); + int (*walk)(struct net *, struct sk_buff *, + struct netlink_callback *, int, struct tc_action *); +}; + +struct tc_action_net { + struct tcf_hashinfo *hinfo; + const struct tc_action_ops *ops; }; -int tcf_hash_search(struct tc_action *a, u32 index); -u32 tcf_hash_new_index(struct tcf_hashinfo *hinfo); -int tcf_hash_check(u32 index, struct tc_action *a, int bind); -int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a, - int size, int bind, bool cpustats); +static inline +int tc_action_net_init(struct tc_action_net *tn, const struct tc_action_ops *ops, + unsigned int mask) +{ + int err = 0; + + tn->hinfo = kmalloc(sizeof(*tn->hinfo), GFP_KERNEL); + if (!tn->hinfo) + return -ENOMEM; + tn->ops = ops; + err = tcf_hashinfo_init(tn->hinfo, mask); + if (err) + kfree(tn->hinfo); + return err; +} + +void tcf_hashinfo_destroy(const struct tc_action_ops *ops, + struct tcf_hashinfo *hinfo); + +static inline void tc_action_net_exit(struct tc_action_net *tn) +{ + tcf_hashinfo_destroy(tn->ops, tn->hinfo); +} + +int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb, + struct netlink_callback *cb, int type, + struct tc_action *a); +int tcf_hash_search(struct tc_action_net *tn, struct tc_action *a, u32 index); +u32 tcf_hash_new_index(struct tc_action_net *tn); +int tcf_hash_check(struct tc_action_net *tn, u32 index, struct tc_action *a, + int bind); +int tcf_hash_create(struct tc_action_net *tn, u32 index, struct nlattr *est, + struct tc_action *a, int size, int bind, bool cpustats); void tcf_hash_cleanup(struct tc_action *a, struct nlattr *est); -void tcf_hash_insert(struct tc_action *a); +void tcf_hash_insert(struct tc_action_net *tn, struct tc_action *a); int __tcf_hash_release(struct tc_action *a, bool bind, bool strict); @@ -120,8 +156,8 @@ static inline int tcf_hash_release(struct tc_action *a, bool bind) return __tcf_hash_release(a, bind, false); } -int tcf_register_action(struct tc_action_ops *a, unsigned int mask); -int tcf_unregister_action(struct tc_action_ops *a); +int tcf_register_action(struct tc_action_ops *a, struct pernet_operations *ops); +int tcf_unregister_action(struct tc_action_ops *a, struct pernet_operations *ops); int tcf_action_destroy(struct list_head *actions, int bind); int tcf_action_exec(struct sk_buff *skb, const struct list_head *actions, struct tcf_result *res); diff --git a/net/sched/act_api.c b/net/sched/act_api.c index acafaf7434fc..96066665e376 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -36,10 +36,9 @@ static void free_tcf(struct rcu_head *head) kfree(p); } -static void tcf_hash_destroy(struct tc_action *a) +static void tcf_hash_destroy(struct tcf_hashinfo *hinfo, struct tc_action *a) { struct tcf_common *p = a->priv; - struct tcf_hashinfo *hinfo = a->ops->hinfo; spin_lock_bh(&hinfo->lock); hlist_del(&p->tcfc_head); @@ -68,7 +67,7 @@ int __tcf_hash_release(struct tc_action *a, bool bind, bool strict) if (p->tcfc_bindcnt <= 0 && p->tcfc_refcnt <= 0) { if (a->ops->cleanup) a->ops->cleanup(a, bind); - tcf_hash_destroy(a); + tcf_hash_destroy(a->hinfo, a); ret = ACT_P_DELETED; } } @@ -77,10 +76,9 @@ int __tcf_hash_release(struct tc_action *a, bool bind, bool strict) } EXPORT_SYMBOL(__tcf_hash_release); -static int tcf_dump_walker(struct sk_buff *skb, struct netlink_callback *cb, - struct tc_action *a) +static int tcf_dump_walker(struct tcf_hashinfo *hinfo, struct sk_buff *skb, + struct netlink_callback *cb, struct tc_action *a) { - struct tcf_hashinfo *hinfo = a->ops->hinfo; struct hlist_head *head; struct tcf_common *p; int err = 0, index = -1, i = 0, s_i = 0, n_i = 0; @@ -126,9 +124,9 @@ nla_put_failure: goto done; } -static int tcf_del_walker(struct sk_buff *skb, struct tc_action *a) +static int tcf_del_walker(struct tcf_hashinfo *hinfo, struct sk_buff *skb, + struct tc_action *a) { - struct tcf_hashinfo *hinfo = a->ops->hinfo; struct hlist_head *head; struct hlist_node *n; struct tcf_common *p; @@ -163,18 +161,24 @@ nla_put_failure: return ret; } -static int tcf_generic_walker(struct sk_buff *skb, struct netlink_callback *cb, - int type, struct tc_action *a) +int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb, + struct netlink_callback *cb, int type, + struct tc_action *a) { + struct tcf_hashinfo *hinfo = tn->hinfo; + + a->hinfo = hinfo; + if (type == RTM_DELACTION) { - return tcf_del_walker(skb, a); + return tcf_del_walker(hinfo, skb, a); } else if (type == RTM_GETACTION) { - return tcf_dump_walker(skb, cb, a); + return tcf_dump_walker(hinfo, skb, cb, a); } else { WARN(1, "tcf_generic_walker: unknown action %d\n", type); return -EINVAL; } } +EXPORT_SYMBOL(tcf_generic_walker); static struct tcf_common *tcf_hash_lookup(u32 index, struct tcf_hashinfo *hinfo) { @@ -191,8 +195,9 @@ static struct tcf_common *tcf_hash_lookup(u32 index, struct tcf_hashinfo *hinfo) return p; } -u32 tcf_hash_new_index(struct tcf_hashinfo *hinfo) +u32 tcf_hash_new_index(struct tc_action_net *tn) { + struct tcf_hashinfo *hinfo = tn->hinfo; u32 val = hinfo->index; do { @@ -205,28 +210,31 @@ u32 tcf_hash_new_index(struct tcf_hashinfo *hinfo) } EXPORT_SYMBOL(tcf_hash_new_index); -int tcf_hash_search(struct tc_action *a, u32 index) +int tcf_hash_search(struct tc_action_net *tn, struct tc_action *a, u32 index) { - struct tcf_hashinfo *hinfo = a->ops->hinfo; + struct tcf_hashinfo *hinfo = tn->hinfo; struct tcf_common *p = tcf_hash_lookup(index, hinfo); if (p) { a->priv = p; + a->hinfo = hinfo; return 1; } return 0; } EXPORT_SYMBOL(tcf_hash_search); -int tcf_hash_check(u32 index, struct tc_action *a, int bind) +int tcf_hash_check(struct tc_action_net *tn, u32 index, struct tc_action *a, + int bind) { - struct tcf_hashinfo *hinfo = a->ops->hinfo; + struct tcf_hashinfo *hinfo = tn->hinfo; struct tcf_common *p = NULL; if (index && (p = tcf_hash_lookup(index, hinfo)) != NULL) { if (bind) p->tcfc_bindcnt++; p->tcfc_refcnt++; a->priv = p; + a->hinfo = hinfo; return 1; } return 0; @@ -243,11 +251,11 @@ void tcf_hash_cleanup(struct tc_action *a, struct nlattr *est) } EXPORT_SYMBOL(tcf_hash_cleanup); -int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a, - int size, int bind, bool cpustats) +int tcf_hash_create(struct tc_action_net *tn, u32 index, struct nlattr *est, + struct tc_action *a, int size, int bind, bool cpustats) { - struct tcf_hashinfo *hinfo = a->ops->hinfo; struct tcf_common *p = kzalloc(size, GFP_KERNEL); + struct tcf_hashinfo *hinfo = tn->hinfo; int err = -ENOMEM; if (unlikely(!p)) @@ -272,7 +280,7 @@ err2: } spin_lock_init(&p->tcfc_lock); INIT_HLIST_NODE(&p->tcfc_head); - p->tcfc_index = index ? index : tcf_hash_new_index(hinfo); + p->tcfc_index = index ? index : tcf_hash_new_index(tn); p->tcfc_tm.install = jiffies; p->tcfc_tm.lastuse = jiffies; if (est) { @@ -286,14 +294,15 @@ err2: } a->priv = (void *) p; + a->hinfo = hinfo; return 0; } EXPORT_SYMBOL(tcf_hash_create); -void tcf_hash_insert(struct tc_action *a) +void tcf_hash_insert(struct tc_action_net *tn, struct tc_action *a) { struct tcf_common *p = a->priv; - struct tcf_hashinfo *hinfo = a->ops->hinfo; + struct tcf_hashinfo *hinfo = tn->hinfo; unsigned int h = tcf_hash(p->tcfc_index, hinfo->hmask); spin_lock_bh(&hinfo->lock); @@ -302,11 +311,12 @@ void tcf_hash_insert(struct tc_action *a) } EXPORT_SYMBOL(tcf_hash_insert); -static void tcf_hashinfo_destroy(const struct tc_action_ops *ops) +void tcf_hashinfo_destroy(const struct tc_action_ops *ops, + struct tcf_hashinfo *hinfo) { - struct tcf_hashinfo *hinfo = ops->hinfo; struct tc_action a = { .ops = ops, + .hinfo = hinfo, }; int i; @@ -327,60 +337,52 @@ static void tcf_hashinfo_destroy(const struct tc_action_ops *ops) } kfree(hinfo->htab); } +EXPORT_SYMBOL(tcf_hashinfo_destroy); static LIST_HEAD(act_base); static DEFINE_RWLOCK(act_mod_lock); -int tcf_register_action(struct tc_action_ops *act, unsigned int mask) +int tcf_register_action(struct tc_action_ops *act, + struct pernet_operations *ops) { struct tc_action_ops *a; - int err; + int ret; - /* Must supply act, dump and init */ - if (!act->act || !act->dump || !act->init) + if (!act->act || !act->dump || !act->init || !act->walk || !act->lookup) return -EINVAL; - /* Supply defaults */ - if (!act->lookup) - act->lookup = tcf_hash_search; - if (!act->walk) - act->walk = tcf_generic_walker; - - act->hinfo = kmalloc(sizeof(struct tcf_hashinfo), GFP_KERNEL); - if (!act->hinfo) - return -ENOMEM; - err = tcf_hashinfo_init(act->hinfo, mask); - if (err) { - kfree(act->hinfo); - return err; - } - write_lock(&act_mod_lock); list_for_each_entry(a, &act_base, head) { if (act->type == a->type || (strcmp(act->kind, a->kind) == 0)) { write_unlock(&act_mod_lock); - tcf_hashinfo_destroy(act); - kfree(act->hinfo); return -EEXIST; } } list_add_tail(&act->head, &act_base); write_unlock(&act_mod_lock); + + ret = register_pernet_subsys(ops); + if (ret) { + tcf_unregister_action(act, ops); + return ret; + } + return 0; } EXPORT_SYMBOL(tcf_register_action); -int tcf_unregister_action(struct tc_action_ops *act) +int tcf_unregister_action(struct tc_action_ops *act, + struct pernet_operations *ops) { struct tc_action_ops *a; int err = -ENOENT; + unregister_pernet_subsys(ops); + write_lock(&act_mod_lock); list_for_each_entry(a, &act_base, head) { if (a == act) { list_del(&act->head); - tcf_hashinfo_destroy(act); - kfree(act->hinfo); err = 0; break; } @@ -747,8 +749,8 @@ static struct tc_action *create_a(int i) return act; } -static struct tc_action * -tcf_action_get_1(struct nlattr *nla, struct nlmsghdr *n, u32 portid) +static struct tc_action *tcf_action_get_1(struct net *net, struct nlattr *nla, + struct nlmsghdr *n, u32 portid) { struct nlattr *tb[TCA_ACT_MAX + 1]; struct tc_action *a; @@ -775,7 +777,7 @@ tcf_action_get_1(struct nlattr *nla, struct nlmsghdr *n, u32 portid) if (a->ops == NULL) /* could happen in batch of actions */ goto err_free; err = -ENOENT; - if (a->ops->lookup(a, index) == 0) + if (a->ops->lookup(net, a, index) == 0) goto err_mod; module_put(a->ops->owner); @@ -845,7 +847,7 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, if (nest == NULL) goto out_module_put; - err = a.ops->walk(skb, &dcb, RTM_DELACTION, &a); + err = a.ops->walk(net, skb, &dcb, RTM_DELACTION, &a); if (err < 0) goto out_module_put; if (err == 0) @@ -923,7 +925,7 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, } for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) { - act = tcf_action_get_1(tb[i], n, portid); + act = tcf_action_get_1(net, tb[i], n, portid); if (IS_ERR(act)) { ret = PTR_ERR(act); goto err; @@ -1070,6 +1072,7 @@ find_dump_kind(const struct nlmsghdr *n) static int tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb) { + struct net *net = sock_net(skb->sk); struct nlmsghdr *nlh; unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; @@ -1104,7 +1107,7 @@ tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb) if (nest == NULL) goto out_module_put; - ret = a_o->walk(skb, cb, RTM_GETACTION, &a); + ret = a_o->walk(net, skb, cb, RTM_GETACTION, &a); if (ret < 0) goto out_module_put; diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 0bc6f912f870..8c9f1f0459ab 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -33,6 +33,8 @@ struct tcf_bpf_cfg { bool is_ebpf; }; +static int bpf_net_id; + static int tcf_bpf(struct sk_buff *skb, const struct tc_action *act, struct tcf_result *res) { @@ -275,6 +277,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action *act, int replace, int bind) { + struct tc_action_net *tn = net_generic(net, bpf_net_id); struct nlattr *tb[TCA_ACT_BPF_MAX + 1]; struct tcf_bpf_cfg cfg, old; struct tc_act_bpf *parm; @@ -294,8 +297,8 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, parm = nla_data(tb[TCA_ACT_BPF_PARMS]); - if (!tcf_hash_check(parm->index, act, bind)) { - ret = tcf_hash_create(parm->index, est, act, + if (!tcf_hash_check(tn, parm->index, act, bind)) { + ret = tcf_hash_create(tn, parm->index, est, act, sizeof(*prog), bind, true); if (ret < 0) return ret; @@ -344,7 +347,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, rcu_assign_pointer(prog->filter, cfg.filter); if (res == ACT_P_CREATED) { - tcf_hash_insert(act); + tcf_hash_insert(tn, act); } else { /* make sure the program being replaced is no longer executing */ synchronize_rcu(); @@ -367,6 +370,22 @@ static void tcf_bpf_cleanup(struct tc_action *act, int bind) tcf_bpf_cfg_cleanup(&tmp); } +static int tcf_bpf_walker(struct net *net, struct sk_buff *skb, + struct netlink_callback *cb, int type, + struct tc_action *a) +{ + struct tc_action_net *tn = net_generic(net, bpf_net_id); + + return tcf_generic_walker(tn, skb, cb, type, a); +} + +static int tcf_bpf_search(struct net *net, struct tc_action *a, u32 index) +{ + struct tc_action_net *tn = net_generic(net, bpf_net_id); + + return tcf_hash_search(tn, a, index); +} + static struct tc_action_ops act_bpf_ops __read_mostly = { .kind = "bpf", .type = TCA_ACT_BPF, @@ -375,16 +394,39 @@ static struct tc_action_ops act_bpf_ops __read_mostly = { .dump = tcf_bpf_dump, .cleanup = tcf_bpf_cleanup, .init = tcf_bpf_init, + .walk = tcf_bpf_walker, + .lookup = tcf_bpf_search, +}; + +static __net_init int bpf_init_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, bpf_net_id); + + return tc_action_net_init(tn, &act_bpf_ops, BPF_TAB_MASK); +} + +static void __net_exit bpf_exit_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, bpf_net_id); + + tc_action_net_exit(tn); +} + +static struct pernet_operations bpf_net_ops = { + .init = bpf_init_net, + .exit = bpf_exit_net, + .id = &bpf_net_id, + .size = sizeof(struct tc_action_net), }; static int __init bpf_init_module(void) { - return tcf_register_action(&act_bpf_ops, BPF_TAB_MASK); + return tcf_register_action(&act_bpf_ops, &bpf_net_ops); } static void __exit bpf_cleanup_module(void) { - tcf_unregister_action(&act_bpf_ops); + tcf_unregister_action(&act_bpf_ops, &bpf_net_ops); } module_init(bpf_init_module); diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index bb41699c6c49..c0ed93ce2391 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -30,6 +30,8 @@ #define CONNMARK_TAB_MASK 3 +static int connmark_net_id; + static int tcf_connmark(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { @@ -97,6 +99,7 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action *a, int ovr, int bind) { + struct tc_action_net *tn = net_generic(net, connmark_net_id); struct nlattr *tb[TCA_CONNMARK_MAX + 1]; struct tcf_connmark_info *ci; struct tc_connmark *parm; @@ -111,9 +114,9 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla, parm = nla_data(tb[TCA_CONNMARK_PARMS]); - if (!tcf_hash_check(parm->index, a, bind)) { - ret = tcf_hash_create(parm->index, est, a, sizeof(*ci), - bind, false); + if (!tcf_hash_check(tn, parm->index, a, bind)) { + ret = tcf_hash_create(tn, parm->index, est, a, + sizeof(*ci), bind, false); if (ret) return ret; @@ -122,7 +125,7 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla, ci->net = net; ci->zone = parm->zone; - tcf_hash_insert(a); + tcf_hash_insert(tn, a); ret = ACT_P_CREATED; } else { ci = to_connmark(a); @@ -169,6 +172,22 @@ nla_put_failure: return -1; } +static int tcf_connmark_walker(struct net *net, struct sk_buff *skb, + struct netlink_callback *cb, int type, + struct tc_action *a) +{ + struct tc_action_net *tn = net_generic(net, connmark_net_id); + + return tcf_generic_walker(tn, skb, cb, type, a); +} + +static int tcf_connmark_search(struct net *net, struct tc_action *a, u32 index) +{ + struct tc_action_net *tn = net_generic(net, connmark_net_id); + + return tcf_hash_search(tn, a, index); +} + static struct tc_action_ops act_connmark_ops = { .kind = "connmark", .type = TCA_ACT_CONNMARK, @@ -176,16 +195,39 @@ static struct tc_action_ops act_connmark_ops = { .act = tcf_connmark, .dump = tcf_connmark_dump, .init = tcf_connmark_init, + .walk = tcf_connmark_walker, + .lookup = tcf_connmark_search, +}; + +static __net_init int connmark_init_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, connmark_net_id); + + return tc_action_net_init(tn, &act_connmark_ops, CONNMARK_TAB_MASK); +} + +static void __net_exit connmark_exit_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, connmark_net_id); + + tc_action_net_exit(tn); +} + +static struct pernet_operations connmark_net_ops = { + .init = connmark_init_net, + .exit = connmark_exit_net, + .id = &connmark_net_id, + .size = sizeof(struct tc_action_net), }; static int __init connmark_init_module(void) { - return tcf_register_action(&act_connmark_ops, CONNMARK_TAB_MASK); + return tcf_register_action(&act_connmark_ops, &connmark_net_ops); } static void __exit connmark_cleanup_module(void) { - tcf_unregister_action(&act_connmark_ops); + tcf_unregister_action(&act_connmark_ops, &connmark_net_ops); } module_init(connmark_init_module); diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index eeb3eb3ea9eb..d22426cdebc0 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -42,9 +42,13 @@ static const struct nla_policy csum_policy[TCA_CSUM_MAX + 1] = { [TCA_CSUM_PARMS] = { .len = sizeof(struct tc_csum), }, }; -static int tcf_csum_init(struct net *n, struct nlattr *nla, struct nlattr *est, - struct tc_action *a, int ovr, int bind) +static int csum_net_id; + +static int tcf_csum_init(struct net *net, struct nlattr *nla, + struct nlattr *est, struct tc_action *a, int ovr, + int bind) { + struct tc_action_net *tn = net_generic(net, csum_net_id); struct nlattr *tb[TCA_CSUM_MAX + 1]; struct tc_csum *parm; struct tcf_csum *p; @@ -61,9 +65,9 @@ static int tcf_csum_init(struct net *n, struct nlattr *nla, struct nlattr *est, return -EINVAL; parm = nla_data(tb[TCA_CSUM_PARMS]); - if (!tcf_hash_check(parm->index, a, bind)) { - ret = tcf_hash_create(parm->index, est, a, sizeof(*p), - bind, false); + if (!tcf_hash_check(tn, parm->index, a, bind)) { + ret = tcf_hash_create(tn, parm->index, est, a, + sizeof(*p), bind, false); if (ret) return ret; ret = ACT_P_CREATED; @@ -82,7 +86,7 @@ static int tcf_csum_init(struct net *n, struct nlattr *nla, struct nlattr *est, spin_unlock_bh(&p->tcf_lock); if (ret == ACT_P_CREATED) - tcf_hash_insert(a); + tcf_hash_insert(tn, a); return ret; } @@ -555,6 +559,22 @@ nla_put_failure: return -1; } +static int tcf_csum_walker(struct net *net, struct sk_buff *skb, + struct netlink_callback *cb, int type, + struct tc_action *a) +{ + struct tc_action_net *tn = net_generic(net, csum_net_id); + + return tcf_generic_walker(tn, skb, cb, type, a); +} + +static int tcf_csum_search(struct net *net, struct tc_action *a, u32 index) +{ + struct tc_action_net *tn = net_generic(net, csum_net_id); + + return tcf_hash_search(tn, a, index); +} + static struct tc_action_ops act_csum_ops = { .kind = "csum", .type = TCA_ACT_CSUM, @@ -562,6 +582,29 @@ static struct tc_action_ops act_csum_ops = { .act = tcf_csum, .dump = tcf_csum_dump, .init = tcf_csum_init, + .walk = tcf_csum_walker, + .lookup = tcf_csum_search, +}; + +static __net_init int csum_init_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, csum_net_id); + + return tc_action_net_init(tn, &act_csum_ops, CSUM_TAB_MASK); +} + +static void __net_exit csum_exit_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, csum_net_id); + + tc_action_net_exit(tn); +} + +static struct pernet_operations csum_net_ops = { + .init = csum_init_net, + .exit = csum_exit_net, + .id = &csum_net_id, + .size = sizeof(struct tc_action_net), }; MODULE_DESCRIPTION("Checksum updating actions"); @@ -569,12 +612,12 @@ MODULE_LICENSE("GPL"); static int __init csum_init_module(void) { - return tcf_register_action(&act_csum_ops, CSUM_TAB_MASK); + return tcf_register_action(&act_csum_ops, &csum_net_ops); } static void __exit csum_cleanup_module(void) { - tcf_unregister_action(&act_csum_ops); + tcf_unregister_action(&act_csum_ops, &csum_net_ops); } module_init(csum_init_module); diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index 5c1b05170736..887fc1f209ff 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -25,6 +25,8 @@ #define GACT_TAB_MASK 15 +static int gact_net_id; + #ifdef CONFIG_GACT_PROB static int gact_net_rand(struct tcf_gact *gact) { @@ -57,6 +59,7 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action *a, int ovr, int bind) { + struct tc_action_net *tn = net_generic(net, gact_net_id); struct nlattr *tb[TCA_GACT_MAX + 1]; struct tc_gact *parm; struct tcf_gact *gact; @@ -88,9 +91,9 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, } #endif - if (!tcf_hash_check(parm->index, a, bind)) { - ret = tcf_hash_create(parm->index, est, a, sizeof(*gact), - bind, true); + if (!tcf_hash_check(tn, parm->index, a, bind)) { + ret = tcf_hash_create(tn, parm->index, est, a, + sizeof(*gact), bind, true); if (ret) return ret; ret = ACT_P_CREATED; @@ -118,7 +121,7 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, } #endif if (ret == ACT_P_CREATED) - tcf_hash_insert(a); + tcf_hash_insert(tn, a); return ret; } @@ -183,6 +186,22 @@ nla_put_failure: return -1; } +static int tcf_gact_walker(struct net *net, struct sk_buff *skb, + struct netlink_callback *cb, int type, + struct tc_action *a) +{ + struct tc_action_net *tn = net_generic(net, gact_net_id); + + return tcf_generic_walker(tn, skb, cb, type, a); +} + +static int tcf_gact_search(struct net *net, struct tc_action *a, u32 index) +{ + struct tc_action_net *tn = net_generic(net, gact_net_id); + + return tcf_hash_search(tn, a, index); +} + static struct tc_action_ops act_gact_ops = { .kind = "gact", .type = TCA_ACT_GACT, @@ -190,6 +209,29 @@ static struct tc_action_ops act_gact_ops = { .act = tcf_gact, .dump = tcf_gact_dump, .init = tcf_gact_init, + .walk = tcf_gact_walker, + .lookup = tcf_gact_search, +}; + +static __net_init int gact_init_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, gact_net_id); + + return tc_action_net_init(tn, &act_gact_ops, GACT_TAB_MASK); +} + +static void __net_exit gact_exit_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, gact_net_id); + + tc_action_net_exit(tn); +} + +static struct pernet_operations gact_net_ops = { + .init = gact_init_net, + .exit = gact_exit_net, + .id = &gact_net_id, + .size = sizeof(struct tc_action_net), }; MODULE_AUTHOR("Jamal Hadi Salim(2002-4)"); @@ -203,12 +245,13 @@ static int __init gact_init_module(void) #else pr_info("GACT probability NOT on\n"); #endif - return tcf_register_action(&act_gact_ops, GACT_TAB_MASK); + + return tcf_register_action(&act_gact_ops, &gact_net_ops); } static void __exit gact_cleanup_module(void) { - tcf_unregister_action(&act_gact_ops); + tcf_unregister_action(&act_gact_ops, &gact_net_ops); } module_init(gact_init_module); diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index d05869646515..89c41a1f3589 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -30,6 +30,10 @@ #define IPT_TAB_MASK 15 +static int ipt_net_id; + +static int xt_net_id; + static int ipt_init_target(struct xt_entry_target *t, char *table, unsigned int hook) { struct xt_tgchk_param par; @@ -83,8 +87,9 @@ static const struct nla_policy ipt_policy[TCA_IPT_MAX + 1] = { [TCA_IPT_TARG] = { .len = sizeof(struct xt_entry_target) }, }; -static int tcf_ipt_init(struct net *net, struct nlattr *nla, struct nlattr *est, - struct tc_action *a, int ovr, int bind) +static int __tcf_ipt_init(struct tc_action_net *tn, struct nlattr *nla, + struct nlattr *est, struct tc_action *a, int ovr, + int bind) { struct nlattr *tb[TCA_IPT_MAX + 1]; struct tcf_ipt *ipt; @@ -113,8 +118,9 @@ static int tcf_ipt_init(struct net *net, struct nlattr *nla, struct nlattr *est, if (tb[TCA_IPT_INDEX] != NULL) index = nla_get_u32(tb[TCA_IPT_INDEX]); - if (!tcf_hash_check(index, a, bind) ) { - ret = tcf_hash_create(index, est, a, sizeof(*ipt), bind, false); + if (!tcf_hash_check(tn, index, a, bind)) { + ret = tcf_hash_create(tn, index, est, a, sizeof(*ipt), bind, + false); if (ret) return ret; ret = ACT_P_CREATED; @@ -157,7 +163,7 @@ static int tcf_ipt_init(struct net *net, struct nlattr *nla, struct nlattr *est, ipt->tcfi_hook = hook; spin_unlock_bh(&ipt->tcf_lock); if (ret == ACT_P_CREATED) - tcf_hash_insert(a); + tcf_hash_insert(tn, a); return ret; err3: @@ -170,6 +176,24 @@ err1: return err; } +static int tcf_ipt_init(struct net *net, struct nlattr *nla, + struct nlattr *est, struct tc_action *a, int ovr, + int bind) +{ + struct tc_action_net *tn = net_generic(net, ipt_net_id); + + return __tcf_ipt_init(tn, nla, est, a, ovr, bind); +} + +static int tcf_xt_init(struct net *net, struct nlattr *nla, + struct nlattr *est, struct tc_action *a, int ovr, + int bind) +{ + struct tc_action_net *tn = net_generic(net, xt_net_id); + + return __tcf_ipt_init(tn, nla, est, a, ovr, bind); +} + static int tcf_ipt(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { @@ -260,6 +284,22 @@ nla_put_failure: return -1; } +static int tcf_ipt_walker(struct net *net, struct sk_buff *skb, + struct netlink_callback *cb, int type, + struct tc_action *a) +{ + struct tc_action_net *tn = net_generic(net, ipt_net_id); + + return tcf_generic_walker(tn, skb, cb, type, a); +} + +static int tcf_ipt_search(struct net *net, struct tc_action *a, u32 index) +{ + struct tc_action_net *tn = net_generic(net, ipt_net_id); + + return tcf_hash_search(tn, a, index); +} + static struct tc_action_ops act_ipt_ops = { .kind = "ipt", .type = TCA_ACT_IPT, @@ -268,8 +308,47 @@ static struct tc_action_ops act_ipt_ops = { .dump = tcf_ipt_dump, .cleanup = tcf_ipt_release, .init = tcf_ipt_init, + .walk = tcf_ipt_walker, + .lookup = tcf_ipt_search, +}; + +static __net_init int ipt_init_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, ipt_net_id); + + return tc_action_net_init(tn, &act_ipt_ops, IPT_TAB_MASK); +} + +static void __net_exit ipt_exit_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, ipt_net_id); + + tc_action_net_exit(tn); +} + +static struct pernet_operations ipt_net_ops = { + .init = ipt_init_net, + .exit = ipt_exit_net, + .id = &ipt_net_id, + .size = sizeof(struct tc_action_net), }; +static int tcf_xt_walker(struct net *net, struct sk_buff *skb, + struct netlink_callback *cb, int type, + struct tc_action *a) +{ + struct tc_action_net *tn = net_generic(net, xt_net_id); + + return tcf_generic_walker(tn, skb, cb, type, a); +} + +static int tcf_xt_search(struct net *net, struct tc_action *a, u32 index) +{ + struct tc_action_net *tn = net_generic(net, xt_net_id); + + return tcf_hash_search(tn, a, index); +} + static struct tc_action_ops act_xt_ops = { .kind = "xt", .type = TCA_ACT_XT, @@ -277,7 +356,30 @@ static struct tc_action_ops act_xt_ops = { .act = tcf_ipt, .dump = tcf_ipt_dump, .cleanup = tcf_ipt_release, - .init = tcf_ipt_init, + .init = tcf_xt_init, + .walk = tcf_xt_walker, + .lookup = tcf_xt_search, +}; + +static __net_init int xt_init_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, xt_net_id); + + return tc_action_net_init(tn, &act_xt_ops, IPT_TAB_MASK); +} + +static void __net_exit xt_exit_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, xt_net_id); + + tc_action_net_exit(tn); +} + +static struct pernet_operations xt_net_ops = { + .init = xt_init_net, + .exit = xt_exit_net, + .id = &xt_net_id, + .size = sizeof(struct tc_action_net), }; MODULE_AUTHOR("Jamal Hadi Salim(2002-13)"); @@ -289,12 +391,13 @@ static int __init ipt_init_module(void) { int ret1, ret2; - ret1 = tcf_register_action(&act_xt_ops, IPT_TAB_MASK); + ret1 = tcf_register_action(&act_xt_ops, &xt_net_ops); if (ret1 < 0) - printk("Failed to load xt action\n"); - ret2 = tcf_register_action(&act_ipt_ops, IPT_TAB_MASK); + pr_err("Failed to load xt action\n"); + + ret2 = tcf_register_action(&act_ipt_ops, &ipt_net_ops); if (ret2 < 0) - printk("Failed to load ipt action\n"); + pr_err("Failed to load ipt action\n"); if (ret1 < 0 && ret2 < 0) { return ret1; @@ -304,8 +407,8 @@ static int __init ipt_init_module(void) static void __exit ipt_cleanup_module(void) { - tcf_unregister_action(&act_xt_ops); - tcf_unregister_action(&act_ipt_ops); + tcf_unregister_action(&act_ipt_ops, &ipt_net_ops); + tcf_unregister_action(&act_xt_ops, &xt_net_ops); } module_init(ipt_init_module); diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 32fcdecdb9e2..6b284d991e0b 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -50,10 +50,13 @@ static const struct nla_policy mirred_policy[TCA_MIRRED_MAX + 1] = { [TCA_MIRRED_PARMS] = { .len = sizeof(struct tc_mirred) }, }; +static int mirred_net_id; + static int tcf_mirred_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action *a, int ovr, int bind) { + struct tc_action_net *tn = net_generic(net, mirred_net_id); struct nlattr *tb[TCA_MIRRED_MAX + 1]; struct tc_mirred *parm; struct tcf_mirred *m; @@ -96,11 +99,11 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, dev = NULL; } - if (!tcf_hash_check(parm->index, a, bind)) { + if (!tcf_hash_check(tn, parm->index, a, bind)) { if (dev == NULL) return -EINVAL; - ret = tcf_hash_create(parm->index, est, a, sizeof(*m), - bind, true); + ret = tcf_hash_create(tn, parm->index, est, a, + sizeof(*m), bind, true); if (ret) return ret; ret = ACT_P_CREATED; @@ -130,7 +133,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, spin_lock_bh(&mirred_list_lock); list_add(&m->tcfm_list, &mirred_list); spin_unlock_bh(&mirred_list_lock); - tcf_hash_insert(a); + tcf_hash_insert(tn, a); } return ret; @@ -221,6 +224,22 @@ nla_put_failure: return -1; } +static int tcf_mirred_walker(struct net *net, struct sk_buff *skb, + struct netlink_callback *cb, int type, + struct tc_action *a) +{ + struct tc_action_net *tn = net_generic(net, mirred_net_id); + + return tcf_generic_walker(tn, skb, cb, type, a); +} + +static int tcf_mirred_search(struct net *net, struct tc_action *a, u32 index) +{ + struct tc_action_net *tn = net_generic(net, mirred_net_id); + + return tcf_hash_search(tn, a, index); +} + static int mirred_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { @@ -257,6 +276,29 @@ static struct tc_action_ops act_mirred_ops = { .dump = tcf_mirred_dump, .cleanup = tcf_mirred_release, .init = tcf_mirred_init, + .walk = tcf_mirred_walker, + .lookup = tcf_mirred_search, +}; + +static __net_init int mirred_init_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, mirred_net_id); + + return tc_action_net_init(tn, &act_mirred_ops, MIRRED_TAB_MASK); +} + +static void __net_exit mirred_exit_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, mirred_net_id); + + tc_action_net_exit(tn); +} + +static struct pernet_operations mirred_net_ops = { + .init = mirred_init_net, + .exit = mirred_exit_net, + .id = &mirred_net_id, + .size = sizeof(struct tc_action_net), }; MODULE_AUTHOR("Jamal Hadi Salim(2002)"); @@ -270,12 +312,12 @@ static int __init mirred_init_module(void) return err; pr_info("Mirror/redirect action on\n"); - return tcf_register_action(&act_mirred_ops, MIRRED_TAB_MASK); + return tcf_register_action(&act_mirred_ops, &mirred_net_ops); } static void __exit mirred_cleanup_module(void) { - tcf_unregister_action(&act_mirred_ops); + tcf_unregister_action(&act_mirred_ops, &mirred_net_ops); unregister_netdevice_notifier(&mirred_device_notifier); } diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 27607b863aba..0f65cdfbfb1d 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -31,6 +31,8 @@ #define NAT_TAB_MASK 15 +static int nat_net_id; + static const struct nla_policy nat_policy[TCA_NAT_MAX + 1] = { [TCA_NAT_PARMS] = { .len = sizeof(struct tc_nat) }, }; @@ -38,6 +40,7 @@ static const struct nla_policy nat_policy[TCA_NAT_MAX + 1] = { static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action *a, int ovr, int bind) { + struct tc_action_net *tn = net_generic(net, nat_net_id); struct nlattr *tb[TCA_NAT_MAX + 1]; struct tc_nat *parm; int ret = 0, err; @@ -54,9 +57,9 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, return -EINVAL; parm = nla_data(tb[TCA_NAT_PARMS]); - if (!tcf_hash_check(parm->index, a, bind)) { - ret = tcf_hash_create(parm->index, est, a, sizeof(*p), - bind, false); + if (!tcf_hash_check(tn, parm->index, a, bind)) { + ret = tcf_hash_create(tn, parm->index, est, a, + sizeof(*p), bind, false); if (ret) return ret; ret = ACT_P_CREATED; @@ -79,7 +82,7 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, spin_unlock_bh(&p->tcf_lock); if (ret == ACT_P_CREATED) - tcf_hash_insert(a); + tcf_hash_insert(tn, a); return ret; } @@ -274,6 +277,22 @@ nla_put_failure: return -1; } +static int tcf_nat_walker(struct net *net, struct sk_buff *skb, + struct netlink_callback *cb, int type, + struct tc_action *a) +{ + struct tc_action_net *tn = net_generic(net, nat_net_id); + + return tcf_generic_walker(tn, skb, cb, type, a); +} + +static int tcf_nat_search(struct net *net, struct tc_action *a, u32 index) +{ + struct tc_action_net *tn = net_generic(net, nat_net_id); + + return tcf_hash_search(tn, a, index); +} + static struct tc_action_ops act_nat_ops = { .kind = "nat", .type = TCA_ACT_NAT, @@ -281,6 +300,29 @@ static struct tc_action_ops act_nat_ops = { .act = tcf_nat, .dump = tcf_nat_dump, .init = tcf_nat_init, + .walk = tcf_nat_walker, + .lookup = tcf_nat_search, +}; + +static __net_init int nat_init_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, nat_net_id); + + return tc_action_net_init(tn, &act_nat_ops, NAT_TAB_MASK); +} + +static void __net_exit nat_exit_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, nat_net_id); + + tc_action_net_exit(tn); +} + +static struct pernet_operations nat_net_ops = { + .init = nat_init_net, + .exit = nat_exit_net, + .id = &nat_net_id, + .size = sizeof(struct tc_action_net), }; MODULE_DESCRIPTION("Stateless NAT actions"); @@ -288,12 +330,12 @@ MODULE_LICENSE("GPL"); static int __init nat_init_module(void) { - return tcf_register_action(&act_nat_ops, NAT_TAB_MASK); + return tcf_register_action(&act_nat_ops, &nat_net_ops); } static void __exit nat_cleanup_module(void) { - tcf_unregister_action(&act_nat_ops); + tcf_unregister_action(&act_nat_ops, &nat_net_ops); } module_init(nat_init_module); diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index e38a7701f154..429c3ab65142 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -25,6 +25,8 @@ #define PEDIT_TAB_MASK 15 +static int pedit_net_id; + static const struct nla_policy pedit_policy[TCA_PEDIT_MAX + 1] = { [TCA_PEDIT_PARMS] = { .len = sizeof(struct tc_pedit) }, }; @@ -33,6 +35,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action *a, int ovr, int bind) { + struct tc_action_net *tn = net_generic(net, pedit_net_id); struct nlattr *tb[TCA_PEDIT_MAX + 1]; struct tc_pedit *parm; int ret = 0, err; @@ -54,11 +57,11 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, if (nla_len(tb[TCA_PEDIT_PARMS]) < sizeof(*parm) + ksize) return -EINVAL; - if (!tcf_hash_check(parm->index, a, bind)) { + if (!tcf_hash_check(tn, parm->index, a, bind)) { if (!parm->nkeys) return -EINVAL; - ret = tcf_hash_create(parm->index, est, a, sizeof(*p), - bind, false); + ret = tcf_hash_create(tn, parm->index, est, a, + sizeof(*p), bind, false); if (ret) return ret; p = to_pedit(a); @@ -93,7 +96,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, memcpy(p->tcfp_keys, parm->keys, ksize); spin_unlock_bh(&p->tcf_lock); if (ret == ACT_P_CREATED) - tcf_hash_insert(a); + tcf_hash_insert(tn, a); return ret; } @@ -211,6 +214,22 @@ nla_put_failure: return -1; } +static int tcf_pedit_walker(struct net *net, struct sk_buff *skb, + struct netlink_callback *cb, int type, + struct tc_action *a) +{ + struct tc_action_net *tn = net_generic(net, pedit_net_id); + + return tcf_generic_walker(tn, skb, cb, type, a); +} + +static int tcf_pedit_search(struct net *net, struct tc_action *a, u32 index) +{ + struct tc_action_net *tn = net_generic(net, pedit_net_id); + + return tcf_hash_search(tn, a, index); +} + static struct tc_action_ops act_pedit_ops = { .kind = "pedit", .type = TCA_ACT_PEDIT, @@ -219,6 +238,29 @@ static struct tc_action_ops act_pedit_ops = { .dump = tcf_pedit_dump, .cleanup = tcf_pedit_cleanup, .init = tcf_pedit_init, + .walk = tcf_pedit_walker, + .lookup = tcf_pedit_search, +}; + +static __net_init int pedit_init_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, pedit_net_id); + + return tc_action_net_init(tn, &act_pedit_ops, PEDIT_TAB_MASK); +} + +static void __net_exit pedit_exit_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, pedit_net_id); + + tc_action_net_exit(tn); +} + +static struct pernet_operations pedit_net_ops = { + .init = pedit_init_net, + .exit = pedit_exit_net, + .id = &pedit_net_id, + .size = sizeof(struct tc_action_net), }; MODULE_AUTHOR("Jamal Hadi Salim(2002-4)"); @@ -227,12 +269,12 @@ MODULE_LICENSE("GPL"); static int __init pedit_init_module(void) { - return tcf_register_action(&act_pedit_ops, PEDIT_TAB_MASK); + return tcf_register_action(&act_pedit_ops, &pedit_net_ops); } static void __exit pedit_cleanup_module(void) { - tcf_unregister_action(&act_pedit_ops); + tcf_unregister_action(&act_pedit_ops, &pedit_net_ops); } module_init(pedit_init_module); diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 9a1c42a43f92..330f14e302e8 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -55,10 +55,14 @@ struct tc_police_compat { /* Each policer is serialized by its individual spinlock */ -static int tcf_act_police_walker(struct sk_buff *skb, struct netlink_callback *cb, - int type, struct tc_action *a) +static int police_net_id; + +static int tcf_act_police_walker(struct net *net, struct sk_buff *skb, + struct netlink_callback *cb, int type, + struct tc_action *a) { - struct tcf_hashinfo *hinfo = a->ops->hinfo; + struct tc_action_net *tn = net_generic(net, police_net_id); + struct tcf_hashinfo *hinfo = tn->hinfo; struct hlist_head *head; struct tcf_common *p; int err = 0, index = -1, i = 0, s_i = 0, n_i = 0; @@ -121,7 +125,8 @@ static int tcf_act_police_locate(struct net *net, struct nlattr *nla, struct tc_police *parm; struct tcf_police *police; struct qdisc_rate_table *R_tab = NULL, *P_tab = NULL; - struct tcf_hashinfo *hinfo = a->ops->hinfo; + struct tc_action_net *tn = net_generic(net, police_net_id); + struct tcf_hashinfo *hinfo = tn->hinfo; int size; if (nla == NULL) @@ -139,7 +144,7 @@ static int tcf_act_police_locate(struct net *net, struct nlattr *nla, parm = nla_data(tb[TCA_POLICE_TBF]); if (parm->index) { - if (tcf_hash_search(a, parm->index)) { + if (tcf_hash_search(tn, a, parm->index)) { police = to_police(a->priv); if (bind) { police->tcf_bindcnt += 1; @@ -233,7 +238,7 @@ override: police->tcfp_t_c = ktime_get_ns(); police->tcf_index = parm->index ? parm->index : - tcf_hash_new_index(hinfo); + tcf_hash_new_index(tn); h = tcf_hash(police->tcf_index, POL_TAB_MASK); spin_lock_bh(&hinfo->lock); hlist_add_head(&police->tcf_head, &hinfo->htab[h]); @@ -342,6 +347,13 @@ nla_put_failure: return -1; } +static int tcf_police_search(struct net *net, struct tc_action *a, u32 index) +{ + struct tc_action_net *tn = net_generic(net, police_net_id); + + return tcf_hash_search(tn, a, index); +} + MODULE_AUTHOR("Alexey Kuznetsov"); MODULE_DESCRIPTION("Policing actions"); MODULE_LICENSE("GPL"); @@ -353,19 +365,41 @@ static struct tc_action_ops act_police_ops = { .act = tcf_act_police, .dump = tcf_act_police_dump, .init = tcf_act_police_locate, - .walk = tcf_act_police_walker + .walk = tcf_act_police_walker, + .lookup = tcf_police_search, +}; + +static __net_init int police_init_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, police_net_id); + + return tc_action_net_init(tn, &act_police_ops, POL_TAB_MASK); +} + +static void __net_exit police_exit_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, police_net_id); + + tc_action_net_exit(tn); +} + +static struct pernet_operations police_net_ops = { + .init = police_init_net, + .exit = police_exit_net, + .id = &police_net_id, + .size = sizeof(struct tc_action_net), }; static int __init police_init_module(void) { - return tcf_register_action(&act_police_ops, POL_TAB_MASK); + return tcf_register_action(&act_police_ops, &police_net_ops); } static void __exit police_cleanup_module(void) { - tcf_unregister_action(&act_police_ops); + tcf_unregister_action(&act_police_ops, &police_net_ops); } module_init(police_init_module); diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index d6b708d6afdf..75b2be13fbcc 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -26,6 +26,8 @@ #define SIMP_TAB_MASK 7 +static int simp_net_id; + #define SIMP_MAX_DATA 32 static int tcf_simp(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) @@ -80,6 +82,7 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action *a, int ovr, int bind) { + struct tc_action_net *tn = net_generic(net, simp_net_id); struct nlattr *tb[TCA_DEF_MAX + 1]; struct tc_defact *parm; struct tcf_defact *d; @@ -102,9 +105,9 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, parm = nla_data(tb[TCA_DEF_PARMS]); defdata = nla_data(tb[TCA_DEF_DATA]); - if (!tcf_hash_check(parm->index, a, bind)) { - ret = tcf_hash_create(parm->index, est, a, sizeof(*d), - bind, false); + if (!tcf_hash_check(tn, parm->index, a, bind)) { + ret = tcf_hash_create(tn, parm->index, est, a, + sizeof(*d), bind, false); if (ret) return ret; @@ -129,7 +132,7 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, } if (ret == ACT_P_CREATED) - tcf_hash_insert(a); + tcf_hash_insert(tn, a); return ret; } @@ -161,6 +164,22 @@ nla_put_failure: return -1; } +static int tcf_simp_walker(struct net *net, struct sk_buff *skb, + struct netlink_callback *cb, int type, + struct tc_action *a) +{ + struct tc_action_net *tn = net_generic(net, simp_net_id); + + return tcf_generic_walker(tn, skb, cb, type, a); +} + +static int tcf_simp_search(struct net *net, struct tc_action *a, u32 index) +{ + struct tc_action_net *tn = net_generic(net, simp_net_id); + + return tcf_hash_search(tn, a, index); +} + static struct tc_action_ops act_simp_ops = { .kind = "simple", .type = TCA_ACT_SIMP, @@ -169,6 +188,29 @@ static struct tc_action_ops act_simp_ops = { .dump = tcf_simp_dump, .cleanup = tcf_simp_release, .init = tcf_simp_init, + .walk = tcf_simp_walker, + .lookup = tcf_simp_search, +}; + +static __net_init int simp_init_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, simp_net_id); + + return tc_action_net_init(tn, &act_simp_ops, SIMP_TAB_MASK); +} + +static void __net_exit simp_exit_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, simp_net_id); + + tc_action_net_exit(tn); +} + +static struct pernet_operations simp_net_ops = { + .init = simp_init_net, + .exit = simp_exit_net, + .id = &simp_net_id, + .size = sizeof(struct tc_action_net), }; MODULE_AUTHOR("Jamal Hadi Salim(2005)"); @@ -177,8 +219,7 @@ MODULE_LICENSE("GPL"); static int __init simp_init_module(void) { - int ret; - ret = tcf_register_action(&act_simp_ops, SIMP_TAB_MASK); + int ret = tcf_register_action(&act_simp_ops, &simp_net_ops); if (!ret) pr_info("Simple TC action Loaded\n"); return ret; @@ -186,7 +227,7 @@ static int __init simp_init_module(void) static void __exit simp_cleanup_module(void) { - tcf_unregister_action(&act_simp_ops); + tcf_unregister_action(&act_simp_ops, &simp_net_ops); } module_init(simp_init_module); diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 6751b5f8c046..cfcdbdc00c9b 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -29,6 +29,8 @@ #define SKBEDIT_TAB_MASK 15 +static int skbedit_net_id; + static int tcf_skbedit(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { @@ -61,6 +63,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action *a, int ovr, int bind) { + struct tc_action_net *tn = net_generic(net, skbedit_net_id); struct nlattr *tb[TCA_SKBEDIT_MAX + 1]; struct tc_skbedit *parm; struct tcf_skbedit *d; @@ -98,9 +101,9 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, parm = nla_data(tb[TCA_SKBEDIT_PARMS]); - if (!tcf_hash_check(parm->index, a, bind)) { - ret = tcf_hash_create(parm->index, est, a, sizeof(*d), - bind, false); + if (!tcf_hash_check(tn, parm->index, a, bind)) { + ret = tcf_hash_create(tn, parm->index, est, a, + sizeof(*d), bind, false); if (ret) return ret; @@ -130,7 +133,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, spin_unlock_bh(&d->tcf_lock); if (ret == ACT_P_CREATED) - tcf_hash_insert(a); + tcf_hash_insert(tn, a); return ret; } @@ -173,6 +176,22 @@ nla_put_failure: return -1; } +static int tcf_skbedit_walker(struct net *net, struct sk_buff *skb, + struct netlink_callback *cb, int type, + struct tc_action *a) +{ + struct tc_action_net *tn = net_generic(net, skbedit_net_id); + + return tcf_generic_walker(tn, skb, cb, type, a); +} + +static int tcf_skbedit_search(struct net *net, struct tc_action *a, u32 index) +{ + struct tc_action_net *tn = net_generic(net, skbedit_net_id); + + return tcf_hash_search(tn, a, index); +} + static struct tc_action_ops act_skbedit_ops = { .kind = "skbedit", .type = TCA_ACT_SKBEDIT, @@ -180,6 +199,29 @@ static struct tc_action_ops act_skbedit_ops = { .act = tcf_skbedit, .dump = tcf_skbedit_dump, .init = tcf_skbedit_init, + .walk = tcf_skbedit_walker, + .lookup = tcf_skbedit_search, +}; + +static __net_init int skbedit_init_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, skbedit_net_id); + + return tc_action_net_init(tn, &act_skbedit_ops, SKBEDIT_TAB_MASK); +} + +static void __net_exit skbedit_exit_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, skbedit_net_id); + + tc_action_net_exit(tn); +} + +static struct pernet_operations skbedit_net_ops = { + .init = skbedit_init_net, + .exit = skbedit_exit_net, + .id = &skbedit_net_id, + .size = sizeof(struct tc_action_net), }; MODULE_AUTHOR("Alexander Duyck, "); @@ -188,12 +230,12 @@ MODULE_LICENSE("GPL"); static int __init skbedit_init_module(void) { - return tcf_register_action(&act_skbedit_ops, SKBEDIT_TAB_MASK); + return tcf_register_action(&act_skbedit_ops, &skbedit_net_ops); } static void __exit skbedit_cleanup_module(void) { - tcf_unregister_action(&act_skbedit_ops); + tcf_unregister_action(&act_skbedit_ops, &skbedit_net_ops); } module_init(skbedit_init_module); diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 796785e0bf96..bab8ae0cefc0 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -21,6 +21,8 @@ #define VLAN_TAB_MASK 15 +static int vlan_net_id; + static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { @@ -68,6 +70,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action *a, int ovr, int bind) { + struct tc_action_net *tn = net_generic(net, vlan_net_id); struct nlattr *tb[TCA_VLAN_MAX + 1]; struct tc_vlan *parm; struct tcf_vlan *v; @@ -115,9 +118,9 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, } action = parm->v_action; - if (!tcf_hash_check(parm->index, a, bind)) { - ret = tcf_hash_create(parm->index, est, a, sizeof(*v), - bind, false); + if (!tcf_hash_check(tn, parm->index, a, bind)) { + ret = tcf_hash_create(tn, parm->index, est, a, + sizeof(*v), bind, false); if (ret) return ret; @@ -143,7 +146,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, spin_unlock_bh(&v->tcf_lock); if (ret == ACT_P_CREATED) - tcf_hash_insert(a); + tcf_hash_insert(tn, a); return ret; } @@ -181,6 +184,22 @@ nla_put_failure: return -1; } +static int tcf_vlan_walker(struct net *net, struct sk_buff *skb, + struct netlink_callback *cb, int type, + struct tc_action *a) +{ + struct tc_action_net *tn = net_generic(net, vlan_net_id); + + return tcf_generic_walker(tn, skb, cb, type, a); +} + +static int tcf_vlan_search(struct net *net, struct tc_action *a, u32 index) +{ + struct tc_action_net *tn = net_generic(net, vlan_net_id); + + return tcf_hash_search(tn, a, index); +} + static struct tc_action_ops act_vlan_ops = { .kind = "vlan", .type = TCA_ACT_VLAN, @@ -188,16 +207,39 @@ static struct tc_action_ops act_vlan_ops = { .act = tcf_vlan, .dump = tcf_vlan_dump, .init = tcf_vlan_init, + .walk = tcf_vlan_walker, + .lookup = tcf_vlan_search, +}; + +static __net_init int vlan_init_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, vlan_net_id); + + return tc_action_net_init(tn, &act_vlan_ops, VLAN_TAB_MASK); +} + +static void __net_exit vlan_exit_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, vlan_net_id); + + tc_action_net_exit(tn); +} + +static struct pernet_operations vlan_net_ops = { + .init = vlan_init_net, + .exit = vlan_exit_net, + .id = &vlan_net_id, + .size = sizeof(struct tc_action_net), }; static int __init vlan_init_module(void) { - return tcf_register_action(&act_vlan_ops, VLAN_TAB_MASK); + return tcf_register_action(&act_vlan_ops, &vlan_net_ops); } static void __exit vlan_cleanup_module(void) { - tcf_unregister_action(&act_vlan_ops); + tcf_unregister_action(&act_vlan_ops, &vlan_net_ops); } module_init(vlan_init_module); -- cgit v1.2.3-71-gd317 From 65aebfc002abc1827ac7c8644a2bba0459ce3ce2 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Tue, 23 Feb 2016 12:13:54 -0500 Subject: net: dsa: add port_vlan_dump routine Similar to port_fdb_dump, add a port_vlan_dump function to DSA drivers which gets passed the switchdev VLAN object and callback. This function, if implemented, takes precedence over the soon legacy vlan_getnext/port_pvid_get approach. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- Documentation/networking/dsa/dsa.txt | 4 ++++ include/net/dsa.h | 3 +++ net/dsa/slave.c | 3 +++ 3 files changed, 10 insertions(+) (limited to 'include/net') diff --git a/Documentation/networking/dsa/dsa.txt b/Documentation/networking/dsa/dsa.txt index ebf21530471f..350a502e031f 100644 --- a/Documentation/networking/dsa/dsa.txt +++ b/Documentation/networking/dsa/dsa.txt @@ -554,6 +554,10 @@ Bridge VLAN filtering - port_vlan_del: bridge layer function invoked when a VLAN is removed from the given switch port +- port_vlan_dump: bridge layer function invoked with a switchdev callback + function that the driver has to call for each VLAN the given port is a member + of. A switchdev object is used to carry the VID and bridge flags. + - vlan_getnext: bridge layer function invoked to query the next configured VLAN in the switch, i.e. returns the bitmaps of members and untagged ports diff --git a/include/net/dsa.h b/include/net/dsa.h index 1c845d7bf0b2..ebc0d9ea96a1 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -313,6 +313,9 @@ struct dsa_switch_driver { struct switchdev_trans *trans); int (*port_vlan_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan); + int (*port_vlan_dump)(struct dsa_switch *ds, int port, + struct switchdev_obj_port_vlan *vlan, + int (*cb)(struct switchdev_obj *obj)); int (*port_pvid_get)(struct dsa_switch *ds, int port, u16 *pvid); int (*vlan_getnext)(struct dsa_switch *ds, u16 *vid, unsigned long *ports, unsigned long *untagged); diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 14ca9784ec0c..a9cbb72fb155 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -248,6 +248,9 @@ static int dsa_slave_port_vlan_dump(struct net_device *dev, u16 pvid, vid = 0; int err; + if (ds->drv->port_vlan_dump) + return ds->drv->port_vlan_dump(ds, p->port, vlan, cb); + if (!ds->drv->vlan_getnext || !ds->drv->port_pvid_get) return -EOPNOTSUPP; -- cgit v1.2.3-71-gd317 From 477b184526a7f44164029eea720da0e0c888cac6 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Tue, 23 Feb 2016 12:13:56 -0500 Subject: net: dsa: drop vlan_getnext The VLAN GetNext operation is specific to some switches, and thus can be complicated to implement for some drivers. Remove the support for the vlan_getnext/port_pvid_get approach in favor of the generic and simpler port_vlan_dump function. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- Documentation/networking/dsa/dsa.txt | 9 --------- include/net/dsa.h | 3 --- net/dsa/slave.c | 35 +---------------------------------- 3 files changed, 1 insertion(+), 46 deletions(-) (limited to 'include/net') diff --git a/Documentation/networking/dsa/dsa.txt b/Documentation/networking/dsa/dsa.txt index 350a502e031f..974e9c387d1e 100644 --- a/Documentation/networking/dsa/dsa.txt +++ b/Documentation/networking/dsa/dsa.txt @@ -542,12 +542,6 @@ Bridge layer Bridge VLAN filtering --------------------- -- port_pvid_get: bridge layer function invoked when a Port-based VLAN ID is - queried for the given switch port - -- port_pvid_set: bridge layer function invoked when a Port-based VLAN ID needs - to be configured on the given switch port - - port_vlan_add: bridge layer function invoked when a VLAN is configured (tagged or untagged) for the given switch port @@ -558,9 +552,6 @@ Bridge VLAN filtering function that the driver has to call for each VLAN the given port is a member of. A switchdev object is used to carry the VID and bridge flags. -- vlan_getnext: bridge layer function invoked to query the next configured VLAN - in the switch, i.e. returns the bitmaps of members and untagged ports - - port_fdb_add: bridge layer function invoked when the bridge wants to install a Forwarding Database entry, the switch hardware should be programmed with the specified address in the specified VLAN Id in the forwarding database diff --git a/include/net/dsa.h b/include/net/dsa.h index ebc0d9ea96a1..3dd54867174a 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -316,9 +316,6 @@ struct dsa_switch_driver { int (*port_vlan_dump)(struct dsa_switch *ds, int port, struct switchdev_obj_port_vlan *vlan, int (*cb)(struct switchdev_obj *obj)); - int (*port_pvid_get)(struct dsa_switch *ds, int port, u16 *pvid); - int (*vlan_getnext)(struct dsa_switch *ds, u16 *vid, - unsigned long *ports, unsigned long *untagged); /* * Forwarding database diff --git a/net/dsa/slave.c b/net/dsa/slave.c index a9cbb72fb155..cde29239b60d 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -243,44 +243,11 @@ static int dsa_slave_port_vlan_dump(struct net_device *dev, { struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; - DECLARE_BITMAP(members, DSA_MAX_PORTS); - DECLARE_BITMAP(untagged, DSA_MAX_PORTS); - u16 pvid, vid = 0; - int err; if (ds->drv->port_vlan_dump) return ds->drv->port_vlan_dump(ds, p->port, vlan, cb); - if (!ds->drv->vlan_getnext || !ds->drv->port_pvid_get) - return -EOPNOTSUPP; - - err = ds->drv->port_pvid_get(ds, p->port, &pvid); - if (err) - return err; - - for (;;) { - err = ds->drv->vlan_getnext(ds, &vid, members, untagged); - if (err) - break; - - if (!test_bit(p->port, members)) - continue; - - memset(vlan, 0, sizeof(*vlan)); - vlan->vid_begin = vlan->vid_end = vid; - - if (vid == pvid) - vlan->flags |= BRIDGE_VLAN_INFO_PVID; - - if (test_bit(p->port, untagged)) - vlan->flags |= BRIDGE_VLAN_INFO_UNTAGGED; - - err = cb(&vlan->obj); - if (err) - break; - } - - return err == -ENOENT ? 0 : err; + return -EOPNOTSUPP; } static int dsa_slave_port_fdb_add(struct net_device *dev, -- cgit v1.2.3-71-gd317 From 3f2fb9a834cb1fcddbae22deca7fde136944dc89 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 24 Feb 2016 11:47:02 -0800 Subject: net: l3mdev: address selection should only consider devices in L3 domain David Lamparter noted a use case where the source address selection fails to pick an address from a VRF interface - unnumbered interfaces. Relevant commands from his script: ip addr add 9.9.9.9/32 dev lo ip link set lo up ip link add name vrf0 type vrf table 101 ip rule add oif vrf0 table 101 ip rule add iif vrf0 table 101 ip link set vrf0 up ip addr add 10.0.0.3/32 dev vrf0 ip link add name dummy2 type dummy ip link set dummy2 master vrf0 up --> note dummy2 has no address - unnumbered device ip route add 10.2.2.2/32 dev dummy2 table 101 ip neigh add 10.2.2.2 dev dummy2 lladdr 02:00:00:00:00:02 tcpdump -ni dummy2 & And using ping instead of his socat example: $ ping -I vrf0 -c1 10.2.2.2 ping: Warning: source address might be selected on device other than vrf0. PING 10.2.2.2 (10.2.2.2) from 9.9.9.9 vrf0: 56(84) bytes of data. >From tcpdump: 12:57:29.449128 IP 9.9.9.9 > 10.2.2.2: ICMP echo request, id 2491, seq 1, length 64 Note the source address is from lo and is not a VRF local address. With this patch: $ ping -I vrf0 -c1 10.2.2.2 PING 10.2.2.2 (10.2.2.2) from 10.0.0.3 vrf0: 56(84) bytes of data. >From tcpdump: 12:59:25.096426 IP 10.0.0.3 > 10.2.2.2: ICMP echo request, id 2113, seq 1, length 64 Now the source address comes from vrf0. The ipv4 function for selecting source address takes a const argument. Removing the const requires touching a lot of places, so instead l3mdev_master_ifindex_rcu is changed to take a const argument and then do the typecast to non-const as required by netdev_master_upper_dev_get_rcu. This is similar to what l3mdev_fib_table_rcu does. IPv6 for unnumbered interfaces appears to be selecting the addresses properly. Cc: David Lamparter Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/l3mdev.h | 4 ++-- net/ipv4/devinet.c | 5 +++++ net/l3mdev/l3mdev.c | 11 +++++++++-- 3 files changed, 16 insertions(+), 4 deletions(-) (limited to 'include/net') diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h index 5567d46b3cff..c43a9c73de5e 100644 --- a/include/net/l3mdev.h +++ b/include/net/l3mdev.h @@ -39,7 +39,7 @@ struct l3mdev_ops { #ifdef CONFIG_NET_L3_MASTER_DEV -int l3mdev_master_ifindex_rcu(struct net_device *dev); +int l3mdev_master_ifindex_rcu(const struct net_device *dev); static inline int l3mdev_master_ifindex(struct net_device *dev) { int ifindex; @@ -179,7 +179,7 @@ struct dst_entry *l3mdev_rt6_dst_by_oif(struct net *net, #else -static inline int l3mdev_master_ifindex_rcu(struct net_device *dev) +static inline int l3mdev_master_ifindex_rcu(const struct net_device *dev) { return 0; } diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 29b8d3a7b19b..18d510fa7ee2 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1194,6 +1194,7 @@ __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope) __be32 addr = 0; struct in_device *in_dev; struct net *net = dev_net(dev); + int master_idx; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); @@ -1214,12 +1215,16 @@ __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope) if (addr) goto out_unlock; no_in_dev: + master_idx = l3mdev_master_ifindex_rcu(dev); /* Not loopback addresses on loopback should be preferred in this case. It is important that lo is the first interface in dev_base list. */ for_each_netdev_rcu(net, dev) { + if (l3mdev_master_ifindex_rcu(dev) != master_idx) + continue; + in_dev = __in_dev_get_rcu(dev); if (!in_dev) continue; diff --git a/net/l3mdev/l3mdev.c b/net/l3mdev/l3mdev.c index 8e5ead366e7f..e925037fa0df 100644 --- a/net/l3mdev/l3mdev.c +++ b/net/l3mdev/l3mdev.c @@ -17,7 +17,7 @@ * @dev: targeted interface */ -int l3mdev_master_ifindex_rcu(struct net_device *dev) +int l3mdev_master_ifindex_rcu(const struct net_device *dev) { int ifindex = 0; @@ -28,8 +28,15 @@ int l3mdev_master_ifindex_rcu(struct net_device *dev) ifindex = dev->ifindex; } else if (netif_is_l3_slave(dev)) { struct net_device *master; + struct net_device *_dev = (struct net_device *)dev; - master = netdev_master_upper_dev_get_rcu(dev); + /* netdev_master_upper_dev_get_rcu calls + * list_first_or_null_rcu to walk the upper dev list. + * list_first_or_null_rcu does not handle a const arg. We aren't + * making changes, just want the master device from that list so + * typecast to remove the const + */ + master = netdev_master_upper_dev_get_rcu(_dev); if (master) ifindex = master->ifindex; } -- cgit v1.2.3-71-gd317 From 86a7996cc8a078793670d82ed97d5a99bb4e8496 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Thu, 25 Feb 2016 14:55:00 -0800 Subject: net_sched: introduce qdisc_replace() helper Remove nearly duplicated code and prepare for the following patch. Cc: Jamal Hadi Salim Acked-by: Jamal Hadi Salim Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/net/sch_generic.h | 17 +++++++++++++++++ net/sched/sch_cbq.c | 7 +------ net/sched/sch_drr.c | 6 +----- net/sched/sch_dsmark.c | 8 +------- net/sched/sch_hfsc.c | 6 +----- net/sched/sch_htb.c | 9 +-------- net/sched/sch_multiq.c | 8 +------- net/sched/sch_netem.c | 10 +--------- net/sched/sch_prio.c | 8 +------- net/sched/sch_qfq.c | 6 +----- net/sched/sch_red.c | 7 +------ net/sched/sch_sfb.c | 7 +------ net/sched/sch_tbf.c | 8 +------- 13 files changed, 29 insertions(+), 78 deletions(-) (limited to 'include/net') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 636a362a0e03..8fdad9f7a2fb 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -707,6 +707,23 @@ static inline void qdisc_reset_queue(struct Qdisc *sch) sch->qstats.backlog = 0; } +static inline struct Qdisc *qdisc_replace(struct Qdisc *sch, struct Qdisc *new, + struct Qdisc **pold) +{ + struct Qdisc *old; + + sch_tree_lock(sch); + old = *pold; + *pold = new; + if (old != NULL) { + qdisc_tree_decrease_qlen(old, old->q.qlen); + qdisc_reset(old); + } + sch_tree_unlock(sch); + + return old; +} + static inline unsigned int __qdisc_queue_drop(struct Qdisc *sch, struct sk_buff_head *list) { diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index c538d9e4a8f6..7f8474cdce32 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1624,13 +1624,8 @@ static int cbq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, new->reshape_fail = cbq_reshape_fail; #endif } - sch_tree_lock(sch); - *old = cl->q; - cl->q = new; - qdisc_tree_decrease_qlen(*old, (*old)->q.qlen); - qdisc_reset(*old); - sch_tree_unlock(sch); + *old = qdisc_replace(sch, new, &cl->q); return 0; } diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index a1cd778240cd..b96c9a8e70ab 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -226,11 +226,7 @@ static int drr_graft_class(struct Qdisc *sch, unsigned long arg, new = &noop_qdisc; } - sch_tree_lock(sch); - drr_purge_queue(cl); - *old = cl->qdisc; - cl->qdisc = new; - sch_tree_unlock(sch); + *old = qdisc_replace(sch, new, &cl->qdisc); return 0; } diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index f357f34d02d2..cfddb1c635c3 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -73,13 +73,7 @@ static int dsmark_graft(struct Qdisc *sch, unsigned long arg, new = &noop_qdisc; } - sch_tree_lock(sch); - *old = p->q; - p->q = new; - qdisc_tree_decrease_qlen(*old, (*old)->q.qlen); - qdisc_reset(*old); - sch_tree_unlock(sch); - + *old = qdisc_replace(sch, new, &p->q); return 0; } diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index b7ebe2c87586..089f3b667d36 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1215,11 +1215,7 @@ hfsc_graft_class(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, new = &noop_qdisc; } - sch_tree_lock(sch); - hfsc_purge_queue(sch, cl); - *old = cl->qdisc; - cl->qdisc = new; - sch_tree_unlock(sch); + *old = qdisc_replace(sch, new, &cl->qdisc); return 0; } diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 15ccd7f8fb2a..0efbcf358cd0 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1163,14 +1163,7 @@ static int htb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, cl->common.classid)) == NULL) return -ENOBUFS; - sch_tree_lock(sch); - *old = cl->un.leaf.q; - cl->un.leaf.q = new; - if (*old != NULL) { - qdisc_tree_decrease_qlen(*old, (*old)->q.qlen); - qdisc_reset(*old); - } - sch_tree_unlock(sch); + *old = qdisc_replace(sch, new, &cl->un.leaf.q); return 0; } diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index 4e904ca0af9d..a0103a138563 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -303,13 +303,7 @@ static int multiq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, if (new == NULL) new = &noop_qdisc; - sch_tree_lock(sch); - *old = q->queues[band]; - q->queues[band] = new; - qdisc_tree_decrease_qlen(*old, (*old)->q.qlen); - qdisc_reset(*old); - sch_tree_unlock(sch); - + *old = qdisc_replace(sch, new, &q->queues[band]); return 0; } diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 5abd1d9de989..0a6ddaf7f561 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -1037,15 +1037,7 @@ static int netem_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, { struct netem_sched_data *q = qdisc_priv(sch); - sch_tree_lock(sch); - *old = q->qdisc; - q->qdisc = new; - if (*old) { - qdisc_tree_decrease_qlen(*old, (*old)->q.qlen); - qdisc_reset(*old); - } - sch_tree_unlock(sch); - + *old = qdisc_replace(sch, new, &q->qdisc); return 0; } diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index ba6487f2741f..1b4aaec64a24 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -268,13 +268,7 @@ static int prio_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, if (new == NULL) new = &noop_qdisc; - sch_tree_lock(sch); - *old = q->queues[band]; - q->queues[band] = new; - qdisc_tree_decrease_qlen(*old, (*old)->q.qlen); - qdisc_reset(*old); - sch_tree_unlock(sch); - + *old = qdisc_replace(sch, new, &q->queues[band]); return 0; } diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 3dc3a6e56052..b5c52caf2e73 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -617,11 +617,7 @@ static int qfq_graft_class(struct Qdisc *sch, unsigned long arg, new = &noop_qdisc; } - sch_tree_lock(sch); - qfq_purge_queue(cl); - *old = cl->qdisc; - cl->qdisc = new; - sch_tree_unlock(sch); + *old = qdisc_replace(sch, new, &cl->qdisc); return 0; } diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 6c0534cc7758..d5abcee454d8 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -313,12 +313,7 @@ static int red_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, if (new == NULL) new = &noop_qdisc; - sch_tree_lock(sch); - *old = q->qdisc; - q->qdisc = new; - qdisc_tree_decrease_qlen(*old, (*old)->q.qlen); - qdisc_reset(*old); - sch_tree_unlock(sch); + *old = qdisc_replace(sch, new, &q->qdisc); return 0; } diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index 5bbb6332ec57..0e74e55fda15 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -606,12 +606,7 @@ static int sfb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, if (new == NULL) new = &noop_qdisc; - sch_tree_lock(sch); - *old = q->qdisc; - q->qdisc = new; - qdisc_tree_decrease_qlen(*old, (*old)->q.qlen); - qdisc_reset(*old); - sch_tree_unlock(sch); + *old = qdisc_replace(sch, new, &q->qdisc); return 0; } diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index a4afde14e865..56a1aef3495f 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -502,13 +502,7 @@ static int tbf_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, if (new == NULL) new = &noop_qdisc; - sch_tree_lock(sch); - *old = q->qdisc; - q->qdisc = new; - qdisc_tree_decrease_qlen(*old, (*old)->q.qlen); - qdisc_reset(*old); - sch_tree_unlock(sch); - + *old = qdisc_replace(sch, new, &q->qdisc); return 0; } -- cgit v1.2.3-71-gd317 From 2ccccf5fb43ff62b2b96cc58d95fc0b3596516e4 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Thu, 25 Feb 2016 14:55:01 -0800 Subject: net_sched: update hierarchical backlog too When the bottom qdisc decides to, for example, drop some packet, it calls qdisc_tree_decrease_qlen() to update the queue length for all its ancestors, we need to update the backlog too to keep the stats on root qdisc accurate. Cc: Jamal Hadi Salim Acked-by: Jamal Hadi Salim Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/net/codel.h | 4 ++++ include/net/sch_generic.h | 5 +++-- net/sched/sch_api.c | 8 +++++--- net/sched/sch_cbq.c | 5 +++-- net/sched/sch_choke.c | 6 ++++-- net/sched/sch_codel.c | 10 ++++++---- net/sched/sch_drr.c | 3 ++- net/sched/sch_fq.c | 4 +++- net/sched/sch_fq_codel.c | 17 ++++++++++++----- net/sched/sch_hfsc.c | 3 ++- net/sched/sch_hhf.c | 10 +++++++--- net/sched/sch_htb.c | 10 ++++++---- net/sched/sch_multiq.c | 8 +++++--- net/sched/sch_netem.c | 3 ++- net/sched/sch_pie.c | 5 +++-- net/sched/sch_prio.c | 7 ++++--- net/sched/sch_qfq.c | 3 ++- net/sched/sch_red.c | 3 ++- net/sched/sch_sfb.c | 3 ++- net/sched/sch_sfq.c | 16 +++++++++------- net/sched/sch_tbf.c | 7 +++++-- 21 files changed, 91 insertions(+), 49 deletions(-) (limited to 'include/net') diff --git a/include/net/codel.h b/include/net/codel.h index 267e70210061..d168aca115cc 100644 --- a/include/net/codel.h +++ b/include/net/codel.h @@ -162,12 +162,14 @@ struct codel_vars { * struct codel_stats - contains codel shared variables and stats * @maxpacket: largest packet we've seen so far * @drop_count: temp count of dropped packets in dequeue() + * @drop_len: bytes of dropped packets in dequeue() * ecn_mark: number of packets we ECN marked instead of dropping * ce_mark: number of packets CE marked because sojourn time was above ce_threshold */ struct codel_stats { u32 maxpacket; u32 drop_count; + u32 drop_len; u32 ecn_mark; u32 ce_mark; }; @@ -308,6 +310,7 @@ static struct sk_buff *codel_dequeue(struct Qdisc *sch, vars->rec_inv_sqrt); goto end; } + stats->drop_len += qdisc_pkt_len(skb); qdisc_drop(skb, sch); stats->drop_count++; skb = dequeue_func(vars, sch); @@ -330,6 +333,7 @@ static struct sk_buff *codel_dequeue(struct Qdisc *sch, if (params->ecn && INET_ECN_set_ce(skb)) { stats->ecn_mark++; } else { + stats->drop_len += qdisc_pkt_len(skb); qdisc_drop(skb, sch); stats->drop_count++; diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 8fdad9f7a2fb..e5bba897d206 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -396,7 +396,8 @@ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, struct Qdisc *qdisc); void qdisc_reset(struct Qdisc *qdisc); void qdisc_destroy(struct Qdisc *qdisc); -void qdisc_tree_decrease_qlen(struct Qdisc *qdisc, unsigned int n); +void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, unsigned int n, + unsigned int len); struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops); struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, @@ -716,7 +717,7 @@ static inline struct Qdisc *qdisc_replace(struct Qdisc *sch, struct Qdisc *new, old = *pold; *pold = new; if (old != NULL) { - qdisc_tree_decrease_qlen(old, old->q.qlen); + qdisc_tree_reduce_backlog(old, old->q.qlen, old->qstats.backlog); qdisc_reset(old); } sch_tree_unlock(sch); diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index de1e176e35cc..3b180ff72f79 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -744,14 +744,15 @@ static u32 qdisc_alloc_handle(struct net_device *dev) return 0; } -void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n) +void qdisc_tree_reduce_backlog(struct Qdisc *sch, unsigned int n, + unsigned int len) { const struct Qdisc_class_ops *cops; unsigned long cl; u32 parentid; int drops; - if (n == 0) + if (n == 0 && len == 0) return; drops = max_t(int, n, 0); rcu_read_lock(); @@ -774,11 +775,12 @@ void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n) cops->put(sch, cl); } sch->q.qlen -= n; + sch->qstats.backlog -= len; __qdisc_qstats_drop(sch, drops); } rcu_read_unlock(); } -EXPORT_SYMBOL(qdisc_tree_decrease_qlen); +EXPORT_SYMBOL(qdisc_tree_reduce_backlog); static void notify_and_destroy(struct net *net, struct sk_buff *skb, struct nlmsghdr *n, u32 clid, diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 7f8474cdce32..baafddf229ce 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1909,7 +1909,7 @@ static int cbq_delete(struct Qdisc *sch, unsigned long arg) { struct cbq_sched_data *q = qdisc_priv(sch); struct cbq_class *cl = (struct cbq_class *)arg; - unsigned int qlen; + unsigned int qlen, backlog; if (cl->filters || cl->children || cl == &q->link) return -EBUSY; @@ -1917,8 +1917,9 @@ static int cbq_delete(struct Qdisc *sch, unsigned long arg) sch_tree_lock(sch); qlen = cl->q->q.qlen; + backlog = cl->q->qstats.backlog; qdisc_reset(cl->q); - qdisc_tree_decrease_qlen(cl->q, qlen); + qdisc_tree_reduce_backlog(cl->q, qlen, backlog); if (cl->next_alive) cbq_deactivate_class(cl); diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index 5ffb8b8337c7..0a08c860eee4 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -128,8 +128,8 @@ static void choke_drop_by_idx(struct Qdisc *sch, unsigned int idx) choke_zap_tail_holes(q); qdisc_qstats_backlog_dec(sch, skb); + qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(skb)); qdisc_drop(skb, sch); - qdisc_tree_decrease_qlen(sch, 1); --sch->q.qlen; } @@ -456,6 +456,7 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt) old = q->tab; if (old) { unsigned int oqlen = sch->q.qlen, tail = 0; + unsigned dropped = 0; while (q->head != q->tail) { struct sk_buff *skb = q->tab[q->head]; @@ -467,11 +468,12 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt) ntab[tail++] = skb; continue; } + dropped += qdisc_pkt_len(skb); qdisc_qstats_backlog_dec(sch, skb); --sch->q.qlen; qdisc_drop(skb, sch); } - qdisc_tree_decrease_qlen(sch, oqlen - sch->q.qlen); + qdisc_tree_reduce_backlog(sch, oqlen - sch->q.qlen, dropped); q->head = 0; q->tail = tail; } diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c index 535007d5f0b5..9b7e2980ee5c 100644 --- a/net/sched/sch_codel.c +++ b/net/sched/sch_codel.c @@ -79,12 +79,13 @@ static struct sk_buff *codel_qdisc_dequeue(struct Qdisc *sch) skb = codel_dequeue(sch, &q->params, &q->vars, &q->stats, dequeue); - /* We cant call qdisc_tree_decrease_qlen() if our qlen is 0, + /* We cant call qdisc_tree_reduce_backlog() if our qlen is 0, * or HTB crashes. Defer it for next round. */ if (q->stats.drop_count && sch->q.qlen) { - qdisc_tree_decrease_qlen(sch, q->stats.drop_count); + qdisc_tree_reduce_backlog(sch, q->stats.drop_count, q->stats.drop_len); q->stats.drop_count = 0; + q->stats.drop_len = 0; } if (skb) qdisc_bstats_update(sch, skb); @@ -116,7 +117,7 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt) { struct codel_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_CODEL_MAX + 1]; - unsigned int qlen; + unsigned int qlen, dropped = 0; int err; if (!opt) @@ -156,10 +157,11 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt) while (sch->q.qlen > sch->limit) { struct sk_buff *skb = __skb_dequeue(&sch->q); + dropped += qdisc_pkt_len(skb); qdisc_qstats_backlog_dec(sch, skb); qdisc_drop(skb, sch); } - qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen); + qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped); sch_tree_unlock(sch); return 0; diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index b96c9a8e70ab..a63e879e8975 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -53,9 +53,10 @@ static struct drr_class *drr_find_class(struct Qdisc *sch, u32 classid) static void drr_purge_queue(struct drr_class *cl) { unsigned int len = cl->qdisc->q.qlen; + unsigned int backlog = cl->qdisc->qstats.backlog; qdisc_reset(cl->qdisc); - qdisc_tree_decrease_qlen(cl->qdisc, len); + qdisc_tree_reduce_backlog(cl->qdisc, len, backlog); } static const struct nla_policy drr_policy[TCA_DRR_MAX + 1] = { diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 109b2322778f..3c6a47d66a04 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -662,6 +662,7 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt) struct fq_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_FQ_MAX + 1]; int err, drop_count = 0; + unsigned drop_len = 0; u32 fq_log; if (!opt) @@ -736,10 +737,11 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt) if (!skb) break; + drop_len += qdisc_pkt_len(skb); kfree_skb(skb); drop_count++; } - qdisc_tree_decrease_qlen(sch, drop_count); + qdisc_tree_reduce_backlog(sch, drop_count, drop_len); sch_tree_unlock(sch); return err; diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 4c834e93dafb..d3fc8f9dd3d4 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -175,7 +175,7 @@ static unsigned int fq_codel_qdisc_drop(struct Qdisc *sch) static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct fq_codel_sched_data *q = qdisc_priv(sch); - unsigned int idx; + unsigned int idx, prev_backlog; struct fq_codel_flow *flow; int uninitialized_var(ret); @@ -203,6 +203,7 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch) if (++sch->q.qlen <= sch->limit) return NET_XMIT_SUCCESS; + prev_backlog = sch->qstats.backlog; q->drop_overlimit++; /* Return Congestion Notification only if we dropped a packet * from this flow. @@ -211,7 +212,7 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch) return NET_XMIT_CN; /* As we dropped a packet, better let upper stack know this */ - qdisc_tree_decrease_qlen(sch, 1); + qdisc_tree_reduce_backlog(sch, 1, prev_backlog - sch->qstats.backlog); return NET_XMIT_SUCCESS; } @@ -241,6 +242,7 @@ static struct sk_buff *fq_codel_dequeue(struct Qdisc *sch) struct fq_codel_flow *flow; struct list_head *head; u32 prev_drop_count, prev_ecn_mark; + unsigned int prev_backlog; begin: head = &q->new_flows; @@ -259,6 +261,7 @@ begin: prev_drop_count = q->cstats.drop_count; prev_ecn_mark = q->cstats.ecn_mark; + prev_backlog = sch->qstats.backlog; skb = codel_dequeue(sch, &q->cparams, &flow->cvars, &q->cstats, dequeue); @@ -276,12 +279,14 @@ begin: } qdisc_bstats_update(sch, skb); flow->deficit -= qdisc_pkt_len(skb); - /* We cant call qdisc_tree_decrease_qlen() if our qlen is 0, + /* We cant call qdisc_tree_reduce_backlog() if our qlen is 0, * or HTB crashes. Defer it for next round. */ if (q->cstats.drop_count && sch->q.qlen) { - qdisc_tree_decrease_qlen(sch, q->cstats.drop_count); + qdisc_tree_reduce_backlog(sch, q->cstats.drop_count, + q->cstats.drop_len); q->cstats.drop_count = 0; + q->cstats.drop_len = 0; } return skb; } @@ -372,11 +377,13 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt) while (sch->q.qlen > sch->limit) { struct sk_buff *skb = fq_codel_dequeue(sch); + q->cstats.drop_len += qdisc_pkt_len(skb); kfree_skb(skb); q->cstats.drop_count++; } - qdisc_tree_decrease_qlen(sch, q->cstats.drop_count); + qdisc_tree_reduce_backlog(sch, q->cstats.drop_count, q->cstats.drop_len); q->cstats.drop_count = 0; + q->cstats.drop_len = 0; sch_tree_unlock(sch); return 0; diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 089f3b667d36..d783d7cc3348 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -895,9 +895,10 @@ static void hfsc_purge_queue(struct Qdisc *sch, struct hfsc_class *cl) { unsigned int len = cl->qdisc->q.qlen; + unsigned int backlog = cl->qdisc->qstats.backlog; qdisc_reset(cl->qdisc); - qdisc_tree_decrease_qlen(cl->qdisc, len); + qdisc_tree_reduce_backlog(cl->qdisc, len, backlog); } static void diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index 86b04e31e60b..13d6f83ec491 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -382,6 +382,7 @@ static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch) struct hhf_sched_data *q = qdisc_priv(sch); enum wdrr_bucket_idx idx; struct wdrr_bucket *bucket; + unsigned int prev_backlog; idx = hhf_classify(skb, sch); @@ -409,6 +410,7 @@ static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch) if (++sch->q.qlen <= sch->limit) return NET_XMIT_SUCCESS; + prev_backlog = sch->qstats.backlog; q->drop_overlimit++; /* Return Congestion Notification only if we dropped a packet from this * bucket. @@ -417,7 +419,7 @@ static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch) return NET_XMIT_CN; /* As we dropped a packet, better let upper stack know this. */ - qdisc_tree_decrease_qlen(sch, 1); + qdisc_tree_reduce_backlog(sch, 1, prev_backlog - sch->qstats.backlog); return NET_XMIT_SUCCESS; } @@ -527,7 +529,7 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt) { struct hhf_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_HHF_MAX + 1]; - unsigned int qlen; + unsigned int qlen, prev_backlog; int err; u64 non_hh_quantum; u32 new_quantum = q->quantum; @@ -577,12 +579,14 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt) } qlen = sch->q.qlen; + prev_backlog = sch->qstats.backlog; while (sch->q.qlen > sch->limit) { struct sk_buff *skb = hhf_dequeue(sch); kfree_skb(skb); } - qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen); + qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, + prev_backlog - sch->qstats.backlog); sch_tree_unlock(sch); return 0; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 0efbcf358cd0..846a7f98cef9 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1265,7 +1265,6 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg) { struct htb_sched *q = qdisc_priv(sch); struct htb_class *cl = (struct htb_class *)arg; - unsigned int qlen; struct Qdisc *new_q = NULL; int last_child = 0; @@ -1285,9 +1284,11 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg) sch_tree_lock(sch); if (!cl->level) { - qlen = cl->un.leaf.q->q.qlen; + unsigned int qlen = cl->un.leaf.q->q.qlen; + unsigned int backlog = cl->un.leaf.q->qstats.backlog; + qdisc_reset(cl->un.leaf.q); - qdisc_tree_decrease_qlen(cl->un.leaf.q, qlen); + qdisc_tree_reduce_backlog(cl->un.leaf.q, qlen, backlog); } /* delete from hash and active; remainder in destroy_class */ @@ -1421,10 +1422,11 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, sch_tree_lock(sch); if (parent && !parent->level) { unsigned int qlen = parent->un.leaf.q->q.qlen; + unsigned int backlog = parent->un.leaf.q->qstats.backlog; /* turn parent into inner node */ qdisc_reset(parent->un.leaf.q); - qdisc_tree_decrease_qlen(parent->un.leaf.q, qlen); + qdisc_tree_reduce_backlog(parent->un.leaf.q, qlen, backlog); qdisc_destroy(parent->un.leaf.q); if (parent->prio_activity) htb_deactivate(q, parent); diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index a0103a138563..bcdd54bb101c 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -218,7 +218,8 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt) if (q->queues[i] != &noop_qdisc) { struct Qdisc *child = q->queues[i]; q->queues[i] = &noop_qdisc; - qdisc_tree_decrease_qlen(child, child->q.qlen); + qdisc_tree_reduce_backlog(child, child->q.qlen, + child->qstats.backlog); qdisc_destroy(child); } } @@ -238,8 +239,9 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt) q->queues[i] = child; if (old != &noop_qdisc) { - qdisc_tree_decrease_qlen(old, - old->q.qlen); + qdisc_tree_reduce_backlog(old, + old->q.qlen, + old->qstats.backlog); qdisc_destroy(old); } sch_tree_unlock(sch); diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 0a6ddaf7f561..9640bb39a5d2 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -598,7 +598,8 @@ deliver: if (unlikely(err != NET_XMIT_SUCCESS)) { if (net_xmit_drop_count(err)) { qdisc_qstats_drop(sch); - qdisc_tree_decrease_qlen(sch, 1); + qdisc_tree_reduce_backlog(sch, 1, + qdisc_pkt_len(skb)); } } goto tfifo_dequeue; diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index b783a446d884..71ae3b9629f9 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -183,7 +183,7 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt) { struct pie_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_PIE_MAX + 1]; - unsigned int qlen; + unsigned int qlen, dropped = 0; int err; if (!opt) @@ -232,10 +232,11 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt) while (sch->q.qlen > sch->limit) { struct sk_buff *skb = __skb_dequeue(&sch->q); + dropped += qdisc_pkt_len(skb); qdisc_qstats_backlog_dec(sch, skb); qdisc_drop(skb, sch); } - qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen); + qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped); sch_tree_unlock(sch); return 0; diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 1b4aaec64a24..fee1b15506b2 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -191,7 +191,7 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt) struct Qdisc *child = q->queues[i]; q->queues[i] = &noop_qdisc; if (child != &noop_qdisc) { - qdisc_tree_decrease_qlen(child, child->q.qlen); + qdisc_tree_reduce_backlog(child, child->q.qlen, child->qstats.backlog); qdisc_destroy(child); } } @@ -210,8 +210,9 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt) q->queues[i] = child; if (old != &noop_qdisc) { - qdisc_tree_decrease_qlen(old, - old->q.qlen); + qdisc_tree_reduce_backlog(old, + old->q.qlen, + old->qstats.backlog); qdisc_destroy(old); } sch_tree_unlock(sch); diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index b5c52caf2e73..8d2d8d953432 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -220,9 +220,10 @@ static struct qfq_class *qfq_find_class(struct Qdisc *sch, u32 classid) static void qfq_purge_queue(struct qfq_class *cl) { unsigned int len = cl->qdisc->q.qlen; + unsigned int backlog = cl->qdisc->qstats.backlog; qdisc_reset(cl->qdisc); - qdisc_tree_decrease_qlen(cl->qdisc, len); + qdisc_tree_reduce_backlog(cl->qdisc, len, backlog); } static const struct nla_policy qfq_policy[TCA_QFQ_MAX + 1] = { diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index d5abcee454d8..8c0508c0e287 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -210,7 +210,8 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt) q->flags = ctl->flags; q->limit = ctl->limit; if (child) { - qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen); + qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen, + q->qdisc->qstats.backlog); qdisc_destroy(q->qdisc); q->qdisc = child; } diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index 0e74e55fda15..c69611640fa5 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -510,7 +510,8 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt) sch_tree_lock(sch); - qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen); + qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen, + q->qdisc->qstats.backlog); qdisc_destroy(q->qdisc); q->qdisc = child; diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 3abab534eb5c..498f0a2cb47f 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -346,7 +346,7 @@ static int sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct sfq_sched_data *q = qdisc_priv(sch); - unsigned int hash; + unsigned int hash, dropped; sfq_index x, qlen; struct sfq_slot *slot; int uninitialized_var(ret); @@ -461,7 +461,7 @@ enqueue: return NET_XMIT_SUCCESS; qlen = slot->qlen; - sfq_drop(sch); + dropped = sfq_drop(sch); /* Return Congestion Notification only if we dropped a packet * from this flow. */ @@ -469,7 +469,7 @@ enqueue: return NET_XMIT_CN; /* As we dropped a packet, better let upper stack know this */ - qdisc_tree_decrease_qlen(sch, 1); + qdisc_tree_reduce_backlog(sch, 1, dropped); return NET_XMIT_SUCCESS; } @@ -537,6 +537,7 @@ static void sfq_rehash(struct Qdisc *sch) struct sfq_slot *slot; struct sk_buff_head list; int dropped = 0; + unsigned int drop_len = 0; __skb_queue_head_init(&list); @@ -565,6 +566,7 @@ static void sfq_rehash(struct Qdisc *sch) if (x >= SFQ_MAX_FLOWS) { drop: qdisc_qstats_backlog_dec(sch, skb); + drop_len += qdisc_pkt_len(skb); kfree_skb(skb); dropped++; continue; @@ -594,7 +596,7 @@ drop: } } sch->q.qlen -= dropped; - qdisc_tree_decrease_qlen(sch, dropped); + qdisc_tree_reduce_backlog(sch, dropped, drop_len); } static void sfq_perturbation(unsigned long arg) @@ -618,7 +620,7 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt) struct sfq_sched_data *q = qdisc_priv(sch); struct tc_sfq_qopt *ctl = nla_data(opt); struct tc_sfq_qopt_v1 *ctl_v1 = NULL; - unsigned int qlen; + unsigned int qlen, dropped = 0; struct red_parms *p = NULL; if (opt->nla_len < nla_attr_size(sizeof(*ctl))) @@ -667,8 +669,8 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt) qlen = sch->q.qlen; while (sch->q.qlen > q->limit) - sfq_drop(sch); - qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen); + dropped += sfq_drop(sch); + qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped); del_timer(&q->perturb_timer); if (q->perturb_period) { diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 56a1aef3495f..c2fbde742f37 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -160,6 +160,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch) struct tbf_sched_data *q = qdisc_priv(sch); struct sk_buff *segs, *nskb; netdev_features_t features = netif_skb_features(skb); + unsigned int len = 0, prev_len = qdisc_pkt_len(skb); int ret, nb; segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); @@ -172,6 +173,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch) nskb = segs->next; segs->next = NULL; qdisc_skb_cb(segs)->pkt_len = segs->len; + len += segs->len; ret = qdisc_enqueue(segs, q->qdisc); if (ret != NET_XMIT_SUCCESS) { if (net_xmit_drop_count(ret)) @@ -183,7 +185,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch) } sch->q.qlen += nb; if (nb > 1) - qdisc_tree_decrease_qlen(sch, 1 - nb); + qdisc_tree_reduce_backlog(sch, 1 - nb, prev_len - len); consume_skb(skb); return nb > 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP; } @@ -399,7 +401,8 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt) sch_tree_lock(sch); if (child) { - qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen); + qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen, + q->qdisc->qstats.backlog); qdisc_destroy(q->qdisc); q->qdisc = child; } -- cgit v1.2.3-71-gd317 From 6843e7a2abe7cac10c19702ffec90018df6f040d Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 26 Feb 2016 07:53:49 -0800 Subject: net: sched: consolidate offload decision in cls_u32 The offload decision was originally very basic and tied to if the dev implemented the appropriate ndo op hook. The next step is to allow the user to more flexibly define if any paticular rule should be offloaded or not. In order to have this logic in one function lift the current check into a helper routine tc_should_offload(). Signed-off-by: John Fastabend Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 5 +++++ net/sched/cls_u32.c | 8 ++++---- 2 files changed, 9 insertions(+), 4 deletions(-) (limited to 'include/net') diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 2121df574262..e64d20b81047 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -392,4 +392,9 @@ struct tc_cls_u32_offload { }; }; +static inline bool tc_should_offload(struct net_device *dev) +{ + return dev->netdev_ops->ndo_setup_tc; +} + #endif diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index d54bc942ea87..24e888b9b728 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -434,7 +434,7 @@ static void u32_remove_hw_knode(struct tcf_proto *tp, u32 handle) offload.type = TC_SETUP_CLSU32; offload.cls_u32 = &u32_offload; - if (dev->netdev_ops->ndo_setup_tc) { + if (tc_should_offload(dev)) { offload.cls_u32->command = TC_CLSU32_DELETE_KNODE; offload.cls_u32->knode.handle = handle; dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, @@ -451,7 +451,7 @@ static void u32_replace_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h) offload.type = TC_SETUP_CLSU32; offload.cls_u32 = &u32_offload; - if (dev->netdev_ops->ndo_setup_tc) { + if (tc_should_offload(dev)) { offload.cls_u32->command = TC_CLSU32_NEW_HNODE; offload.cls_u32->hnode.divisor = h->divisor; offload.cls_u32->hnode.handle = h->handle; @@ -471,7 +471,7 @@ static void u32_clear_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h) offload.type = TC_SETUP_CLSU32; offload.cls_u32 = &u32_offload; - if (dev->netdev_ops->ndo_setup_tc) { + if (tc_should_offload(dev)) { offload.cls_u32->command = TC_CLSU32_DELETE_HNODE; offload.cls_u32->hnode.divisor = h->divisor; offload.cls_u32->hnode.handle = h->handle; @@ -491,7 +491,7 @@ static void u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n) offload.type = TC_SETUP_CLSU32; offload.cls_u32 = &u32_offload; - if (dev->netdev_ops->ndo_setup_tc) { + if (tc_should_offload(dev)) { offload.cls_u32->command = TC_CLSU32_REPLACE_KNODE; offload.cls_u32->knode.handle = n->handle; offload.cls_u32->knode.fshift = n->fshift; -- cgit v1.2.3-71-gd317 From 2b6ab0d3aae6bf1e08118060b0c5565778cd6b21 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 26 Feb 2016 07:54:13 -0800 Subject: net: cls_u32: move TC offload feature bit into cls_u32 offload logic In the original series drivers would get offload requests for cls_u32 rules even if the feature bit is disabled. This meant the driver had to do a boiler plate check on the feature bit before adding/deleting the rule. This patch lifts the check into the core code and removes it from the driver specific case. Signed-off-by: John Fastabend Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 3 --- include/net/pkt_cls.h | 3 +++ 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/net') diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index cf4b729c92d7..b893ff8e65f5 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -8400,9 +8400,6 @@ int __ixgbe_setup_tc(struct net_device *dev, u32 handle, __be16 proto, if (TC_H_MAJ(handle) == TC_H_MAJ(TC_H_INGRESS) && tc->type == TC_SETUP_CLSU32) { - if (!(dev->features & NETIF_F_HW_TC)) - return -EINVAL; - switch (tc->cls_u32->command) { case TC_CLSU32_NEW_KNODE: case TC_CLSU32_REPLACE_KNODE: diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index e64d20b81047..6096e96fb78b 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -394,6 +394,9 @@ struct tc_cls_u32_offload { static inline bool tc_should_offload(struct net_device *dev) { + if (!(dev->features & NETIF_F_HW_TC)) + return false; + return dev->netdev_ops->ndo_setup_tc; } -- cgit v1.2.3-71-gd317 From 9e8ce79cd711d4dfe09d8bba6822cd9bb7db96bd Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 26 Feb 2016 07:54:39 -0800 Subject: net: sched: cls_u32 add bit to specify software only rules In the initial implementation the only way to stop a rule from being inserted into the hardware table was via the device feature flag. However this doesn't work well when working on an end host system where packets are expect to hit both the hardware and software datapaths. For example we can imagine a rule that will match an IP address and increment a field. If we install this rule in both hardware and software we may increment the field twice. To date we have only added support for the drop action so we have been able to ignore these cases. But as we extend the action support we will hit this example plus more such cases. Arguably these are not even corner cases in many working systems these cases will be common. To avoid forcing the driver to always abort (i.e. the above example) this patch adds a flag to add a rule in software only. A careful user can use this flag to build software and hardware datapaths that work together. One example we have found particularly useful is to use hardware resources to set the skb->mark on the skb when the match may be expensive to run in software but a mark lookup in a hash table is cheap. The idea here is hardware can do in one lookup what the u32 classifier may need to traverse multiple lists and hash tables to compute. The flag is only passed down on inserts. On deletion to avoid stale references in hardware we always try to remove a rule if it exists. The flags field is part of the classifier specific options. Although it is tempting to lift this into the generic structure doing this proves difficult do to how the tc netlink attributes are implemented along with how the dump/change routines are called. There is also precedence for putting seemingly generic pieces in the specific classifier options such as TCA_U32_POLICE, TCA_U32_ACT, etc. So although not ideal I've left FLAGS in the u32 options as well as it simplifies the code greatly and user space has already learned how to manage these bits ala 'tc' tool. Another thing if trying to update a rule we require the flags to be unchanged. This is to force user space, software u32 and the hardware u32 to keep in sync. Thanks to Simon Horman for catching this case. Signed-off-by: John Fastabend Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 13 +++++++++++-- include/uapi/linux/pkt_cls.h | 1 + net/sched/cls_u32.c | 37 +++++++++++++++++++++++++++---------- 3 files changed, 39 insertions(+), 12 deletions(-) (limited to 'include/net') diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 6096e96fb78b..bea14eee373e 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -392,12 +392,21 @@ struct tc_cls_u32_offload { }; }; -static inline bool tc_should_offload(struct net_device *dev) +/* tca flags definitions */ +#define TCA_CLS_FLAGS_SKIP_HW 1 + +static inline bool tc_should_offload(struct net_device *dev, u32 flags) { if (!(dev->features & NETIF_F_HW_TC)) return false; - return dev->netdev_ops->ndo_setup_tc; + if (flags & TCA_CLS_FLAGS_SKIP_HW) + return false; + + if (!dev->netdev_ops->ndo_setup_tc) + return false; + + return true; } #endif diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 439873775d49..9874f5680926 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -172,6 +172,7 @@ enum { TCA_U32_INDEV, TCA_U32_PCNT, TCA_U32_MARK, + TCA_U32_FLAGS, __TCA_U32_MAX }; diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 24e888b9b728..563cdad76448 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -59,6 +59,7 @@ struct tc_u_knode { #ifdef CONFIG_CLS_U32_PERF struct tc_u32_pcnt __percpu *pf; #endif + u32 flags; #ifdef CONFIG_CLS_U32_MARK u32 val; u32 mask; @@ -434,7 +435,7 @@ static void u32_remove_hw_knode(struct tcf_proto *tp, u32 handle) offload.type = TC_SETUP_CLSU32; offload.cls_u32 = &u32_offload; - if (tc_should_offload(dev)) { + if (tc_should_offload(dev, 0)) { offload.cls_u32->command = TC_CLSU32_DELETE_KNODE; offload.cls_u32->knode.handle = handle; dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, @@ -442,7 +443,9 @@ static void u32_remove_hw_knode(struct tcf_proto *tp, u32 handle) } } -static void u32_replace_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h) +static void u32_replace_hw_hnode(struct tcf_proto *tp, + struct tc_u_hnode *h, + u32 flags) { struct net_device *dev = tp->q->dev_queue->dev; struct tc_cls_u32_offload u32_offload = {0}; @@ -451,7 +454,7 @@ static void u32_replace_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h) offload.type = TC_SETUP_CLSU32; offload.cls_u32 = &u32_offload; - if (tc_should_offload(dev)) { + if (tc_should_offload(dev, flags)) { offload.cls_u32->command = TC_CLSU32_NEW_HNODE; offload.cls_u32->hnode.divisor = h->divisor; offload.cls_u32->hnode.handle = h->handle; @@ -471,7 +474,7 @@ static void u32_clear_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h) offload.type = TC_SETUP_CLSU32; offload.cls_u32 = &u32_offload; - if (tc_should_offload(dev)) { + if (tc_should_offload(dev, 0)) { offload.cls_u32->command = TC_CLSU32_DELETE_HNODE; offload.cls_u32->hnode.divisor = h->divisor; offload.cls_u32->hnode.handle = h->handle; @@ -482,7 +485,9 @@ static void u32_clear_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h) } } -static void u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n) +static void u32_replace_hw_knode(struct tcf_proto *tp, + struct tc_u_knode *n, + u32 flags) { struct net_device *dev = tp->q->dev_queue->dev; struct tc_cls_u32_offload u32_offload = {0}; @@ -491,7 +496,7 @@ static void u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n) offload.type = TC_SETUP_CLSU32; offload.cls_u32 = &u32_offload; - if (tc_should_offload(dev)) { + if (tc_should_offload(dev, flags)) { offload.cls_u32->command = TC_CLSU32_REPLACE_KNODE; offload.cls_u32->knode.handle = n->handle; offload.cls_u32->knode.fshift = n->fshift; @@ -679,6 +684,7 @@ static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = { [TCA_U32_SEL] = { .len = sizeof(struct tc_u32_sel) }, [TCA_U32_INDEV] = { .type = NLA_STRING, .len = IFNAMSIZ }, [TCA_U32_MARK] = { .len = sizeof(struct tc_u32_mark) }, + [TCA_U32_FLAGS] = { .type = NLA_U32 }, }; static int u32_set_parms(struct net *net, struct tcf_proto *tp, @@ -786,6 +792,7 @@ static struct tc_u_knode *u32_init_knode(struct tcf_proto *tp, #endif new->fshift = n->fshift; new->res = n->res; + new->flags = n->flags; RCU_INIT_POINTER(new->ht_down, n->ht_down); /* bump reference count as long as we hold pointer to structure */ @@ -825,7 +832,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, struct tc_u32_sel *s; struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_U32_MAX + 1]; - u32 htid; + u32 htid, flags = 0; int err; #ifdef CONFIG_CLS_U32_PERF size_t size; @@ -838,6 +845,9 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, if (err < 0) return err; + if (tb[TCA_U32_FLAGS]) + flags = nla_get_u32(tb[TCA_U32_FLAGS]); + n = (struct tc_u_knode *)*arg; if (n) { struct tc_u_knode *new; @@ -845,6 +855,9 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, if (TC_U32_KEY(n->handle) == 0) return -EINVAL; + if (n->flags != flags) + return -EINVAL; + new = u32_init_knode(tp, n); if (!new) return -ENOMEM; @@ -861,7 +874,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, u32_replace_knode(tp, tp_c, new); tcf_unbind_filter(tp, &n->res); call_rcu(&n->rcu, u32_delete_key_rcu); - u32_replace_hw_knode(tp, new); + u32_replace_hw_knode(tp, new, flags); return 0; } @@ -889,7 +902,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, rcu_assign_pointer(tp_c->hlist, ht); *arg = (unsigned long)ht; - u32_replace_hw_hnode(tp, ht); + u32_replace_hw_hnode(tp, ht, flags); return 0; } @@ -940,6 +953,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, RCU_INIT_POINTER(n->ht_up, ht); n->handle = handle; n->fshift = s->hmask ? ffs(ntohl(s->hmask)) - 1 : 0; + n->flags = flags; tcf_exts_init(&n->exts, TCA_U32_ACT, TCA_U32_POLICE); n->tp = tp; @@ -972,7 +986,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, RCU_INIT_POINTER(n->next, pins); rcu_assign_pointer(*ins, n); - u32_replace_hw_knode(tp, n); + u32_replace_hw_knode(tp, n, flags); *arg = (unsigned long)n; return 0; } @@ -1077,6 +1091,9 @@ static int u32_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, nla_put_u32(skb, TCA_U32_LINK, ht_down->handle)) goto nla_put_failure; + if (n->flags && nla_put_u32(skb, TCA_U32_FLAGS, n->flags)) + goto nla_put_failure; + #ifdef CONFIG_CLS_U32_MARK if ((n->val || n->mask)) { struct tc_u32_mark mark = {.val = n->val, -- cgit v1.2.3-71-gd317 From bfcd3a46617209454cfc0947ab093e37fd1e84ef Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 26 Feb 2016 17:32:23 +0100 Subject: Introduce devlink infrastructure Introduce devlink infrastructure for drivers to register and expose to userspace via generic Netlink interface. There are two basic objects defined: devlink - one instance for every "parent device", for example switch ASIC devlink port - one instance for every physical port of the device. This initial portion implements basic get/dump of objects to userspace. Also, port splitter and port type setting is implemented. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- MAINTAINERS | 8 + include/net/devlink.h | 140 ++++++++ include/uapi/linux/devlink.h | 72 +++++ net/Kconfig | 7 + net/core/Makefile | 1 + net/core/devlink.c | 738 +++++++++++++++++++++++++++++++++++++++++++ 6 files changed, 966 insertions(+) create mode 100644 include/net/devlink.h create mode 100644 include/uapi/linux/devlink.h create mode 100644 net/core/devlink.c (limited to 'include/net') diff --git a/MAINTAINERS b/MAINTAINERS index 12b764f4c93c..e45682745263 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3499,6 +3499,14 @@ F: include/linux/device-mapper.h F: include/linux/dm-*.h F: include/uapi/linux/dm-*.h +DEVLINK +M: Jiri Pirko +L: netdev@vger.kernel.org +S: Supported +F: net/core/devlink.c +F: include/net/devlink.h +F: include/uapi/linux/devlink.h + DIALOG SEMICONDUCTOR DRIVERS M: Support Opensource W: http://www.dialog-semiconductor.com/products diff --git a/include/net/devlink.h b/include/net/devlink.h new file mode 100644 index 000000000000..c37d257891d6 --- /dev/null +++ b/include/net/devlink.h @@ -0,0 +1,140 @@ +/* + * include/net/devlink.h - Network physical device Netlink interface + * Copyright (c) 2016 Mellanox Technologies. All rights reserved. + * Copyright (c) 2016 Jiri Pirko + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ +#ifndef _NET_DEVLINK_H_ +#define _NET_DEVLINK_H_ + +#include +#include +#include +#include +#include +#include +#include + +struct devlink_ops; + +struct devlink { + struct list_head list; + struct list_head port_list; + const struct devlink_ops *ops; + struct device *dev; + possible_net_t _net; + char priv[0] __aligned(NETDEV_ALIGN); +}; + +struct devlink_port { + struct list_head list; + struct devlink *devlink; + unsigned index; + bool registered; + enum devlink_port_type type; + enum devlink_port_type desired_type; + void *type_dev; + bool split; + u32 split_group; +}; + +struct devlink_ops { + size_t priv_size; + int (*port_type_set)(struct devlink_port *devlink_port, + enum devlink_port_type port_type); + int (*port_split)(struct devlink *devlink, unsigned int port_index, + unsigned int count); + int (*port_unsplit)(struct devlink *devlink, unsigned int port_index); +}; + +static inline void *devlink_priv(struct devlink *devlink) +{ + BUG_ON(!devlink); + return &devlink->priv; +} + +static inline struct devlink *priv_to_devlink(void *priv) +{ + BUG_ON(!priv); + return container_of(priv, struct devlink, priv); +} + +struct ib_device; + +#if IS_ENABLED(CONFIG_NET_DEVLINK) + +struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size); +int devlink_register(struct devlink *devlink, struct device *dev); +void devlink_unregister(struct devlink *devlink); +void devlink_free(struct devlink *devlink); +int devlink_port_register(struct devlink *devlink, + struct devlink_port *devlink_port, + unsigned int port_index); +void devlink_port_unregister(struct devlink_port *devlink_port); +void devlink_port_type_eth_set(struct devlink_port *devlink_port, + struct net_device *netdev); +void devlink_port_type_ib_set(struct devlink_port *devlink_port, + struct ib_device *ibdev); +void devlink_port_type_clear(struct devlink_port *devlink_port); +void devlink_port_split_set(struct devlink_port *devlink_port, + u32 split_group); + +#else + +static inline struct devlink *devlink_alloc(const struct devlink_ops *ops, + size_t priv_size) +{ + return kzalloc(sizeof(struct devlink) + priv_size, GFP_KERNEL); +} + +static inline int devlink_register(struct devlink *devlink, struct device *dev) +{ + return 0; +} + +static inline void devlink_unregister(struct devlink *devlink) +{ +} + +static inline void devlink_free(struct devlink *devlink) +{ + kfree(devlink); +} + +static inline int devlink_port_register(struct devlink *devlink, + struct devlink_port *devlink_port, + unsigned int port_index) +{ + return 0; +} + +static inline void devlink_port_unregister(struct devlink_port *devlink_port) +{ +} + +static inline void devlink_port_type_eth_set(struct devlink_port *devlink_port, + struct net_device *netdev) +{ +} + +static inline void devlink_port_type_ib_set(struct devlink_port *devlink_port, + struct ib_device *ibdev) +{ +} + +static inline void devlink_port_type_clear(struct devlink_port *devlink_port) +{ +} + +static inline void devlink_port_split_set(struct devlink_port *devlink_port, + u32 split_group) +{ +} + +#endif + +#endif /* _NET_DEVLINK_H_ */ diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h new file mode 100644 index 000000000000..c9fee5781eb1 --- /dev/null +++ b/include/uapi/linux/devlink.h @@ -0,0 +1,72 @@ +/* + * include/uapi/linux/devlink.h - Network physical device Netlink interface + * Copyright (c) 2016 Mellanox Technologies. All rights reserved. + * Copyright (c) 2016 Jiri Pirko + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef _UAPI_LINUX_DEVLINK_H_ +#define _UAPI_LINUX_DEVLINK_H_ + +#define DEVLINK_GENL_NAME "devlink" +#define DEVLINK_GENL_VERSION 0x1 +#define DEVLINK_GENL_MCGRP_CONFIG_NAME "config" + +enum devlink_command { + /* don't change the order or add anything between, this is ABI! */ + DEVLINK_CMD_UNSPEC, + + DEVLINK_CMD_GET, /* can dump */ + DEVLINK_CMD_SET, + DEVLINK_CMD_NEW, + DEVLINK_CMD_DEL, + + DEVLINK_CMD_PORT_GET, /* can dump */ + DEVLINK_CMD_PORT_SET, + DEVLINK_CMD_PORT_NEW, + DEVLINK_CMD_PORT_DEL, + + DEVLINK_CMD_PORT_SPLIT, + DEVLINK_CMD_PORT_UNSPLIT, + + /* add new commands above here */ + + __DEVLINK_CMD_MAX, + DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1 +}; + +enum devlink_port_type { + DEVLINK_PORT_TYPE_NOTSET, + DEVLINK_PORT_TYPE_AUTO, + DEVLINK_PORT_TYPE_ETH, + DEVLINK_PORT_TYPE_IB, +}; + +enum devlink_attr { + /* don't change the order or add anything between, this is ABI! */ + DEVLINK_ATTR_UNSPEC, + + /* bus name + dev name together are a handle for devlink entity */ + DEVLINK_ATTR_BUS_NAME, /* string */ + DEVLINK_ATTR_DEV_NAME, /* string */ + + DEVLINK_ATTR_PORT_INDEX, /* u32 */ + DEVLINK_ATTR_PORT_TYPE, /* u16 */ + DEVLINK_ATTR_PORT_DESIRED_TYPE, /* u16 */ + DEVLINK_ATTR_PORT_NETDEV_IFINDEX, /* u32 */ + DEVLINK_ATTR_PORT_NETDEV_NAME, /* string */ + DEVLINK_ATTR_PORT_IBDEV_NAME, /* string */ + DEVLINK_ATTR_PORT_SPLIT_COUNT, /* u32 */ + DEVLINK_ATTR_PORT_SPLIT_GROUP, /* u32 */ + + /* add new attributes above here, update the policy in devlink.c */ + + __DEVLINK_ATTR_MAX, + DEVLINK_ATTR_MAX = __DEVLINK_ATTR_MAX - 1 +}; + +#endif /* _UAPI_LINUX_DEVLINK_H_ */ diff --git a/net/Kconfig b/net/Kconfig index b80efecfc1a0..6c9cfb0d7639 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -396,6 +396,13 @@ config DST_CACHE bool "dst cache" default n +config NET_DEVLINK + tristate "Network physical/parent device Netlink interface" + help + Network physical/parent device Netlink interface provides + infrastructure to support access to physical chip-wide config and + monitoring. + endif # if NET # Used by archs to tell that they support BPF_JIT diff --git a/net/core/Makefile b/net/core/Makefile index 7a8fb8aef992..014422e2561f 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -25,3 +25,4 @@ obj-$(CONFIG_CGROUP_NET_PRIO) += netprio_cgroup.o obj-$(CONFIG_CGROUP_NET_CLASSID) += netclassid_cgroup.o obj-$(CONFIG_LWTUNNEL) += lwtunnel.o obj-$(CONFIG_DST_CACHE) += dst_cache.o +obj-$(CONFIG_NET_DEVLINK) += devlink.o diff --git a/net/core/devlink.c b/net/core/devlink.c new file mode 100644 index 000000000000..590fa561cb7f --- /dev/null +++ b/net/core/devlink.c @@ -0,0 +1,738 @@ +/* + * net/core/devlink.c - Network physical/parent device Netlink interface + * + * Heavily inspired by net/wireless/ + * Copyright (c) 2016 Mellanox Technologies. All rights reserved. + * Copyright (c) 2016 Jiri Pirko + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static LIST_HEAD(devlink_list); + +/* devlink_mutex + * + * An overall lock guarding every operation coming from userspace. + * It also guards devlink devices list and it is taken when + * driver registers/unregisters it. + */ +static DEFINE_MUTEX(devlink_mutex); + +/* devlink_port_mutex + * + * Shared lock to guard lists of ports in all devlink devices. + */ +static DEFINE_MUTEX(devlink_port_mutex); + +static struct net *devlink_net(const struct devlink *devlink) +{ + return read_pnet(&devlink->_net); +} + +static void devlink_net_set(struct devlink *devlink, struct net *net) +{ + write_pnet(&devlink->_net, net); +} + +static struct devlink *devlink_get_from_attrs(struct net *net, + struct nlattr **attrs) +{ + struct devlink *devlink; + char *busname; + char *devname; + + if (!attrs[DEVLINK_ATTR_BUS_NAME] || !attrs[DEVLINK_ATTR_DEV_NAME]) + return ERR_PTR(-EINVAL); + + busname = nla_data(attrs[DEVLINK_ATTR_BUS_NAME]); + devname = nla_data(attrs[DEVLINK_ATTR_DEV_NAME]); + + list_for_each_entry(devlink, &devlink_list, list) { + if (strcmp(devlink->dev->bus->name, busname) == 0 && + strcmp(dev_name(devlink->dev), devname) == 0 && + net_eq(devlink_net(devlink), net)) + return devlink; + } + + return ERR_PTR(-ENODEV); +} + +static struct devlink *devlink_get_from_info(struct genl_info *info) +{ + return devlink_get_from_attrs(genl_info_net(info), info->attrs); +} + +static struct devlink_port *devlink_port_get_by_index(struct devlink *devlink, + int port_index) +{ + struct devlink_port *devlink_port; + + list_for_each_entry(devlink_port, &devlink->port_list, list) { + if (devlink_port->index == port_index) + return devlink_port; + } + return NULL; +} + +static bool devlink_port_index_exists(struct devlink *devlink, int port_index) +{ + return devlink_port_get_by_index(devlink, port_index); +} + +static struct devlink_port *devlink_port_get_from_attrs(struct devlink *devlink, + struct nlattr **attrs) +{ + if (attrs[DEVLINK_ATTR_PORT_INDEX]) { + u32 port_index = nla_get_u32(attrs[DEVLINK_ATTR_PORT_INDEX]); + struct devlink_port *devlink_port; + + devlink_port = devlink_port_get_by_index(devlink, port_index); + if (!devlink_port) + return ERR_PTR(-ENODEV); + return devlink_port; + } + return ERR_PTR(-EINVAL); +} + +static struct devlink_port *devlink_port_get_from_info(struct devlink *devlink, + struct genl_info *info) +{ + return devlink_port_get_from_attrs(devlink, info->attrs); +} + +#define DEVLINK_NL_FLAG_NEED_PORT BIT(0) + +static int devlink_nl_pre_doit(const struct genl_ops *ops, + struct sk_buff *skb, struct genl_info *info) +{ + struct devlink *devlink; + + mutex_lock(&devlink_mutex); + devlink = devlink_get_from_info(info); + if (IS_ERR(devlink)) { + mutex_unlock(&devlink_mutex); + return PTR_ERR(devlink); + } + info->user_ptr[0] = devlink; + if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_PORT) { + struct devlink_port *devlink_port; + + mutex_lock(&devlink_port_mutex); + devlink_port = devlink_port_get_from_info(devlink, info); + if (IS_ERR(devlink_port)) { + mutex_unlock(&devlink_port_mutex); + mutex_unlock(&devlink_mutex); + return PTR_ERR(devlink_port); + } + info->user_ptr[1] = devlink_port; + } + return 0; +} + +static void devlink_nl_post_doit(const struct genl_ops *ops, + struct sk_buff *skb, struct genl_info *info) +{ + if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_PORT) + mutex_unlock(&devlink_port_mutex); + mutex_unlock(&devlink_mutex); +} + +static struct genl_family devlink_nl_family = { + .id = GENL_ID_GENERATE, + .name = DEVLINK_GENL_NAME, + .version = DEVLINK_GENL_VERSION, + .maxattr = DEVLINK_ATTR_MAX, + .netnsok = true, + .pre_doit = devlink_nl_pre_doit, + .post_doit = devlink_nl_post_doit, +}; + +enum devlink_multicast_groups { + DEVLINK_MCGRP_CONFIG, +}; + +static const struct genl_multicast_group devlink_nl_mcgrps[] = { + [DEVLINK_MCGRP_CONFIG] = { .name = DEVLINK_GENL_MCGRP_CONFIG_NAME }, +}; + +static int devlink_nl_put_handle(struct sk_buff *msg, struct devlink *devlink) +{ + if (nla_put_string(msg, DEVLINK_ATTR_BUS_NAME, devlink->dev->bus->name)) + return -EMSGSIZE; + if (nla_put_string(msg, DEVLINK_ATTR_DEV_NAME, dev_name(devlink->dev))) + return -EMSGSIZE; + return 0; +} + +static int devlink_nl_fill(struct sk_buff *msg, struct devlink *devlink, + enum devlink_command cmd, u32 portid, + u32 seq, int flags) +{ + void *hdr; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static void devlink_notify(struct devlink *devlink, enum devlink_command cmd) +{ + struct sk_buff *msg; + int err; + + WARN_ON(cmd != DEVLINK_CMD_NEW && cmd != DEVLINK_CMD_DEL); + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + err = devlink_nl_fill(msg, devlink, cmd, 0, 0, 0); + if (err) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), + msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); +} + +static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink, + struct devlink_port *devlink_port, + enum devlink_command cmd, u32 portid, + u32 seq, int flags) +{ + void *hdr; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index)) + goto nla_put_failure; + if (nla_put_u16(msg, DEVLINK_ATTR_PORT_TYPE, devlink_port->type)) + goto nla_put_failure; + if (devlink_port->desired_type != DEVLINK_PORT_TYPE_NOTSET && + nla_put_u16(msg, DEVLINK_ATTR_PORT_DESIRED_TYPE, + devlink_port->desired_type)) + goto nla_put_failure; + if (devlink_port->type == DEVLINK_PORT_TYPE_ETH) { + struct net_device *netdev = devlink_port->type_dev; + + if (netdev && + (nla_put_u32(msg, DEVLINK_ATTR_PORT_NETDEV_IFINDEX, + netdev->ifindex) || + nla_put_string(msg, DEVLINK_ATTR_PORT_NETDEV_NAME, + netdev->name))) + goto nla_put_failure; + } + if (devlink_port->type == DEVLINK_PORT_TYPE_IB) { + struct ib_device *ibdev = devlink_port->type_dev; + + if (ibdev && + nla_put_string(msg, DEVLINK_ATTR_PORT_IBDEV_NAME, + ibdev->name)) + goto nla_put_failure; + } + if (devlink_port->split && + nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_GROUP, + devlink_port->split_group)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static void devlink_port_notify(struct devlink_port *devlink_port, + enum devlink_command cmd) +{ + struct devlink *devlink = devlink_port->devlink; + struct sk_buff *msg; + int err; + + if (!devlink_port->registered) + return; + + WARN_ON(cmd != DEVLINK_CMD_PORT_NEW && cmd != DEVLINK_CMD_PORT_DEL); + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + err = devlink_nl_port_fill(msg, devlink, devlink_port, cmd, 0, 0, 0); + if (err) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), + msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); +} + +static int devlink_nl_cmd_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct sk_buff *msg; + int err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_fill(msg, devlink, DEVLINK_CMD_NEW, + info->snd_portid, info->snd_seq, 0); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int devlink_nl_cmd_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink *devlink; + int start = cb->args[0]; + int idx = 0; + int err; + + mutex_lock(&devlink_mutex); + list_for_each_entry(devlink, &devlink_list, list) { + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + continue; + if (idx < start) { + idx++; + continue; + } + err = devlink_nl_fill(msg, devlink, DEVLINK_CMD_NEW, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI); + if (err) + goto out; + idx++; + } +out: + mutex_unlock(&devlink_mutex); + + cb->args[0] = idx; + return msg->len; +} + +static int devlink_nl_cmd_port_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_port *devlink_port = info->user_ptr[1]; + struct sk_buff *msg; + int err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_port_fill(msg, devlink, devlink_port, + DEVLINK_CMD_PORT_NEW, + info->snd_portid, info->snd_seq, 0); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int devlink_nl_cmd_port_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink *devlink; + struct devlink_port *devlink_port; + int start = cb->args[0]; + int idx = 0; + int err; + + mutex_lock(&devlink_mutex); + mutex_lock(&devlink_port_mutex); + list_for_each_entry(devlink, &devlink_list, list) { + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + continue; + list_for_each_entry(devlink_port, &devlink->port_list, list) { + if (idx < start) { + idx++; + continue; + } + err = devlink_nl_port_fill(msg, devlink, devlink_port, + DEVLINK_CMD_NEW, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI); + if (err) + goto out; + idx++; + } + } +out: + mutex_unlock(&devlink_port_mutex); + mutex_unlock(&devlink_mutex); + + cb->args[0] = idx; + return msg->len; +} + +static int devlink_port_type_set(struct devlink *devlink, + struct devlink_port *devlink_port, + enum devlink_port_type port_type) + +{ + int err; + + if (devlink->ops && devlink->ops->port_type_set) { + if (port_type == DEVLINK_PORT_TYPE_NOTSET) + return -EINVAL; + err = devlink->ops->port_type_set(devlink_port, port_type); + if (err) + return err; + devlink_port->desired_type = port_type; + devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); + return 0; + } + return -EOPNOTSUPP; +} + +static int devlink_nl_cmd_port_set_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_port *devlink_port = info->user_ptr[1]; + int err; + + if (info->attrs[DEVLINK_ATTR_PORT_TYPE]) { + enum devlink_port_type port_type; + + port_type = nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_TYPE]); + err = devlink_port_type_set(devlink, devlink_port, port_type); + if (err) + return err; + } + return 0; +} + +static int devlink_port_split(struct devlink *devlink, + u32 port_index, u32 count) + +{ + if (devlink->ops && devlink->ops->port_split) + return devlink->ops->port_split(devlink, port_index, count); + return -EOPNOTSUPP; +} + +static int devlink_nl_cmd_port_split_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + u32 port_index; + u32 count; + + if (!info->attrs[DEVLINK_ATTR_PORT_INDEX] || + !info->attrs[DEVLINK_ATTR_PORT_SPLIT_COUNT]) + return -EINVAL; + + port_index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); + count = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_SPLIT_COUNT]); + return devlink_port_split(devlink, port_index, count); +} + +static int devlink_port_unsplit(struct devlink *devlink, u32 port_index) + +{ + if (devlink->ops && devlink->ops->port_unsplit) + return devlink->ops->port_unsplit(devlink, port_index); + return -EOPNOTSUPP; +} + +static int devlink_nl_cmd_port_unsplit_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + u32 port_index; + + if (!info->attrs[DEVLINK_ATTR_PORT_INDEX]) + return -EINVAL; + + port_index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); + return devlink_port_unsplit(devlink, port_index); +} + +static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32 }, + [DEVLINK_ATTR_PORT_TYPE] = { .type = NLA_U16 }, + [DEVLINK_ATTR_PORT_SPLIT_COUNT] = { .type = NLA_U32 }, +}; + +static const struct genl_ops devlink_nl_ops[] = { + { + .cmd = DEVLINK_CMD_GET, + .doit = devlink_nl_cmd_get_doit, + .dumpit = devlink_nl_cmd_get_dumpit, + .policy = devlink_nl_policy, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_PORT_GET, + .doit = devlink_nl_cmd_port_get_doit, + .dumpit = devlink_nl_cmd_port_get_dumpit, + .policy = devlink_nl_policy, + .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_PORT_SET, + .doit = devlink_nl_cmd_port_set_doit, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, + }, + { + .cmd = DEVLINK_CMD_PORT_SPLIT, + .doit = devlink_nl_cmd_port_split_doit, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = DEVLINK_CMD_PORT_UNSPLIT, + .doit = devlink_nl_cmd_port_unsplit_doit, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + }, +}; + +/** + * devlink_alloc - Allocate new devlink instance resources + * + * @ops: ops + * @priv_size: size of user private data + * + * Allocate new devlink instance resources, including devlink index + * and name. + */ +struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size) +{ + struct devlink *devlink; + + devlink = kzalloc(sizeof(*devlink) + priv_size, GFP_KERNEL); + if (!devlink) + return NULL; + devlink->ops = ops; + devlink_net_set(devlink, &init_net); + INIT_LIST_HEAD(&devlink->port_list); + return devlink; +} +EXPORT_SYMBOL_GPL(devlink_alloc); + +/** + * devlink_register - Register devlink instance + * + * @devlink: devlink + */ +int devlink_register(struct devlink *devlink, struct device *dev) +{ + mutex_lock(&devlink_mutex); + devlink->dev = dev; + list_add_tail(&devlink->list, &devlink_list); + devlink_notify(devlink, DEVLINK_CMD_NEW); + mutex_unlock(&devlink_mutex); + return 0; +} +EXPORT_SYMBOL_GPL(devlink_register); + +/** + * devlink_unregister - Unregister devlink instance + * + * @devlink: devlink + */ +void devlink_unregister(struct devlink *devlink) +{ + mutex_lock(&devlink_mutex); + devlink_notify(devlink, DEVLINK_CMD_DEL); + list_del(&devlink->list); + mutex_unlock(&devlink_mutex); +} +EXPORT_SYMBOL_GPL(devlink_unregister); + +/** + * devlink_free - Free devlink instance resources + * + * @devlink: devlink + */ +void devlink_free(struct devlink *devlink) +{ + kfree(devlink); +} +EXPORT_SYMBOL_GPL(devlink_free); + +/** + * devlink_port_register - Register devlink port + * + * @devlink: devlink + * @devlink_port: devlink port + * @port_index + * + * Register devlink port with provided port index. User can use + * any indexing, even hw-related one. devlink_port structure + * is convenient to be embedded inside user driver private structure. + * Note that the caller should take care of zeroing the devlink_port + * structure. + */ +int devlink_port_register(struct devlink *devlink, + struct devlink_port *devlink_port, + unsigned int port_index) +{ + mutex_lock(&devlink_port_mutex); + if (devlink_port_index_exists(devlink, port_index)) { + mutex_unlock(&devlink_port_mutex); + return -EEXIST; + } + devlink_port->devlink = devlink; + devlink_port->index = port_index; + devlink_port->type = DEVLINK_PORT_TYPE_NOTSET; + devlink_port->registered = true; + list_add_tail(&devlink_port->list, &devlink->port_list); + mutex_unlock(&devlink_port_mutex); + devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); + return 0; +} +EXPORT_SYMBOL_GPL(devlink_port_register); + +/** + * devlink_port_unregister - Unregister devlink port + * + * @devlink_port: devlink port + */ +void devlink_port_unregister(struct devlink_port *devlink_port) +{ + devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_DEL); + mutex_lock(&devlink_port_mutex); + list_del(&devlink_port->list); + mutex_unlock(&devlink_port_mutex); +} +EXPORT_SYMBOL_GPL(devlink_port_unregister); + +static void __devlink_port_type_set(struct devlink_port *devlink_port, + enum devlink_port_type type, + void *type_dev) +{ + devlink_port->type = type; + devlink_port->type_dev = type_dev; + devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); +} + +/** + * devlink_port_type_eth_set - Set port type to Ethernet + * + * @devlink_port: devlink port + * @netdev: related netdevice + */ +void devlink_port_type_eth_set(struct devlink_port *devlink_port, + struct net_device *netdev) +{ + return __devlink_port_type_set(devlink_port, + DEVLINK_PORT_TYPE_ETH, netdev); +} +EXPORT_SYMBOL_GPL(devlink_port_type_eth_set); + +/** + * devlink_port_type_ib_set - Set port type to InfiniBand + * + * @devlink_port: devlink port + * @ibdev: related IB device + */ +void devlink_port_type_ib_set(struct devlink_port *devlink_port, + struct ib_device *ibdev) +{ + return __devlink_port_type_set(devlink_port, + DEVLINK_PORT_TYPE_IB, ibdev); +} +EXPORT_SYMBOL_GPL(devlink_port_type_ib_set); + +/** + * devlink_port_type_clear - Clear port type + * + * @devlink_port: devlink port + */ +void devlink_port_type_clear(struct devlink_port *devlink_port) +{ + return __devlink_port_type_set(devlink_port, + DEVLINK_PORT_TYPE_NOTSET, NULL); +} +EXPORT_SYMBOL_GPL(devlink_port_type_clear); + +/** + * devlink_port_split_set - Set port is split + * + * @devlink_port: devlink port + * @split_group: split group - identifies group split port is part of + */ +void devlink_port_split_set(struct devlink_port *devlink_port, + u32 split_group) +{ + devlink_port->split = true; + devlink_port->split_group = split_group; + devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); +} +EXPORT_SYMBOL_GPL(devlink_port_split_set); + +static int __init devlink_module_init(void) +{ + return genl_register_family_with_ops_groups(&devlink_nl_family, + devlink_nl_ops, + devlink_nl_mcgrps); +} + +static void __exit devlink_module_exit(void) +{ + genl_unregister_family(&devlink_nl_family); +} + +module_init(devlink_module_init); +module_exit(devlink_module_exit); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Jiri Pirko "); +MODULE_DESCRIPTION("Network physical device Netlink interface"); +MODULE_ALIAS_GENL_FAMILY(DEVLINK_GENL_NAME); -- cgit v1.2.3-71-gd317 From fb2dabad69f099fb9c03a44276778911da50ba29 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Fri, 26 Feb 2016 13:16:00 -0500 Subject: net: dsa: support VLAN filtering switchdev attr When a user explicitly requests VLAN filtering with something like: # echo 1 > /sys/class/net//bridge/vlan_filtering Switchdev propagates a SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING port attribute. Add support for it in the DSA layer with a new port_vlan_filtering function to let drivers toggle 802.1Q filtering on user demand. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- include/net/dsa.h | 2 ++ net/dsa/slave.c | 21 +++++++++++++++++++++ 2 files changed, 23 insertions(+) (limited to 'include/net') diff --git a/include/net/dsa.h b/include/net/dsa.h index 3dd54867174a..26c0a3fa009a 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -305,6 +305,8 @@ struct dsa_switch_driver { /* * VLAN support */ + int (*port_vlan_filtering)(struct dsa_switch *ds, int port, + bool vlan_filtering); int (*port_vlan_prepare)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan, struct switchdev_trans *trans); diff --git a/net/dsa/slave.c b/net/dsa/slave.c index cde29239b60d..27bf03d11670 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -317,6 +317,24 @@ static int dsa_slave_stp_update(struct net_device *dev, u8 state) return ret; } +static int dsa_slave_vlan_filtering(struct net_device *dev, + const struct switchdev_attr *attr, + struct switchdev_trans *trans) +{ + struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_switch *ds = p->parent; + + /* bridge skips -EOPNOTSUPP, so skip the prepare phase */ + if (switchdev_trans_ph_prepare(trans)) + return 0; + + if (ds->drv->port_vlan_filtering) + return ds->drv->port_vlan_filtering(ds, p->port, + attr->u.vlan_filtering); + + return 0; +} + static int dsa_slave_port_attr_set(struct net_device *dev, const struct switchdev_attr *attr, struct switchdev_trans *trans) @@ -333,6 +351,9 @@ static int dsa_slave_port_attr_set(struct net_device *dev, ret = ds->drv->port_stp_update(ds, p->port, attr->u.stp_state); break; + case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING: + ret = dsa_slave_vlan_filtering(dev, attr, trans); + break; default: ret = -EOPNOTSUPP; break; -- cgit v1.2.3-71-gd317 From ef6980b6becb1afd9d82a4f043749a10ae81bf14 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Sat, 27 Feb 2016 08:08:54 -0500 Subject: introduce IFE action This action allows for a sending side to encapsulate arbitrary metadata which is decapsulated by the receiving end. The sender runs in encoding mode and the receiver in decode mode. Both sender and receiver must specify the same ethertype. At some point we hope to have a registered ethertype and we'll then provide a default so the user doesnt have to specify it. For now we enforce the user specify it. Lets show example usage where we encode icmp from a sender towards a receiver with an skbmark of 17; both sender and receiver use ethertype of 0xdead to interop. YYYY: Lets start with Receiver-side policy config: xxx: add an ingress qdisc sudo tc qdisc add dev $ETH ingress xxx: any packets with ethertype 0xdead will be subjected to ife decoding xxx: we then restart the classification so we can match on icmp at prio 3 sudo $TC filter add dev $ETH parent ffff: prio 2 protocol 0xdead \ u32 match u32 0 0 flowid 1:1 \ action ife decode reclassify xxx: on restarting the classification from above if it was an icmp xxx: packet, then match it here and continue to the next rule at prio 4 xxx: which will match based on skb mark of 17 sudo tc filter add dev $ETH parent ffff: prio 3 protocol ip \ u32 match ip protocol 1 0xff flowid 1:1 \ action continue xxx: match on skbmark of 0x11 (decimal 17) and accept sudo tc filter add dev $ETH parent ffff: prio 4 protocol ip \ handle 0x11 fw flowid 1:1 \ action ok xxx: Lets show the decoding policy sudo tc -s filter ls dev $ETH parent ffff: protocol 0xdead xxx: filter pref 2 u32 filter pref 2 u32 fh 800: ht divisor 1 filter pref 2 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:1 (rule hit 0 success 0) match 00000000/00000000 at 0 (success 0 ) action order 1: ife decode action reclassify index 1 ref 1 bind 1 installed 14 sec used 14 sec type: 0x0 Metadata: allow mark allow hash allow prio allow qmap Action statistics: Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 xxx: Observe that above lists all metadatum it can decode. Typically these submodules will already be compiled into a monolithic kernel or loaded as modules YYYY: Lets show the sender side now .. xxx: Add an egress qdisc on the sender netdev sudo tc qdisc add dev $ETH root handle 1: prio xxx: xxx: Match all icmp packets to 192.168.122.237/24, then xxx: tag the packet with skb mark of decimal 17, then xxx: Encode it with: xxx: ethertype 0xdead xxx: add skb->mark to whitelist of metadatum to send xxx: rewrite target dst MAC address to 02:15:15:15:15:15 xxx: sudo $TC filter add dev $ETH parent 1: protocol ip prio 10 u32 \ match ip dst 192.168.122.237/24 \ match ip protocol 1 0xff \ flowid 1:2 \ action skbedit mark 17 \ action ife encode \ type 0xDEAD \ allow mark \ dst 02:15:15:15:15:15 xxx: Lets show the encoding policy sudo tc -s filter ls dev $ETH parent 1: protocol ip xxx: filter pref 10 u32 filter pref 10 u32 fh 800: ht divisor 1 filter pref 10 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:2 (rule hit 0 success 0) match c0a87aed/ffffffff at 16 (success 0 ) match 00010000/00ff0000 at 8 (success 0 ) action order 1: skbedit mark 17 index 6 ref 1 bind 1 Action statistics: Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 action order 2: ife encode action pipe index 3 ref 1 bind 1 dst MAC: 02:15:15:15:15:15 type: 0xDEAD Metadata: allow mark Action statistics: Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 xxx: test by sending ping from sender to destination Signed-off-by: Jamal Hadi Salim Acked-by: Cong Wang Signed-off-by: David S. Miller --- include/net/tc_act/tc_ife.h | 61 +++ include/uapi/linux/tc_act/tc_ife.h | 38 ++ net/sched/Kconfig | 12 + net/sched/Makefile | 1 + net/sched/act_ife.c | 870 +++++++++++++++++++++++++++++++++++++ 5 files changed, 982 insertions(+) create mode 100644 include/net/tc_act/tc_ife.h create mode 100644 include/uapi/linux/tc_act/tc_ife.h create mode 100644 net/sched/act_ife.c (limited to 'include/net') diff --git a/include/net/tc_act/tc_ife.h b/include/net/tc_act/tc_ife.h new file mode 100644 index 000000000000..dc9a09aefb33 --- /dev/null +++ b/include/net/tc_act/tc_ife.h @@ -0,0 +1,61 @@ +#ifndef __NET_TC_IFE_H +#define __NET_TC_IFE_H + +#include +#include +#include +#include + +#define IFE_METAHDRLEN 2 +struct tcf_ife_info { + struct tcf_common common; + u8 eth_dst[ETH_ALEN]; + u8 eth_src[ETH_ALEN]; + u16 eth_type; + u16 flags; + /* list of metaids allowed */ + struct list_head metalist; +}; +#define to_ife(a) \ + container_of(a->priv, struct tcf_ife_info, common) + +struct tcf_meta_info { + const struct tcf_meta_ops *ops; + void *metaval; + u16 metaid; + struct list_head metalist; +}; + +struct tcf_meta_ops { + u16 metaid; /*Maintainer provided ID */ + u16 metatype; /*netlink attribute type (look at net/netlink.h) */ + const char *name; + const char *synopsis; + struct list_head list; + int (*check_presence)(struct sk_buff *, struct tcf_meta_info *); + int (*encode)(struct sk_buff *, void *, struct tcf_meta_info *); + int (*decode)(struct sk_buff *, void *, u16 len); + int (*get)(struct sk_buff *skb, struct tcf_meta_info *mi); + int (*alloc)(struct tcf_meta_info *, void *); + void (*release)(struct tcf_meta_info *); + int (*validate)(void *val, int len); + struct module *owner; +}; + +#define MODULE_ALIAS_IFE_META(metan) MODULE_ALIAS("ifemeta" __stringify_1(metan)) + +int ife_get_meta_u32(struct sk_buff *skb, struct tcf_meta_info *mi); +int ife_get_meta_u16(struct sk_buff *skb, struct tcf_meta_info *mi); +int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen, + const void *dval); +int ife_alloc_meta_u32(struct tcf_meta_info *mi, void *metaval); +int ife_alloc_meta_u16(struct tcf_meta_info *mi, void *metaval); +int ife_check_meta_u32(u32 metaval, struct tcf_meta_info *mi); +int ife_encode_meta_u32(u32 metaval, void *skbdata, struct tcf_meta_info *mi); +int ife_validate_meta_u32(void *val, int len); +int ife_validate_meta_u16(void *val, int len); +void ife_release_meta_gen(struct tcf_meta_info *mi); +int register_ife_op(struct tcf_meta_ops *mops); +int unregister_ife_op(struct tcf_meta_ops *mops); + +#endif /* __NET_TC_IFE_H */ diff --git a/include/uapi/linux/tc_act/tc_ife.h b/include/uapi/linux/tc_act/tc_ife.h new file mode 100644 index 000000000000..d648ff66586f --- /dev/null +++ b/include/uapi/linux/tc_act/tc_ife.h @@ -0,0 +1,38 @@ +#ifndef __UAPI_TC_IFE_H +#define __UAPI_TC_IFE_H + +#include +#include + +#define TCA_ACT_IFE 25 +/* Flag bits for now just encoding/decoding; mutually exclusive */ +#define IFE_ENCODE 1 +#define IFE_DECODE 0 + +struct tc_ife { + tc_gen; + __u16 flags; +}; + +/*XXX: We need to encode the total number of bytes consumed */ +enum { + TCA_IFE_UNSPEC, + TCA_IFE_PARMS, + TCA_IFE_TM, + TCA_IFE_DMAC, + TCA_IFE_SMAC, + TCA_IFE_TYPE, + TCA_IFE_METALST, + __TCA_IFE_MAX +}; +#define TCA_IFE_MAX (__TCA_IFE_MAX - 1) + +#define IFE_META_SKBMARK 1 +#define IFE_META_HASHID 2 +#define IFE_META_PRIO 3 +#define IFE_META_QMAP 4 +/*Can be overridden at runtime by module option*/ +#define __IFE_META_MAX 5 +#define IFE_META_MAX (__IFE_META_MAX - 1) + +#endif diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 82830824fb1f..4d48ef57e564 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -739,6 +739,18 @@ config NET_ACT_CONNMARK To compile this code as a module, choose M here: the module will be called act_connmark. +config NET_ACT_IFE + tristate "Inter-FE action based on IETF ForCES InterFE LFB" + depends on NET_CLS_ACT + ---help--- + Say Y here to allow for sourcing and terminating metadata + For details refer to netdev01 paper: + "Distributing Linux Traffic Control Classifier-Action Subsystem" + Authors: Jamal Hadi Salim and Damascene M. Joachimpillai + + To compile this code as a module, choose M here: the + module will be called act_ife. + config NET_CLS_IND bool "Incoming device classification" depends on NET_CLS_U32 || NET_CLS_FW diff --git a/net/sched/Makefile b/net/sched/Makefile index 690c1689e090..3d176671b0e1 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -19,6 +19,7 @@ obj-$(CONFIG_NET_ACT_CSUM) += act_csum.o obj-$(CONFIG_NET_ACT_VLAN) += act_vlan.o obj-$(CONFIG_NET_ACT_BPF) += act_bpf.o obj-$(CONFIG_NET_ACT_CONNMARK) += act_connmark.o +obj-$(CONFIG_NET_ACT_IFE) += act_ife.o obj-$(CONFIG_NET_SCH_FIFO) += sch_fifo.o obj-$(CONFIG_NET_SCH_CBQ) += sch_cbq.o obj-$(CONFIG_NET_SCH_HTB) += sch_htb.o diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c new file mode 100644 index 000000000000..6e7ec257790d --- /dev/null +++ b/net/sched/act_ife.c @@ -0,0 +1,870 @@ +/* + * net/sched/ife.c Inter-FE action based on ForCES WG InterFE LFB + * + * Refer to: + * draft-ietf-forces-interfelfb-03 + * and + * netdev01 paper: + * "Distributing Linux Traffic Control Classifier-Action + * Subsystem" + * Authors: Jamal Hadi Salim and Damascene M. Joachimpillai + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * copyright Jamal Hadi Salim (2015) + * +*/ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define IFE_TAB_MASK 15 + +static int ife_net_id; +static int max_metacnt = IFE_META_MAX + 1; + +static const struct nla_policy ife_policy[TCA_IFE_MAX + 1] = { + [TCA_IFE_PARMS] = { .len = sizeof(struct tc_ife)}, + [TCA_IFE_DMAC] = { .len = ETH_ALEN}, + [TCA_IFE_SMAC] = { .len = ETH_ALEN}, + [TCA_IFE_TYPE] = { .type = NLA_U16}, +}; + +/* Caller takes care of presenting data in network order +*/ +int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen, const void *dval) +{ + u32 *tlv = (u32 *)(skbdata); + u16 totlen = nla_total_size(dlen); /*alignment + hdr */ + char *dptr = (char *)tlv + NLA_HDRLEN; + u32 htlv = attrtype << 16 | totlen; + + *tlv = htonl(htlv); + memset(dptr, 0, totlen - NLA_HDRLEN); + memcpy(dptr, dval, dlen); + + return totlen; +} +EXPORT_SYMBOL_GPL(ife_tlv_meta_encode); + +int ife_get_meta_u32(struct sk_buff *skb, struct tcf_meta_info *mi) +{ + if (mi->metaval) + return nla_put_u32(skb, mi->metaid, *(u32 *)mi->metaval); + else + return nla_put(skb, mi->metaid, 0, NULL); +} +EXPORT_SYMBOL_GPL(ife_get_meta_u32); + +int ife_check_meta_u32(u32 metaval, struct tcf_meta_info *mi) +{ + if (metaval || mi->metaval) + return 8; /* T+L+V == 2+2+4 */ + + return 0; +} +EXPORT_SYMBOL_GPL(ife_check_meta_u32); + +int ife_encode_meta_u32(u32 metaval, void *skbdata, struct tcf_meta_info *mi) +{ + u32 edata = metaval; + + if (mi->metaval) + edata = *(u32 *)mi->metaval; + else if (metaval) + edata = metaval; + + if (!edata) /* will not encode */ + return 0; + + edata = htonl(edata); + return ife_tlv_meta_encode(skbdata, mi->metaid, 4, &edata); +} +EXPORT_SYMBOL_GPL(ife_encode_meta_u32); + +int ife_get_meta_u16(struct sk_buff *skb, struct tcf_meta_info *mi) +{ + if (mi->metaval) + return nla_put_u16(skb, mi->metaid, *(u16 *)mi->metaval); + else + return nla_put(skb, mi->metaid, 0, NULL); +} +EXPORT_SYMBOL_GPL(ife_get_meta_u16); + +int ife_alloc_meta_u32(struct tcf_meta_info *mi, void *metaval) +{ + mi->metaval = kmemdup(&metaval, sizeof(u32), GFP_KERNEL); + if (!mi->metaval) + return -ENOMEM; + + return 0; +} +EXPORT_SYMBOL_GPL(ife_alloc_meta_u32); + +int ife_alloc_meta_u16(struct tcf_meta_info *mi, void *metaval) +{ + mi->metaval = kmemdup(&metaval, sizeof(u16), GFP_KERNEL); + if (!mi->metaval) + return -ENOMEM; + + return 0; +} +EXPORT_SYMBOL_GPL(ife_alloc_meta_u16); + +void ife_release_meta_gen(struct tcf_meta_info *mi) +{ + kfree(mi->metaval); +} +EXPORT_SYMBOL_GPL(ife_release_meta_gen); + +int ife_validate_meta_u32(void *val, int len) +{ + if (len == 4) + return 0; + + return -EINVAL; +} +EXPORT_SYMBOL_GPL(ife_validate_meta_u32); + +int ife_validate_meta_u16(void *val, int len) +{ + /* length will include padding */ + if (len == NLA_ALIGN(2)) + return 0; + + return -EINVAL; +} +EXPORT_SYMBOL_GPL(ife_validate_meta_u16); + +static LIST_HEAD(ifeoplist); +static DEFINE_RWLOCK(ife_mod_lock); + +static struct tcf_meta_ops *find_ife_oplist(u16 metaid) +{ + struct tcf_meta_ops *o; + + read_lock(&ife_mod_lock); + list_for_each_entry(o, &ifeoplist, list) { + if (o->metaid == metaid) { + if (!try_module_get(o->owner)) + o = NULL; + read_unlock(&ife_mod_lock); + return o; + } + } + read_unlock(&ife_mod_lock); + + return NULL; +} + +int register_ife_op(struct tcf_meta_ops *mops) +{ + struct tcf_meta_ops *m; + + if (!mops->metaid || !mops->metatype || !mops->name || + !mops->check_presence || !mops->encode || !mops->decode || + !mops->get || !mops->alloc) + return -EINVAL; + + write_lock(&ife_mod_lock); + + list_for_each_entry(m, &ifeoplist, list) { + if (m->metaid == mops->metaid || + (strcmp(mops->name, m->name) == 0)) { + write_unlock(&ife_mod_lock); + return -EEXIST; + } + } + + if (!mops->release) + mops->release = ife_release_meta_gen; + + list_add_tail(&mops->list, &ifeoplist); + write_unlock(&ife_mod_lock); + return 0; +} +EXPORT_SYMBOL_GPL(unregister_ife_op); + +int unregister_ife_op(struct tcf_meta_ops *mops) +{ + struct tcf_meta_ops *m; + int err = -ENOENT; + + write_lock(&ife_mod_lock); + list_for_each_entry(m, &ifeoplist, list) { + if (m->metaid == mops->metaid) { + list_del(&mops->list); + err = 0; + break; + } + } + write_unlock(&ife_mod_lock); + + return err; +} +EXPORT_SYMBOL_GPL(register_ife_op); + +static int ife_validate_metatype(struct tcf_meta_ops *ops, void *val, int len) +{ + int ret = 0; + /* XXX: unfortunately cant use nla_policy at this point + * because a length of 0 is valid in the case of + * "allow". "use" semantics do enforce for proper + * length and i couldve use nla_policy but it makes it hard + * to use it just for that.. + */ + if (ops->validate) + return ops->validate(val, len); + + if (ops->metatype == NLA_U32) + ret = ife_validate_meta_u32(val, len); + else if (ops->metatype == NLA_U16) + ret = ife_validate_meta_u16(val, len); + + return ret; +} + +/* called when adding new meta information + * under ife->tcf_lock +*/ +static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid, + void *val, int len) +{ + struct tcf_meta_ops *ops = find_ife_oplist(metaid); + int ret = 0; + + if (!ops) { + ret = -ENOENT; +#ifdef CONFIG_MODULES + spin_unlock_bh(&ife->tcf_lock); + rtnl_unlock(); + request_module("ifemeta%u", metaid); + rtnl_lock(); + spin_lock_bh(&ife->tcf_lock); + ops = find_ife_oplist(metaid); +#endif + } + + if (ops) { + ret = 0; + if (len) + ret = ife_validate_metatype(ops, val, len); + + module_put(ops->owner); + } + + return ret; +} + +/* called when adding new meta information + * under ife->tcf_lock +*/ +static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval, + int len) +{ + struct tcf_meta_info *mi = NULL; + struct tcf_meta_ops *ops = find_ife_oplist(metaid); + int ret = 0; + + if (!ops) + return -ENOENT; + + mi = kzalloc(sizeof(*mi), GFP_KERNEL); + if (!mi) { + /*put back what find_ife_oplist took */ + module_put(ops->owner); + return -ENOMEM; + } + + mi->metaid = metaid; + mi->ops = ops; + if (len > 0) { + ret = ops->alloc(mi, metaval); + if (ret != 0) { + kfree(mi); + module_put(ops->owner); + return ret; + } + } + + list_add_tail(&mi->metalist, &ife->metalist); + + return ret; +} + +static int use_all_metadata(struct tcf_ife_info *ife) +{ + struct tcf_meta_ops *o; + int rc = 0; + int installed = 0; + + list_for_each_entry(o, &ifeoplist, list) { + rc = add_metainfo(ife, o->metaid, NULL, 0); + if (rc == 0) + installed += 1; + } + + if (installed) + return 0; + else + return -EINVAL; +} + +static int dump_metalist(struct sk_buff *skb, struct tcf_ife_info *ife) +{ + struct tcf_meta_info *e; + struct nlattr *nest; + unsigned char *b = skb_tail_pointer(skb); + int total_encoded = 0; + + /*can only happen on decode */ + if (list_empty(&ife->metalist)) + return 0; + + nest = nla_nest_start(skb, TCA_IFE_METALST); + if (!nest) + goto out_nlmsg_trim; + + list_for_each_entry(e, &ife->metalist, metalist) { + if (!e->ops->get(skb, e)) + total_encoded += 1; + } + + if (!total_encoded) + goto out_nlmsg_trim; + + nla_nest_end(skb, nest); + + return 0; + +out_nlmsg_trim: + nlmsg_trim(skb, b); + return -1; +} + +/* under ife->tcf_lock */ +static void _tcf_ife_cleanup(struct tc_action *a, int bind) +{ + struct tcf_ife_info *ife = a->priv; + struct tcf_meta_info *e, *n; + + list_for_each_entry_safe(e, n, &ife->metalist, metalist) { + module_put(e->ops->owner); + list_del(&e->metalist); + if (e->metaval) { + if (e->ops->release) + e->ops->release(e); + else + kfree(e->metaval); + } + kfree(e); + } +} + +static void tcf_ife_cleanup(struct tc_action *a, int bind) +{ + struct tcf_ife_info *ife = a->priv; + + spin_lock_bh(&ife->tcf_lock); + _tcf_ife_cleanup(a, bind); + spin_unlock_bh(&ife->tcf_lock); +} + +/* under ife->tcf_lock */ +static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb) +{ + int len = 0; + int rc = 0; + int i = 0; + void *val; + + for (i = 1; i < max_metacnt; i++) { + if (tb[i]) { + val = nla_data(tb[i]); + len = nla_len(tb[i]); + + rc = load_metaops_and_vet(ife, i, val, len); + if (rc != 0) + return rc; + + rc = add_metainfo(ife, i, val, len); + if (rc) + return rc; + } + } + + return rc; +} + +static int tcf_ife_init(struct net *net, struct nlattr *nla, + struct nlattr *est, struct tc_action *a, + int ovr, int bind) +{ + struct tc_action_net *tn = net_generic(net, ife_net_id); + struct nlattr *tb[TCA_IFE_MAX + 1]; + struct nlattr *tb2[IFE_META_MAX + 1]; + struct tcf_ife_info *ife; + struct tc_ife *parm; + u16 ife_type = 0; + u8 *daddr = NULL; + u8 *saddr = NULL; + int ret = 0; + int err; + + err = nla_parse_nested(tb, TCA_IFE_MAX, nla, ife_policy); + if (err < 0) + return err; + + if (!tb[TCA_IFE_PARMS]) + return -EINVAL; + + parm = nla_data(tb[TCA_IFE_PARMS]); + + if (parm->flags & IFE_ENCODE) { + /* Until we get issued the ethertype, we cant have + * a default.. + **/ + if (!tb[TCA_IFE_TYPE]) { + pr_info("You MUST pass etherype for encoding\n"); + return -EINVAL; + } + } + + if (!tcf_hash_check(tn, parm->index, a, bind)) { + ret = tcf_hash_create(tn, parm->index, est, a, sizeof(*ife), + bind, false); + if (ret) + return ret; + ret = ACT_P_CREATED; + } else { + if (bind) /* dont override defaults */ + return 0; + tcf_hash_release(a, bind); + if (!ovr) + return -EEXIST; + } + + ife = to_ife(a); + ife->flags = parm->flags; + + if (parm->flags & IFE_ENCODE) { + ife_type = nla_get_u16(tb[TCA_IFE_TYPE]); + if (tb[TCA_IFE_DMAC]) + daddr = nla_data(tb[TCA_IFE_DMAC]); + if (tb[TCA_IFE_SMAC]) + saddr = nla_data(tb[TCA_IFE_SMAC]); + } + + spin_lock_bh(&ife->tcf_lock); + ife->tcf_action = parm->action; + + if (parm->flags & IFE_ENCODE) { + if (daddr) + ether_addr_copy(ife->eth_dst, daddr); + else + eth_zero_addr(ife->eth_dst); + + if (saddr) + ether_addr_copy(ife->eth_src, saddr); + else + eth_zero_addr(ife->eth_src); + + ife->eth_type = ife_type; + } + + if (ret == ACT_P_CREATED) + INIT_LIST_HEAD(&ife->metalist); + + if (tb[TCA_IFE_METALST]) { + err = nla_parse_nested(tb2, IFE_META_MAX, tb[TCA_IFE_METALST], + NULL); + if (err) { +metadata_parse_err: + if (ret == ACT_P_CREATED) + _tcf_ife_cleanup(a, bind); + + spin_unlock_bh(&ife->tcf_lock); + return err; + } + + err = populate_metalist(ife, tb2); + if (err) + goto metadata_parse_err; + + } else { + /* if no passed metadata allow list or passed allow-all + * then here we process by adding as many supported metadatum + * as we can. You better have at least one else we are + * going to bail out + */ + err = use_all_metadata(ife); + if (err) { + if (ret == ACT_P_CREATED) + _tcf_ife_cleanup(a, bind); + + spin_unlock_bh(&ife->tcf_lock); + return err; + } + } + + spin_unlock_bh(&ife->tcf_lock); + + if (ret == ACT_P_CREATED) + tcf_hash_insert(tn, a); + + return ret; +} + +static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind, + int ref) +{ + unsigned char *b = skb_tail_pointer(skb); + struct tcf_ife_info *ife = a->priv; + struct tc_ife opt = { + .index = ife->tcf_index, + .refcnt = ife->tcf_refcnt - ref, + .bindcnt = ife->tcf_bindcnt - bind, + .action = ife->tcf_action, + .flags = ife->flags, + }; + struct tcf_t t; + + if (nla_put(skb, TCA_IFE_PARMS, sizeof(opt), &opt)) + goto nla_put_failure; + + t.install = jiffies_to_clock_t(jiffies - ife->tcf_tm.install); + t.lastuse = jiffies_to_clock_t(jiffies - ife->tcf_tm.lastuse); + t.expires = jiffies_to_clock_t(ife->tcf_tm.expires); + if (nla_put(skb, TCA_IFE_TM, sizeof(t), &t)) + goto nla_put_failure; + + if (!is_zero_ether_addr(ife->eth_dst)) { + if (nla_put(skb, TCA_IFE_DMAC, ETH_ALEN, ife->eth_dst)) + goto nla_put_failure; + } + + if (!is_zero_ether_addr(ife->eth_src)) { + if (nla_put(skb, TCA_IFE_SMAC, ETH_ALEN, ife->eth_src)) + goto nla_put_failure; + } + + if (nla_put(skb, TCA_IFE_TYPE, 2, &ife->eth_type)) + goto nla_put_failure; + + if (dump_metalist(skb, ife)) { + /*ignore failure to dump metalist */ + pr_info("Failed to dump metalist\n"); + } + + return skb->len; + +nla_put_failure: + nlmsg_trim(skb, b); + return -1; +} + +int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife, + u16 metaid, u16 mlen, void *mdata) +{ + struct tcf_meta_info *e; + + /* XXX: use hash to speed up */ + list_for_each_entry(e, &ife->metalist, metalist) { + if (metaid == e->metaid) { + if (e->ops) { + /* We check for decode presence already */ + return e->ops->decode(skb, mdata, mlen); + } + } + } + + return 0; +} + +struct ifeheadr { + __be16 metalen; + u8 tlv_data[]; +}; + +struct meta_tlvhdr { + __be16 type; + __be16 len; +}; + +static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, + struct tcf_result *res) +{ + struct tcf_ife_info *ife = a->priv; + int action = ife->tcf_action; + struct ifeheadr *ifehdr = (struct ifeheadr *)skb->data; + u16 ifehdrln = ifehdr->metalen; + struct meta_tlvhdr *tlv = (struct meta_tlvhdr *)(ifehdr->tlv_data); + + spin_lock(&ife->tcf_lock); + bstats_update(&ife->tcf_bstats, skb); + ife->tcf_tm.lastuse = jiffies; + spin_unlock(&ife->tcf_lock); + + ifehdrln = ntohs(ifehdrln); + if (unlikely(!pskb_may_pull(skb, ifehdrln))) { + spin_lock(&ife->tcf_lock); + ife->tcf_qstats.drops++; + spin_unlock(&ife->tcf_lock); + return TC_ACT_SHOT; + } + + skb_set_mac_header(skb, ifehdrln); + __skb_pull(skb, ifehdrln); + skb->protocol = eth_type_trans(skb, skb->dev); + ifehdrln -= IFE_METAHDRLEN; + + while (ifehdrln > 0) { + u8 *tlvdata = (u8 *)tlv; + u16 mtype = tlv->type; + u16 mlen = tlv->len; + + mtype = ntohs(mtype); + mlen = ntohs(mlen); + + if (find_decode_metaid(skb, ife, mtype, (mlen - 4), + (void *)(tlvdata + 4))) { + /* abuse overlimits to count when we receive metadata + * but dont have an ops for it + */ + pr_info_ratelimited("Unknown metaid %d alnlen %d\n", + mtype, mlen); + ife->tcf_qstats.overlimits++; + } + + tlvdata += mlen; + ifehdrln -= mlen; + tlv = (struct meta_tlvhdr *)tlvdata; + } + + skb_reset_network_header(skb); + return action; +} + +/*XXX: check if we can do this at install time instead of current + * send data path +**/ +static int ife_get_sz(struct sk_buff *skb, struct tcf_ife_info *ife) +{ + struct tcf_meta_info *e, *n; + int tot_run_sz = 0, run_sz = 0; + + list_for_each_entry_safe(e, n, &ife->metalist, metalist) { + if (e->ops->check_presence) { + run_sz = e->ops->check_presence(skb, e); + tot_run_sz += run_sz; + } + } + + return tot_run_sz; +} + +static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, + struct tcf_result *res) +{ + struct tcf_ife_info *ife = a->priv; + int action = ife->tcf_action; + struct ethhdr *oethh; /* outer ether header */ + struct ethhdr *iethh; /* inner eth header */ + struct tcf_meta_info *e; + /* + OUTERHDR:TOTMETALEN:{TLVHDR:Metadatum:TLVHDR..}:ORIGDATA + where ORIGDATA = original ethernet header ... + */ + u16 metalen = ife_get_sz(skb, ife); + int hdrm = metalen + skb->dev->hard_header_len + IFE_METAHDRLEN; + unsigned int skboff = skb->dev->hard_header_len; + u32 at = G_TC_AT(skb->tc_verd); + int new_len = skb->len + hdrm; + bool exceed_mtu = false; + int err; + + if (at & AT_EGRESS) { + if (new_len > skb->dev->mtu) + exceed_mtu = true; + } + + spin_lock(&ife->tcf_lock); + bstats_update(&ife->tcf_bstats, skb); + ife->tcf_tm.lastuse = jiffies; + + if (!metalen) { /* no metadata to send */ + /* abuse overlimits to count when we allow packet + * with no metadata + */ + ife->tcf_qstats.overlimits++; + spin_unlock(&ife->tcf_lock); + return action; + } + /* could be stupid policy setup or mtu config + * so lets be conservative.. */ + if ((action == TC_ACT_SHOT) || exceed_mtu) { + ife->tcf_qstats.drops++; + spin_unlock(&ife->tcf_lock); + return TC_ACT_SHOT; + } + + iethh = eth_hdr(skb); + + err = skb_cow_head(skb, hdrm); + if (unlikely(err)) { + ife->tcf_qstats.drops++; + spin_unlock(&ife->tcf_lock); + return TC_ACT_SHOT; + } + + if (!(at & AT_EGRESS)) + skb_push(skb, skb->dev->hard_header_len); + + __skb_push(skb, hdrm); + memcpy(skb->data, iethh, skb->mac_len); + skb_reset_mac_header(skb); + oethh = eth_hdr(skb); + + /*total metadata length */ + metalen += IFE_METAHDRLEN; + metalen = htons(metalen); + memcpy((skb->data + skboff), &metalen, IFE_METAHDRLEN); + skboff += IFE_METAHDRLEN; + + /* XXX: we dont have a clever way of telling encode to + * not repeat some of the computations that are done by + * ops->presence_check... + */ + list_for_each_entry(e, &ife->metalist, metalist) { + if (e->ops->encode) { + err = e->ops->encode(skb, (void *)(skb->data + skboff), + e); + } + if (err < 0) { + /* too corrupt to keep around if overwritten */ + ife->tcf_qstats.drops++; + spin_unlock(&ife->tcf_lock); + return TC_ACT_SHOT; + } + skboff += err; + } + + if (!is_zero_ether_addr(ife->eth_src)) + ether_addr_copy(oethh->h_source, ife->eth_src); + else + ether_addr_copy(oethh->h_source, iethh->h_source); + if (!is_zero_ether_addr(ife->eth_dst)) + ether_addr_copy(oethh->h_dest, ife->eth_dst); + else + ether_addr_copy(oethh->h_dest, iethh->h_dest); + oethh->h_proto = htons(ife->eth_type); + + if (!(at & AT_EGRESS)) + skb_pull(skb, skb->dev->hard_header_len); + + spin_unlock(&ife->tcf_lock); + + return action; +} + +static int tcf_ife_act(struct sk_buff *skb, const struct tc_action *a, + struct tcf_result *res) +{ + struct tcf_ife_info *ife = a->priv; + + if (ife->flags & IFE_ENCODE) + return tcf_ife_encode(skb, a, res); + + if (!(ife->flags & IFE_ENCODE)) + return tcf_ife_decode(skb, a, res); + + pr_info_ratelimited("unknown failure(policy neither de/encode\n"); + spin_lock(&ife->tcf_lock); + bstats_update(&ife->tcf_bstats, skb); + ife->tcf_tm.lastuse = jiffies; + ife->tcf_qstats.drops++; + spin_unlock(&ife->tcf_lock); + + return TC_ACT_SHOT; +} + +static int tcf_ife_walker(struct net *net, struct sk_buff *skb, + struct netlink_callback *cb, int type, + struct tc_action *a) +{ + struct tc_action_net *tn = net_generic(net, ife_net_id); + + return tcf_generic_walker(tn, skb, cb, type, a); +} + +static int tcf_ife_search(struct net *net, struct tc_action *a, u32 index) +{ + struct tc_action_net *tn = net_generic(net, ife_net_id); + + return tcf_hash_search(tn, a, index); +} + +static struct tc_action_ops act_ife_ops = { + .kind = "ife", + .type = TCA_ACT_IFE, + .owner = THIS_MODULE, + .act = tcf_ife_act, + .dump = tcf_ife_dump, + .cleanup = tcf_ife_cleanup, + .init = tcf_ife_init, + .walk = tcf_ife_walker, + .lookup = tcf_ife_search, +}; + +static __net_init int ife_init_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, ife_net_id); + + return tc_action_net_init(tn, &act_ife_ops, IFE_TAB_MASK); +} + +static void __net_exit ife_exit_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, ife_net_id); + + tc_action_net_exit(tn); +} + +static struct pernet_operations ife_net_ops = { + .init = ife_init_net, + .exit = ife_exit_net, + .id = &ife_net_id, + .size = sizeof(struct tc_action_net), +}; + +static int __init ife_init_module(void) +{ + return tcf_register_action(&act_ife_ops, &ife_net_ops); +} + +static void __exit ife_cleanup_module(void) +{ + tcf_unregister_action(&act_ife_ops, &ife_net_ops); +} + +module_init(ife_init_module); +module_exit(ife_cleanup_module); + +MODULE_AUTHOR("Jamal Hadi Salim(2015)"); +MODULE_DESCRIPTION("Inter-FE LFB action"); +MODULE_LICENSE("GPL"); -- cgit v1.2.3-71-gd317 From 822c868532cae2cc1c51f4f18ab61c194d98aaf6 Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Sat, 27 Feb 2016 00:32:15 -0800 Subject: net: ipv4: Convert IP network timestamps to be y2038 safe ICMP timestamp messages and IP source route options require timestamps to be in milliseconds modulo 24 hours from midnight UT format. Add inet_current_timestamp() function to support this. The function returns the required timestamp in network byte order. Timestamp calculation is also changed to call ktime_get_real_ts64() which uses struct timespec64. struct timespec64 is y2038 safe. Previously it called getnstimeofday() which uses struct timespec. struct timespec is not y2038 safe. Signed-off-by: Deepa Dinamani Cc: "David S. Miller" Cc: Alexey Kuznetsov Cc: Hideaki YOSHIFUJI Cc: James Morris Cc: Patrick McHardy Acked-by: YOSHIFUJI Hideaki Acked-by: Arnd Bergmann Signed-off-by: David S. Miller --- include/net/ip.h | 2 ++ net/ipv4/af_inet.c | 26 ++++++++++++++++++++++++++ net/ipv4/icmp.c | 5 +---- net/ipv4/ip_options.c | 14 ++++++-------- 4 files changed, 35 insertions(+), 12 deletions(-) (limited to 'include/net') diff --git a/include/net/ip.h b/include/net/ip.h index cbb134b2f0e4..fad74d323bd6 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -240,6 +240,8 @@ static inline int inet_is_local_reserved_port(struct net *net, int port) } #endif +__be32 inet_current_timestamp(void); + /* From inetpeer.c */ extern int inet_peer_threshold; extern int inet_peer_minttl; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 209d1ed28954..0cc923f83e10 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1380,6 +1380,32 @@ out: return pp; } +#define SECONDS_PER_DAY 86400 + +/* inet_current_timestamp - Return IP network timestamp + * + * Return milliseconds since midnight in network byte order. + */ +__be32 inet_current_timestamp(void) +{ + u32 secs; + u32 msecs; + struct timespec64 ts; + + ktime_get_real_ts64(&ts); + + /* Get secs since midnight. */ + (void)div_u64_rem(ts.tv_sec, SECONDS_PER_DAY, &secs); + /* Convert to msecs. */ + msecs = secs * MSEC_PER_SEC; + /* Convert nsec to msec. */ + msecs += (u32)ts.tv_nsec / NSEC_PER_MSEC; + + /* Convert to network byte order. */ + return htons(msecs); +} +EXPORT_SYMBOL(inet_current_timestamp); + int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { if (sk->sk_family == AF_INET) diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 36e26977c908..6333489771ed 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -931,7 +931,6 @@ static bool icmp_echo(struct sk_buff *skb) */ static bool icmp_timestamp(struct sk_buff *skb) { - struct timespec tv; struct icmp_bxm icmp_param; /* * Too short. @@ -942,9 +941,7 @@ static bool icmp_timestamp(struct sk_buff *skb) /* * Fill in the current time as ms since midnight UT: */ - getnstimeofday(&tv); - icmp_param.data.times[1] = htonl((tv.tv_sec % 86400) * MSEC_PER_SEC + - tv.tv_nsec / NSEC_PER_MSEC); + icmp_param.data.times[1] = inet_current_timestamp(); icmp_param.data.times[2] = icmp_param.data.times[1]; if (skb_copy_bits(skb, 0, &icmp_param.data.times[0], 4)) BUG(); diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index bd246792360b..4d158ff1def1 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -58,10 +58,9 @@ void ip_options_build(struct sk_buff *skb, struct ip_options *opt, if (opt->ts_needaddr) ip_rt_get_source(iph+opt->ts+iph[opt->ts+2]-9, skb, rt); if (opt->ts_needtime) { - struct timespec tv; __be32 midtime; - getnstimeofday(&tv); - midtime = htonl((tv.tv_sec % 86400) * MSEC_PER_SEC + tv.tv_nsec / NSEC_PER_MSEC); + + midtime = inet_current_timestamp(); memcpy(iph+opt->ts+iph[opt->ts+2]-5, &midtime, 4); } return; @@ -415,11 +414,10 @@ int ip_options_compile(struct net *net, break; } if (timeptr) { - struct timespec tv; - u32 midtime; - getnstimeofday(&tv); - midtime = (tv.tv_sec % 86400) * MSEC_PER_SEC + tv.tv_nsec / NSEC_PER_MSEC; - put_unaligned_be32(midtime, timeptr); + __be32 midtime; + + midtime = inet_current_timestamp(); + memcpy(timeptr, &midtime, 4); opt->is_changed = 1; } } else if ((optptr[3]&0xF) != IPOPT_TS_PRESPEC) { -- cgit v1.2.3-71-gd317 From 8a6bf5da1aefdafd60b73d9122c7af9fd2d7bb9c Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 1 Mar 2016 19:55:14 +0100 Subject: netfilter: nft_masq: support port range Complete masquerading support by allowing port range selection. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nft_masq.h | 4 ++- include/uapi/linux/netfilter/nf_tables.h | 4 +++ net/ipv4/netfilter/nft_masq_ipv4.c | 7 ++++- net/ipv6/netfilter/nft_masq_ipv6.c | 7 ++++- net/netfilter/nft_masq.c | 51 +++++++++++++++++++++++++------- 5 files changed, 59 insertions(+), 14 deletions(-) (limited to 'include/net') diff --git a/include/net/netfilter/nft_masq.h b/include/net/netfilter/nft_masq.h index e2a518b60e19..a3f3c11b2526 100644 --- a/include/net/netfilter/nft_masq.h +++ b/include/net/netfilter/nft_masq.h @@ -2,7 +2,9 @@ #define _NFT_MASQ_H_ struct nft_masq { - u32 flags; + u32 flags; + enum nft_registers sreg_proto_min:8; + enum nft_registers sreg_proto_max:8; }; extern const struct nla_policy nft_masq_policy[]; diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index b19be0a098c0..eeffde196f80 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -951,10 +951,14 @@ enum nft_nat_attributes { * enum nft_masq_attributes - nf_tables masquerade expression attributes * * @NFTA_MASQ_FLAGS: NAT flags (see NF_NAT_RANGE_* in linux/netfilter/nf_nat.h) (NLA_U32) + * @NFTA_MASQ_REG_PROTO_MIN: source register of proto range start (NLA_U32: nft_registers) + * @NFTA_MASQ_REG_PROTO_MAX: source register of proto range end (NLA_U32: nft_registers) */ enum nft_masq_attributes { NFTA_MASQ_UNSPEC, NFTA_MASQ_FLAGS, + NFTA_MASQ_REG_PROTO_MIN, + NFTA_MASQ_REG_PROTO_MAX, __NFTA_MASQ_MAX }; #define NFTA_MASQ_MAX (__NFTA_MASQ_MAX - 1) diff --git a/net/ipv4/netfilter/nft_masq_ipv4.c b/net/ipv4/netfilter/nft_masq_ipv4.c index b72ffc58e255..51ced81b616c 100644 --- a/net/ipv4/netfilter/nft_masq_ipv4.c +++ b/net/ipv4/netfilter/nft_masq_ipv4.c @@ -25,7 +25,12 @@ static void nft_masq_ipv4_eval(const struct nft_expr *expr, memset(&range, 0, sizeof(range)); range.flags = priv->flags; - + if (priv->sreg_proto_min) { + range.min_proto.all = + *(__be16 *)®s->data[priv->sreg_proto_min]; + range.max_proto.all = + *(__be16 *)®s->data[priv->sreg_proto_max]; + } regs->verdict.code = nf_nat_masquerade_ipv4(pkt->skb, pkt->hook, &range, pkt->out); } diff --git a/net/ipv6/netfilter/nft_masq_ipv6.c b/net/ipv6/netfilter/nft_masq_ipv6.c index cd1ac1637a05..9597ffb74077 100644 --- a/net/ipv6/netfilter/nft_masq_ipv6.c +++ b/net/ipv6/netfilter/nft_masq_ipv6.c @@ -26,7 +26,12 @@ static void nft_masq_ipv6_eval(const struct nft_expr *expr, memset(&range, 0, sizeof(range)); range.flags = priv->flags; - + if (priv->sreg_proto_min) { + range.min_proto.all = + *(__be16 *)®s->data[priv->sreg_proto_min]; + range.max_proto.all = + *(__be16 *)®s->data[priv->sreg_proto_max]; + } regs->verdict.code = nf_nat_masquerade_ipv6(pkt->skb, &range, pkt->out); } diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c index 9aea747b43ea..81b5ad6165ac 100644 --- a/net/netfilter/nft_masq.c +++ b/net/netfilter/nft_masq.c @@ -17,7 +17,9 @@ #include const struct nla_policy nft_masq_policy[NFTA_MASQ_MAX + 1] = { - [NFTA_MASQ_FLAGS] = { .type = NLA_U32 }, + [NFTA_MASQ_FLAGS] = { .type = NLA_U32 }, + [NFTA_MASQ_REG_PROTO_MIN] = { .type = NLA_U32 }, + [NFTA_MASQ_REG_PROTO_MAX] = { .type = NLA_U32 }, }; EXPORT_SYMBOL_GPL(nft_masq_policy); @@ -40,6 +42,7 @@ int nft_masq_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { + u32 plen = FIELD_SIZEOF(struct nf_nat_range, min_addr.all); struct nft_masq *priv = nft_expr_priv(expr); int err; @@ -47,12 +50,32 @@ int nft_masq_init(const struct nft_ctx *ctx, if (err) return err; - if (tb[NFTA_MASQ_FLAGS] == NULL) - return 0; - - priv->flags = ntohl(nla_get_be32(tb[NFTA_MASQ_FLAGS])); - if (priv->flags & ~NF_NAT_RANGE_MASK) - return -EINVAL; + if (tb[NFTA_MASQ_FLAGS]) { + priv->flags = ntohl(nla_get_be32(tb[NFTA_MASQ_FLAGS])); + if (priv->flags & ~NF_NAT_RANGE_MASK) + return -EINVAL; + } + + if (tb[NFTA_MASQ_REG_PROTO_MIN]) { + priv->sreg_proto_min = + nft_parse_register(tb[NFTA_MASQ_REG_PROTO_MIN]); + + err = nft_validate_register_load(priv->sreg_proto_min, plen); + if (err < 0) + return err; + + if (tb[NFTA_MASQ_REG_PROTO_MAX]) { + priv->sreg_proto_max = + nft_parse_register(tb[NFTA_MASQ_REG_PROTO_MAX]); + + err = nft_validate_register_load(priv->sreg_proto_max, + plen); + if (err < 0) + return err; + } else { + priv->sreg_proto_max = priv->sreg_proto_min; + } + } return 0; } @@ -62,12 +85,18 @@ int nft_masq_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_masq *priv = nft_expr_priv(expr); - if (priv->flags == 0) - return 0; - - if (nla_put_be32(skb, NFTA_MASQ_FLAGS, htonl(priv->flags))) + if (priv->flags != 0 && + nla_put_be32(skb, NFTA_MASQ_FLAGS, htonl(priv->flags))) goto nla_put_failure; + if (priv->sreg_proto_min) { + if (nft_dump_register(skb, NFTA_MASQ_REG_PROTO_MIN, + priv->sreg_proto_min) || + nft_dump_register(skb, NFTA_MASQ_REG_PROTO_MAX, + priv->sreg_proto_max)) + goto nla_put_failure; + } + return 0; nla_put_failure: -- cgit v1.2.3-71-gd317 From 1f27cde313d72d6b44a73ba89c8b2c6a99c628cf Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 2 Mar 2016 08:21:43 -0800 Subject: net: sched: use pfifo_fast for non real queues Some devices declare a high number of TX queues, then set a much lower real_num_tx_queues This cause setups using fq_codel, sfq or fq as the default qdisc to consume more memory than really needed. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sch_generic.h | 6 ++++++ net/sched/sch_generic.c | 1 + net/sched/sch_mq.c | 2 +- net/sched/sch_mqprio.c | 3 ++- 4 files changed, 10 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index e5bba897d206..46e55f0202a6 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -345,6 +345,12 @@ extern struct Qdisc_ops pfifo_fast_ops; extern struct Qdisc_ops mq_qdisc_ops; extern struct Qdisc_ops noqueue_qdisc_ops; extern const struct Qdisc_ops *default_qdisc_ops; +static inline const struct Qdisc_ops * +get_default_qdisc_ops(const struct net_device *dev, int ntx) +{ + return ntx < dev->real_num_tx_queues ? + default_qdisc_ops : &pfifo_fast_ops; +} struct Qdisc_class_common { u32 classid; diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 16bc83b2842a..f18c35024207 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -567,6 +567,7 @@ struct Qdisc_ops pfifo_fast_ops __read_mostly = { .dump = pfifo_fast_dump, .owner = THIS_MODULE, }; +EXPORT_SYMBOL(pfifo_fast_ops); static struct lock_class_key qdisc_tx_busylock; diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c index 3e82f047caaf..56a77b878eb3 100644 --- a/net/sched/sch_mq.c +++ b/net/sched/sch_mq.c @@ -57,7 +57,7 @@ static int mq_init(struct Qdisc *sch, struct nlattr *opt) for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { dev_queue = netdev_get_tx_queue(dev, ntx); - qdisc = qdisc_create_dflt(dev_queue, default_qdisc_ops, + qdisc = qdisc_create_dflt(dev_queue, get_default_qdisc_ops(dev, ntx), TC_H_MAKE(TC_H_MAJ(sch->handle), TC_H_MIN(ntx + 1))); if (qdisc == NULL) diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index 02ffb3fbbc20..b8002ce3d010 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -125,7 +125,8 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) for (i = 0; i < dev->num_tx_queues; i++) { dev_queue = netdev_get_tx_queue(dev, i); - qdisc = qdisc_create_dflt(dev_queue, default_qdisc_ops, + qdisc = qdisc_create_dflt(dev_queue, + get_default_qdisc_ops(dev, i), TC_H_MAKE(TC_H_MAJ(sch->handle), TC_H_MIN(i + 1))); if (qdisc == NULL) { -- cgit v1.2.3-71-gd317 From f719e3754ee2f7275437e61a6afd520181fdd43b Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Sat, 5 Mar 2016 15:03:22 +0200 Subject: ipvs: drop first packet to redirect conntrack Jiri Bohac is reporting for a problem where the attempt to reschedule existing connection to another real server needs proper redirect for the conntrack used by the IPVS connection. For example, when IPVS connection is created to NAT-ed real server we alter the reply direction of conntrack. If we later decide to select different real server we can not alter again the conntrack. And if we expire the old connection, the new connection is left without conntrack. So, the only way to redirect both the IPVS connection and the Netfilter's conntrack is to drop the SYN packet that hits existing connection, to wait for the next jiffie to expire the old connection and its conntrack and to rely on client's retransmission to create new connection as usually. Jiri Bohac provided a fix that drops all SYNs on rescheduling, I extended his patch to do such drops only for connections that use conntrack. Here is the original report from Jiri Bohac: Since commit dc7b3eb900aa ("ipvs: Fix reuse connection if real server is dead"), new connections to dead servers are redistributed immediately to new servers. The old connection is expired using ip_vs_conn_expire_now() which sets the connection timer to expire immediately. However, before the timer callback, ip_vs_conn_expire(), is run to clean the connection's conntrack entry, the new redistributed connection may already be established and its conntrack removed instead. Fix this by dropping the first packet of the new connection instead, like we do when the destination server is not available. The timer will have deleted the old conntrack entry long before the first packet of the new connection is retransmitted. Fixes: dc7b3eb900aa ("ipvs: Fix reuse connection if real server is dead") Signed-off-by: Jiri Bohac Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 17 +++++++++++++++++ net/netfilter/ipvs/ip_vs_core.c | 37 ++++++++++++++++++++++++++++--------- 2 files changed, 45 insertions(+), 9 deletions(-) (limited to 'include/net') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 0816c872b689..a6cc576fd467 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1588,6 +1588,23 @@ static inline void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp) } #endif /* CONFIG_IP_VS_NFCT */ +/* Really using conntrack? */ +static inline bool ip_vs_conn_uses_conntrack(struct ip_vs_conn *cp, + struct sk_buff *skb) +{ +#ifdef CONFIG_IP_VS_NFCT + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + + if (!(cp->flags & IP_VS_CONN_F_NFCT)) + return false; + ct = nf_ct_get(skb, &ctinfo); + if (ct && !nf_ct_is_untracked(ct)) + return true; +#endif + return false; +} + static inline int ip_vs_dest_conn_overhead(struct ip_vs_dest *dest) { diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index f57b4dcdb233..4da560005b0e 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1757,15 +1757,34 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int cp = pp->conn_in_get(ipvs, af, skb, &iph); conn_reuse_mode = sysctl_conn_reuse_mode(ipvs); - if (conn_reuse_mode && !iph.fragoffs && - is_new_conn(skb, &iph) && cp && - ((unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest && - unlikely(!atomic_read(&cp->dest->weight))) || - unlikely(is_new_conn_expected(cp, conn_reuse_mode)))) { - if (!atomic_read(&cp->n_control)) - ip_vs_conn_expire_now(cp); - __ip_vs_conn_put(cp); - cp = NULL; + if (conn_reuse_mode && !iph.fragoffs && is_new_conn(skb, &iph) && cp) { + bool uses_ct = false, resched = false; + + if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest && + unlikely(!atomic_read(&cp->dest->weight))) { + resched = true; + uses_ct = ip_vs_conn_uses_conntrack(cp, skb); + } else if (is_new_conn_expected(cp, conn_reuse_mode)) { + uses_ct = ip_vs_conn_uses_conntrack(cp, skb); + if (!atomic_read(&cp->n_control)) { + resched = true; + } else { + /* Do not reschedule controlling connection + * that uses conntrack while it is still + * referenced by controlled connection(s). + */ + resched = !uses_ct; + } + } + + if (resched) { + if (!atomic_read(&cp->n_control)) + ip_vs_conn_expire_now(cp); + __ip_vs_conn_put(cp); + if (uses_ct) + return NF_DROP; + cp = NULL; + } } if (unlikely(!cp)) { -- cgit v1.2.3-71-gd317 From 8050c0f0274a15841756968857cfb07b3ab809ae Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 4 Mar 2016 15:15:02 +0100 Subject: bpf: allow bpf_csum_diff to feed bpf_l3_csum_replace as well Commit 7d672345ed29 ("bpf: add generic bpf_csum_diff helper") added a generic checksum diff helper that can feed bpf_l4_csum_replace() with a target __wsum diff that is to be applied to the L4 checksum. This facility is very flexible, can be cascaded, allows for adding, removing, or diffing data, or for calculating the pseudo header checksum from scratch, but it can also be reused for working with the IPv4 header checksum. Thus, analogous to bpf_l4_csum_replace(), add a case for header field value of 0 to change the checksum at a given offset through a new helper csum_replace_by_diff(). Also, in addition to that, this provides an easy to use interface for feeding precalculated diffs f.e. coming from a map. It nicely complements bpf_l3_csum_replace() that currently allows only for csum updates of 2 and 4 byte diffs. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/net/checksum.h | 5 +++++ net/core/filter.c | 6 ++++++ 2 files changed, 11 insertions(+) (limited to 'include/net') diff --git a/include/net/checksum.h b/include/net/checksum.h index 10a16b5bd1c7..abffc64e7300 100644 --- a/include/net/checksum.h +++ b/include/net/checksum.h @@ -120,6 +120,11 @@ static inline __wsum csum_partial_ext(const void *buff, int len, __wsum sum) #define CSUM_MANGLED_0 ((__force __sum16)0xffff) +static inline void csum_replace_by_diff(__sum16 *sum, __wsum diff) +{ + *sum = csum_fold(csum_add(diff, ~csum_unfold(*sum))); +} + static inline void csum_replace4(__sum16 *sum, __be32 from, __be32 to) { __wsum tmp = csum_sub(~csum_unfold(*sum), (__force __wsum)from); diff --git a/net/core/filter.c b/net/core/filter.c index 69f4ffc0a282..356a251657a5 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1447,6 +1447,12 @@ static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) return -EFAULT; switch (flags & BPF_F_HDR_FIELD_MASK) { + case 0: + if (unlikely(from != 0)) + return -EINVAL; + + csum_replace_by_diff(ptr, to); + break; case 2: csum_replace2(ptr, from, to); break; -- cgit v1.2.3-71-gd317 From db3c6139e6ead91b42e7c2ad044ed8beaee884e6 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 4 Mar 2016 15:15:07 +0100 Subject: bpf, vxlan, geneve, gre: fix usage of dst_cache on xmit The assumptions from commit 0c1d70af924b ("net: use dst_cache for vxlan device"), 468dfffcd762 ("geneve: add dst caching support") and 3c1cb4d2604c ("net/ipv4: add dst cache support for gre lwtunnels") on dst_cache usage when ip_tunnel_info is used is unfortunately not always valid as assumed. While it seems correct for ip_tunnel_info front-ends such as OVS, eBPF however can fill in ip_tunnel_info for consumers like vxlan, geneve or gre with different remote dsts, tos, etc, therefore they cannot be assumed as packet independent. Right now vxlan, geneve, gre would cache the dst for eBPF and every packet would reuse the same entry that was first created on the initial route lookup. eBPF doesn't store/cache the ip_tunnel_info, so each skb may have a different one. Fix it by adding a flag that checks the ip_tunnel_info. Also the !tos test in vxlan needs to be handeled differently in this context as it is currently inferred from ip_tunnel_info as well if present. ip_tunnel_dst_cache_usable() helper is added for the three tunnel cases, which checks if we can use dst cache. Fixes: 0c1d70af924b ("net: use dst_cache for vxlan device") Fixes: 468dfffcd762 ("geneve: add dst caching support") Fixes: 3c1cb4d2604c ("net/ipv4: add dst cache support for gre lwtunnels") Signed-off-by: Daniel Borkmann Acked-by: Paolo Abeni Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- drivers/net/geneve.c | 6 ++---- drivers/net/vxlan.c | 24 ++++++++++++------------ include/net/ip_tunnels.h | 15 +++++++++++++++ net/core/filter.c | 2 +- net/ipv4/ip_gre.c | 10 ++++++---- 5 files changed, 36 insertions(+), 21 deletions(-) (limited to 'include/net') diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 36db4cf0579c..6a0cbbe03e5d 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -775,10 +775,10 @@ static struct rtable *geneve_get_v4_rt(struct sk_buff *skb, struct flowi4 *fl4, struct ip_tunnel_info *info) { + bool use_cache = ip_tunnel_dst_cache_usable(skb, info); struct geneve_dev *geneve = netdev_priv(dev); struct dst_cache *dst_cache; struct rtable *rt = NULL; - bool use_cache = true; __u8 tos; memset(fl4, 0, sizeof(*fl4)); @@ -804,7 +804,6 @@ static struct rtable *geneve_get_v4_rt(struct sk_buff *skb, dst_cache = &geneve->dst_cache; } - use_cache = use_cache && !skb->mark; if (use_cache) { rt = dst_cache_get_ip4(dst_cache, &fl4->saddr); if (rt) @@ -832,11 +831,11 @@ static struct dst_entry *geneve_get_v6_dst(struct sk_buff *skb, struct flowi6 *fl6, struct ip_tunnel_info *info) { + bool use_cache = ip_tunnel_dst_cache_usable(skb, info); struct geneve_dev *geneve = netdev_priv(dev); struct geneve_sock *gs6 = geneve->sock6; struct dst_entry *dst = NULL; struct dst_cache *dst_cache; - bool use_cache = true; __u8 prio; memset(fl6, 0, sizeof(*fl6)); @@ -862,7 +861,6 @@ static struct dst_entry *geneve_get_v6_dst(struct sk_buff *skb, dst_cache = &geneve->dst_cache; } - use_cache = use_cache && !skb->mark; if (use_cache) { dst = dst_cache_get_ip6(dst_cache, &fl6->saddr); if (dst) diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index fc998a3bd234..7294a459b13c 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -1756,17 +1756,15 @@ static struct rtable *vxlan_get_route(struct vxlan_dev *vxlan, struct sk_buff *skb, int oif, u8 tos, __be32 daddr, __be32 *saddr, struct dst_cache *dst_cache, - struct ip_tunnel_info *info) + const struct ip_tunnel_info *info) { + bool use_cache = ip_tunnel_dst_cache_usable(skb, info); struct rtable *rt = NULL; - bool use_cache = false; struct flowi4 fl4; - /* when the ip_tunnel_info is availble, the tos used for lookup is - * packet independent, so we can use the cache - */ - if (!skb->mark && (!tos || info)) { - use_cache = true; + if (tos && !info) + use_cache = false; + if (use_cache) { rt = dst_cache_get_ip4(dst_cache, saddr); if (rt) return rt; @@ -1794,13 +1792,15 @@ static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan, struct sk_buff *skb, int oif, const struct in6_addr *daddr, struct in6_addr *saddr, - struct dst_cache *dst_cache) + struct dst_cache *dst_cache, + const struct ip_tunnel_info *info) { + bool use_cache = ip_tunnel_dst_cache_usable(skb, info); struct dst_entry *ndst; struct flowi6 fl6; int err; - if (!skb->mark) { + if (use_cache) { ndst = dst_cache_get_ip6(dst_cache, saddr); if (ndst) return ndst; @@ -1820,7 +1820,7 @@ static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan, return ERR_PTR(err); *saddr = fl6.saddr; - if (!skb->mark) + if (use_cache) dst_cache_set_ip6(dst_cache, ndst, saddr); return ndst; } @@ -2018,7 +2018,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, ndst = vxlan6_get_route(vxlan, skb, rdst ? rdst->remote_ifindex : 0, &dst->sin6.sin6_addr, &saddr, - dst_cache); + dst_cache, info); if (IS_ERR(ndst)) { netdev_dbg(dev, "no route to %pI6\n", &dst->sin6.sin6_addr); @@ -2387,7 +2387,7 @@ static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) return -EINVAL; ndst = vxlan6_get_route(vxlan, skb, 0, &info->key.u.ipv6.dst, - &info->key.u.ipv6.src, NULL); + &info->key.u.ipv6.src, NULL, info); if (IS_ERR(ndst)) return PTR_ERR(ndst); dst_release(ndst); diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 5f28b606633e..e1395d70fb48 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -140,6 +140,7 @@ struct ip_tunnel { #define TUNNEL_CRIT_OPT __cpu_to_be16(0x0400) #define TUNNEL_GENEVE_OPT __cpu_to_be16(0x0800) #define TUNNEL_VXLAN_OPT __cpu_to_be16(0x1000) +#define TUNNEL_NOCACHE __cpu_to_be16(0x2000) #define TUNNEL_OPTIONS_PRESENT (TUNNEL_GENEVE_OPT | TUNNEL_VXLAN_OPT) @@ -206,6 +207,20 @@ static inline void ip_tunnel_key_init(struct ip_tunnel_key *key, 0, sizeof(*key) - IP_TUNNEL_KEY_SIZE); } +static inline bool +ip_tunnel_dst_cache_usable(const struct sk_buff *skb, + const struct ip_tunnel_info *info) +{ + if (skb->mark) + return false; + if (!info) + return true; + if (info->key.tun_flags & TUNNEL_NOCACHE) + return false; + + return true; +} + static inline unsigned short ip_tunnel_info_af(const struct ip_tunnel_info *tun_info) { diff --git a/net/core/filter.c b/net/core/filter.c index 012a10c2da94..a66dc03c261f 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1870,7 +1870,7 @@ static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) info = &md->u.tun_info; info->mode = IP_TUNNEL_INFO_TX; - info->key.tun_flags = TUNNEL_KEY | TUNNEL_CSUM; + info->key.tun_flags = TUNNEL_KEY | TUNNEL_CSUM | TUNNEL_NOCACHE; if (flags & BPF_F_DONT_FRAGMENT) info->key.tun_flags |= TUNNEL_DONT_FRAGMENT; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 202437d6087b..31936d387cfd 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -527,11 +527,12 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; + struct rtable *rt = NULL; struct flowi4 fl; - struct rtable *rt; int min_headroom; int tunnel_hlen; __be16 df, flags; + bool use_cache; int err; tun_info = skb_tunnel_info(skb); @@ -540,13 +541,14 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev) goto err_free_skb; key = &tun_info->key; - rt = !skb->mark ? dst_cache_get_ip4(&tun_info->dst_cache, &fl.saddr) : - NULL; + use_cache = ip_tunnel_dst_cache_usable(skb, tun_info); + if (use_cache) + rt = dst_cache_get_ip4(&tun_info->dst_cache, &fl.saddr); if (!rt) { rt = gre_get_rt(skb, dev, &fl, key); if (IS_ERR(rt)) goto err_free_skb; - if (!skb->mark) + if (use_cache) dst_cache_set_ip4(&tun_info->dst_cache, &rt->dst, fl.saddr); } -- cgit v1.2.3-71-gd317 From 9a03cd8f38efb83c13fbe62aff50eea4efff93da Mon Sep 17 00:00:00 2001 From: Michal Kubeček Date: Tue, 8 Mar 2016 14:44:35 +0100 Subject: ipv6: per netns fib6 walkers The IPv6 FIB data structures are separated per network namespace but there is still only one global walkers list and one global walker list lock. This means changes in one namespace unnecessarily interfere with walkers in other namespaces. Replace the global list with per-netns lists (and give each its own lock). Signed-off-by: Michal Kubecek Reviewed-by: Cong Wang Signed-off-by: David S. Miller --- include/net/netns/ipv6.h | 2 ++ net/ipv6/ip6_fib.c | 68 +++++++++++++++++++++++++----------------------- 2 files changed, 38 insertions(+), 32 deletions(-) (limited to 'include/net') diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index c0368db6df54..f0109b973648 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -58,7 +58,9 @@ struct netns_ipv6 { struct timer_list ip6_fib_timer; struct hlist_head *fib_table_hash; struct fib6_table *fib6_main_tbl; + struct list_head fib6_walkers; struct dst_ops ip6_dst_ops; + rwlock_t fib6_walker_lock; unsigned int ip6_rt_gc_expire; unsigned long ip6_rt_last_gc; #ifdef CONFIG_IPV6_MULTIPLE_TABLES diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index d7c715accac9..883f2836beab 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -55,8 +55,6 @@ struct fib6_cleaner { void *arg; }; -static DEFINE_RWLOCK(fib6_walker_lock); - #ifdef CONFIG_IPV6_SUBTREES #define FWS_INIT FWS_S #else @@ -66,7 +64,7 @@ static DEFINE_RWLOCK(fib6_walker_lock); static void fib6_prune_clones(struct net *net, struct fib6_node *fn); static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn); static struct fib6_node *fib6_repair_tree(struct net *net, struct fib6_node *fn); -static int fib6_walk(struct fib6_walker *w); +static int fib6_walk(struct net *net, struct fib6_walker *w); static int fib6_walk_continue(struct fib6_walker *w); /* @@ -78,21 +76,21 @@ static int fib6_walk_continue(struct fib6_walker *w); static void fib6_gc_timer_cb(unsigned long arg); -static LIST_HEAD(fib6_walkers); -#define FOR_WALKERS(w) list_for_each_entry(w, &fib6_walkers, lh) +#define FOR_WALKERS(net, w) \ + list_for_each_entry(w, &(net)->ipv6.fib6_walkers, lh) -static void fib6_walker_link(struct fib6_walker *w) +static void fib6_walker_link(struct net *net, struct fib6_walker *w) { - write_lock_bh(&fib6_walker_lock); - list_add(&w->lh, &fib6_walkers); - write_unlock_bh(&fib6_walker_lock); + write_lock_bh(&net->ipv6.fib6_walker_lock); + list_add(&w->lh, &net->ipv6.fib6_walkers); + write_unlock_bh(&net->ipv6.fib6_walker_lock); } -static void fib6_walker_unlink(struct fib6_walker *w) +static void fib6_walker_unlink(struct net *net, struct fib6_walker *w) { - write_lock_bh(&fib6_walker_lock); + write_lock_bh(&net->ipv6.fib6_walker_lock); list_del(&w->lh); - write_unlock_bh(&fib6_walker_lock); + write_unlock_bh(&net->ipv6.fib6_walker_lock); } static int fib6_new_sernum(struct net *net) @@ -325,12 +323,13 @@ static int fib6_dump_node(struct fib6_walker *w) static void fib6_dump_end(struct netlink_callback *cb) { + struct net *net = sock_net(cb->skb->sk); struct fib6_walker *w = (void *)cb->args[2]; if (w) { if (cb->args[4]) { cb->args[4] = 0; - fib6_walker_unlink(w); + fib6_walker_unlink(net, w); } cb->args[2] = 0; kfree(w); @@ -348,6 +347,7 @@ static int fib6_dump_done(struct netlink_callback *cb) static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb, struct netlink_callback *cb) { + struct net *net = sock_net(skb->sk); struct fib6_walker *w; int res; @@ -359,7 +359,7 @@ static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb, w->skip = 0; read_lock_bh(&table->tb6_lock); - res = fib6_walk(w); + res = fib6_walk(net, w); read_unlock_bh(&table->tb6_lock); if (res > 0) { cb->args[4] = 1; @@ -379,7 +379,7 @@ static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb, res = fib6_walk_continue(w); read_unlock_bh(&table->tb6_lock); if (res <= 0) { - fib6_walker_unlink(w); + fib6_walker_unlink(net, w); cb->args[4] = 0; } } @@ -1340,8 +1340,8 @@ static struct fib6_node *fib6_repair_tree(struct net *net, } #endif - read_lock(&fib6_walker_lock); - FOR_WALKERS(w) { + read_lock(&net->ipv6.fib6_walker_lock); + FOR_WALKERS(net, w) { if (!child) { if (w->root == fn) { w->root = w->node = NULL; @@ -1368,7 +1368,7 @@ static struct fib6_node *fib6_repair_tree(struct net *net, } } } - read_unlock(&fib6_walker_lock); + read_unlock(&net->ipv6.fib6_walker_lock); node_free(fn); if (pn->fn_flags & RTN_RTINFO || FIB6_SUBTREE(pn)) @@ -1411,8 +1411,8 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, } /* Adjust walkers */ - read_lock(&fib6_walker_lock); - FOR_WALKERS(w) { + read_lock(&net->ipv6.fib6_walker_lock); + FOR_WALKERS(net, w) { if (w->state == FWS_C && w->leaf == rt) { RT6_TRACE("walker %p adjusted by delroute\n", w); w->leaf = rt->dst.rt6_next; @@ -1420,7 +1420,7 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, w->state = FWS_U; } } - read_unlock(&fib6_walker_lock); + read_unlock(&net->ipv6.fib6_walker_lock); rt->dst.rt6_next = NULL; @@ -1588,17 +1588,17 @@ skip: } } -static int fib6_walk(struct fib6_walker *w) +static int fib6_walk(struct net *net, struct fib6_walker *w) { int res; w->state = FWS_INIT; w->node = w->root; - fib6_walker_link(w); + fib6_walker_link(net, w); res = fib6_walk_continue(w); if (res <= 0) - fib6_walker_unlink(w); + fib6_walker_unlink(net, w); return res; } @@ -1668,7 +1668,7 @@ static void fib6_clean_tree(struct net *net, struct fib6_node *root, c.arg = arg; c.net = net; - fib6_walk(&c.w); + fib6_walk(net, &c.w); } static void __fib6_clean_all(struct net *net, @@ -1816,6 +1816,8 @@ static int __net_init fib6_net_init(struct net *net) { size_t size = sizeof(struct hlist_head) * FIB6_TABLE_HASHSZ; + rwlock_init(&net->ipv6.fib6_walker_lock); + INIT_LIST_HEAD(&net->ipv6.fib6_walkers); setup_timer(&net->ipv6.ip6_fib_timer, fib6_gc_timer_cb, (unsigned long)net); net->ipv6.rt6_stats = kzalloc(sizeof(*net->ipv6.rt6_stats), GFP_KERNEL); @@ -1976,7 +1978,8 @@ static int ipv6_route_yield(struct fib6_walker *w) return 0; } -static void ipv6_route_seq_setup_walk(struct ipv6_route_iter *iter) +static void ipv6_route_seq_setup_walk(struct ipv6_route_iter *iter, + struct net *net) { memset(&iter->w, 0, sizeof(iter->w)); iter->w.func = ipv6_route_yield; @@ -1986,7 +1989,7 @@ static void ipv6_route_seq_setup_walk(struct ipv6_route_iter *iter) iter->w.args = iter; iter->sernum = iter->w.root->fn_sernum; INIT_LIST_HEAD(&iter->w.lh); - fib6_walker_link(&iter->w); + fib6_walker_link(net, &iter->w); } static struct fib6_table *ipv6_route_seq_next_table(struct fib6_table *tbl, @@ -2047,16 +2050,16 @@ iter_table: ++*pos; return iter->w.leaf; } else if (r < 0) { - fib6_walker_unlink(&iter->w); + fib6_walker_unlink(net, &iter->w); return NULL; } - fib6_walker_unlink(&iter->w); + fib6_walker_unlink(net, &iter->w); iter->tbl = ipv6_route_seq_next_table(iter->tbl, net); if (!iter->tbl) return NULL; - ipv6_route_seq_setup_walk(iter); + ipv6_route_seq_setup_walk(iter, net); goto iter_table; } @@ -2071,7 +2074,7 @@ static void *ipv6_route_seq_start(struct seq_file *seq, loff_t *pos) iter->skip = *pos; if (iter->tbl) { - ipv6_route_seq_setup_walk(iter); + ipv6_route_seq_setup_walk(iter, net); return ipv6_route_seq_next(seq, NULL, pos); } else { return NULL; @@ -2087,10 +2090,11 @@ static bool ipv6_route_iter_active(struct ipv6_route_iter *iter) static void ipv6_route_seq_stop(struct seq_file *seq, void *v) __releases(RCU_BH) { + struct net *net = seq_file_net(seq); struct ipv6_route_iter *iter = seq->private; if (ipv6_route_iter_active(iter)) - fib6_walker_unlink(&iter->w); + fib6_walker_unlink(net, &iter->w); rcu_read_unlock_bh(); } -- cgit v1.2.3-71-gd317 From 3dc94f93be161ec4203673de9a34b7362d8985b5 Mon Sep 17 00:00:00 2001 From: Michal Kubeček Date: Tue, 8 Mar 2016 14:44:45 +0100 Subject: ipv6: per netns FIB garbage collection One of our customers observed issues with FIB6 garbage collectors running in different network namespaces blocking each other, resulting in soft lockups (fib6_run_gc() initiated from timer runs always in forced mode). Now that FIB6 walkers are separated per namespace, there is no more need for instances of fib6_run_gc() in different namespaces blocking each other. There is still a call to icmp6_dst_gc() which operates on shared data but this function is protected by its own shared lock. Signed-off-by: Michal Kubecek Reviewed-by: Cong Wang Signed-off-by: David S. Miller --- include/net/netns/ipv6.h | 1 + net/ipv6/ip6_fib.c | 9 ++++----- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/net') diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index f0109b973648..10d0848f5b8a 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -61,6 +61,7 @@ struct netns_ipv6 { struct list_head fib6_walkers; struct dst_ops ip6_dst_ops; rwlock_t fib6_walker_lock; + spinlock_t fib6_gc_lock; unsigned int ip6_rt_gc_expire; unsigned long ip6_rt_last_gc; #ifdef CONFIG_IPV6_MULTIPLE_TABLES diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 883f2836beab..ea071fad67a0 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1776,16 +1776,14 @@ static int fib6_age(struct rt6_info *rt, void *arg) return 0; } -static DEFINE_SPINLOCK(fib6_gc_lock); - void fib6_run_gc(unsigned long expires, struct net *net, bool force) { struct fib6_gc_args gc_args; unsigned long now; if (force) { - spin_lock_bh(&fib6_gc_lock); - } else if (!spin_trylock_bh(&fib6_gc_lock)) { + spin_lock_bh(&net->ipv6.fib6_gc_lock); + } else if (!spin_trylock_bh(&net->ipv6.fib6_gc_lock)) { mod_timer(&net->ipv6.ip6_fib_timer, jiffies + HZ); return; } @@ -1804,7 +1802,7 @@ void fib6_run_gc(unsigned long expires, struct net *net, bool force) + net->ipv6.sysctl.ip6_rt_gc_interval)); else del_timer(&net->ipv6.ip6_fib_timer); - spin_unlock_bh(&fib6_gc_lock); + spin_unlock_bh(&net->ipv6.fib6_gc_lock); } static void fib6_gc_timer_cb(unsigned long arg) @@ -1816,6 +1814,7 @@ static int __net_init fib6_net_init(struct net *net) { size_t size = sizeof(struct hlist_head) * FIB6_TABLE_HASHSZ; + spin_lock_init(&net->ipv6.fib6_gc_lock); rwlock_init(&net->ipv6.fib6_walker_lock); INIT_LIST_HEAD(&net->ipv6.fib6_walkers); setup_timer(&net->ipv6.ip6_fib_timer, fib6_gc_timer_cb, (unsigned long)net); -- cgit v1.2.3-71-gd317 From e28e87ed474c5a0b378c66fb85efc8e487f4f63f Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 8 Mar 2016 23:36:03 +0100 Subject: ip_tunnel, bpf: ip_tunnel_info_opts_{get, set} depends on CONFIG_INET Helpers like ip_tunnel_info_opts_{get,set}() are only available if CONFIG_INET is set, thus add an empty definition into the header for the !CONFIG_INET case, where already other empty inline helpers are defined. This avoids ifdef kludge inside filter.c, but also vxlan and geneve themself where this facility can only be used with, depend on INET being set. For the !INET case TUNNEL_OPTIONS_PRESENT would never be set in flags. Fixes: 14ca0751c96f ("bpf: support for access to tunnel options") Reported-by: Fengguang Wu Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/net/ip_tunnels.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/net') diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index e1395d70fb48..0acd80fadb32 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -369,6 +369,17 @@ static inline void ip_tunnel_unneed_metadata(void) { } +static inline void ip_tunnel_info_opts_get(void *to, + const struct ip_tunnel_info *info) +{ +} + +static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info, + const void *from, int len) +{ + info->options_len = 0; +} + #endif /* CONFIG_INET */ #endif /* __NET_IP_TUNNELS_H */ -- cgit v1.2.3-71-gd317 From 473bd239b808a8af5241ce9996a16d283d88ddff Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Mon, 7 Mar 2016 14:11:05 -0800 Subject: tcp: Add tcp_inq to get available receive bytes on socket Create a common kernel function to get the number of bytes available on a TCP socket. This is based on code in INQ getsockopt and we now call the function for that getsockopt. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/net/tcp.h | 24 ++++++++++++++++++++++++ net/ipv4/tcp.c | 15 +-------------- 2 files changed, 25 insertions(+), 14 deletions(-) (limited to 'include/net') diff --git a/include/net/tcp.h b/include/net/tcp.h index e90db8546806..0302636af98c 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1816,4 +1816,28 @@ static inline void skb_set_tcp_pure_ack(struct sk_buff *skb) skb->truesize = 2; } +static inline int tcp_inq(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + int answ; + + if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { + answ = 0; + } else if (sock_flag(sk, SOCK_URGINLINE) || + !tp->urg_data || + before(tp->urg_seq, tp->copied_seq) || + !before(tp->urg_seq, tp->rcv_nxt)) { + + answ = tp->rcv_nxt - tp->copied_seq; + + /* Subtract 1, if FIN was received */ + if (answ && sock_flag(sk, SOCK_DONE)) + answ--; + } else { + answ = tp->urg_seq - tp->copied_seq; + } + + return answ; +} + #endif /* _TCP_H */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index f9faadb42485..a265f00b9df9 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -556,20 +556,7 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg) return -EINVAL; slow = lock_sock_fast(sk); - if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) - answ = 0; - else if (sock_flag(sk, SOCK_URGINLINE) || - !tp->urg_data || - before(tp->urg_seq, tp->copied_seq) || - !before(tp->urg_seq, tp->rcv_nxt)) { - - answ = tp->rcv_nxt - tp->copied_seq; - - /* Subtract 1, if FIN was received */ - if (answ && sock_flag(sk, SOCK_DONE)) - answ--; - } else - answ = tp->urg_seq - tp->copied_seq; + answ = tcp_inq(sk); unlock_sock_fast(sk, slow); break; case SIOCATMARK: -- cgit v1.2.3-71-gd317 From ab7ac4eb9832e32a09f4e8042705484d2fb0aad3 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Mon, 7 Mar 2016 14:11:06 -0800 Subject: kcm: Kernel Connection Multiplexor module This module implements the Kernel Connection Multiplexor. Kernel Connection Multiplexor (KCM) is a facility that provides a message based interface over TCP for generic application protocols. With KCM an application can efficiently send and receive application protocol messages over TCP using datagram sockets. For more information see the included Documentation/networking/kcm.txt Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/socket.h | 6 +- include/net/kcm.h | 125 +++ include/uapi/linux/kcm.h | 40 + net/Kconfig | 1 + net/Makefile | 1 + net/kcm/Kconfig | 10 + net/kcm/Makefile | 3 + net/kcm/kcmsock.c | 2016 ++++++++++++++++++++++++++++++++++++++++++++++ 8 files changed, 2201 insertions(+), 1 deletion(-) create mode 100644 include/net/kcm.h create mode 100644 include/uapi/linux/kcm.h create mode 100644 net/kcm/Kconfig create mode 100644 net/kcm/Makefile create mode 100644 net/kcm/kcmsock.c (limited to 'include/net') diff --git a/include/linux/socket.h b/include/linux/socket.h index d834af22a460..73bf6c6a833b 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -200,7 +200,9 @@ struct ucred { #define AF_ALG 38 /* Algorithm sockets */ #define AF_NFC 39 /* NFC sockets */ #define AF_VSOCK 40 /* vSockets */ -#define AF_MAX 41 /* For now.. */ +#define AF_KCM 41 /* Kernel Connection Multiplexor*/ + +#define AF_MAX 42 /* For now.. */ /* Protocol families, same as address families. */ #define PF_UNSPEC AF_UNSPEC @@ -246,6 +248,7 @@ struct ucred { #define PF_ALG AF_ALG #define PF_NFC AF_NFC #define PF_VSOCK AF_VSOCK +#define PF_KCM AF_KCM #define PF_MAX AF_MAX /* Maximum queue length specifiable by listen. */ @@ -323,6 +326,7 @@ struct ucred { #define SOL_CAIF 278 #define SOL_ALG 279 #define SOL_NFC 280 +#define SOL_KCM 281 /* IPX options */ #define IPX_TYPE 1 diff --git a/include/net/kcm.h b/include/net/kcm.h new file mode 100644 index 000000000000..1bcae39070ec --- /dev/null +++ b/include/net/kcm.h @@ -0,0 +1,125 @@ +/* + * Kernel Connection Multiplexor + * + * Copyright (c) 2016 Tom Herbert + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + */ + +#ifndef __NET_KCM_H_ +#define __NET_KCM_H_ + +#include +#include +#include + +extern unsigned int kcm_net_id; + +struct kcm_tx_msg { + unsigned int sent; + unsigned int fragidx; + unsigned int frag_offset; + unsigned int msg_flags; + struct sk_buff *frag_skb; + struct sk_buff *last_skb; +}; + +struct kcm_rx_msg { + int full_len; + int accum_len; + int offset; +}; + +/* Socket structure for KCM client sockets */ +struct kcm_sock { + struct sock sk; + struct kcm_mux *mux; + struct list_head kcm_sock_list; + int index; + u32 done : 1; + struct work_struct done_work; + + /* Transmit */ + struct kcm_psock *tx_psock; + struct work_struct tx_work; + struct list_head wait_psock_list; + struct sk_buff *seq_skb; + + /* Don't use bit fields here, these are set under different locks */ + bool tx_wait; + bool tx_wait_more; + + /* Receive */ + struct kcm_psock *rx_psock; + struct list_head wait_rx_list; /* KCMs waiting for receiving */ + bool rx_wait; + u32 rx_disabled : 1; +}; + +struct bpf_prog; + +/* Structure for an attached lower socket */ +struct kcm_psock { + struct sock *sk; + struct kcm_mux *mux; + int index; + + u32 tx_stopped : 1; + u32 rx_stopped : 1; + u32 done : 1; + u32 unattaching : 1; + + void (*save_state_change)(struct sock *sk); + void (*save_data_ready)(struct sock *sk); + void (*save_write_space)(struct sock *sk); + + struct list_head psock_list; + + /* Receive */ + struct sk_buff *rx_skb_head; + struct sk_buff **rx_skb_nextp; + struct sk_buff *ready_rx_msg; + struct list_head psock_ready_list; + struct work_struct rx_work; + struct delayed_work rx_delayed_work; + struct bpf_prog *bpf_prog; + struct kcm_sock *rx_kcm; + + /* Transmit */ + struct kcm_sock *tx_kcm; + struct list_head psock_avail_list; +}; + +/* Per net MUX list */ +struct kcm_net { + struct mutex mutex; + struct list_head mux_list; + int count; +}; + +/* Structure for a MUX */ +struct kcm_mux { + struct list_head kcm_mux_list; + struct rcu_head rcu; + struct kcm_net *knet; + + struct list_head kcm_socks; /* All KCM sockets on MUX */ + int kcm_socks_cnt; /* Total KCM socket count for MUX */ + struct list_head psocks; /* List of all psocks on MUX */ + int psocks_cnt; /* Total attached sockets */ + + /* Receive */ + spinlock_t rx_lock ____cacheline_aligned_in_smp; + struct list_head kcm_rx_waiters; /* KCMs waiting for receiving */ + struct list_head psocks_ready; /* List of psocks with a msg ready */ + struct sk_buff_head rx_hold_queue; + + /* Transmit */ + spinlock_t lock ____cacheline_aligned_in_smp; /* TX and mux locking */ + struct list_head psocks_avail; /* List of available psocks */ + struct list_head kcm_tx_waiters; /* KCMs waiting for a TX psock */ +}; + +#endif /* __NET_KCM_H_ */ diff --git a/include/uapi/linux/kcm.h b/include/uapi/linux/kcm.h new file mode 100644 index 000000000000..a5a530940b99 --- /dev/null +++ b/include/uapi/linux/kcm.h @@ -0,0 +1,40 @@ +/* + * Kernel Connection Multiplexor + * + * Copyright (c) 2016 Tom Herbert + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + * + * User API to clone KCM sockets and attach transport socket to a KCM + * multiplexor. + */ + +#ifndef KCM_KERNEL_H +#define KCM_KERNEL_H + +struct kcm_attach { + int fd; + int bpf_fd; +}; + +struct kcm_unattach { + int fd; +}; + +struct kcm_clone { + int fd; +}; + +#define SIOCKCMATTACH (SIOCPROTOPRIVATE + 0) +#define SIOCKCMUNATTACH (SIOCPROTOPRIVATE + 1) +#define SIOCKCMCLONE (SIOCPROTOPRIVATE + 2) + +#define KCMPROTO_CONNECTED 0 + +/* Socket options */ +#define KCM_RECV_DISABLE 1 + +#endif + diff --git a/net/Kconfig b/net/Kconfig index 2760825e53fa..10640d5f8bee 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -360,6 +360,7 @@ source "net/can/Kconfig" source "net/irda/Kconfig" source "net/bluetooth/Kconfig" source "net/rxrpc/Kconfig" +source "net/kcm/Kconfig" config FIB_RULES bool diff --git a/net/Makefile b/net/Makefile index a5d04098dfce..81d14119eab5 100644 --- a/net/Makefile +++ b/net/Makefile @@ -34,6 +34,7 @@ obj-$(CONFIG_IRDA) += irda/ obj-$(CONFIG_BT) += bluetooth/ obj-$(CONFIG_SUNRPC) += sunrpc/ obj-$(CONFIG_AF_RXRPC) += rxrpc/ +obj-$(CONFIG_AF_KCM) += kcm/ obj-$(CONFIG_ATM) += atm/ obj-$(CONFIG_L2TP) += l2tp/ obj-$(CONFIG_DECNET) += decnet/ diff --git a/net/kcm/Kconfig b/net/kcm/Kconfig new file mode 100644 index 000000000000..5db94d940ecc --- /dev/null +++ b/net/kcm/Kconfig @@ -0,0 +1,10 @@ + +config AF_KCM + tristate "KCM sockets" + depends on INET + select BPF_SYSCALL + ---help--- + KCM (Kernel Connection Multiplexor) sockets provide a method + for multiplexing messages of a message based application + protocol over kernel connectons (e.g. TCP connections). + diff --git a/net/kcm/Makefile b/net/kcm/Makefile new file mode 100644 index 000000000000..cb525f7c5a13 --- /dev/null +++ b/net/kcm/Makefile @@ -0,0 +1,3 @@ +obj-$(CONFIG_AF_KCM) += kcm.o + +kcm-y := kcmsock.o diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c new file mode 100644 index 000000000000..30ef69ac6b81 --- /dev/null +++ b/net/kcm/kcmsock.c @@ -0,0 +1,2016 @@ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +unsigned int kcm_net_id; + +static struct kmem_cache *kcm_psockp __read_mostly; +static struct kmem_cache *kcm_muxp __read_mostly; +static struct workqueue_struct *kcm_wq; + +static inline struct kcm_sock *kcm_sk(const struct sock *sk) +{ + return (struct kcm_sock *)sk; +} + +static inline struct kcm_tx_msg *kcm_tx_msg(struct sk_buff *skb) +{ + return (struct kcm_tx_msg *)skb->cb; +} + +static inline struct kcm_rx_msg *kcm_rx_msg(struct sk_buff *skb) +{ + return (struct kcm_rx_msg *)((void *)skb->cb + + offsetof(struct qdisc_skb_cb, data)); +} + +static void report_csk_error(struct sock *csk, int err) +{ + csk->sk_err = EPIPE; + csk->sk_error_report(csk); +} + +/* Callback lock held */ +static void kcm_abort_rx_psock(struct kcm_psock *psock, int err, + struct sk_buff *skb) +{ + struct sock *csk = psock->sk; + + /* Unrecoverable error in receive */ + + if (psock->rx_stopped) + return; + + psock->rx_stopped = 1; + + /* Report an error on the lower socket */ + report_csk_error(csk, err); +} + +static void kcm_abort_tx_psock(struct kcm_psock *psock, int err, + bool wakeup_kcm) +{ + struct sock *csk = psock->sk; + struct kcm_mux *mux = psock->mux; + + /* Unrecoverable error in transmit */ + + spin_lock_bh(&mux->lock); + + if (psock->tx_stopped) { + spin_unlock_bh(&mux->lock); + return; + } + + psock->tx_stopped = 1; + + if (!psock->tx_kcm) { + /* Take off psocks_avail list */ + list_del(&psock->psock_avail_list); + } else if (wakeup_kcm) { + /* In this case psock is being aborted while outside of + * write_msgs and psock is reserved. Schedule tx_work + * to handle the failure there. Need to commit tx_stopped + * before queuing work. + */ + smp_mb(); + + queue_work(kcm_wq, &psock->tx_kcm->tx_work); + } + + spin_unlock_bh(&mux->lock); + + /* Report error on lower socket */ + report_csk_error(csk, err); +} + +static int kcm_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); + +/* KCM is ready to receive messages on its queue-- either the KCM is new or + * has become unblocked after being blocked on full socket buffer. Queue any + * pending ready messages on a psock. RX mux lock held. + */ +static void kcm_rcv_ready(struct kcm_sock *kcm) +{ + struct kcm_mux *mux = kcm->mux; + struct kcm_psock *psock; + struct sk_buff *skb; + + if (unlikely(kcm->rx_wait || kcm->rx_psock || kcm->rx_disabled)) + return; + + while (unlikely((skb = __skb_dequeue(&mux->rx_hold_queue)))) { + if (kcm_queue_rcv_skb(&kcm->sk, skb)) { + /* Assuming buffer limit has been reached */ + skb_queue_head(&mux->rx_hold_queue, skb); + WARN_ON(!sk_rmem_alloc_get(&kcm->sk)); + return; + } + } + + while (!list_empty(&mux->psocks_ready)) { + psock = list_first_entry(&mux->psocks_ready, struct kcm_psock, + psock_ready_list); + + if (kcm_queue_rcv_skb(&kcm->sk, psock->ready_rx_msg)) { + /* Assuming buffer limit has been reached */ + WARN_ON(!sk_rmem_alloc_get(&kcm->sk)); + return; + } + + /* Consumed the ready message on the psock. Schedule rx_work to + * get more messages. + */ + list_del(&psock->psock_ready_list); + psock->ready_rx_msg = NULL; + + /* Commit clearing of ready_rx_msg for queuing work */ + smp_mb(); + + queue_work(kcm_wq, &psock->rx_work); + } + + /* Buffer limit is okay now, add to ready list */ + list_add_tail(&kcm->wait_rx_list, + &kcm->mux->kcm_rx_waiters); + kcm->rx_wait = true; +} + +static void kcm_rfree(struct sk_buff *skb) +{ + struct sock *sk = skb->sk; + struct kcm_sock *kcm = kcm_sk(sk); + struct kcm_mux *mux = kcm->mux; + unsigned int len = skb->truesize; + + sk_mem_uncharge(sk, len); + atomic_sub(len, &sk->sk_rmem_alloc); + + /* For reading rx_wait and rx_psock without holding lock */ + smp_mb__after_atomic(); + + if (!kcm->rx_wait && !kcm->rx_psock && + sk_rmem_alloc_get(sk) < sk->sk_rcvlowat) { + spin_lock_bh(&mux->rx_lock); + kcm_rcv_ready(kcm); + spin_unlock_bh(&mux->rx_lock); + } +} + +static int kcm_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) +{ + struct sk_buff_head *list = &sk->sk_receive_queue; + + if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) + return -ENOMEM; + + if (!sk_rmem_schedule(sk, skb, skb->truesize)) + return -ENOBUFS; + + skb->dev = NULL; + + skb_orphan(skb); + skb->sk = sk; + skb->destructor = kcm_rfree; + atomic_add(skb->truesize, &sk->sk_rmem_alloc); + sk_mem_charge(sk, skb->truesize); + + skb_queue_tail(list, skb); + + if (!sock_flag(sk, SOCK_DEAD)) + sk->sk_data_ready(sk); + + return 0; +} + +/* Requeue received messages for a kcm socket to other kcm sockets. This is + * called with a kcm socket is receive disabled. + * RX mux lock held. + */ +static void requeue_rx_msgs(struct kcm_mux *mux, struct sk_buff_head *head) +{ + struct sk_buff *skb; + struct kcm_sock *kcm; + + while ((skb = __skb_dequeue(head))) { + /* Reset destructor to avoid calling kcm_rcv_ready */ + skb->destructor = sock_rfree; + skb_orphan(skb); +try_again: + if (list_empty(&mux->kcm_rx_waiters)) { + skb_queue_tail(&mux->rx_hold_queue, skb); + continue; + } + + kcm = list_first_entry(&mux->kcm_rx_waiters, + struct kcm_sock, wait_rx_list); + + if (kcm_queue_rcv_skb(&kcm->sk, skb)) { + /* Should mean socket buffer full */ + list_del(&kcm->wait_rx_list); + kcm->rx_wait = false; + + /* Commit rx_wait to read in kcm_free */ + smp_wmb(); + + goto try_again; + } + } +} + +/* Lower sock lock held */ +static struct kcm_sock *reserve_rx_kcm(struct kcm_psock *psock, + struct sk_buff *head) +{ + struct kcm_mux *mux = psock->mux; + struct kcm_sock *kcm; + + WARN_ON(psock->ready_rx_msg); + + if (psock->rx_kcm) + return psock->rx_kcm; + + spin_lock_bh(&mux->rx_lock); + + if (psock->rx_kcm) { + spin_unlock_bh(&mux->rx_lock); + return psock->rx_kcm; + } + + if (list_empty(&mux->kcm_rx_waiters)) { + psock->ready_rx_msg = head; + list_add_tail(&psock->psock_ready_list, + &mux->psocks_ready); + spin_unlock_bh(&mux->rx_lock); + return NULL; + } + + kcm = list_first_entry(&mux->kcm_rx_waiters, + struct kcm_sock, wait_rx_list); + list_del(&kcm->wait_rx_list); + kcm->rx_wait = false; + + psock->rx_kcm = kcm; + kcm->rx_psock = psock; + + spin_unlock_bh(&mux->rx_lock); + + return kcm; +} + +static void kcm_done(struct kcm_sock *kcm); + +static void kcm_done_work(struct work_struct *w) +{ + kcm_done(container_of(w, struct kcm_sock, done_work)); +} + +/* Lower sock held */ +static void unreserve_rx_kcm(struct kcm_psock *psock, + bool rcv_ready) +{ + struct kcm_sock *kcm = psock->rx_kcm; + struct kcm_mux *mux = psock->mux; + + if (!kcm) + return; + + spin_lock_bh(&mux->rx_lock); + + psock->rx_kcm = NULL; + kcm->rx_psock = NULL; + + /* Commit kcm->rx_psock before sk_rmem_alloc_get to sync with + * kcm_rfree + */ + smp_mb(); + + if (unlikely(kcm->done)) { + spin_unlock_bh(&mux->rx_lock); + + /* Need to run kcm_done in a task since we need to qcquire + * callback locks which may already be held here. + */ + INIT_WORK(&kcm->done_work, kcm_done_work); + schedule_work(&kcm->done_work); + return; + } + + if (unlikely(kcm->rx_disabled)) { + requeue_rx_msgs(mux, &kcm->sk.sk_receive_queue); + } else if (rcv_ready || unlikely(!sk_rmem_alloc_get(&kcm->sk))) { + /* Check for degenerative race with rx_wait that all + * data was dequeued (accounted for in kcm_rfree). + */ + kcm_rcv_ready(kcm); + } + spin_unlock_bh(&mux->rx_lock); +} + +/* Macro to invoke filter function. */ +#define KCM_RUN_FILTER(prog, ctx) \ + (*prog->bpf_func)(ctx, prog->insnsi) + +/* Lower socket lock held */ +static int kcm_tcp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, + unsigned int orig_offset, size_t orig_len) +{ + struct kcm_psock *psock = (struct kcm_psock *)desc->arg.data; + struct kcm_rx_msg *rxm; + struct kcm_sock *kcm; + struct sk_buff *head, *skb; + size_t eaten = 0, cand_len; + ssize_t extra; + int err; + bool cloned_orig = false; + + if (psock->ready_rx_msg) + return 0; + + head = psock->rx_skb_head; + if (head) { + /* Message already in progress */ + + if (unlikely(orig_offset)) { + /* Getting data with a non-zero offset when a message is + * in progress is not expected. If it does happen, we + * need to clone and pull since we can't deal with + * offsets in the skbs for a message expect in the head. + */ + orig_skb = skb_clone(orig_skb, GFP_ATOMIC); + if (!orig_skb) { + desc->error = -ENOMEM; + return 0; + } + if (!pskb_pull(orig_skb, orig_offset)) { + kfree_skb(orig_skb); + desc->error = -ENOMEM; + return 0; + } + cloned_orig = true; + orig_offset = 0; + } + + if (!psock->rx_skb_nextp) { + /* We are going to append to the frags_list of head. + * Need to unshare the frag_list. + */ + err = skb_unclone(head, GFP_ATOMIC); + if (err) { + desc->error = err; + return 0; + } + + if (unlikely(skb_shinfo(head)->frag_list)) { + /* We can't append to an sk_buff that already + * has a frag_list. We create a new head, point + * the frag_list of that to the old head, and + * then are able to use the old head->next for + * appending to the message. + */ + if (WARN_ON(head->next)) { + desc->error = -EINVAL; + return 0; + } + + skb = alloc_skb(0, GFP_ATOMIC); + if (!skb) { + desc->error = -ENOMEM; + return 0; + } + skb->len = head->len; + skb->data_len = head->len; + skb->truesize = head->truesize; + *kcm_rx_msg(skb) = *kcm_rx_msg(head); + psock->rx_skb_nextp = &head->next; + skb_shinfo(skb)->frag_list = head; + psock->rx_skb_head = skb; + head = skb; + } else { + psock->rx_skb_nextp = + &skb_shinfo(head)->frag_list; + } + } + } + + while (eaten < orig_len) { + /* Always clone since we will consume something */ + skb = skb_clone(orig_skb, GFP_ATOMIC); + if (!skb) { + desc->error = -ENOMEM; + break; + } + + cand_len = orig_len - eaten; + + head = psock->rx_skb_head; + if (!head) { + head = skb; + psock->rx_skb_head = head; + /* Will set rx_skb_nextp on next packet if needed */ + psock->rx_skb_nextp = NULL; + rxm = kcm_rx_msg(head); + memset(rxm, 0, sizeof(*rxm)); + rxm->offset = orig_offset + eaten; + } else { + /* Unclone since we may be appending to an skb that we + * already share a frag_list with. + */ + err = skb_unclone(skb, GFP_ATOMIC); + if (err) { + desc->error = err; + break; + } + + rxm = kcm_rx_msg(head); + *psock->rx_skb_nextp = skb; + psock->rx_skb_nextp = &skb->next; + head->data_len += skb->len; + head->len += skb->len; + head->truesize += skb->truesize; + } + + if (!rxm->full_len) { + ssize_t len; + + len = KCM_RUN_FILTER(psock->bpf_prog, head); + + if (!len) { + /* Need more header to determine length */ + rxm->accum_len += cand_len; + eaten += cand_len; + WARN_ON(eaten != orig_len); + break; + } else if (len <= (ssize_t)head->len - + skb->len - rxm->offset) { + /* Length must be into new skb (and also + * greater than zero) + */ + desc->error = -EPROTO; + psock->rx_skb_head = NULL; + kcm_abort_rx_psock(psock, EPROTO, head); + break; + } + + rxm->full_len = len; + } + + extra = (ssize_t)(rxm->accum_len + cand_len) - rxm->full_len; + + if (extra < 0) { + /* Message not complete yet. */ + rxm->accum_len += cand_len; + eaten += cand_len; + WARN_ON(eaten != orig_len); + break; + } + + /* Positive extra indicates ore bytes than needed for the + * message + */ + + WARN_ON(extra > cand_len); + + eaten += (cand_len - extra); + + /* Hurray, we have a new message! */ + psock->rx_skb_head = NULL; + +try_queue: + kcm = reserve_rx_kcm(psock, head); + if (!kcm) { + /* Unable to reserve a KCM, message is held in psock. */ + break; + } + + if (kcm_queue_rcv_skb(&kcm->sk, head)) { + /* Should mean socket buffer full */ + unreserve_rx_kcm(psock, false); + goto try_queue; + } + } + + if (cloned_orig) + kfree_skb(orig_skb); + + return eaten; +} + +/* Called with lock held on lower socket */ +static int psock_tcp_read_sock(struct kcm_psock *psock) +{ + read_descriptor_t desc; + + desc.arg.data = psock; + desc.error = 0; + desc.count = 1; /* give more than one skb per call */ + + /* sk should be locked here, so okay to do tcp_read_sock */ + tcp_read_sock(psock->sk, &desc, kcm_tcp_recv); + + unreserve_rx_kcm(psock, true); + + return desc.error; +} + +/* Lower sock lock held */ +static void psock_tcp_data_ready(struct sock *sk) +{ + struct kcm_psock *psock; + + read_lock_bh(&sk->sk_callback_lock); + + psock = (struct kcm_psock *)sk->sk_user_data; + if (unlikely(!psock || psock->rx_stopped)) + goto out; + + if (psock->ready_rx_msg) + goto out; + + if (psock_tcp_read_sock(psock) == -ENOMEM) + queue_delayed_work(kcm_wq, &psock->rx_delayed_work, 0); + +out: + read_unlock_bh(&sk->sk_callback_lock); +} + +static void do_psock_rx_work(struct kcm_psock *psock) +{ + read_descriptor_t rd_desc; + struct sock *csk = psock->sk; + + /* We need the read lock to synchronize with psock_tcp_data_ready. We + * need the socket lock for calling tcp_read_sock. + */ + lock_sock(csk); + read_lock_bh(&csk->sk_callback_lock); + + if (unlikely(csk->sk_user_data != psock)) + goto out; + + if (unlikely(psock->rx_stopped)) + goto out; + + if (psock->ready_rx_msg) + goto out; + + rd_desc.arg.data = psock; + + if (psock_tcp_read_sock(psock) == -ENOMEM) + queue_delayed_work(kcm_wq, &psock->rx_delayed_work, 0); + +out: + read_unlock_bh(&csk->sk_callback_lock); + release_sock(csk); +} + +static void psock_rx_work(struct work_struct *w) +{ + do_psock_rx_work(container_of(w, struct kcm_psock, rx_work)); +} + +static void psock_rx_delayed_work(struct work_struct *w) +{ + do_psock_rx_work(container_of(w, struct kcm_psock, + rx_delayed_work.work)); +} + +static void psock_tcp_state_change(struct sock *sk) +{ + /* TCP only does a POLLIN for a half close. Do a POLLHUP here + * since application will normally not poll with POLLIN + * on the TCP sockets. + */ + + report_csk_error(sk, EPIPE); +} + +static void psock_tcp_write_space(struct sock *sk) +{ + struct kcm_psock *psock; + struct kcm_mux *mux; + struct kcm_sock *kcm; + + read_lock_bh(&sk->sk_callback_lock); + + psock = (struct kcm_psock *)sk->sk_user_data; + if (unlikely(!psock)) + goto out; + + mux = psock->mux; + + spin_lock_bh(&mux->lock); + + /* Check if the socket is reserved so someone is waiting for sending. */ + kcm = psock->tx_kcm; + if (kcm) + queue_work(kcm_wq, &kcm->tx_work); + + spin_unlock_bh(&mux->lock); +out: + read_unlock_bh(&sk->sk_callback_lock); +} + +static void unreserve_psock(struct kcm_sock *kcm); + +/* kcm sock is locked. */ +static struct kcm_psock *reserve_psock(struct kcm_sock *kcm) +{ + struct kcm_mux *mux = kcm->mux; + struct kcm_psock *psock; + + psock = kcm->tx_psock; + + smp_rmb(); /* Must read tx_psock before tx_wait */ + + if (psock) { + WARN_ON(kcm->tx_wait); + if (unlikely(psock->tx_stopped)) + unreserve_psock(kcm); + else + return kcm->tx_psock; + } + + spin_lock_bh(&mux->lock); + + /* Check again under lock to see if psock was reserved for this + * psock via psock_unreserve. + */ + psock = kcm->tx_psock; + if (unlikely(psock)) { + WARN_ON(kcm->tx_wait); + spin_unlock_bh(&mux->lock); + return kcm->tx_psock; + } + + if (!list_empty(&mux->psocks_avail)) { + psock = list_first_entry(&mux->psocks_avail, + struct kcm_psock, + psock_avail_list); + list_del(&psock->psock_avail_list); + if (kcm->tx_wait) { + list_del(&kcm->wait_psock_list); + kcm->tx_wait = false; + } + kcm->tx_psock = psock; + psock->tx_kcm = kcm; + } else if (!kcm->tx_wait) { + list_add_tail(&kcm->wait_psock_list, + &mux->kcm_tx_waiters); + kcm->tx_wait = true; + } + + spin_unlock_bh(&mux->lock); + + return psock; +} + +/* mux lock held */ +static void psock_now_avail(struct kcm_psock *psock) +{ + struct kcm_mux *mux = psock->mux; + struct kcm_sock *kcm; + + if (list_empty(&mux->kcm_tx_waiters)) { + list_add_tail(&psock->psock_avail_list, + &mux->psocks_avail); + } else { + kcm = list_first_entry(&mux->kcm_tx_waiters, + struct kcm_sock, + wait_psock_list); + list_del(&kcm->wait_psock_list); + kcm->tx_wait = false; + psock->tx_kcm = kcm; + + /* Commit before changing tx_psock since that is read in + * reserve_psock before queuing work. + */ + smp_mb(); + + kcm->tx_psock = psock; + queue_work(kcm_wq, &kcm->tx_work); + } +} + +/* kcm sock is locked. */ +static void unreserve_psock(struct kcm_sock *kcm) +{ + struct kcm_psock *psock; + struct kcm_mux *mux = kcm->mux; + + spin_lock_bh(&mux->lock); + + psock = kcm->tx_psock; + + if (WARN_ON(!psock)) { + spin_unlock_bh(&mux->lock); + return; + } + + smp_rmb(); /* Read tx_psock before tx_wait */ + + WARN_ON(kcm->tx_wait); + + kcm->tx_psock = NULL; + psock->tx_kcm = NULL; + + if (unlikely(psock->tx_stopped)) { + if (psock->done) { + /* Deferred free */ + list_del(&psock->psock_list); + mux->psocks_cnt--; + sock_put(psock->sk); + fput(psock->sk->sk_socket->file); + kmem_cache_free(kcm_psockp, psock); + } + + /* Don't put back on available list */ + + spin_unlock_bh(&mux->lock); + + return; + } + + psock_now_avail(psock); + + spin_unlock_bh(&mux->lock); +} + +/* Write any messages ready on the kcm socket. Called with kcm sock lock + * held. Return bytes actually sent or error. + */ +static int kcm_write_msgs(struct kcm_sock *kcm) +{ + struct sock *sk = &kcm->sk; + struct kcm_psock *psock; + struct sk_buff *skb, *head; + struct kcm_tx_msg *txm; + unsigned short fragidx, frag_offset; + unsigned int sent, total_sent = 0; + int ret = 0; + + kcm->tx_wait_more = false; + psock = kcm->tx_psock; + if (unlikely(psock && psock->tx_stopped)) { + /* A reserved psock was aborted asynchronously. Unreserve + * it and we'll retry the message. + */ + unreserve_psock(kcm); + if (skb_queue_empty(&sk->sk_write_queue)) + return 0; + + kcm_tx_msg(skb_peek(&sk->sk_write_queue))->sent = 0; + + } else if (skb_queue_empty(&sk->sk_write_queue)) { + return 0; + } + + head = skb_peek(&sk->sk_write_queue); + txm = kcm_tx_msg(head); + + if (txm->sent) { + /* Send of first skbuff in queue already in progress */ + if (WARN_ON(!psock)) { + ret = -EINVAL; + goto out; + } + sent = txm->sent; + frag_offset = txm->frag_offset; + fragidx = txm->fragidx; + skb = txm->frag_skb; + + goto do_frag; + } + +try_again: + psock = reserve_psock(kcm); + if (!psock) + goto out; + + do { + skb = head; + txm = kcm_tx_msg(head); + sent = 0; + +do_frag_list: + if (WARN_ON(!skb_shinfo(skb)->nr_frags)) { + ret = -EINVAL; + goto out; + } + + for (fragidx = 0; fragidx < skb_shinfo(skb)->nr_frags; + fragidx++) { + skb_frag_t *frag; + + frag_offset = 0; +do_frag: + frag = &skb_shinfo(skb)->frags[fragidx]; + if (WARN_ON(!frag->size)) { + ret = -EINVAL; + goto out; + } + + ret = kernel_sendpage(psock->sk->sk_socket, + frag->page.p, + frag->page_offset + frag_offset, + frag->size - frag_offset, + MSG_DONTWAIT); + if (ret <= 0) { + if (ret == -EAGAIN) { + /* Save state to try again when there's + * write space on the socket + */ + txm->sent = sent; + txm->frag_offset = frag_offset; + txm->fragidx = fragidx; + txm->frag_skb = skb; + + ret = 0; + goto out; + } + + /* Hard failure in sending message, abort this + * psock since it has lost framing + * synchonization and retry sending the + * message from the beginning. + */ + kcm_abort_tx_psock(psock, ret ? -ret : EPIPE, + true); + unreserve_psock(kcm); + + txm->sent = 0; + ret = 0; + + goto try_again; + } + + sent += ret; + frag_offset += ret; + if (frag_offset < frag->size) { + /* Not finished with this frag */ + goto do_frag; + } + } + + if (skb == head) { + if (skb_has_frag_list(skb)) { + skb = skb_shinfo(skb)->frag_list; + goto do_frag_list; + } + } else if (skb->next) { + skb = skb->next; + goto do_frag_list; + } + + /* Successfully sent the whole packet, account for it. */ + skb_dequeue(&sk->sk_write_queue); + kfree_skb(head); + sk->sk_wmem_queued -= sent; + total_sent += sent; + } while ((head = skb_peek(&sk->sk_write_queue))); +out: + if (!head) { + /* Done with all queued messages. */ + WARN_ON(!skb_queue_empty(&sk->sk_write_queue)); + unreserve_psock(kcm); + } + + /* Check if write space is available */ + sk->sk_write_space(sk); + + return total_sent ? : ret; +} + +static void kcm_tx_work(struct work_struct *w) +{ + struct kcm_sock *kcm = container_of(w, struct kcm_sock, tx_work); + struct sock *sk = &kcm->sk; + int err; + + lock_sock(sk); + + /* Primarily for SOCK_DGRAM sockets, also handle asynchronous tx + * aborts + */ + err = kcm_write_msgs(kcm); + if (err < 0) { + /* Hard failure in write, report error on KCM socket */ + pr_warn("KCM: Hard failure on kcm_write_msgs %d\n", err); + report_csk_error(&kcm->sk, -err); + goto out; + } + + /* Primarily for SOCK_SEQPACKET sockets */ + if (likely(sk->sk_socket) && + test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) { + clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags); + sk->sk_write_space(sk); + } + +out: + release_sock(sk); +} + +static void kcm_push(struct kcm_sock *kcm) +{ + if (kcm->tx_wait_more) + kcm_write_msgs(kcm); +} + +static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) +{ + struct sock *sk = sock->sk; + struct kcm_sock *kcm = kcm_sk(sk); + struct sk_buff *skb = NULL, *head = NULL; + size_t copy, copied = 0; + long timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); + int eor = (sock->type == SOCK_DGRAM) ? + !(msg->msg_flags & MSG_MORE) : !!(msg->msg_flags & MSG_EOR); + int err = -EPIPE; + + lock_sock(sk); + + /* Per tcp_sendmsg this should be in poll */ + sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); + + if (sk->sk_err) + goto out_error; + + if (kcm->seq_skb) { + /* Previously opened message */ + head = kcm->seq_skb; + skb = kcm_tx_msg(head)->last_skb; + goto start; + } + + /* Call the sk_stream functions to manage the sndbuf mem. */ + if (!sk_stream_memory_free(sk)) { + kcm_push(kcm); + set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); + err = sk_stream_wait_memory(sk, &timeo); + if (err) + goto out_error; + } + + /* New message, alloc head skb */ + head = alloc_skb(0, sk->sk_allocation); + while (!head) { + kcm_push(kcm); + err = sk_stream_wait_memory(sk, &timeo); + if (err) + goto out_error; + + head = alloc_skb(0, sk->sk_allocation); + } + + skb = head; + + /* Set ip_summed to CHECKSUM_UNNECESSARY to avoid calling + * csum_and_copy_from_iter from skb_do_copy_data_nocache. + */ + skb->ip_summed = CHECKSUM_UNNECESSARY; + +start: + while (msg_data_left(msg)) { + bool merge = true; + int i = skb_shinfo(skb)->nr_frags; + struct page_frag *pfrag = sk_page_frag(sk); + + if (!sk_page_frag_refill(sk, pfrag)) + goto wait_for_memory; + + if (!skb_can_coalesce(skb, i, pfrag->page, + pfrag->offset)) { + if (i == MAX_SKB_FRAGS) { + struct sk_buff *tskb; + + tskb = alloc_skb(0, sk->sk_allocation); + if (!tskb) + goto wait_for_memory; + + if (head == skb) + skb_shinfo(head)->frag_list = tskb; + else + skb->next = tskb; + + skb = tskb; + skb->ip_summed = CHECKSUM_UNNECESSARY; + continue; + } + merge = false; + } + + copy = min_t(int, msg_data_left(msg), + pfrag->size - pfrag->offset); + + if (!sk_wmem_schedule(sk, copy)) + goto wait_for_memory; + + err = skb_copy_to_page_nocache(sk, &msg->msg_iter, skb, + pfrag->page, + pfrag->offset, + copy); + if (err) + goto out_error; + + /* Update the skb. */ + if (merge) { + skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); + } else { + skb_fill_page_desc(skb, i, pfrag->page, + pfrag->offset, copy); + get_page(pfrag->page); + } + + pfrag->offset += copy; + copied += copy; + if (head != skb) { + head->len += copy; + head->data_len += copy; + } + + continue; + +wait_for_memory: + kcm_push(kcm); + err = sk_stream_wait_memory(sk, &timeo); + if (err) + goto out_error; + } + + if (eor) { + bool not_busy = skb_queue_empty(&sk->sk_write_queue); + + /* Message complete, queue it on send buffer */ + __skb_queue_tail(&sk->sk_write_queue, head); + kcm->seq_skb = NULL; + + if (msg->msg_flags & MSG_BATCH) { + kcm->tx_wait_more = true; + } else if (kcm->tx_wait_more || not_busy) { + err = kcm_write_msgs(kcm); + if (err < 0) { + /* We got a hard error in write_msgs but have + * already queued this message. Report an error + * in the socket, but don't affect return value + * from sendmsg + */ + pr_warn("KCM: Hard failure on kcm_write_msgs\n"); + report_csk_error(&kcm->sk, -err); + } + } + } else { + /* Message not complete, save state */ +partial_message: + kcm->seq_skb = head; + kcm_tx_msg(head)->last_skb = skb; + } + + release_sock(sk); + return copied; + +out_error: + kcm_push(kcm); + + if (copied && sock->type == SOCK_SEQPACKET) { + /* Wrote some bytes before encountering an + * error, return partial success. + */ + goto partial_message; + } + + if (head != kcm->seq_skb) + kfree_skb(head); + + err = sk_stream_error(sk, msg->msg_flags, err); + + /* make sure we wake any epoll edge trigger waiter */ + if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && err == -EAGAIN)) + sk->sk_write_space(sk); + + release_sock(sk); + return err; +} + +static struct sk_buff *kcm_wait_data(struct sock *sk, int flags, + long timeo, int *err) +{ + struct sk_buff *skb; + + while (!(skb = skb_peek(&sk->sk_receive_queue))) { + if (sk->sk_err) { + *err = sock_error(sk); + return NULL; + } + + if (sock_flag(sk, SOCK_DONE)) + return NULL; + + if ((flags & MSG_DONTWAIT) || !timeo) { + *err = -EAGAIN; + return NULL; + } + + sk_wait_data(sk, &timeo, NULL); + + /* Handle signals */ + if (signal_pending(current)) { + *err = sock_intr_errno(timeo); + return NULL; + } + } + + return skb; +} + +static int kcm_recvmsg(struct socket *sock, struct msghdr *msg, + size_t len, int flags) +{ + struct sock *sk = sock->sk; + int err = 0; + long timeo; + struct kcm_rx_msg *rxm; + int copied = 0; + struct sk_buff *skb; + + timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); + + lock_sock(sk); + + skb = kcm_wait_data(sk, flags, timeo, &err); + if (!skb) + goto out; + + /* Okay, have a message on the receive queue */ + + rxm = kcm_rx_msg(skb); + + if (len > rxm->full_len) + len = rxm->full_len; + + err = skb_copy_datagram_msg(skb, rxm->offset, msg, len); + if (err < 0) + goto out; + + copied = len; + if (likely(!(flags & MSG_PEEK))) { + if (copied < rxm->full_len) { + if (sock->type == SOCK_DGRAM) { + /* Truncated message */ + msg->msg_flags |= MSG_TRUNC; + goto msg_finished; + } + rxm->offset += copied; + rxm->full_len -= copied; + } else { +msg_finished: + /* Finished with message */ + msg->msg_flags |= MSG_EOR; + skb_unlink(skb, &sk->sk_receive_queue); + kfree_skb(skb); + } + } + +out: + release_sock(sk); + + return copied ? : err; +} + +/* kcm sock lock held */ +static void kcm_recv_disable(struct kcm_sock *kcm) +{ + struct kcm_mux *mux = kcm->mux; + + if (kcm->rx_disabled) + return; + + spin_lock_bh(&mux->rx_lock); + + kcm->rx_disabled = 1; + + /* If a psock is reserved we'll do cleanup in unreserve */ + if (!kcm->rx_psock) { + if (kcm->rx_wait) { + list_del(&kcm->wait_rx_list); + kcm->rx_wait = false; + } + + requeue_rx_msgs(mux, &kcm->sk.sk_receive_queue); + } + + spin_unlock_bh(&mux->rx_lock); +} + +/* kcm sock lock held */ +static void kcm_recv_enable(struct kcm_sock *kcm) +{ + struct kcm_mux *mux = kcm->mux; + + if (!kcm->rx_disabled) + return; + + spin_lock_bh(&mux->rx_lock); + + kcm->rx_disabled = 0; + kcm_rcv_ready(kcm); + + spin_unlock_bh(&mux->rx_lock); +} + +static int kcm_setsockopt(struct socket *sock, int level, int optname, + char __user *optval, unsigned int optlen) +{ + struct kcm_sock *kcm = kcm_sk(sock->sk); + int val, valbool; + int err = 0; + + if (level != SOL_KCM) + return -ENOPROTOOPT; + + if (optlen < sizeof(int)) + return -EINVAL; + + if (get_user(val, (int __user *)optval)) + return -EINVAL; + + valbool = val ? 1 : 0; + + switch (optname) { + case KCM_RECV_DISABLE: + lock_sock(&kcm->sk); + if (valbool) + kcm_recv_disable(kcm); + else + kcm_recv_enable(kcm); + release_sock(&kcm->sk); + break; + default: + err = -ENOPROTOOPT; + } + + return err; +} + +static int kcm_getsockopt(struct socket *sock, int level, int optname, + char __user *optval, int __user *optlen) +{ + struct kcm_sock *kcm = kcm_sk(sock->sk); + int val, len; + + if (level != SOL_KCM) + return -ENOPROTOOPT; + + if (get_user(len, optlen)) + return -EFAULT; + + len = min_t(unsigned int, len, sizeof(int)); + if (len < 0) + return -EINVAL; + + switch (optname) { + case KCM_RECV_DISABLE: + val = kcm->rx_disabled; + break; + default: + return -ENOPROTOOPT; + } + + if (put_user(len, optlen)) + return -EFAULT; + if (copy_to_user(optval, &val, len)) + return -EFAULT; + return 0; +} + +static void init_kcm_sock(struct kcm_sock *kcm, struct kcm_mux *mux) +{ + struct kcm_sock *tkcm; + struct list_head *head; + int index = 0; + + /* For SOCK_SEQPACKET sock type, datagram_poll checks the sk_state, so + * we set sk_state, otherwise epoll_wait always returns right away with + * POLLHUP + */ + kcm->sk.sk_state = TCP_ESTABLISHED; + + /* Add to mux's kcm sockets list */ + kcm->mux = mux; + spin_lock_bh(&mux->lock); + + head = &mux->kcm_socks; + list_for_each_entry(tkcm, &mux->kcm_socks, kcm_sock_list) { + if (tkcm->index != index) + break; + head = &tkcm->kcm_sock_list; + index++; + } + + list_add(&kcm->kcm_sock_list, head); + kcm->index = index; + + mux->kcm_socks_cnt++; + spin_unlock_bh(&mux->lock); + + INIT_WORK(&kcm->tx_work, kcm_tx_work); + + spin_lock_bh(&mux->rx_lock); + kcm_rcv_ready(kcm); + spin_unlock_bh(&mux->rx_lock); +} + +static int kcm_attach(struct socket *sock, struct socket *csock, + struct bpf_prog *prog) +{ + struct kcm_sock *kcm = kcm_sk(sock->sk); + struct kcm_mux *mux = kcm->mux; + struct sock *csk; + struct kcm_psock *psock = NULL, *tpsock; + struct list_head *head; + int index = 0; + + if (csock->ops->family != PF_INET && + csock->ops->family != PF_INET6) + return -EINVAL; + + csk = csock->sk; + if (!csk) + return -EINVAL; + + /* Only support TCP for now */ + if (csk->sk_protocol != IPPROTO_TCP) + return -EINVAL; + + psock = kmem_cache_zalloc(kcm_psockp, GFP_KERNEL); + if (!psock) + return -ENOMEM; + + psock->mux = mux; + psock->sk = csk; + psock->bpf_prog = prog; + INIT_WORK(&psock->rx_work, psock_rx_work); + INIT_DELAYED_WORK(&psock->rx_delayed_work, psock_rx_delayed_work); + + sock_hold(csk); + + write_lock_bh(&csk->sk_callback_lock); + psock->save_data_ready = csk->sk_data_ready; + psock->save_write_space = csk->sk_write_space; + psock->save_state_change = csk->sk_state_change; + csk->sk_user_data = psock; + csk->sk_data_ready = psock_tcp_data_ready; + csk->sk_write_space = psock_tcp_write_space; + csk->sk_state_change = psock_tcp_state_change; + write_unlock_bh(&csk->sk_callback_lock); + + /* Finished initialization, now add the psock to the MUX. */ + spin_lock_bh(&mux->lock); + head = &mux->psocks; + list_for_each_entry(tpsock, &mux->psocks, psock_list) { + if (tpsock->index != index) + break; + head = &tpsock->psock_list; + index++; + } + + list_add(&psock->psock_list, head); + psock->index = index; + + mux->psocks_cnt++; + psock_now_avail(psock); + spin_unlock_bh(&mux->lock); + + /* Schedule RX work in case there are already bytes queued */ + queue_work(kcm_wq, &psock->rx_work); + + return 0; +} + +static int kcm_attach_ioctl(struct socket *sock, struct kcm_attach *info) +{ + struct socket *csock; + struct bpf_prog *prog; + int err; + + csock = sockfd_lookup(info->fd, &err); + if (!csock) + return -ENOENT; + + prog = bpf_prog_get(info->bpf_fd); + if (IS_ERR(prog)) { + err = PTR_ERR(prog); + goto out; + } + + if (prog->type != BPF_PROG_TYPE_SOCKET_FILTER) { + bpf_prog_put(prog); + err = -EINVAL; + goto out; + } + + err = kcm_attach(sock, csock, prog); + if (err) { + bpf_prog_put(prog); + goto out; + } + + /* Keep reference on file also */ + + return 0; +out: + fput(csock->file); + return err; +} + +static void kcm_unattach(struct kcm_psock *psock) +{ + struct sock *csk = psock->sk; + struct kcm_mux *mux = psock->mux; + + /* Stop getting callbacks from TCP socket. After this there should + * be no way to reserve a kcm for this psock. + */ + write_lock_bh(&csk->sk_callback_lock); + csk->sk_user_data = NULL; + csk->sk_data_ready = psock->save_data_ready; + csk->sk_write_space = psock->save_write_space; + csk->sk_state_change = psock->save_state_change; + psock->rx_stopped = 1; + + if (WARN_ON(psock->rx_kcm)) { + write_unlock_bh(&csk->sk_callback_lock); + return; + } + + spin_lock_bh(&mux->rx_lock); + + /* Stop receiver activities. After this point psock should not be + * able to get onto ready list either through callbacks or work. + */ + if (psock->ready_rx_msg) { + list_del(&psock->psock_ready_list); + kfree_skb(psock->ready_rx_msg); + psock->ready_rx_msg = NULL; + } + + spin_unlock_bh(&mux->rx_lock); + + write_unlock_bh(&csk->sk_callback_lock); + + cancel_work_sync(&psock->rx_work); + cancel_delayed_work_sync(&psock->rx_delayed_work); + + bpf_prog_put(psock->bpf_prog); + + kfree_skb(psock->rx_skb_head); + psock->rx_skb_head = NULL; + + spin_lock_bh(&mux->lock); + + if (psock->tx_kcm) { + /* psock was reserved. Just mark it finished and we will clean + * up in the kcm paths, we need kcm lock which can not be + * acquired here. + */ + spin_unlock_bh(&mux->lock); + + /* We are unattaching a socket that is reserved. Abort the + * socket since we may be out of sync in sending on it. We need + * to do this without the mux lock. + */ + kcm_abort_tx_psock(psock, EPIPE, false); + + spin_lock_bh(&mux->lock); + if (!psock->tx_kcm) { + /* psock now unreserved in window mux was unlocked */ + goto no_reserved; + } + psock->done = 1; + + /* Commit done before queuing work to process it */ + smp_mb(); + + /* Queue tx work to make sure psock->done is handled */ + queue_work(kcm_wq, &psock->tx_kcm->tx_work); + spin_unlock_bh(&mux->lock); + } else { +no_reserved: + if (!psock->tx_stopped) + list_del(&psock->psock_avail_list); + list_del(&psock->psock_list); + mux->psocks_cnt--; + spin_unlock_bh(&mux->lock); + + sock_put(csk); + fput(csk->sk_socket->file); + kmem_cache_free(kcm_psockp, psock); + } +} + +static int kcm_unattach_ioctl(struct socket *sock, struct kcm_unattach *info) +{ + struct kcm_sock *kcm = kcm_sk(sock->sk); + struct kcm_mux *mux = kcm->mux; + struct kcm_psock *psock; + struct socket *csock; + struct sock *csk; + int err; + + csock = sockfd_lookup(info->fd, &err); + if (!csock) + return -ENOENT; + + csk = csock->sk; + if (!csk) { + err = -EINVAL; + goto out; + } + + err = -ENOENT; + + spin_lock_bh(&mux->lock); + + list_for_each_entry(psock, &mux->psocks, psock_list) { + if (psock->sk != csk) + continue; + + /* Found the matching psock */ + + if (psock->unattaching || WARN_ON(psock->done)) { + err = -EALREADY; + break; + } + + psock->unattaching = 1; + + spin_unlock_bh(&mux->lock); + + kcm_unattach(psock); + + err = 0; + goto out; + } + + spin_unlock_bh(&mux->lock); + +out: + fput(csock->file); + return err; +} + +static struct proto kcm_proto = { + .name = "KCM", + .owner = THIS_MODULE, + .obj_size = sizeof(struct kcm_sock), +}; + +/* Clone a kcm socket. */ +static int kcm_clone(struct socket *osock, struct kcm_clone *info, + struct socket **newsockp) +{ + struct socket *newsock; + struct sock *newsk; + struct file *newfile; + int err, newfd; + + err = -ENFILE; + newsock = sock_alloc(); + if (!newsock) + goto out; + + newsock->type = osock->type; + newsock->ops = osock->ops; + + __module_get(newsock->ops->owner); + + newfd = get_unused_fd_flags(0); + if (unlikely(newfd < 0)) { + err = newfd; + goto out_fd_fail; + } + + newfile = sock_alloc_file(newsock, 0, osock->sk->sk_prot_creator->name); + if (unlikely(IS_ERR(newfile))) { + err = PTR_ERR(newfile); + goto out_sock_alloc_fail; + } + + newsk = sk_alloc(sock_net(osock->sk), PF_KCM, GFP_KERNEL, + &kcm_proto, true); + if (!newsk) { + err = -ENOMEM; + goto out_sk_alloc_fail; + } + + sock_init_data(newsock, newsk); + init_kcm_sock(kcm_sk(newsk), kcm_sk(osock->sk)->mux); + + fd_install(newfd, newfile); + *newsockp = newsock; + info->fd = newfd; + + return 0; + +out_sk_alloc_fail: + fput(newfile); +out_sock_alloc_fail: + put_unused_fd(newfd); +out_fd_fail: + sock_release(newsock); +out: + return err; +} + +static int kcm_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) +{ + int err; + + switch (cmd) { + case SIOCKCMATTACH: { + struct kcm_attach info; + + if (copy_from_user(&info, (void __user *)arg, sizeof(info))) + err = -EFAULT; + + err = kcm_attach_ioctl(sock, &info); + + break; + } + case SIOCKCMUNATTACH: { + struct kcm_unattach info; + + if (copy_from_user(&info, (void __user *)arg, sizeof(info))) + err = -EFAULT; + + err = kcm_unattach_ioctl(sock, &info); + + break; + } + case SIOCKCMCLONE: { + struct kcm_clone info; + struct socket *newsock = NULL; + + if (copy_from_user(&info, (void __user *)arg, sizeof(info))) + err = -EFAULT; + + err = kcm_clone(sock, &info, &newsock); + + if (!err) { + if (copy_to_user((void __user *)arg, &info, + sizeof(info))) { + err = -EFAULT; + sock_release(newsock); + } + } + + break; + } + default: + err = -ENOIOCTLCMD; + break; + } + + return err; +} + +static void free_mux(struct rcu_head *rcu) +{ + struct kcm_mux *mux = container_of(rcu, + struct kcm_mux, rcu); + + kmem_cache_free(kcm_muxp, mux); +} + +static void release_mux(struct kcm_mux *mux) +{ + struct kcm_net *knet = mux->knet; + struct kcm_psock *psock, *tmp_psock; + + /* Release psocks */ + list_for_each_entry_safe(psock, tmp_psock, + &mux->psocks, psock_list) { + if (!WARN_ON(psock->unattaching)) + kcm_unattach(psock); + } + + if (WARN_ON(mux->psocks_cnt)) + return; + + __skb_queue_purge(&mux->rx_hold_queue); + + mutex_lock(&knet->mutex); + list_del_rcu(&mux->kcm_mux_list); + knet->count--; + mutex_unlock(&knet->mutex); + + call_rcu(&mux->rcu, free_mux); +} + +static void kcm_done(struct kcm_sock *kcm) +{ + struct kcm_mux *mux = kcm->mux; + struct sock *sk = &kcm->sk; + int socks_cnt; + + spin_lock_bh(&mux->rx_lock); + if (kcm->rx_psock) { + /* Cleanup in unreserve_rx_kcm */ + WARN_ON(kcm->done); + kcm->rx_disabled = 1; + kcm->done = 1; + spin_unlock_bh(&mux->rx_lock); + return; + } + + if (kcm->rx_wait) { + list_del(&kcm->wait_rx_list); + kcm->rx_wait = false; + } + /* Move any pending receive messages to other kcm sockets */ + requeue_rx_msgs(mux, &sk->sk_receive_queue); + + spin_unlock_bh(&mux->rx_lock); + + if (WARN_ON(sk_rmem_alloc_get(sk))) + return; + + /* Detach from MUX */ + spin_lock_bh(&mux->lock); + + list_del(&kcm->kcm_sock_list); + mux->kcm_socks_cnt--; + socks_cnt = mux->kcm_socks_cnt; + + spin_unlock_bh(&mux->lock); + + if (!socks_cnt) { + /* We are done with the mux now. */ + release_mux(mux); + } + + WARN_ON(kcm->rx_wait); + + sock_put(&kcm->sk); +} + +/* Called by kcm_release to close a KCM socket. + * If this is the last KCM socket on the MUX, destroy the MUX. + */ +static int kcm_release(struct socket *sock) +{ + struct sock *sk = sock->sk; + struct kcm_sock *kcm; + struct kcm_mux *mux; + struct kcm_psock *psock; + + if (!sk) + return 0; + + kcm = kcm_sk(sk); + mux = kcm->mux; + + sock_orphan(sk); + kfree_skb(kcm->seq_skb); + + lock_sock(sk); + /* Purge queue under lock to avoid race condition with tx_work trying + * to act when queue is nonempty. If tx_work runs after this point + * it will just return. + */ + __skb_queue_purge(&sk->sk_write_queue); + release_sock(sk); + + spin_lock_bh(&mux->lock); + if (kcm->tx_wait) { + /* Take of tx_wait list, after this point there should be no way + * that a psock will be assigned to this kcm. + */ + list_del(&kcm->wait_psock_list); + kcm->tx_wait = false; + } + spin_unlock_bh(&mux->lock); + + /* Cancel work. After this point there should be no outside references + * to the kcm socket. + */ + cancel_work_sync(&kcm->tx_work); + + lock_sock(sk); + psock = kcm->tx_psock; + if (psock) { + /* A psock was reserved, so we need to kill it since it + * may already have some bytes queued from a message. We + * need to do this after removing kcm from tx_wait list. + */ + kcm_abort_tx_psock(psock, EPIPE, false); + unreserve_psock(kcm); + } + release_sock(sk); + + WARN_ON(kcm->tx_wait); + WARN_ON(kcm->tx_psock); + + sock->sk = NULL; + + kcm_done(kcm); + + return 0; +} + +static const struct proto_ops kcm_ops = { + .family = PF_KCM, + .owner = THIS_MODULE, + .release = kcm_release, + .bind = sock_no_bind, + .connect = sock_no_connect, + .socketpair = sock_no_socketpair, + .accept = sock_no_accept, + .getname = sock_no_getname, + .poll = datagram_poll, + .ioctl = kcm_ioctl, + .listen = sock_no_listen, + .shutdown = sock_no_shutdown, + .setsockopt = kcm_setsockopt, + .getsockopt = kcm_getsockopt, + .sendmsg = kcm_sendmsg, + .recvmsg = kcm_recvmsg, + .mmap = sock_no_mmap, + .sendpage = sock_no_sendpage, +}; + +/* Create proto operation for kcm sockets */ +static int kcm_create(struct net *net, struct socket *sock, + int protocol, int kern) +{ + struct kcm_net *knet = net_generic(net, kcm_net_id); + struct sock *sk; + struct kcm_mux *mux; + + switch (sock->type) { + case SOCK_DGRAM: + case SOCK_SEQPACKET: + sock->ops = &kcm_ops; + break; + default: + return -ESOCKTNOSUPPORT; + } + + if (protocol != KCMPROTO_CONNECTED) + return -EPROTONOSUPPORT; + + sk = sk_alloc(net, PF_KCM, GFP_KERNEL, &kcm_proto, kern); + if (!sk) + return -ENOMEM; + + /* Allocate a kcm mux, shared between KCM sockets */ + mux = kmem_cache_zalloc(kcm_muxp, GFP_KERNEL); + if (!mux) { + sk_free(sk); + return -ENOMEM; + } + + spin_lock_init(&mux->lock); + spin_lock_init(&mux->rx_lock); + INIT_LIST_HEAD(&mux->kcm_socks); + INIT_LIST_HEAD(&mux->kcm_rx_waiters); + INIT_LIST_HEAD(&mux->kcm_tx_waiters); + + INIT_LIST_HEAD(&mux->psocks); + INIT_LIST_HEAD(&mux->psocks_ready); + INIT_LIST_HEAD(&mux->psocks_avail); + + mux->knet = knet; + + /* Add new MUX to list */ + mutex_lock(&knet->mutex); + list_add_rcu(&mux->kcm_mux_list, &knet->mux_list); + knet->count++; + mutex_unlock(&knet->mutex); + + skb_queue_head_init(&mux->rx_hold_queue); + + /* Init KCM socket */ + sock_init_data(sock, sk); + init_kcm_sock(kcm_sk(sk), mux); + + return 0; +} + +static struct net_proto_family kcm_family_ops = { + .family = PF_KCM, + .create = kcm_create, + .owner = THIS_MODULE, +}; + +static __net_init int kcm_init_net(struct net *net) +{ + struct kcm_net *knet = net_generic(net, kcm_net_id); + + INIT_LIST_HEAD_RCU(&knet->mux_list); + mutex_init(&knet->mutex); + + return 0; +} + +static __net_exit void kcm_exit_net(struct net *net) +{ + struct kcm_net *knet = net_generic(net, kcm_net_id); + + /* All KCM sockets should be closed at this point, which should mean + * that all multiplexors and psocks have been destroyed. + */ + WARN_ON(!list_empty(&knet->mux_list)); +} + +static struct pernet_operations kcm_net_ops = { + .init = kcm_init_net, + .exit = kcm_exit_net, + .id = &kcm_net_id, + .size = sizeof(struct kcm_net), +}; + +static int __init kcm_init(void) +{ + int err = -ENOMEM; + + kcm_muxp = kmem_cache_create("kcm_mux_cache", + sizeof(struct kcm_mux), 0, + SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); + if (!kcm_muxp) + goto fail; + + kcm_psockp = kmem_cache_create("kcm_psock_cache", + sizeof(struct kcm_psock), 0, + SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); + if (!kcm_psockp) + goto fail; + + kcm_wq = create_singlethread_workqueue("kkcmd"); + if (!kcm_wq) + goto fail; + + err = proto_register(&kcm_proto, 1); + if (err) + goto fail; + + err = sock_register(&kcm_family_ops); + if (err) + goto sock_register_fail; + + err = register_pernet_device(&kcm_net_ops); + if (err) + goto net_ops_fail; + + return 0; + +net_ops_fail: + sock_unregister(PF_KCM); + +sock_register_fail: + proto_unregister(&kcm_proto); + +fail: + kmem_cache_destroy(kcm_muxp); + kmem_cache_destroy(kcm_psockp); + + if (kcm_wq) + destroy_workqueue(kcm_wq); + + return err; +} + +static void __exit kcm_exit(void) +{ + unregister_pernet_device(&kcm_net_ops); + sock_unregister(PF_KCM); + proto_unregister(&kcm_proto); + destroy_workqueue(kcm_wq); + + kmem_cache_destroy(kcm_muxp); + kmem_cache_destroy(kcm_psockp); +} + +module_init(kcm_init); +module_exit(kcm_exit); + +MODULE_LICENSE("GPL"); +MODULE_ALIAS_NETPROTO(PF_KCM); + -- cgit v1.2.3-71-gd317 From cd6e111bf5be5c70aef96a86d791ee7be0c0e137 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Mon, 7 Mar 2016 14:11:07 -0800 Subject: kcm: Add statistics and proc interfaces This patch adds various counters for KCM. These include counters for messages and bytes received or sent, as well as counters for number of attached/unattached TCP sockets and other error or edge events. The statistics are exposed via a proc interface. /proc/net/kcm provides statistics per KCM socket and per psock (attached TCP sockets). /proc/net/kcm_stats provides aggregate statistics. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/net/kcm.h | 94 ++++++++++++ net/kcm/Makefile | 2 +- net/kcm/kcmproc.c | 422 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ net/kcm/kcmsock.c | 80 +++++++++++ 4 files changed, 597 insertions(+), 1 deletion(-) create mode 100644 net/kcm/kcmproc.c (limited to 'include/net') diff --git a/include/net/kcm.h b/include/net/kcm.h index 1bcae39070ec..39c7abe98552 100644 --- a/include/net/kcm.h +++ b/include/net/kcm.h @@ -17,6 +17,42 @@ extern unsigned int kcm_net_id; +#define KCM_STATS_ADD(stat, count) ((stat) += (count)) +#define KCM_STATS_INCR(stat) ((stat)++) + +struct kcm_psock_stats { + unsigned long long rx_msgs; + unsigned long long rx_bytes; + unsigned long long tx_msgs; + unsigned long long tx_bytes; + unsigned int rx_aborts; + unsigned int rx_mem_fail; + unsigned int rx_need_more_hdr; + unsigned int rx_bad_hdr_len; + unsigned long long reserved; + unsigned long long unreserved; + unsigned int tx_aborts; +}; + +struct kcm_mux_stats { + unsigned long long rx_msgs; + unsigned long long rx_bytes; + unsigned long long tx_msgs; + unsigned long long tx_bytes; + unsigned int rx_ready_drops; + unsigned int tx_retries; + unsigned int psock_attach; + unsigned int psock_unattach_rsvd; + unsigned int psock_unattach; +}; + +struct kcm_stats { + unsigned long long rx_msgs; + unsigned long long rx_bytes; + unsigned long long tx_msgs; + unsigned long long tx_bytes; +}; + struct kcm_tx_msg { unsigned int sent; unsigned int fragidx; @@ -41,6 +77,8 @@ struct kcm_sock { u32 done : 1; struct work_struct done_work; + struct kcm_stats stats; + /* Transmit */ struct kcm_psock *tx_psock; struct work_struct tx_work; @@ -77,6 +115,8 @@ struct kcm_psock { struct list_head psock_list; + struct kcm_psock_stats stats; + /* Receive */ struct sk_buff *rx_skb_head; struct sk_buff **rx_skb_nextp; @@ -86,15 +126,21 @@ struct kcm_psock { struct delayed_work rx_delayed_work; struct bpf_prog *bpf_prog; struct kcm_sock *rx_kcm; + unsigned long long saved_rx_bytes; + unsigned long long saved_rx_msgs; /* Transmit */ struct kcm_sock *tx_kcm; struct list_head psock_avail_list; + unsigned long long saved_tx_bytes; + unsigned long long saved_tx_msgs; }; /* Per net MUX list */ struct kcm_net { struct mutex mutex; + struct kcm_psock_stats aggregate_psock_stats; + struct kcm_mux_stats aggregate_mux_stats; struct list_head mux_list; int count; }; @@ -110,6 +156,9 @@ struct kcm_mux { struct list_head psocks; /* List of all psocks on MUX */ int psocks_cnt; /* Total attached sockets */ + struct kcm_mux_stats stats; + struct kcm_psock_stats aggregate_psock_stats; + /* Receive */ spinlock_t rx_lock ____cacheline_aligned_in_smp; struct list_head kcm_rx_waiters; /* KCMs waiting for receiving */ @@ -122,4 +171,49 @@ struct kcm_mux { struct list_head kcm_tx_waiters; /* KCMs waiting for a TX psock */ }; +#ifdef CONFIG_PROC_FS +int kcm_proc_init(void); +void kcm_proc_exit(void); +#else +static int kcm_proc_init(void) { return 0; } +static void kcm_proc_exit(void) { } +#endif + +static inline void aggregate_psock_stats(struct kcm_psock_stats *stats, + struct kcm_psock_stats *agg_stats) +{ + /* Save psock statistics in the mux when psock is being unattached. */ + +#define SAVE_PSOCK_STATS(_stat) (agg_stats->_stat += stats->_stat) + SAVE_PSOCK_STATS(rx_msgs); + SAVE_PSOCK_STATS(rx_bytes); + SAVE_PSOCK_STATS(rx_aborts); + SAVE_PSOCK_STATS(rx_mem_fail); + SAVE_PSOCK_STATS(rx_need_more_hdr); + SAVE_PSOCK_STATS(rx_bad_hdr_len); + SAVE_PSOCK_STATS(tx_msgs); + SAVE_PSOCK_STATS(tx_bytes); + SAVE_PSOCK_STATS(reserved); + SAVE_PSOCK_STATS(unreserved); + SAVE_PSOCK_STATS(tx_aborts); +#undef SAVE_PSOCK_STATS +} + +static inline void aggregate_mux_stats(struct kcm_mux_stats *stats, + struct kcm_mux_stats *agg_stats) +{ + /* Save psock statistics in the mux when psock is being unattached. */ + +#define SAVE_MUX_STATS(_stat) (agg_stats->_stat += stats->_stat) + SAVE_MUX_STATS(rx_msgs); + SAVE_MUX_STATS(rx_bytes); + SAVE_MUX_STATS(tx_msgs); + SAVE_MUX_STATS(tx_bytes); + SAVE_MUX_STATS(rx_ready_drops); + SAVE_MUX_STATS(psock_attach); + SAVE_MUX_STATS(psock_unattach_rsvd); + SAVE_MUX_STATS(psock_unattach); +#undef SAVE_MUX_STATS +} + #endif /* __NET_KCM_H_ */ diff --git a/net/kcm/Makefile b/net/kcm/Makefile index cb525f7c5a13..71256133e677 100644 --- a/net/kcm/Makefile +++ b/net/kcm/Makefile @@ -1,3 +1,3 @@ obj-$(CONFIG_AF_KCM) += kcm.o -kcm-y := kcmsock.o +kcm-y := kcmsock.o kcmproc.o diff --git a/net/kcm/kcmproc.c b/net/kcm/kcmproc.c new file mode 100644 index 000000000000..5eb9809c0f59 --- /dev/null +++ b/net/kcm/kcmproc.c @@ -0,0 +1,422 @@ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#ifdef CONFIG_PROC_FS +struct kcm_seq_muxinfo { + char *name; + const struct file_operations *seq_fops; + const struct seq_operations seq_ops; +}; + +static struct kcm_mux *kcm_get_first(struct seq_file *seq) +{ + struct net *net = seq_file_net(seq); + struct kcm_net *knet = net_generic(net, kcm_net_id); + + return list_first_or_null_rcu(&knet->mux_list, + struct kcm_mux, kcm_mux_list); +} + +static struct kcm_mux *kcm_get_next(struct kcm_mux *mux) +{ + struct kcm_net *knet = mux->knet; + + return list_next_or_null_rcu(&knet->mux_list, &mux->kcm_mux_list, + struct kcm_mux, kcm_mux_list); +} + +static struct kcm_mux *kcm_get_idx(struct seq_file *seq, loff_t pos) +{ + struct net *net = seq_file_net(seq); + struct kcm_net *knet = net_generic(net, kcm_net_id); + struct kcm_mux *m; + + list_for_each_entry_rcu(m, &knet->mux_list, kcm_mux_list) { + if (!pos) + return m; + --pos; + } + return NULL; +} + +static void *kcm_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + void *p; + + if (v == SEQ_START_TOKEN) + p = kcm_get_first(seq); + else + p = kcm_get_next(v); + ++*pos; + return p; +} + +static void *kcm_seq_start(struct seq_file *seq, loff_t *pos) + __acquires(rcu) +{ + rcu_read_lock(); + + if (!*pos) + return SEQ_START_TOKEN; + else + return kcm_get_idx(seq, *pos - 1); +} + +static void kcm_seq_stop(struct seq_file *seq, void *v) + __releases(rcu) +{ + rcu_read_unlock(); +} + +struct kcm_proc_mux_state { + struct seq_net_private p; + int idx; +}; + +static int kcm_seq_open(struct inode *inode, struct file *file) +{ + struct kcm_seq_muxinfo *muxinfo = PDE_DATA(inode); + int err; + + err = seq_open_net(inode, file, &muxinfo->seq_ops, + sizeof(struct kcm_proc_mux_state)); + if (err < 0) + return err; + return err; +} + +static void kcm_format_mux_header(struct seq_file *seq) +{ + struct net *net = seq_file_net(seq); + struct kcm_net *knet = net_generic(net, kcm_net_id); + + seq_printf(seq, + "*** KCM statistics (%d MUX) ****\n", + knet->count); + + seq_printf(seq, + "%-14s %-10s %-16s %-10s %-16s %-8s %-8s %-8s %-8s %s", + "Object", + "RX-Msgs", + "RX-Bytes", + "TX-Msgs", + "TX-Bytes", + "Recv-Q", + "Rmem", + "Send-Q", + "Smem", + "Status"); + + /* XXX: pdsts header stuff here */ + seq_puts(seq, "\n"); +} + +static void kcm_format_sock(struct kcm_sock *kcm, struct seq_file *seq, + int i, int *len) +{ + seq_printf(seq, + " kcm-%-7u %-10llu %-16llu %-10llu %-16llu %-8d %-8d %-8d %-8s ", + kcm->index, + kcm->stats.rx_msgs, + kcm->stats.rx_bytes, + kcm->stats.tx_msgs, + kcm->stats.tx_bytes, + kcm->sk.sk_receive_queue.qlen, + sk_rmem_alloc_get(&kcm->sk), + kcm->sk.sk_write_queue.qlen, + "-"); + + if (kcm->tx_psock) + seq_printf(seq, "Psck-%u ", kcm->tx_psock->index); + + if (kcm->tx_wait) + seq_puts(seq, "TxWait "); + + if (kcm->tx_wait_more) + seq_puts(seq, "WMore "); + + if (kcm->rx_wait) + seq_puts(seq, "RxWait "); + + seq_puts(seq, "\n"); +} + +static void kcm_format_psock(struct kcm_psock *psock, struct seq_file *seq, + int i, int *len) +{ + seq_printf(seq, + " psock-%-5u %-10llu %-16llu %-10llu %-16llu %-8d %-8d %-8d %-8d ", + psock->index, + psock->stats.rx_msgs, + psock->stats.rx_bytes, + psock->stats.tx_msgs, + psock->stats.tx_bytes, + psock->sk->sk_receive_queue.qlen, + atomic_read(&psock->sk->sk_rmem_alloc), + psock->sk->sk_write_queue.qlen, + atomic_read(&psock->sk->sk_wmem_alloc)); + + if (psock->done) + seq_puts(seq, "Done "); + + if (psock->tx_stopped) + seq_puts(seq, "TxStop "); + + if (psock->rx_stopped) + seq_puts(seq, "RxStop "); + + if (psock->tx_kcm) + seq_printf(seq, "Rsvd-%d ", psock->tx_kcm->index); + + if (psock->ready_rx_msg) + seq_puts(seq, "RdyRx "); + + seq_puts(seq, "\n"); +} + +static void +kcm_format_mux(struct kcm_mux *mux, loff_t idx, struct seq_file *seq) +{ + int i, len; + struct kcm_sock *kcm; + struct kcm_psock *psock; + + /* mux information */ + seq_printf(seq, + "%-6s%-8s %-10llu %-16llu %-10llu %-16llu %-8s %-8s %-8s %-8s ", + "mux", "", + mux->stats.rx_msgs, + mux->stats.rx_bytes, + mux->stats.tx_msgs, + mux->stats.tx_bytes, + "-", "-", "-", "-"); + + seq_printf(seq, "KCMs: %d, Psocks %d\n", + mux->kcm_socks_cnt, mux->psocks_cnt); + + /* kcm sock information */ + i = 0; + spin_lock_bh(&mux->lock); + list_for_each_entry(kcm, &mux->kcm_socks, kcm_sock_list) { + kcm_format_sock(kcm, seq, i, &len); + i++; + } + i = 0; + list_for_each_entry(psock, &mux->psocks, psock_list) { + kcm_format_psock(psock, seq, i, &len); + i++; + } + spin_unlock_bh(&mux->lock); +} + +static int kcm_seq_show(struct seq_file *seq, void *v) +{ + struct kcm_proc_mux_state *mux_state; + + mux_state = seq->private; + if (v == SEQ_START_TOKEN) { + mux_state->idx = 0; + kcm_format_mux_header(seq); + } else { + kcm_format_mux(v, mux_state->idx, seq); + mux_state->idx++; + } + return 0; +} + +static const struct file_operations kcm_seq_fops = { + .owner = THIS_MODULE, + .open = kcm_seq_open, + .read = seq_read, + .llseek = seq_lseek, +}; + +static struct kcm_seq_muxinfo kcm_seq_muxinfo = { + .name = "kcm", + .seq_fops = &kcm_seq_fops, + .seq_ops = { + .show = kcm_seq_show, + .start = kcm_seq_start, + .next = kcm_seq_next, + .stop = kcm_seq_stop, + } +}; + +static int kcm_proc_register(struct net *net, struct kcm_seq_muxinfo *muxinfo) +{ + struct proc_dir_entry *p; + int rc = 0; + + p = proc_create_data(muxinfo->name, S_IRUGO, net->proc_net, + muxinfo->seq_fops, muxinfo); + if (!p) + rc = -ENOMEM; + return rc; +} +EXPORT_SYMBOL(kcm_proc_register); + +static void kcm_proc_unregister(struct net *net, + struct kcm_seq_muxinfo *muxinfo) +{ + remove_proc_entry(muxinfo->name, net->proc_net); +} +EXPORT_SYMBOL(kcm_proc_unregister); + +static int kcm_stats_seq_show(struct seq_file *seq, void *v) +{ + struct kcm_psock_stats psock_stats; + struct kcm_mux_stats mux_stats; + struct kcm_mux *mux; + struct kcm_psock *psock; + struct net *net = seq->private; + struct kcm_net *knet = net_generic(net, kcm_net_id); + + memset(&mux_stats, 0, sizeof(mux_stats)); + memset(&psock_stats, 0, sizeof(psock_stats)); + + mutex_lock(&knet->mutex); + + aggregate_mux_stats(&knet->aggregate_mux_stats, &mux_stats); + aggregate_psock_stats(&knet->aggregate_psock_stats, + &psock_stats); + + list_for_each_entry_rcu(mux, &knet->mux_list, kcm_mux_list) { + spin_lock_bh(&mux->lock); + aggregate_mux_stats(&mux->stats, &mux_stats); + aggregate_psock_stats(&mux->aggregate_psock_stats, + &psock_stats); + list_for_each_entry(psock, &mux->psocks, psock_list) + aggregate_psock_stats(&psock->stats, &psock_stats); + spin_unlock_bh(&mux->lock); + } + + mutex_unlock(&knet->mutex); + + seq_printf(seq, + "%-8s %-10s %-16s %-10s %-16s %-10s %-10s %-10s %-10s %-10s\n", + "MUX", + "RX-Msgs", + "RX-Bytes", + "TX-Msgs", + "TX-Bytes", + "TX-Retries", + "Attach", + "Unattach", + "UnattchRsvd", + "RX-RdyDrops"); + + seq_printf(seq, + "%-8s %-10llu %-16llu %-10llu %-16llu %-10u %-10u %-10u %-10u %-10u\n", + "", + mux_stats.rx_msgs, + mux_stats.rx_bytes, + mux_stats.tx_msgs, + mux_stats.tx_bytes, + mux_stats.tx_retries, + mux_stats.psock_attach, + mux_stats.psock_unattach_rsvd, + mux_stats.psock_unattach, + mux_stats.rx_ready_drops); + + seq_printf(seq, + "%-8s %-10s %-16s %-10s %-16s %-10s %-10s %-10s %-10s %-10s %-10s %-10s\n", + "Psock", + "RX-Msgs", + "RX-Bytes", + "TX-Msgs", + "TX-Bytes", + "Reserved", + "Unreserved", + "RX-Aborts", + "RX-MemFail", + "RX-NeedMor", + "RX-BadLen", + "TX-Aborts"); + + seq_printf(seq, + "%-8s %-10llu %-16llu %-10llu %-16llu %-10llu %-10llu %-10u %-10u %-10u %-10u %-10u\n", + "", + psock_stats.rx_msgs, + psock_stats.rx_bytes, + psock_stats.tx_msgs, + psock_stats.tx_bytes, + psock_stats.reserved, + psock_stats.unreserved, + psock_stats.rx_aborts, + psock_stats.rx_mem_fail, + psock_stats.rx_need_more_hdr, + psock_stats.rx_bad_hdr_len, + psock_stats.tx_aborts); + + return 0; +} + +static int kcm_stats_seq_open(struct inode *inode, struct file *file) +{ + return single_open_net(inode, file, kcm_stats_seq_show); +} + +static const struct file_operations kcm_stats_seq_fops = { + .owner = THIS_MODULE, + .open = kcm_stats_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release_net, +}; + +static int kcm_proc_init_net(struct net *net) +{ + int err; + + if (!proc_create("kcm_stats", S_IRUGO, net->proc_net, + &kcm_stats_seq_fops)) { + err = -ENOMEM; + goto out_kcm_stats; + } + + err = kcm_proc_register(net, &kcm_seq_muxinfo); + if (err) + goto out_kcm; + + return 0; + +out_kcm: + remove_proc_entry("kcm_stats", net->proc_net); +out_kcm_stats: + return err; +} + +static void kcm_proc_exit_net(struct net *net) +{ + kcm_proc_unregister(net, &kcm_seq_muxinfo); + remove_proc_entry("kcm_stats", net->proc_net); +} + +static struct pernet_operations kcm_net_ops = { + .init = kcm_proc_init_net, + .exit = kcm_proc_exit_net, +}; + +int __init kcm_proc_init(void) +{ + return register_pernet_subsys(&kcm_net_ops); +} + +void __exit kcm_proc_exit(void) +{ + unregister_pernet_subsys(&kcm_net_ops); +} + +#endif /* CONFIG_PROC_FS */ diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 30ef69ac6b81..f938d7d3e6e2 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -59,6 +59,7 @@ static void kcm_abort_rx_psock(struct kcm_psock *psock, int err, return; psock->rx_stopped = 1; + KCM_STATS_INCR(psock->stats.rx_aborts); /* Report an error on the lower socket */ report_csk_error(csk, err); @@ -80,6 +81,7 @@ static void kcm_abort_tx_psock(struct kcm_psock *psock, int err, } psock->tx_stopped = 1; + KCM_STATS_INCR(psock->stats.tx_aborts); if (!psock->tx_kcm) { /* Take off psocks_avail list */ @@ -101,6 +103,29 @@ static void kcm_abort_tx_psock(struct kcm_psock *psock, int err, report_csk_error(csk, err); } +/* RX mux lock held. */ +static void kcm_update_rx_mux_stats(struct kcm_mux *mux, + struct kcm_psock *psock) +{ + KCM_STATS_ADD(mux->stats.rx_bytes, + psock->stats.rx_bytes - psock->saved_rx_bytes); + mux->stats.rx_msgs += + psock->stats.rx_msgs - psock->saved_rx_msgs; + psock->saved_rx_msgs = psock->stats.rx_msgs; + psock->saved_rx_bytes = psock->stats.rx_bytes; +} + +static void kcm_update_tx_mux_stats(struct kcm_mux *mux, + struct kcm_psock *psock) +{ + KCM_STATS_ADD(mux->stats.tx_bytes, + psock->stats.tx_bytes - psock->saved_tx_bytes); + mux->stats.tx_msgs += + psock->stats.tx_msgs - psock->saved_tx_msgs; + psock->saved_tx_msgs = psock->stats.tx_msgs; + psock->saved_tx_bytes = psock->stats.tx_bytes; +} + static int kcm_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); /* KCM is ready to receive messages on its queue-- either the KCM is new or @@ -254,6 +279,8 @@ static struct kcm_sock *reserve_rx_kcm(struct kcm_psock *psock, return psock->rx_kcm; } + kcm_update_rx_mux_stats(mux, psock); + if (list_empty(&mux->kcm_rx_waiters)) { psock->ready_rx_msg = head; list_add_tail(&psock->psock_ready_list, @@ -356,10 +383,12 @@ static int kcm_tcp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, */ orig_skb = skb_clone(orig_skb, GFP_ATOMIC); if (!orig_skb) { + KCM_STATS_INCR(psock->stats.rx_mem_fail); desc->error = -ENOMEM; return 0; } if (!pskb_pull(orig_skb, orig_offset)) { + KCM_STATS_INCR(psock->stats.rx_mem_fail); kfree_skb(orig_skb); desc->error = -ENOMEM; return 0; @@ -374,6 +403,7 @@ static int kcm_tcp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, */ err = skb_unclone(head, GFP_ATOMIC); if (err) { + KCM_STATS_INCR(psock->stats.rx_mem_fail); desc->error = err; return 0; } @@ -392,6 +422,7 @@ static int kcm_tcp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, skb = alloc_skb(0, GFP_ATOMIC); if (!skb) { + KCM_STATS_INCR(psock->stats.rx_mem_fail); desc->error = -ENOMEM; return 0; } @@ -414,6 +445,7 @@ static int kcm_tcp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, /* Always clone since we will consume something */ skb = skb_clone(orig_skb, GFP_ATOMIC); if (!skb) { + KCM_STATS_INCR(psock->stats.rx_mem_fail); desc->error = -ENOMEM; break; } @@ -435,6 +467,7 @@ static int kcm_tcp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, */ err = skb_unclone(skb, GFP_ATOMIC); if (err) { + KCM_STATS_INCR(psock->stats.rx_mem_fail); desc->error = err; break; } @@ -456,6 +489,7 @@ static int kcm_tcp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, /* Need more header to determine length */ rxm->accum_len += cand_len; eaten += cand_len; + KCM_STATS_INCR(psock->stats.rx_need_more_hdr); WARN_ON(eaten != orig_len); break; } else if (len <= (ssize_t)head->len - @@ -463,6 +497,7 @@ static int kcm_tcp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, /* Length must be into new skb (and also * greater than zero) */ + KCM_STATS_INCR(psock->stats.rx_bad_hdr_len); desc->error = -EPROTO; psock->rx_skb_head = NULL; kcm_abort_rx_psock(psock, EPROTO, head); @@ -492,6 +527,7 @@ static int kcm_tcp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, /* Hurray, we have a new message! */ psock->rx_skb_head = NULL; + KCM_STATS_INCR(psock->stats.rx_msgs); try_queue: kcm = reserve_rx_kcm(psock, head); @@ -510,6 +546,8 @@ try_queue: if (cloned_orig) kfree_skb(orig_skb); + KCM_STATS_ADD(psock->stats.rx_bytes, eaten); + return eaten; } @@ -671,6 +709,7 @@ static struct kcm_psock *reserve_psock(struct kcm_sock *kcm) } kcm->tx_psock = psock; psock->tx_kcm = kcm; + KCM_STATS_INCR(psock->stats.reserved); } else if (!kcm->tx_wait) { list_add_tail(&kcm->wait_psock_list, &mux->kcm_tx_waiters); @@ -705,6 +744,7 @@ static void psock_now_avail(struct kcm_psock *psock) smp_mb(); kcm->tx_psock = psock; + KCM_STATS_INCR(psock->stats.reserved); queue_work(kcm_wq, &kcm->tx_work); } } @@ -726,10 +766,13 @@ static void unreserve_psock(struct kcm_sock *kcm) smp_rmb(); /* Read tx_psock before tx_wait */ + kcm_update_tx_mux_stats(mux, psock); + WARN_ON(kcm->tx_wait); kcm->tx_psock = NULL; psock->tx_kcm = NULL; + KCM_STATS_INCR(psock->stats.unreserved); if (unlikely(psock->tx_stopped)) { if (psock->done) { @@ -753,6 +796,15 @@ static void unreserve_psock(struct kcm_sock *kcm) spin_unlock_bh(&mux->lock); } +static void kcm_report_tx_retry(struct kcm_sock *kcm) +{ + struct kcm_mux *mux = kcm->mux; + + spin_lock_bh(&mux->lock); + KCM_STATS_INCR(mux->stats.tx_retries); + spin_unlock_bh(&mux->lock); +} + /* Write any messages ready on the kcm socket. Called with kcm sock lock * held. Return bytes actually sent or error. */ @@ -773,6 +825,7 @@ static int kcm_write_msgs(struct kcm_sock *kcm) * it and we'll retry the message. */ unreserve_psock(kcm); + kcm_report_tx_retry(kcm); if (skb_queue_empty(&sk->sk_write_queue)) return 0; @@ -856,6 +909,7 @@ do_frag: unreserve_psock(kcm); txm->sent = 0; + kcm_report_tx_retry(kcm); ret = 0; goto try_again; @@ -863,6 +917,7 @@ do_frag: sent += ret; frag_offset += ret; + KCM_STATS_ADD(psock->stats.tx_bytes, ret); if (frag_offset < frag->size) { /* Not finished with this frag */ goto do_frag; @@ -884,6 +939,7 @@ do_frag: kfree_skb(head); sk->sk_wmem_queued -= sent; total_sent += sent; + KCM_STATS_INCR(psock->stats.tx_msgs); } while ((head = skb_peek(&sk->sk_write_queue))); out: if (!head) { @@ -1061,6 +1117,7 @@ wait_for_memory: /* Message complete, queue it on send buffer */ __skb_queue_tail(&sk->sk_write_queue, head); kcm->seq_skb = NULL; + KCM_STATS_INCR(kcm->stats.tx_msgs); if (msg->msg_flags & MSG_BATCH) { kcm->tx_wait_more = true; @@ -1083,6 +1140,8 @@ partial_message: kcm_tx_msg(head)->last_skb = skb; } + KCM_STATS_ADD(kcm->stats.tx_bytes, copied); + release_sock(sk); return copied; @@ -1144,6 +1203,7 @@ static int kcm_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct sock *sk = sock->sk; + struct kcm_sock *kcm = kcm_sk(sk); int err = 0; long timeo; struct kcm_rx_msg *rxm; @@ -1171,6 +1231,7 @@ static int kcm_recvmsg(struct socket *sock, struct msghdr *msg, copied = len; if (likely(!(flags & MSG_PEEK))) { + KCM_STATS_ADD(kcm->stats.rx_bytes, copied); if (copied < rxm->full_len) { if (sock->type == SOCK_DGRAM) { /* Truncated message */ @@ -1183,6 +1244,7 @@ static int kcm_recvmsg(struct socket *sock, struct msghdr *msg, msg_finished: /* Finished with message */ msg->msg_flags |= MSG_EOR; + KCM_STATS_INCR(kcm->stats.rx_msgs); skb_unlink(skb, &sk->sk_receive_queue); kfree_skb(skb); } @@ -1394,6 +1456,7 @@ static int kcm_attach(struct socket *sock, struct socket *csock, list_add(&psock->psock_list, head); psock->index = index; + KCM_STATS_INCR(mux->stats.psock_attach); mux->psocks_cnt++; psock_now_avail(psock); spin_unlock_bh(&mux->lock); @@ -1469,6 +1532,7 @@ static void kcm_unattach(struct kcm_psock *psock) list_del(&psock->psock_ready_list); kfree_skb(psock->ready_rx_msg); psock->ready_rx_msg = NULL; + KCM_STATS_INCR(mux->stats.rx_ready_drops); } spin_unlock_bh(&mux->rx_lock); @@ -1485,11 +1549,16 @@ static void kcm_unattach(struct kcm_psock *psock) spin_lock_bh(&mux->lock); + aggregate_psock_stats(&psock->stats, &mux->aggregate_psock_stats); + + KCM_STATS_INCR(mux->stats.psock_unattach); + if (psock->tx_kcm) { /* psock was reserved. Just mark it finished and we will clean * up in the kcm paths, we need kcm lock which can not be * acquired here. */ + KCM_STATS_INCR(mux->stats.psock_unattach_rsvd); spin_unlock_bh(&mux->lock); /* We are unattaching a socket that is reserved. Abort the @@ -1717,6 +1786,9 @@ static void release_mux(struct kcm_mux *mux) __skb_queue_purge(&mux->rx_hold_queue); mutex_lock(&knet->mutex); + aggregate_mux_stats(&mux->stats, &knet->aggregate_mux_stats); + aggregate_psock_stats(&mux->aggregate_psock_stats, + &knet->aggregate_psock_stats); list_del_rcu(&mux->kcm_mux_list); knet->count--; mutex_unlock(&knet->mutex); @@ -1979,8 +2051,15 @@ static int __init kcm_init(void) if (err) goto net_ops_fail; + err = kcm_proc_init(); + if (err) + goto proc_init_fail; + return 0; +proc_init_fail: + unregister_pernet_device(&kcm_net_ops); + net_ops_fail: sock_unregister(PF_KCM); @@ -1999,6 +2078,7 @@ fail: static void __exit kcm_exit(void) { + kcm_proc_exit(); unregister_pernet_device(&kcm_net_ops); sock_unregister(PF_KCM); proto_unregister(&kcm_proto); -- cgit v1.2.3-71-gd317 From 7ced95ef525c329f947c424859cf2b0a3b731f8c Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Mon, 7 Mar 2016 14:11:10 -0800 Subject: kcm: Add memory limit for receive message construction Message assembly is performed on the TCP socket. This is logically equivalent of an application that performs a peek on the socket to find out how much memory is needed for a receive buffer. The receive socket buffer also provides the maximum message size which is checked. The receive algorithm is something like: 1) Receive the first skbuf for a message (or skbufs if multiple are needed to determine message length). 2) Check the message length against the number of bytes in the TCP receive queue (tcp_inq()). - If all the bytes of the message are in the queue (incluing the skbuf received), then proceed with message assembly (it should complete with the tcp_read_sock) - Else, mark the psock with the number of bytes needed to complete the message. 3) In TCP data ready function, if the psock indicates that we are waiting for the rest of the bytes of a messages, check the number of queued bytes against that. - If there are still not enough bytes for the message, just return - Else, clear the waiting bytes and proceed to receive the skbufs. The message should now be received in one tcp_read_sock Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/net/kcm.h | 4 ++++ net/kcm/kcmproc.c | 6 ++++-- net/kcm/kcmsock.c | 44 ++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 52 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/kcm.h b/include/net/kcm.h index 39c7abe98552..d892956ff552 100644 --- a/include/net/kcm.h +++ b/include/net/kcm.h @@ -28,6 +28,7 @@ struct kcm_psock_stats { unsigned int rx_aborts; unsigned int rx_mem_fail; unsigned int rx_need_more_hdr; + unsigned int rx_msg_too_big; unsigned int rx_bad_hdr_len; unsigned long long reserved; unsigned long long unreserved; @@ -66,6 +67,7 @@ struct kcm_rx_msg { int full_len; int accum_len; int offset; + int early_eaten; }; /* Socket structure for KCM client sockets */ @@ -128,6 +130,7 @@ struct kcm_psock { struct kcm_sock *rx_kcm; unsigned long long saved_rx_bytes; unsigned long long saved_rx_msgs; + unsigned int rx_need_bytes; /* Transmit */ struct kcm_sock *tx_kcm; @@ -190,6 +193,7 @@ static inline void aggregate_psock_stats(struct kcm_psock_stats *stats, SAVE_PSOCK_STATS(rx_aborts); SAVE_PSOCK_STATS(rx_mem_fail); SAVE_PSOCK_STATS(rx_need_more_hdr); + SAVE_PSOCK_STATS(rx_msg_too_big); SAVE_PSOCK_STATS(rx_bad_hdr_len); SAVE_PSOCK_STATS(tx_msgs); SAVE_PSOCK_STATS(tx_bytes); diff --git a/net/kcm/kcmproc.c b/net/kcm/kcmproc.c index 5eb9809c0f59..7638b3555b17 100644 --- a/net/kcm/kcmproc.c +++ b/net/kcm/kcmproc.c @@ -331,7 +331,7 @@ static int kcm_stats_seq_show(struct seq_file *seq, void *v) mux_stats.rx_ready_drops); seq_printf(seq, - "%-8s %-10s %-16s %-10s %-16s %-10s %-10s %-10s %-10s %-10s %-10s %-10s\n", + "%-8s %-10s %-16s %-10s %-16s %-10s %-10s %-10s %-10s %-10s %-10s %-10s %-10s\n", "Psock", "RX-Msgs", "RX-Bytes", @@ -343,10 +343,11 @@ static int kcm_stats_seq_show(struct seq_file *seq, void *v) "RX-MemFail", "RX-NeedMor", "RX-BadLen", + "RX-TooBig", "TX-Aborts"); seq_printf(seq, - "%-8s %-10llu %-16llu %-10llu %-16llu %-10llu %-10llu %-10u %-10u %-10u %-10u %-10u\n", + "%-8s %-10llu %-16llu %-10llu %-16llu %-10llu %-10llu %-10u %-10u %-10u %-10u %-10u %-10u\n", "", psock_stats.rx_msgs, psock_stats.rx_bytes, @@ -358,6 +359,7 @@ static int kcm_stats_seq_show(struct seq_file *seq, void *v) psock_stats.rx_mem_fail, psock_stats.rx_need_more_hdr, psock_stats.rx_bad_hdr_len, + psock_stats.rx_msg_too_big, psock_stats.tx_aborts); return 0; diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 9ac24995691c..8bc38d3fff9a 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -375,6 +375,19 @@ static int kcm_tcp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, if (head) { /* Message already in progress */ + rxm = kcm_rx_msg(head); + if (unlikely(rxm->early_eaten)) { + /* Already some number of bytes on the receive sock + * data saved in rx_skb_head, just indicate they + * are consumed. + */ + eaten = orig_len <= rxm->early_eaten ? + orig_len : rxm->early_eaten; + rxm->early_eaten -= eaten; + + return eaten; + } + if (unlikely(orig_offset)) { /* Getting data with a non-zero offset when a message is * in progress is not expected. If it does happen, we @@ -492,6 +505,13 @@ static int kcm_tcp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, KCM_STATS_INCR(psock->stats.rx_need_more_hdr); WARN_ON(eaten != orig_len); break; + } else if (len > psock->sk->sk_rcvbuf) { + /* Message length exceeds maximum allowed */ + KCM_STATS_INCR(psock->stats.rx_msg_too_big); + desc->error = -EMSGSIZE; + psock->rx_skb_head = NULL; + kcm_abort_rx_psock(psock, EMSGSIZE, head); + break; } else if (len <= (ssize_t)head->len - skb->len - rxm->offset) { /* Length must be into new skb (and also @@ -511,6 +531,23 @@ static int kcm_tcp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, if (extra < 0) { /* Message not complete yet. */ + if (rxm->full_len - rxm->accum_len > + tcp_inq(psock->sk)) { + /* Don't have the whole messages in the socket + * buffer. Set psock->rx_need_bytes to wait for + * the rest of the message. Also, set "early + * eaten" since we've already buffered the skb + * but don't consume yet per tcp_read_sock. + */ + + psock->rx_need_bytes = rxm->full_len - + rxm->accum_len; + rxm->accum_len += cand_len; + rxm->early_eaten = cand_len; + KCM_STATS_ADD(psock->stats.rx_bytes, cand_len); + desc->count = 0; /* Stop reading socket */ + break; + } rxm->accum_len += cand_len; eaten += cand_len; WARN_ON(eaten != orig_len); @@ -582,6 +619,13 @@ static void psock_tcp_data_ready(struct sock *sk) if (psock->ready_rx_msg) goto out; + if (psock->rx_need_bytes) { + if (tcp_inq(sk) >= psock->rx_need_bytes) + psock->rx_need_bytes = 0; + else + goto out; + } + if (psock_tcp_read_sock(psock) == -ENOMEM) queue_delayed_work(kcm_wq, &psock->rx_delayed_work, 0); -- cgit v1.2.3-71-gd317 From 29152a34f72cb4d7ab32885ad2f20a482c92a8f3 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Mon, 7 Mar 2016 14:11:11 -0800 Subject: kcm: Add receive message timeout This patch adds receive timeout for message assembly on the attached TCP sockets. The timeout is set when a new messages is started and the whole message has not been received by TCP (not in the receive queue). If the completely message is subsequently received the timer is cancelled, if the timer expires the RX side is aborted. The timeout value is taken from the socket timeout (SO_RCVTIMEO) that is set on a TCP socket (i.e. set by get sockopt before attaching a TCP socket to KCM. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/net/kcm.h | 3 +++ net/kcm/kcmproc.c | 6 ++++-- net/kcm/kcmsock.c | 32 ++++++++++++++++++++++++++++++++ 3 files changed, 39 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/kcm.h b/include/net/kcm.h index d892956ff552..95c425ca97b6 100644 --- a/include/net/kcm.h +++ b/include/net/kcm.h @@ -29,6 +29,7 @@ struct kcm_psock_stats { unsigned int rx_mem_fail; unsigned int rx_need_more_hdr; unsigned int rx_msg_too_big; + unsigned int rx_msg_timeouts; unsigned int rx_bad_hdr_len; unsigned long long reserved; unsigned long long unreserved; @@ -130,6 +131,7 @@ struct kcm_psock { struct kcm_sock *rx_kcm; unsigned long long saved_rx_bytes; unsigned long long saved_rx_msgs; + struct timer_list rx_msg_timer; unsigned int rx_need_bytes; /* Transmit */ @@ -194,6 +196,7 @@ static inline void aggregate_psock_stats(struct kcm_psock_stats *stats, SAVE_PSOCK_STATS(rx_mem_fail); SAVE_PSOCK_STATS(rx_need_more_hdr); SAVE_PSOCK_STATS(rx_msg_too_big); + SAVE_PSOCK_STATS(rx_msg_timeouts); SAVE_PSOCK_STATS(rx_bad_hdr_len); SAVE_PSOCK_STATS(tx_msgs); SAVE_PSOCK_STATS(tx_bytes); diff --git a/net/kcm/kcmproc.c b/net/kcm/kcmproc.c index 7638b3555b17..738008726cc6 100644 --- a/net/kcm/kcmproc.c +++ b/net/kcm/kcmproc.c @@ -331,7 +331,7 @@ static int kcm_stats_seq_show(struct seq_file *seq, void *v) mux_stats.rx_ready_drops); seq_printf(seq, - "%-8s %-10s %-16s %-10s %-16s %-10s %-10s %-10s %-10s %-10s %-10s %-10s %-10s\n", + "%-8s %-10s %-16s %-10s %-16s %-10s %-10s %-10s %-10s %-10s %-10s %-10s %-10s %-10s\n", "Psock", "RX-Msgs", "RX-Bytes", @@ -344,10 +344,11 @@ static int kcm_stats_seq_show(struct seq_file *seq, void *v) "RX-NeedMor", "RX-BadLen", "RX-TooBig", + "RX-Timeout", "TX-Aborts"); seq_printf(seq, - "%-8s %-10llu %-16llu %-10llu %-16llu %-10llu %-10llu %-10u %-10u %-10u %-10u %-10u %-10u\n", + "%-8s %-10llu %-16llu %-10llu %-16llu %-10llu %-10llu %-10u %-10u %-10u %-10u %-10u %-10u %-10u\n", "", psock_stats.rx_msgs, psock_stats.rx_bytes, @@ -360,6 +361,7 @@ static int kcm_stats_seq_show(struct seq_file *seq, void *v) psock_stats.rx_need_more_hdr, psock_stats.rx_bad_hdr_len, psock_stats.rx_msg_too_big, + psock_stats.rx_msg_timeouts, psock_stats.tx_aborts); return 0; diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 8bc38d3fff9a..40662d73204f 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -55,6 +55,8 @@ static void kcm_abort_rx_psock(struct kcm_psock *psock, int err, /* Unrecoverable error in receive */ + del_timer(&psock->rx_msg_timer); + if (psock->rx_stopped) return; @@ -351,6 +353,12 @@ static void unreserve_rx_kcm(struct kcm_psock *psock, spin_unlock_bh(&mux->rx_lock); } +static void kcm_start_rx_timer(struct kcm_psock *psock) +{ + if (psock->sk->sk_rcvtimeo) + mod_timer(&psock->rx_msg_timer, psock->sk->sk_rcvtimeo); +} + /* Macro to invoke filter function. */ #define KCM_RUN_FILTER(prog, ctx) \ (*prog->bpf_func)(ctx, prog->insnsi) @@ -500,6 +508,10 @@ static int kcm_tcp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, if (!len) { /* Need more header to determine length */ + if (!rxm->accum_len) { + /* Start RX timer for new message */ + kcm_start_rx_timer(psock); + } rxm->accum_len += cand_len; eaten += cand_len; KCM_STATS_INCR(psock->stats.rx_need_more_hdr); @@ -540,6 +552,11 @@ static int kcm_tcp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, * but don't consume yet per tcp_read_sock. */ + if (!rxm->accum_len) { + /* Start RX timer for new message */ + kcm_start_rx_timer(psock); + } + psock->rx_need_bytes = rxm->full_len - rxm->accum_len; rxm->accum_len += cand_len; @@ -563,6 +580,7 @@ static int kcm_tcp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, eaten += (cand_len - extra); /* Hurray, we have a new message! */ + del_timer(&psock->rx_msg_timer); psock->rx_skb_head = NULL; KCM_STATS_INCR(psock->stats.rx_msgs); @@ -1656,6 +1674,15 @@ static void init_kcm_sock(struct kcm_sock *kcm, struct kcm_mux *mux) spin_unlock_bh(&mux->rx_lock); } +static void kcm_rx_msg_timeout(unsigned long arg) +{ + struct kcm_psock *psock = (struct kcm_psock *)arg; + + /* Message assembly timed out */ + KCM_STATS_INCR(psock->stats.rx_msg_timeouts); + kcm_abort_rx_psock(psock, ETIMEDOUT, NULL); +} + static int kcm_attach(struct socket *sock, struct socket *csock, struct bpf_prog *prog) { @@ -1685,6 +1712,10 @@ static int kcm_attach(struct socket *sock, struct socket *csock, psock->mux = mux; psock->sk = csk; psock->bpf_prog = prog; + + setup_timer(&psock->rx_msg_timer, kcm_rx_msg_timeout, + (unsigned long)psock); + INIT_WORK(&psock->rx_work, psock_rx_work); INIT_DELAYED_WORK(&psock->rx_delayed_work, psock_rx_delayed_work); @@ -1796,6 +1827,7 @@ static void kcm_unattach(struct kcm_psock *psock) write_unlock_bh(&csk->sk_callback_lock); + del_timer_sync(&psock->rx_msg_timer); cancel_work_sync(&psock->rx_work); cancel_delayed_work_sync(&psock->rx_delayed_work); -- cgit v1.2.3-71-gd317 From f16089209e1029d45ae78dd238b6ab9b2c9a886c Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Fri, 4 Mar 2016 10:10:20 +0100 Subject: mac802154: use put and get unaligned functions This patch removes the swap pointer and memmove functionality. Instead we use the well known put/get unaligned access with specific byte order handling. Signed-off-by: Alexander Aring Suggested-by: Marc Kleine-Budde Signed-off-by: Marcel Holtmann --- include/net/mac802154.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/net') diff --git a/include/net/mac802154.h b/include/net/mac802154.h index 2e3cdd2048d2..6cd7a70706a9 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -16,10 +16,10 @@ #ifndef NET_MAC802154_H #define NET_MAC802154_H +#include #include #include #include -#include #include @@ -254,7 +254,7 @@ static inline __le16 ieee802154_get_fc_from_skb(const struct sk_buff *skb) return cpu_to_le16(0); } - return (__force __le16)__get_unaligned_memmove16(skb_mac_header(skb)); + return get_unaligned_le16(skb_mac_header(skb)); } /** @@ -264,7 +264,7 @@ static inline __le16 ieee802154_get_fc_from_skb(const struct sk_buff *skb) */ static inline void ieee802154_be64_to_le64(void *le64_dst, const void *be64_src) { - __put_unaligned_memmove64(swab64p(be64_src), le64_dst); + put_unaligned_le64(get_unaligned_be64(be64_src), le64_dst); } /** @@ -274,7 +274,7 @@ static inline void ieee802154_be64_to_le64(void *le64_dst, const void *be64_src) */ static inline void ieee802154_le64_to_be64(void *be64_dst, const void *le64_src) { - __put_unaligned_memmove64(swab64p(le64_src), be64_dst); + put_unaligned_be64(get_unaligned_le64(le64_src), be64_dst); } /** @@ -284,7 +284,7 @@ static inline void ieee802154_le64_to_be64(void *be64_dst, const void *le64_src) */ static inline void ieee802154_le16_to_be16(void *be16_dst, const void *le16_src) { - __put_unaligned_memmove16(swab16p(le16_src), be16_dst); + put_unaligned_be16(get_unaligned_le16(le16_src), be16_dst); } /** -- cgit v1.2.3-71-gd317 From 82a37adeedd38880940e2772ec1ae27a09353e5a Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Wed, 9 Mar 2016 17:30:34 +0200 Subject: Bluetooth: Add support for limited privacy mode Introduce a limited privacy mode indicated by value 0x02 to the mgmt Set Privacy command. With value 0x02 the kernel will use privacy mode with a resolvable private address. In case the controller is bondable and discoverable the identity address will be used. Signed-off-by: Johan Hedberg Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci.h | 1 + net/bluetooth/hci_conn.c | 13 ++++++++++-- net/bluetooth/hci_request.c | 51 +++++++++++++++++++++++++++++++++++++++------ net/bluetooth/hci_request.h | 2 +- net/bluetooth/mgmt.c | 20 ++++++++++++++++-- 5 files changed, 76 insertions(+), 11 deletions(-) (limited to 'include/net') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 339ea57be423..5d38d980b89d 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -233,6 +233,7 @@ enum { HCI_SC_ENABLED, HCI_SC_ONLY, HCI_PRIVACY, + HCI_LIMITED_PRIVACY, HCI_RPA_EXPIRED, HCI_RPA_RESOLVING, HCI_HS_ENABLED, diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 7264025dc781..bf9f8a801a2e 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -719,6 +719,13 @@ done: hci_dev_unlock(hdev); } +static bool conn_use_rpa(struct hci_conn *conn) +{ + struct hci_dev *hdev = conn->hdev; + + return hci_dev_test_flag(hdev, HCI_PRIVACY); +} + static void hci_req_add_le_create_conn(struct hci_request *req, struct hci_conn *conn) { @@ -729,7 +736,8 @@ static void hci_req_add_le_create_conn(struct hci_request *req, /* Update random address, but set require_privacy to false so * that we never connect with an non-resolvable address. */ - if (hci_update_random_address(req, false, &own_addr_type)) + if (hci_update_random_address(req, false, conn_use_rpa(conn), + &own_addr_type)) return; memset(&cp, 0, sizeof(cp)); @@ -774,7 +782,8 @@ static void hci_req_directed_advertising(struct hci_request *req, /* Set require_privacy to false so that the remote device has a * chance of identifying us. */ - if (hci_update_random_address(req, false, &own_addr_type) < 0) + if (hci_update_random_address(req, false, conn_use_rpa(conn), + &own_addr_type) < 0) return; memset(&cp, 0, sizeof(cp)); diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index 77be344efd18..95a545ca9dbc 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -771,6 +771,11 @@ static u8 update_white_list(struct hci_request *req) return 0x01; } +static bool scan_use_rpa(struct hci_dev *hdev) +{ + return hci_dev_test_flag(hdev, HCI_PRIVACY); +} + void hci_req_add_le_passive_scan(struct hci_request *req) { struct hci_cp_le_set_scan_param param_cp; @@ -785,7 +790,8 @@ void hci_req_add_le_passive_scan(struct hci_request *req) * advertising with our address will be correctly reported * by the controller. */ - if (hci_update_random_address(req, false, &own_addr_type)) + if (hci_update_random_address(req, false, scan_use_rpa(hdev), + &own_addr_type)) return; /* Adding or removing entries from the white list must @@ -881,6 +887,29 @@ static u32 get_adv_instance_flags(struct hci_dev *hdev, u8 instance) return adv_instance->flags; } +static bool adv_use_rpa(struct hci_dev *hdev, uint32_t flags) +{ + /* If privacy is not enabled don't use RPA */ + if (!hci_dev_test_flag(hdev, HCI_PRIVACY)) + return false; + + /* If basic privacy mode is enabled use RPA */ + if (!hci_dev_test_flag(hdev, HCI_LIMITED_PRIVACY)) + return true; + + /* If limited privacy mode is enabled don't use RPA if we're + * both discoverable and bondable. + */ + if ((flags & MGMT_ADV_FLAG_DISCOV) && + hci_dev_test_flag(hdev, HCI_BONDABLE)) + return false; + + /* We're neither bondable nor discoverable in the limited + * privacy mode, therefore use RPA. + */ + return true; +} + void __hci_req_enable_advertising(struct hci_request *req) { struct hci_dev *hdev = req->hdev; @@ -914,7 +943,9 @@ void __hci_req_enable_advertising(struct hci_request *req) * advertising is used. In that case it is fine to use a * non-resolvable private address. */ - if (hci_update_random_address(req, !connectable, &own_addr_type) < 0) + if (hci_update_random_address(req, !connectable, + adv_use_rpa(hdev, flags), + &own_addr_type) < 0) return; memset(&cp, 0, sizeof(cp)); @@ -1328,7 +1359,7 @@ static void set_random_addr(struct hci_request *req, bdaddr_t *rpa) } int hci_update_random_address(struct hci_request *req, bool require_privacy, - u8 *own_addr_type) + bool use_rpa, u8 *own_addr_type) { struct hci_dev *hdev = req->hdev; int err; @@ -1337,7 +1368,7 @@ int hci_update_random_address(struct hci_request *req, bool require_privacy, * current RPA has expired or there is something else than * the current RPA in use, then generate a new one. */ - if (hci_dev_test_flag(hdev, HCI_PRIVACY)) { + if (use_rpa) { int to; *own_addr_type = ADDR_LE_DEV_RANDOM; @@ -1599,9 +1630,16 @@ static int discoverable_update(struct hci_request *req, unsigned long opt) /* Advertising instances don't use the global discoverable setting, so * only update AD if advertising was enabled using Set Advertising. */ - if (hci_dev_test_flag(hdev, HCI_ADVERTISING)) + if (hci_dev_test_flag(hdev, HCI_ADVERTISING)) { __hci_req_update_adv_data(req, 0x00); + /* Discoverable mode affects the local advertising + * address in limited privacy mode. + */ + if (hci_dev_test_flag(hdev, HCI_LIMITED_PRIVACY)) + __hci_req_enable_advertising(req); + } + hci_dev_unlock(hdev); return 0; @@ -1944,7 +1982,8 @@ static int active_scan(struct hci_request *req, unsigned long opt) * address (when privacy feature has been enabled) or non-resolvable * private address. */ - err = hci_update_random_address(req, true, &own_addr_type); + err = hci_update_random_address(req, true, scan_use_rpa(hdev), + &own_addr_type); if (err < 0) own_addr_type = ADDR_LE_DEV_PUBLIC; diff --git a/net/bluetooth/hci_request.h b/net/bluetooth/hci_request.h index 64ff8c040d50..b2d044bdc732 100644 --- a/net/bluetooth/hci_request.h +++ b/net/bluetooth/hci_request.h @@ -89,7 +89,7 @@ static inline void hci_req_update_scan(struct hci_dev *hdev) void __hci_req_update_scan(struct hci_request *req); int hci_update_random_address(struct hci_request *req, bool require_privacy, - u8 *own_addr_type); + bool use_rpa, u8 *own_addr_type); int hci_abort_conn(struct hci_conn *conn, u8 reason); void __hci_abort_conn(struct hci_request *req, struct hci_conn *conn, diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 5a5089cb6570..2ca355519d79 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -1382,8 +1382,19 @@ static int set_bondable(struct sock *sk, struct hci_dev *hdev, void *data, if (err < 0) goto unlock; - if (changed) + if (changed) { + /* In limited privacy mode the change of bondable mode + * may affect the local advertising address. + */ + if (hdev_is_powered(hdev) && + hci_dev_test_flag(hdev, HCI_ADVERTISING) && + hci_dev_test_flag(hdev, HCI_DISCOVERABLE) && + hci_dev_test_flag(hdev, HCI_LIMITED_PRIVACY)) + queue_work(hdev->req_workqueue, + &hdev->discoverable_update); + err = new_settings(hdev, sk); + } unlock: hci_dev_unlock(hdev); @@ -4423,7 +4434,7 @@ static int set_privacy(struct sock *sk, struct hci_dev *hdev, void *cp_data, return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_PRIVACY, MGMT_STATUS_NOT_SUPPORTED); - if (cp->privacy != 0x00 && cp->privacy != 0x01) + if (cp->privacy != 0x00 && cp->privacy != 0x01 && cp->privacy != 0x02) return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_PRIVACY, MGMT_STATUS_INVALID_PARAMS); @@ -4442,10 +4453,15 @@ static int set_privacy(struct sock *sk, struct hci_dev *hdev, void *cp_data, changed = !hci_dev_test_and_set_flag(hdev, HCI_PRIVACY); memcpy(hdev->irk, cp->irk, sizeof(hdev->irk)); hci_dev_set_flag(hdev, HCI_RPA_EXPIRED); + if (cp->privacy == 0x02) + hci_dev_set_flag(hdev, HCI_LIMITED_PRIVACY); + else + hci_dev_clear_flag(hdev, HCI_LIMITED_PRIVACY); } else { changed = hci_dev_test_and_clear_flag(hdev, HCI_PRIVACY); memset(hdev->irk, 0, sizeof(hdev->irk)); hci_dev_clear_flag(hdev, HCI_RPA_EXPIRED); + hci_dev_clear_flag(hdev, HCI_LIMITED_PRIVACY); } err = send_settings_rsp(sk, MGMT_OP_SET_PRIVACY, hdev); -- cgit v1.2.3-71-gd317 From f720d0caa0af2c33ad15310974c7320345ab4468 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 10 Mar 2016 19:31:12 +0100 Subject: kcm: mark helper functions inline The stub helper functions for the newly added kcm_proc_init/exit interfaces are defined as 'static' in a header file, which leads to build warnings for each file that includes them without calling them: include/net/kcm.h:183:12: error: 'kcm_proc_init' defined but not used [-Werror=unused-function] include/net/kcm.h:184:13: error: 'kcm_proc_exit' defined but not used [-Werror=unused-function] This marks the two functions as 'static inline' instead, which avoids the warnings and is obviously what was meant here. Signed-off-by: Arnd Bergmann Fixes: cd6e111bf5be ("kcm: Add statistics and proc interfaces") Signed-off-by: David S. Miller --- include/net/kcm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/kcm.h b/include/net/kcm.h index 95c425ca97b6..2840b5825dcc 100644 --- a/include/net/kcm.h +++ b/include/net/kcm.h @@ -180,8 +180,8 @@ struct kcm_mux { int kcm_proc_init(void); void kcm_proc_exit(void); #else -static int kcm_proc_init(void) { return 0; } -static void kcm_proc_exit(void) { } +static inline int kcm_proc_init(void) { return 0; } +static inline void kcm_proc_exit(void) { } #endif static inline void aggregate_psock_stats(struct kcm_psock_stats *stats, -- cgit v1.2.3-71-gd317 From 5b33f48842fa1e13e9c0ea8cc59c1d0df19042db Mon Sep 17 00:00:00 2001 From: Amir Vadai Date: Tue, 8 Mar 2016 12:42:29 +0200 Subject: net/flower: Introduce hardware offload support This patch is based on a patch made by John Fastabend. It adds support for offloading cls_flower. when NETIF_F_HW_TC is on: flags = 0 => Rule will be processed twice - by hardware, and if still relevant, by software. flags = SKIP_HW => Rull will be processed by software only If hardware fail/not capabale to apply the rule, operation will NOT fail. Filter will be processed by SW only. Acked-by: Jiri Pirko Suggested-by: John Fastabend Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 ++ include/net/pkt_cls.h | 14 ++++++++++ include/uapi/linux/pkt_cls.h | 2 ++ net/sched/cls_flower.c | 64 +++++++++++++++++++++++++++++++++++++++++++- 4 files changed, 81 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index fd30cb545c45..41df0b450757 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -786,6 +786,7 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, enum { TC_SETUP_MQPRIO, TC_SETUP_CLSU32, + TC_SETUP_CLSFLOWER, }; struct tc_cls_u32_offload; @@ -795,6 +796,7 @@ struct tc_to_netdev { union { u8 tc; struct tc_cls_u32_offload *cls_u32; + struct tc_cls_flower_offload *cls_flower; }; }; diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index bea14eee373e..5b4e8f08b8f0 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -409,4 +409,18 @@ static inline bool tc_should_offload(struct net_device *dev, u32 flags) return true; } +enum tc_fl_command { + TC_CLSFLOWER_REPLACE, + TC_CLSFLOWER_DESTROY, +}; + +struct tc_cls_flower_offload { + enum tc_fl_command command; + u64 cookie; + struct flow_dissector *dissector; + struct fl_flow_key *mask; + struct fl_flow_key *key; + struct tcf_exts *exts; +}; + #endif diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 9874f5680926..c43c5f78b9c4 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -417,6 +417,8 @@ enum { TCA_FLOWER_KEY_TCP_DST, /* be16 */ TCA_FLOWER_KEY_UDP_SRC, /* be16 */ TCA_FLOWER_KEY_UDP_DST, /* be16 */ + + TCA_FLOWER_FLAGS, __TCA_FLOWER_MAX, }; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 95b021243233..25d87666bf1e 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -165,6 +165,51 @@ static void fl_destroy_filter(struct rcu_head *head) kfree(f); } +static void fl_hw_destroy_filter(struct tcf_proto *tp, u64 cookie) +{ + struct net_device *dev = tp->q->dev_queue->dev; + struct tc_cls_flower_offload offload = {0}; + struct tc_to_netdev tc; + + if (!tc_should_offload(dev, 0)) + return; + + offload.command = TC_CLSFLOWER_DESTROY; + offload.cookie = cookie; + + tc.type = TC_SETUP_CLSFLOWER; + tc.cls_flower = &offload; + + dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, &tc); +} + +static void fl_hw_replace_filter(struct tcf_proto *tp, + struct flow_dissector *dissector, + struct fl_flow_key *mask, + struct fl_flow_key *key, + struct tcf_exts *actions, + u64 cookie, u32 flags) +{ + struct net_device *dev = tp->q->dev_queue->dev; + struct tc_cls_flower_offload offload = {0}; + struct tc_to_netdev tc; + + if (!tc_should_offload(dev, flags)) + return; + + offload.command = TC_CLSFLOWER_REPLACE; + offload.cookie = cookie; + offload.dissector = dissector; + offload.mask = mask; + offload.key = key; + offload.exts = actions; + + tc.type = TC_SETUP_CLSFLOWER; + tc.cls_flower = &offload; + + dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, &tc); +} + static bool fl_destroy(struct tcf_proto *tp, bool force) { struct cls_fl_head *head = rtnl_dereference(tp->root); @@ -174,6 +219,7 @@ static bool fl_destroy(struct tcf_proto *tp, bool force) return false; list_for_each_entry_safe(f, next, &head->filters, list) { + fl_hw_destroy_filter(tp, (u64)f); list_del_rcu(&f->list); call_rcu(&f->rcu, fl_destroy_filter); } @@ -459,6 +505,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, struct cls_fl_filter *fnew; struct nlattr *tb[TCA_FLOWER_MAX + 1]; struct fl_flow_mask mask = {}; + u32 flags = 0; int err; if (!tca[TCA_OPTIONS]) @@ -486,6 +533,9 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, } fnew->handle = handle; + if (tb[TCA_FLOWER_FLAGS]) + flags = nla_get_u32(tb[TCA_FLOWER_FLAGS]); + err = fl_set_parms(net, tp, fnew, &mask, base, tb, tca[TCA_RATE], ovr); if (err) goto errout; @@ -498,9 +548,20 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, head->ht_params); if (err) goto errout; - if (fold) + + fl_hw_replace_filter(tp, + &head->dissector, + &mask.key, + &fnew->key, + &fnew->exts, + (u64)fnew, + flags); + + if (fold) { rhashtable_remove_fast(&head->ht, &fold->ht_node, head->ht_params); + fl_hw_destroy_filter(tp, (u64)fold); + } *arg = (unsigned long) fnew; @@ -527,6 +588,7 @@ static int fl_delete(struct tcf_proto *tp, unsigned long arg) rhashtable_remove_fast(&head->ht, &f->ht_node, head->ht_params); list_del_rcu(&f->list); + fl_hw_destroy_filter(tp, (u64)f); tcf_unbind_filter(tp, &f->res); call_rcu(&f->rcu, fl_destroy_filter); return 0; -- cgit v1.2.3-71-gd317 From 8de2d793daf784f8f109565bcc023a6d198bad85 Mon Sep 17 00:00:00 2001 From: Amir Vadai Date: Tue, 8 Mar 2016 12:42:30 +0200 Subject: net/flow_dissector: Make dissector_uses_key() and skb_flow_dissector_target() public Will be used in a following patch to query if a key is being used, and what it's value in the target object. Acked-by: John Fastabend Acked-by: Jiri Pirko Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- include/net/flow_dissector.h | 13 +++++++++++++ net/core/flow_dissector.c | 13 ------------- 2 files changed, 13 insertions(+), 13 deletions(-) (limited to 'include/net') diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 8c8548cf5888..d3d60dccd19f 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -184,4 +184,17 @@ static inline bool flow_keys_have_l4(struct flow_keys *keys) u32 flow_hash_from_keys(struct flow_keys *keys); +static inline bool dissector_uses_key(const struct flow_dissector *flow_dissector, + enum flow_dissector_key_id key_id) +{ + return flow_dissector->used_keys & (1 << key_id); +} + +static inline void *skb_flow_dissector_target(struct flow_dissector *flow_dissector, + enum flow_dissector_key_id key_id, + void *target_container) +{ + return ((char *)target_container) + flow_dissector->offset[key_id]; +} + #endif diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 7c7b8739b8b8..a669dea146c6 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -19,25 +19,12 @@ #include #include -static bool dissector_uses_key(const struct flow_dissector *flow_dissector, - enum flow_dissector_key_id key_id) -{ - return flow_dissector->used_keys & (1 << key_id); -} - static void dissector_set_key(struct flow_dissector *flow_dissector, enum flow_dissector_key_id key_id) { flow_dissector->used_keys |= (1 << key_id); } -static void *skb_flow_dissector_target(struct flow_dissector *flow_dissector, - enum flow_dissector_key_id key_id, - void *target_container) -{ - return ((char *) target_container) + flow_dissector->offset[key_id]; -} - void skb_flow_dissector_init(struct flow_dissector *flow_dissector, const struct flow_dissector_key *key, unsigned int key_count) -- cgit v1.2.3-71-gd317 From 00175aec941e9c306d8a5ce930b2d91f7c04468c Mon Sep 17 00:00:00 2001 From: Amir Vadai Date: Tue, 8 Mar 2016 12:42:31 +0200 Subject: net/sched: Macro instead of CONFIG_NET_CLS_ACT ifdef Introduce the macros tc_no_actions and tc_for_each_action to make code clearer. Extracted struct tc_action out of the ifdef to make calls to is_tcf_gact_shot() and similar functions valid, even when it is a nop. Acked-by: Jiri Pirko Acked-by: John Fastabend Suggested-by: Jiri Pirko Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- include/net/act_api.h | 21 ++++++++++++++++----- include/net/tc_act/tc_gact.h | 4 ++-- 2 files changed, 18 insertions(+), 7 deletions(-) (limited to 'include/net') diff --git a/include/net/act_api.h b/include/net/act_api.h index 342be6c5ab5c..2a19fe111c78 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -78,11 +78,6 @@ static inline void tcf_lastuse_update(struct tcf_t *tm) tm->lastuse = now; } -#ifdef CONFIG_NET_CLS_ACT - -#define ACT_P_CREATED 1 -#define ACT_P_DELETED 1 - struct tc_action { void *priv; const struct tc_action_ops *ops; @@ -92,6 +87,11 @@ struct tc_action { struct tcf_hashinfo *hinfo; }; +#ifdef CONFIG_NET_CLS_ACT + +#define ACT_P_CREATED 1 +#define ACT_P_DELETED 1 + struct tc_action_ops { struct list_head head; char kind[IFNAMSIZ]; @@ -171,5 +171,16 @@ int tcf_action_dump(struct sk_buff *skb, struct list_head *, int, int); int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int); int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int, int); int tcf_action_copy_stats(struct sk_buff *, struct tc_action *, int); + +#define tc_no_actions(_exts) \ + (list_empty(&(_exts)->actions)) + +#define tc_for_each_action(_a, _exts) \ + list_for_each_entry(a, &(_exts)->actions, list) +#else /* CONFIG_NET_CLS_ACT */ + +#define tc_no_actions(_exts) true +#define tc_for_each_action(_a, _exts) while (0) + #endif /* CONFIG_NET_CLS_ACT */ #endif diff --git a/include/net/tc_act/tc_gact.h b/include/net/tc_act/tc_gact.h index 04a31830711b..93c520b83d10 100644 --- a/include/net/tc_act/tc_gact.h +++ b/include/net/tc_act/tc_gact.h @@ -16,9 +16,9 @@ struct tcf_gact { #define to_gact(a) \ container_of(a->priv, struct tcf_gact, common) -#ifdef CONFIG_NET_CLS_ACT static inline bool is_tcf_gact_shot(const struct tc_action *a) { +#ifdef CONFIG_NET_CLS_ACT struct tcf_gact *gact; if (a->ops && a->ops->type != TCA_ACT_GACT) @@ -28,7 +28,7 @@ static inline bool is_tcf_gact_shot(const struct tc_action *a) if (gact->tcf_action == TC_ACT_SHOT) return true; +#endif return false; } -#endif #endif /* __NET_TC_GACT_H */ -- cgit v1.2.3-71-gd317 From 519afb1813eab066a0c9995a08861fd0af75d5ae Mon Sep 17 00:00:00 2001 From: Amir Vadai Date: Tue, 8 Mar 2016 12:42:32 +0200 Subject: net/act_skbedit: Utility functions for mark action Enable device drivers to query the action, if and only if is a mark action and what value to use for marking. Acked-by: Jiri Pirko Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- include/net/tc_act/tc_skbedit.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/net') diff --git a/include/net/tc_act/tc_skbedit.h b/include/net/tc_act/tc_skbedit.h index 0df9a0db4a8e..b496d5ad7d42 100644 --- a/include/net/tc_act/tc_skbedit.h +++ b/include/net/tc_act/tc_skbedit.h @@ -20,6 +20,7 @@ #define __NET_TC_SKBEDIT_H #include +#include struct tcf_skbedit { struct tcf_common common; @@ -32,4 +33,19 @@ struct tcf_skbedit { #define to_skbedit(a) \ container_of(a->priv, struct tcf_skbedit, common) +/* Return true iff action is mark */ +static inline bool is_tcf_skbedit_mark(const struct tc_action *a) +{ +#ifdef CONFIG_NET_CLS_ACT + if (a->ops && a->ops->type == TCA_ACT_SKBEDIT) + return to_skbedit(a)->flags == SKBEDIT_F_MARK; +#endif + return false; +} + +static inline u32 tcf_skbedit_mark(const struct tc_action *a) +{ + return to_skbedit(a)->mark; +} + #endif /* __NET_TC_SKBEDIT_H */ -- cgit v1.2.3-71-gd317 From 8208d21bf309551686b7a76d19059ae182a956d0 Mon Sep 17 00:00:00 2001 From: Amir Vadai Date: Fri, 11 Mar 2016 11:08:45 +0200 Subject: net/flower: Fix pointer cast Cast pointer to unsigned long instead of u64, to fix compilation warning on 32 bit arch, spotted by 0day build. Fixes: 5b33f48 ("net/flower: Introduce hardware offload support") Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 2 +- net/sched/cls_flower.c | 12 ++++++------ 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/net') diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 5b4e8f08b8f0..caa5e18636df 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -416,7 +416,7 @@ enum tc_fl_command { struct tc_cls_flower_offload { enum tc_fl_command command; - u64 cookie; + unsigned long cookie; struct flow_dissector *dissector; struct fl_flow_key *mask; struct fl_flow_key *key; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 25d87666bf1e..2181ffc76638 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -165,7 +165,7 @@ static void fl_destroy_filter(struct rcu_head *head) kfree(f); } -static void fl_hw_destroy_filter(struct tcf_proto *tp, u64 cookie) +static void fl_hw_destroy_filter(struct tcf_proto *tp, unsigned long cookie) { struct net_device *dev = tp->q->dev_queue->dev; struct tc_cls_flower_offload offload = {0}; @@ -188,7 +188,7 @@ static void fl_hw_replace_filter(struct tcf_proto *tp, struct fl_flow_key *mask, struct fl_flow_key *key, struct tcf_exts *actions, - u64 cookie, u32 flags) + unsigned long cookie, u32 flags) { struct net_device *dev = tp->q->dev_queue->dev; struct tc_cls_flower_offload offload = {0}; @@ -219,7 +219,7 @@ static bool fl_destroy(struct tcf_proto *tp, bool force) return false; list_for_each_entry_safe(f, next, &head->filters, list) { - fl_hw_destroy_filter(tp, (u64)f); + fl_hw_destroy_filter(tp, (unsigned long)f); list_del_rcu(&f->list); call_rcu(&f->rcu, fl_destroy_filter); } @@ -554,13 +554,13 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, &mask.key, &fnew->key, &fnew->exts, - (u64)fnew, + (unsigned long)fnew, flags); if (fold) { rhashtable_remove_fast(&head->ht, &fold->ht_node, head->ht_params); - fl_hw_destroy_filter(tp, (u64)fold); + fl_hw_destroy_filter(tp, (unsigned long)fold); } *arg = (unsigned long) fnew; @@ -588,7 +588,7 @@ static int fl_delete(struct tcf_proto *tp, unsigned long arg) rhashtable_remove_fast(&head->ht, &f->ht_node, head->ht_params); list_del_rcu(&f->list); - fl_hw_destroy_filter(tp, (u64)f); + fl_hw_destroy_filter(tp, (unsigned long)f); tcf_unbind_filter(tp, &f->res); call_rcu(&f->rcu, fl_destroy_filter); return 0; -- cgit v1.2.3-71-gd317 From 134611446dc657e1bbc73ca0e4e6b599df687db0 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 9 Mar 2016 03:00:02 +0100 Subject: ip_tunnel: add support for setting flow label via collect metadata This patch extends udp_tunnel6_xmit_skb() to pass in the IPv6 flow label from call sites. Currently, there's no such option and it's always set to zero when writing ip6_flow_hdr(). Add a label member to ip_tunnel_key, so that flow-based tunnels via collect metadata frontends can make use of it. vxlan and geneve will be converted to add flow label support separately. Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- drivers/net/geneve.c | 2 +- drivers/net/vxlan.c | 2 +- include/net/dst_metadata.h | 5 ++++- include/net/ip_tunnels.h | 4 +++- include/net/udp_tunnel.h | 4 ++-- net/ipv6/ip6_udp_tunnel.c | 6 +++--- net/tipc/udp_media.c | 2 +- 7 files changed, 15 insertions(+), 10 deletions(-) (limited to 'include/net') diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 6a0cbbe03e5d..89ccff79d76c 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -1054,7 +1054,7 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, ttl = ttl ? : ip6_dst_hoplimit(dst); } udp_tunnel6_xmit_skb(dst, gs6->sock->sk, skb, dev, - &fl6.saddr, &fl6.daddr, prio, ttl, + &fl6.saddr, &fl6.daddr, prio, ttl, 0, sport, geneve->dst_port, !!(flags & GENEVE_F_UDP_ZERO_CSUM6_TX)); return NETDEV_TX_OK; diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 2399099e68cf..8bdcd5ea8424 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2066,7 +2066,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, return; } udp_tunnel6_xmit_skb(ndst, sk, skb, dev, - &saddr, &dst->sin6.sin6_addr, tos, ttl, + &saddr, &dst->sin6.sin6_addr, tos, ttl, 0, src_port, dst_port, !udp_sum); #endif } diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h index 84b833af6882..5db9f5910428 100644 --- a/include/net/dst_metadata.h +++ b/include/net/dst_metadata.h @@ -126,7 +126,7 @@ static inline struct metadata_dst *ip_tun_rx_dst(struct sk_buff *skb, ip_tunnel_key_init(&tun_dst->u.tun_info.key, iph->saddr, iph->daddr, iph->tos, iph->ttl, - 0, 0, tunnel_id, flags); + 0, 0, 0, tunnel_id, flags); return tun_dst; } @@ -152,8 +152,11 @@ static inline struct metadata_dst *ipv6_tun_rx_dst(struct sk_buff *skb, info->key.u.ipv6.src = ip6h->saddr; info->key.u.ipv6.dst = ip6h->daddr; + info->key.tos = ipv6_get_dsfield(ip6h); info->key.ttl = ip6h->hop_limit; + info->key.label = ip6_flowlabel(ip6h); + return tun_dst; } diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 0acd80fadb32..5dc2e454f866 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -48,6 +48,7 @@ struct ip_tunnel_key { __be16 tun_flags; u8 tos; /* TOS for IPv4, TC for IPv6 */ u8 ttl; /* TTL for IPv4, HL for IPv6 */ + __be32 label; /* Flow Label for IPv6 */ __be16 tp_src; __be16 tp_dst; }; @@ -181,7 +182,7 @@ int ip_tunnel_encap_del_ops(const struct ip_tunnel_encap_ops *op, static inline void ip_tunnel_key_init(struct ip_tunnel_key *key, __be32 saddr, __be32 daddr, - u8 tos, u8 ttl, + u8 tos, u8 ttl, __be32 label, __be16 tp_src, __be16 tp_dst, __be64 tun_id, __be16 tun_flags) { @@ -192,6 +193,7 @@ static inline void ip_tunnel_key_init(struct ip_tunnel_key *key, 0, IP_TUNNEL_KEY_IPV4_PAD_LEN); key->tos = tos; key->ttl = ttl; + key->label = label; key->tun_flags = tun_flags; /* For the tunnel types on the top of IPsec, the tp_src and tp_dst of diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index 97f5adb121a6..b83114077cee 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -88,8 +88,8 @@ int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, struct net_device *dev, struct in6_addr *saddr, struct in6_addr *daddr, - __u8 prio, __u8 ttl, __be16 src_port, - __be16 dst_port, bool nocheck); + __u8 prio, __u8 ttl, __be32 label, + __be16 src_port, __be16 dst_port, bool nocheck); #endif void udp_tunnel_sock_release(struct socket *sock); diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c index 14dacf1df529..a7520528ecd2 100644 --- a/net/ipv6/ip6_udp_tunnel.c +++ b/net/ipv6/ip6_udp_tunnel.c @@ -73,8 +73,8 @@ int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, struct net_device *dev, struct in6_addr *saddr, struct in6_addr *daddr, - __u8 prio, __u8 ttl, __be16 src_port, - __be16 dst_port, bool nocheck) + __u8 prio, __u8 ttl, __be32 label, + __be16 src_port, __be16 dst_port, bool nocheck) { struct udphdr *uh; struct ipv6hdr *ip6h; @@ -98,7 +98,7 @@ int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, __skb_push(skb, sizeof(*ip6h)); skb_reset_network_header(skb); ip6h = ipv6_hdr(skb); - ip6_flow_hdr(ip6h, prio, htonl(0)); + ip6_flow_hdr(ip6h, prio, label); ip6h->payload_len = htons(skb->len); ip6h->nexthdr = IPPROTO_UDP; ip6h->hop_limit = ttl; diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index 49b3c2ede7ab..c94f9a15e2cd 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -196,7 +196,7 @@ static int tipc_udp_send_msg(struct net *net, struct sk_buff *skb, ttl = ip6_dst_hoplimit(ndst); err = udp_tunnel6_xmit_skb(ndst, ub->ubsock->sk, skb, ndst->dev, &src->ipv6, - &dst->ipv6, 0, ttl, src->udp_port, + &dst->ipv6, 0, ttl, 0, src->udp_port, dst->udp_port, false); #endif } -- cgit v1.2.3-71-gd317 From e7f70af111f086a20800ad2e17f544b2e3e0f375 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 9 Mar 2016 03:00:03 +0100 Subject: vxlan: support setting IPv6 flow label This work adds support for setting the IPv6 flow label for vxlan per device and through collect metadata (ip_tunnel_key) frontends. The vxlan dst cache does not need any special considerations here, for the cases where caches can be used, the label is static per cache. Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 26 +++++++++++++++++++++----- include/net/vxlan.h | 1 + include/uapi/linux/if_link.h | 1 + 3 files changed, 23 insertions(+), 5 deletions(-) (limited to 'include/net') diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 8bdcd5ea8424..8eda76f9e474 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -1790,6 +1790,7 @@ static struct rtable *vxlan_get_route(struct vxlan_dev *vxlan, #if IS_ENABLED(CONFIG_IPV6) static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan, struct sk_buff *skb, int oif, u8 tos, + __be32 label, const struct in6_addr *daddr, struct in6_addr *saddr, struct dst_cache *dst_cache, @@ -1813,6 +1814,7 @@ static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan, fl6.flowi6_tos = RT_TOS(tos); fl6.daddr = *daddr; fl6.saddr = vxlan->cfg.saddr.sin6.sin6_addr; + fl6.flowlabel = label; fl6.flowi6_mark = skb->mark; fl6.flowi6_proto = IPPROTO_UDP; @@ -1888,7 +1890,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, struct vxlan_metadata _md; struct vxlan_metadata *md = &_md; __be16 src_port = 0, dst_port; - __be32 vni; + __be32 vni, label; __be16 df = 0; __u8 tos, ttl; int err; @@ -1939,12 +1941,14 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, if (tos == 1) tos = ip_tunnel_get_dsfield(old_iph, skb); + label = vxlan->cfg.label; src_port = udp_flow_src_port(dev_net(dev), skb, vxlan->cfg.port_min, vxlan->cfg.port_max, true); if (info) { ttl = info->key.ttl; tos = info->key.tos; + label = info->key.label; udp_sum = !!(info->key.tun_flags & TUNNEL_CSUM); if (info->options_len) @@ -2020,7 +2024,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, ndst = vxlan6_get_route(vxlan, skb, rdst ? rdst->remote_ifindex : 0, tos, - &dst->sin6.sin6_addr, &saddr, + label, &dst->sin6.sin6_addr, &saddr, dst_cache, info); if (IS_ERR(ndst)) { netdev_dbg(dev, "no route to %pI6\n", @@ -2066,8 +2070,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, return; } udp_tunnel6_xmit_skb(ndst, sk, skb, dev, - &saddr, &dst->sin6.sin6_addr, tos, ttl, 0, - src_port, dst_port, !udp_sum); + &saddr, &dst->sin6.sin6_addr, tos, ttl, + label, src_port, dst_port, !udp_sum); #endif } @@ -2390,7 +2394,7 @@ static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) if (!vxlan->vn6_sock) return -EINVAL; ndst = vxlan6_get_route(vxlan, skb, 0, info->key.tos, - &info->key.u.ipv6.dst, + info->key.label, &info->key.u.ipv6.dst, &info->key.u.ipv6.src, NULL, info); if (IS_ERR(ndst)) return PTR_ERR(ndst); @@ -2505,6 +2509,7 @@ static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = { [IFLA_VXLAN_LOCAL6] = { .len = sizeof(struct in6_addr) }, [IFLA_VXLAN_TOS] = { .type = NLA_U8 }, [IFLA_VXLAN_TTL] = { .type = NLA_U8 }, + [IFLA_VXLAN_LABEL] = { .type = NLA_U32 }, [IFLA_VXLAN_LEARNING] = { .type = NLA_U8 }, [IFLA_VXLAN_AGEING] = { .type = NLA_U32 }, [IFLA_VXLAN_LIMIT] = { .type = NLA_U32 }, @@ -2739,6 +2744,11 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, vxlan->flags |= VXLAN_F_IPV6; } + if (conf->label && !use_ipv6) { + pr_info("label only supported in use with IPv6\n"); + return -EINVAL; + } + if (conf->remote_ifindex) { lowerdev = __dev_get_by_index(src_net, conf->remote_ifindex); dst->remote_ifindex = conf->remote_ifindex; @@ -2887,6 +2897,10 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev, if (data[IFLA_VXLAN_TTL]) conf.ttl = nla_get_u8(data[IFLA_VXLAN_TTL]); + if (data[IFLA_VXLAN_LABEL]) + conf.label = nla_get_be32(data[IFLA_VXLAN_LABEL]) & + IPV6_FLOWLABEL_MASK; + if (!data[IFLA_VXLAN_LEARNING] || nla_get_u8(data[IFLA_VXLAN_LEARNING])) conf.flags |= VXLAN_F_LEARN; @@ -2990,6 +3004,7 @@ static size_t vxlan_get_size(const struct net_device *dev) nla_total_size(sizeof(struct in6_addr)) + /* IFLA_VXLAN_LOCAL{6} */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TTL */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TOS */ + nla_total_size(sizeof(__be32)) + /* IFLA_VXLAN_LABEL */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_LEARNING */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_PROXY */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_RSC */ @@ -3053,6 +3068,7 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev) if (nla_put_u8(skb, IFLA_VXLAN_TTL, vxlan->cfg.ttl) || nla_put_u8(skb, IFLA_VXLAN_TOS, vxlan->cfg.tos) || + nla_put_be32(skb, IFLA_VXLAN_LABEL, vxlan->cfg.label) || nla_put_u8(skb, IFLA_VXLAN_LEARNING, !!(vxlan->flags & VXLAN_F_LEARN)) || nla_put_u8(skb, IFLA_VXLAN_PROXY, diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 6eda4ed4d78b..a763c96ecde4 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -162,6 +162,7 @@ struct vxlan_config { u16 port_max; u8 tos; u8 ttl; + __be32 label; u32 flags; unsigned long age_interval; unsigned int addrmax; diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index d452cea59020..6bebc975031d 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -456,6 +456,7 @@ enum { IFLA_VXLAN_GBP, IFLA_VXLAN_REMCSUM_NOPARTIAL, IFLA_VXLAN_COLLECT_METADATA, + IFLA_VXLAN_LABEL, __IFLA_VXLAN_MAX }; #define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1) -- cgit v1.2.3-71-gd317 From 338039635d01524090e7bd706a3e555e20d5b337 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 9 Mar 2016 09:25:26 -0800 Subject: csum: Update csum_block_add to use rotate instead of byteswap The code for csum_block_add was doing a funky byteswap to swap the even and odd bytes of the checksum if the offset was odd. Instead of doing this we can save ourselves some trouble and just shift by 8 as this should have the same effect in terms of the final checksum value and only requires one instruction. In addition we can update csum_block_sub to just use csum_block_add with a inverse value for csum2. This way we follow the same code path as csum_block_add without having to duplicate it. Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- include/net/checksum.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/net') diff --git a/include/net/checksum.h b/include/net/checksum.h index abffc64e7300..5c30891e84e5 100644 --- a/include/net/checksum.h +++ b/include/net/checksum.h @@ -88,8 +88,11 @@ static inline __wsum csum_block_add(__wsum csum, __wsum csum2, int offset) { u32 sum = (__force u32)csum2; - if (offset&1) - sum = ((sum&0xFF00FF)<<8)+((sum>>8)&0xFF00FF); + + /* rotate sum to align it with a 16b boundary */ + if (offset & 1) + sum = ror32(sum, 8); + return csum_add(csum, (__force __wsum)sum); } @@ -102,10 +105,7 @@ csum_block_add_ext(__wsum csum, __wsum csum2, int offset, int len) static inline __wsum csum_block_sub(__wsum csum, __wsum csum2, int offset) { - u32 sum = (__force u32)csum2; - if (offset&1) - sum = ((sum&0xFF00FF)<<8)+((sum>>8)&0xFF00FF); - return csum_sub(csum, (__force __wsum)sum); + return csum_block_add(csum, ~csum2, offset); } static inline __wsum csum_unfold(__sum16 n) -- cgit v1.2.3-71-gd317 From cea8768f333e3f0bc231d8b815aa4a9e63fa990c Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Thu, 10 Mar 2016 18:33:07 -0300 Subject: sctp: allow sctp_transmit_packet and others to use gfp Currently sctp_sendmsg() triggers some calls that will allocate memory with GFP_ATOMIC even when not necessary. In the case of sctp_packet_transmit it will allocate a linear skb that will be used to construct the packet and this may cause sends to fail due to ENOMEM more often than anticipated specially with big MTUs. This patch thus allows it to inherit gfp flags from upper calls so that it can use GFP_KERNEL if it was triggered by a sctp_sendmsg call or similar. All others, like retransmits or flushes started from BH, are still allocated using GFP_ATOMIC. In netperf tests this didn't result in any performance drawbacks when memory is not too fragmented and made it trigger ENOMEM way less often. Signed-off-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- include/net/sctp/sm.h | 2 +- include/net/sctp/structs.h | 10 +++--- net/sctp/associola.c | 2 +- net/sctp/chunk.c | 6 ++-- net/sctp/input.c | 2 +- net/sctp/output.c | 6 ++-- net/sctp/outqueue.c | 30 ++++++++--------- net/sctp/sm_make_chunk.c | 80 +++++++++++++++++++++++++++------------------- net/sctp/sm_sideeffect.c | 23 ++++++------- 9 files changed, 89 insertions(+), 72 deletions(-) (limited to 'include/net') diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index 487ef34bbd63..efc01743b9d6 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -201,7 +201,7 @@ struct sctp_chunk *sctp_make_cwr(const struct sctp_association *, struct sctp_chunk * sctp_make_datafrag_empty(struct sctp_association *, const struct sctp_sndrcvinfo *sinfo, int len, const __u8 flags, - __u16 ssn); + __u16 ssn, gfp_t gfp); struct sctp_chunk *sctp_make_ecne(const struct sctp_association *, const __u32); struct sctp_chunk *sctp_make_sack(const struct sctp_association *); diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index d05b56641abc..9d237669c52c 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -655,7 +655,7 @@ void sctp_chunk_free(struct sctp_chunk *); void *sctp_addto_chunk(struct sctp_chunk *, int len, const void *data); struct sctp_chunk *sctp_chunkify(struct sk_buff *, const struct sctp_association *, - struct sock *); + struct sock *, gfp_t gfp); void sctp_init_addrs(struct sctp_chunk *, union sctp_addr *, union sctp_addr *); const union sctp_addr *sctp_source(const struct sctp_chunk *chunk); @@ -717,10 +717,10 @@ struct sctp_packet *sctp_packet_init(struct sctp_packet *, __u16 sport, __u16 dport); struct sctp_packet *sctp_packet_config(struct sctp_packet *, __u32 vtag, int); sctp_xmit_t sctp_packet_transmit_chunk(struct sctp_packet *, - struct sctp_chunk *, int); + struct sctp_chunk *, int, gfp_t); sctp_xmit_t sctp_packet_append_chunk(struct sctp_packet *, struct sctp_chunk *); -int sctp_packet_transmit(struct sctp_packet *); +int sctp_packet_transmit(struct sctp_packet *, gfp_t); void sctp_packet_free(struct sctp_packet *); static inline int sctp_packet_empty(struct sctp_packet *packet) @@ -1053,7 +1053,7 @@ struct sctp_outq { void sctp_outq_init(struct sctp_association *, struct sctp_outq *); void sctp_outq_teardown(struct sctp_outq *); void sctp_outq_free(struct sctp_outq*); -int sctp_outq_tail(struct sctp_outq *, struct sctp_chunk *chunk); +int sctp_outq_tail(struct sctp_outq *, struct sctp_chunk *chunk, gfp_t); int sctp_outq_sack(struct sctp_outq *, struct sctp_chunk *); int sctp_outq_is_empty(const struct sctp_outq *); void sctp_outq_restart(struct sctp_outq *); @@ -1061,7 +1061,7 @@ void sctp_outq_restart(struct sctp_outq *); void sctp_retransmit(struct sctp_outq *, struct sctp_transport *, sctp_retransmit_reason_t); void sctp_retransmit_mark(struct sctp_outq *, struct sctp_transport *, __u8); -int sctp_outq_uncork(struct sctp_outq *); +int sctp_outq_uncork(struct sctp_outq *, gfp_t gfp); /* Uncork and flush an outqueue. */ static inline void sctp_outq_cork(struct sctp_outq *q) { diff --git a/net/sctp/associola.c b/net/sctp/associola.c index cd873446433c..a19b3e607703 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1493,7 +1493,7 @@ void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned int len) asoc->peer.sack_needed = 0; - sctp_outq_tail(&asoc->outqueue, sack); + sctp_outq_tail(&asoc->outqueue, sack, GFP_ATOMIC); /* Stop the SACK timer. */ timer = &asoc->timers[SCTP_EVENT_TIMEOUT_SACK]; diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index 3aa43073e0b9..958ef5f33f4b 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -260,7 +260,8 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, frag |= SCTP_DATA_SACK_IMM; } - chunk = sctp_make_datafrag_empty(asoc, sinfo, len, frag, 0); + chunk = sctp_make_datafrag_empty(asoc, sinfo, len, frag, + 0, GFP_KERNEL); if (!chunk) { err = -ENOMEM; @@ -296,7 +297,8 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, (sinfo->sinfo_flags & SCTP_SACK_IMMEDIATELY)) frag |= SCTP_DATA_SACK_IMM; - chunk = sctp_make_datafrag_empty(asoc, sinfo, over, frag, 0); + chunk = sctp_make_datafrag_empty(asoc, sinfo, over, frag, + 0, GFP_KERNEL); if (!chunk) { err = -ENOMEM; diff --git a/net/sctp/input.c b/net/sctp/input.c index 21a2d6b7abaf..db76f1ab4ac2 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -221,7 +221,7 @@ int sctp_rcv(struct sk_buff *skb) goto discard_release; /* Create an SCTP packet structure. */ - chunk = sctp_chunkify(skb, asoc, sk); + chunk = sctp_chunkify(skb, asoc, sk, GFP_ATOMIC); if (!chunk) goto discard_release; SCTP_INPUT_CB(skb)->chunk = chunk; diff --git a/net/sctp/output.c b/net/sctp/output.c index 9d610eddd19e..736c004abfbc 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -153,7 +153,7 @@ void sctp_packet_free(struct sctp_packet *packet) */ sctp_xmit_t sctp_packet_transmit_chunk(struct sctp_packet *packet, struct sctp_chunk *chunk, - int one_packet) + int one_packet, gfp_t gfp) { sctp_xmit_t retval; int error = 0; @@ -163,7 +163,7 @@ sctp_xmit_t sctp_packet_transmit_chunk(struct sctp_packet *packet, switch ((retval = (sctp_packet_append_chunk(packet, chunk)))) { case SCTP_XMIT_PMTU_FULL: if (!packet->has_cookie_echo) { - error = sctp_packet_transmit(packet); + error = sctp_packet_transmit(packet, gfp); if (error < 0) chunk->skb->sk->sk_err = -error; @@ -376,7 +376,7 @@ static void sctp_packet_set_owner_w(struct sk_buff *skb, struct sock *sk) * * The return value is a normal kernel error return value. */ -int sctp_packet_transmit(struct sctp_packet *packet) +int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) { struct sctp_transport *tp = packet->transport; struct sctp_association *asoc = tp->asoc; diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index c0380cfb16ae..f03541d0f12d 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -68,7 +68,7 @@ static void sctp_mark_missing(struct sctp_outq *q, static void sctp_generate_fwdtsn(struct sctp_outq *q, __u32 sack_ctsn); -static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout); +static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp); /* Add data to the front of the queue. */ static inline void sctp_outq_head_data(struct sctp_outq *q, @@ -285,7 +285,7 @@ void sctp_outq_free(struct sctp_outq *q) } /* Put a new chunk in an sctp_outq. */ -int sctp_outq_tail(struct sctp_outq *q, struct sctp_chunk *chunk) +int sctp_outq_tail(struct sctp_outq *q, struct sctp_chunk *chunk, gfp_t gfp) { struct net *net = sock_net(q->asoc->base.sk); int error = 0; @@ -341,7 +341,7 @@ int sctp_outq_tail(struct sctp_outq *q, struct sctp_chunk *chunk) return error; if (!q->cork) - error = sctp_outq_flush(q, 0); + error = sctp_outq_flush(q, 0, gfp); return error; } @@ -510,7 +510,7 @@ void sctp_retransmit(struct sctp_outq *q, struct sctp_transport *transport, * will be flushed at the end. */ if (reason != SCTP_RTXR_FAST_RTX) - error = sctp_outq_flush(q, /* rtx_timeout */ 1); + error = sctp_outq_flush(q, /* rtx_timeout */ 1, GFP_ATOMIC); if (error) q->asoc->base.sk->sk_err = -error; @@ -601,12 +601,12 @@ redo: * control chunks are already freed so there * is nothing we can do. */ - sctp_packet_transmit(pkt); + sctp_packet_transmit(pkt, GFP_ATOMIC); goto redo; } /* Send this packet. */ - error = sctp_packet_transmit(pkt); + error = sctp_packet_transmit(pkt, GFP_ATOMIC); /* If we are retransmitting, we should only * send a single packet. @@ -622,7 +622,7 @@ redo: case SCTP_XMIT_RWND_FULL: /* Send this packet. */ - error = sctp_packet_transmit(pkt); + error = sctp_packet_transmit(pkt, GFP_ATOMIC); /* Stop sending DATA as there is no more room * at the receiver. @@ -632,7 +632,7 @@ redo: case SCTP_XMIT_DELAY: /* Send this packet. */ - error = sctp_packet_transmit(pkt); + error = sctp_packet_transmit(pkt, GFP_ATOMIC); /* Stop sending DATA because of nagle delay. */ done = 1; @@ -685,12 +685,12 @@ redo: } /* Cork the outqueue so queued chunks are really queued. */ -int sctp_outq_uncork(struct sctp_outq *q) +int sctp_outq_uncork(struct sctp_outq *q, gfp_t gfp) { if (q->cork) q->cork = 0; - return sctp_outq_flush(q, 0); + return sctp_outq_flush(q, 0, gfp); } @@ -703,7 +703,7 @@ int sctp_outq_uncork(struct sctp_outq *q) * locking concerns must be made. Today we use the sock lock to protect * this function. */ -static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) +static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) { struct sctp_packet *packet; struct sctp_packet singleton; @@ -825,7 +825,7 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) sctp_packet_init(&singleton, transport, sport, dport); sctp_packet_config(&singleton, vtag, 0); sctp_packet_append_chunk(&singleton, chunk); - error = sctp_packet_transmit(&singleton); + error = sctp_packet_transmit(&singleton, gfp); if (error < 0) return error; break; @@ -856,7 +856,7 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) case SCTP_CID_ASCONF: case SCTP_CID_FWD_TSN: status = sctp_packet_transmit_chunk(packet, chunk, - one_packet); + one_packet, gfp); if (status != SCTP_XMIT_OK) { /* put the chunk back */ list_add(&chunk->list, &q->control_chunk_list); @@ -1011,7 +1011,7 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) atomic_read(&chunk->skb->users) : -1); /* Add the chunk to the packet. */ - status = sctp_packet_transmit_chunk(packet, chunk, 0); + status = sctp_packet_transmit_chunk(packet, chunk, 0, gfp); switch (status) { case SCTP_XMIT_PMTU_FULL: @@ -1088,7 +1088,7 @@ sctp_flush_out: send_ready); packet = &t->packet; if (!sctp_packet_empty(packet)) - error = sctp_packet_transmit(packet); + error = sctp_packet_transmit(packet, gfp); /* Clear the burst limited state, if any */ sctp_transport_burst_reset(t); diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 5d6a03fad378..8449ca26aa0b 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -62,11 +62,13 @@ #include static struct sctp_chunk *sctp_make_control(const struct sctp_association *asoc, - __u8 type, __u8 flags, int paylen); + __u8 type, __u8 flags, int paylen, + gfp_t gfp); static struct sctp_chunk *sctp_make_data(const struct sctp_association *asoc, - __u8 flags, int paylen); + __u8 flags, int paylen, gfp_t gfp); static struct sctp_chunk *_sctp_make_chunk(const struct sctp_association *asoc, - __u8 type, __u8 flags, int paylen); + __u8 type, __u8 flags, int paylen, + gfp_t gfp); static sctp_cookie_param_t *sctp_pack_cookie(const struct sctp_endpoint *ep, const struct sctp_association *asoc, const struct sctp_chunk *init_chunk, @@ -318,7 +320,7 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc, * PLEASE DO NOT FIXME [This version does not support Host Name.] */ - retval = sctp_make_control(asoc, SCTP_CID_INIT, 0, chunksize); + retval = sctp_make_control(asoc, SCTP_CID_INIT, 0, chunksize, gfp); if (!retval) goto nodata; @@ -465,7 +467,7 @@ struct sctp_chunk *sctp_make_init_ack(const struct sctp_association *asoc, num_ext); /* Now allocate and fill out the chunk. */ - retval = sctp_make_control(asoc, SCTP_CID_INIT_ACK, 0, chunksize); + retval = sctp_make_control(asoc, SCTP_CID_INIT_ACK, 0, chunksize, gfp); if (!retval) goto nomem_chunk; @@ -570,7 +572,8 @@ struct sctp_chunk *sctp_make_cookie_echo(const struct sctp_association *asoc, cookie_len = asoc->peer.cookie_len; /* Build a cookie echo chunk. */ - retval = sctp_make_control(asoc, SCTP_CID_COOKIE_ECHO, 0, cookie_len); + retval = sctp_make_control(asoc, SCTP_CID_COOKIE_ECHO, 0, + cookie_len, GFP_ATOMIC); if (!retval) goto nodata; retval->subh.cookie_hdr = @@ -615,7 +618,7 @@ struct sctp_chunk *sctp_make_cookie_ack(const struct sctp_association *asoc, { struct sctp_chunk *retval; - retval = sctp_make_control(asoc, SCTP_CID_COOKIE_ACK, 0, 0); + retval = sctp_make_control(asoc, SCTP_CID_COOKIE_ACK, 0, 0, GFP_ATOMIC); /* RFC 2960 6.4 Multi-homed SCTP Endpoints * @@ -664,7 +667,7 @@ struct sctp_chunk *sctp_make_cwr(const struct sctp_association *asoc, cwr.lowest_tsn = htonl(lowest_tsn); retval = sctp_make_control(asoc, SCTP_CID_ECN_CWR, 0, - sizeof(sctp_cwrhdr_t)); + sizeof(sctp_cwrhdr_t), GFP_ATOMIC); if (!retval) goto nodata; @@ -698,7 +701,7 @@ struct sctp_chunk *sctp_make_ecne(const struct sctp_association *asoc, ecne.lowest_tsn = htonl(lowest_tsn); retval = sctp_make_control(asoc, SCTP_CID_ECN_ECNE, 0, - sizeof(sctp_ecnehdr_t)); + sizeof(sctp_ecnehdr_t), GFP_ATOMIC); if (!retval) goto nodata; retval->subh.ecne_hdr = @@ -713,7 +716,8 @@ nodata: */ struct sctp_chunk *sctp_make_datafrag_empty(struct sctp_association *asoc, const struct sctp_sndrcvinfo *sinfo, - int data_len, __u8 flags, __u16 ssn) + int data_len, __u8 flags, __u16 ssn, + gfp_t gfp) { struct sctp_chunk *retval; struct sctp_datahdr dp; @@ -734,7 +738,7 @@ struct sctp_chunk *sctp_make_datafrag_empty(struct sctp_association *asoc, dp.ssn = htons(ssn); chunk_len = sizeof(dp) + data_len; - retval = sctp_make_data(asoc, flags, chunk_len); + retval = sctp_make_data(asoc, flags, chunk_len, gfp); if (!retval) goto nodata; @@ -781,7 +785,7 @@ struct sctp_chunk *sctp_make_sack(const struct sctp_association *asoc) + sizeof(__u32) * num_dup_tsns; /* Create the chunk. */ - retval = sctp_make_control(asoc, SCTP_CID_SACK, 0, len); + retval = sctp_make_control(asoc, SCTP_CID_SACK, 0, len, GFP_ATOMIC); if (!retval) goto nodata; @@ -861,7 +865,7 @@ struct sctp_chunk *sctp_make_shutdown(const struct sctp_association *asoc, shut.cum_tsn_ack = htonl(ctsn); retval = sctp_make_control(asoc, SCTP_CID_SHUTDOWN, 0, - sizeof(sctp_shutdownhdr_t)); + sizeof(sctp_shutdownhdr_t), GFP_ATOMIC); if (!retval) goto nodata; @@ -879,7 +883,8 @@ struct sctp_chunk *sctp_make_shutdown_ack(const struct sctp_association *asoc, { struct sctp_chunk *retval; - retval = sctp_make_control(asoc, SCTP_CID_SHUTDOWN_ACK, 0, 0); + retval = sctp_make_control(asoc, SCTP_CID_SHUTDOWN_ACK, 0, 0, + GFP_ATOMIC); /* RFC 2960 6.4 Multi-homed SCTP Endpoints * @@ -908,7 +913,8 @@ struct sctp_chunk *sctp_make_shutdown_complete( */ flags |= asoc ? 0 : SCTP_CHUNK_FLAG_T; - retval = sctp_make_control(asoc, SCTP_CID_SHUTDOWN_COMPLETE, flags, 0); + retval = sctp_make_control(asoc, SCTP_CID_SHUTDOWN_COMPLETE, flags, + 0, GFP_ATOMIC); /* RFC 2960 6.4 Multi-homed SCTP Endpoints * @@ -947,7 +953,8 @@ struct sctp_chunk *sctp_make_abort(const struct sctp_association *asoc, flags = SCTP_CHUNK_FLAG_T; } - retval = sctp_make_control(asoc, SCTP_CID_ABORT, flags, hint); + retval = sctp_make_control(asoc, SCTP_CID_ABORT, flags, hint, + GFP_ATOMIC); /* RFC 2960 6.4 Multi-homed SCTP Endpoints * @@ -1139,7 +1146,8 @@ struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc, struct sctp_chunk *retval; sctp_sender_hb_info_t hbinfo; - retval = sctp_make_control(asoc, SCTP_CID_HEARTBEAT, 0, sizeof(hbinfo)); + retval = sctp_make_control(asoc, SCTP_CID_HEARTBEAT, 0, + sizeof(hbinfo), GFP_ATOMIC); if (!retval) goto nodata; @@ -1167,7 +1175,8 @@ struct sctp_chunk *sctp_make_heartbeat_ack(const struct sctp_association *asoc, { struct sctp_chunk *retval; - retval = sctp_make_control(asoc, SCTP_CID_HEARTBEAT_ACK, 0, paylen); + retval = sctp_make_control(asoc, SCTP_CID_HEARTBEAT_ACK, 0, paylen, + GFP_ATOMIC); if (!retval) goto nodata; @@ -1200,7 +1209,7 @@ static struct sctp_chunk *sctp_make_op_error_space( struct sctp_chunk *retval; retval = sctp_make_control(asoc, SCTP_CID_ERROR, 0, - sizeof(sctp_errhdr_t) + size); + sizeof(sctp_errhdr_t) + size, GFP_ATOMIC); if (!retval) goto nodata; @@ -1271,7 +1280,8 @@ struct sctp_chunk *sctp_make_auth(const struct sctp_association *asoc) return NULL; retval = sctp_make_control(asoc, SCTP_CID_AUTH, 0, - hmac_desc->hmac_len + sizeof(sctp_authhdr_t)); + hmac_desc->hmac_len + sizeof(sctp_authhdr_t), + GFP_ATOMIC); if (!retval) return NULL; @@ -1309,11 +1319,11 @@ struct sctp_chunk *sctp_make_auth(const struct sctp_association *asoc) */ struct sctp_chunk *sctp_chunkify(struct sk_buff *skb, const struct sctp_association *asoc, - struct sock *sk) + struct sock *sk, gfp_t gfp) { struct sctp_chunk *retval; - retval = kmem_cache_zalloc(sctp_chunk_cachep, GFP_ATOMIC); + retval = kmem_cache_zalloc(sctp_chunk_cachep, gfp); if (!retval) goto nodata; @@ -1361,7 +1371,8 @@ const union sctp_addr *sctp_source(const struct sctp_chunk *chunk) * arguments, reserving enough space for a 'paylen' byte payload. */ static struct sctp_chunk *_sctp_make_chunk(const struct sctp_association *asoc, - __u8 type, __u8 flags, int paylen) + __u8 type, __u8 flags, int paylen, + gfp_t gfp) { struct sctp_chunk *retval; sctp_chunkhdr_t *chunk_hdr; @@ -1369,8 +1380,7 @@ static struct sctp_chunk *_sctp_make_chunk(const struct sctp_association *asoc, struct sock *sk; /* No need to allocate LL here, as this is only a chunk. */ - skb = alloc_skb(WORD_ROUND(sizeof(sctp_chunkhdr_t) + paylen), - GFP_ATOMIC); + skb = alloc_skb(WORD_ROUND(sizeof(sctp_chunkhdr_t) + paylen), gfp); if (!skb) goto nodata; @@ -1381,7 +1391,7 @@ static struct sctp_chunk *_sctp_make_chunk(const struct sctp_association *asoc, chunk_hdr->length = htons(sizeof(sctp_chunkhdr_t)); sk = asoc ? asoc->base.sk : NULL; - retval = sctp_chunkify(skb, asoc, sk); + retval = sctp_chunkify(skb, asoc, sk, gfp); if (!retval) { kfree_skb(skb); goto nodata; @@ -1400,16 +1410,18 @@ nodata: } static struct sctp_chunk *sctp_make_data(const struct sctp_association *asoc, - __u8 flags, int paylen) + __u8 flags, int paylen, gfp_t gfp) { - return _sctp_make_chunk(asoc, SCTP_CID_DATA, flags, paylen); + return _sctp_make_chunk(asoc, SCTP_CID_DATA, flags, paylen, gfp); } static struct sctp_chunk *sctp_make_control(const struct sctp_association *asoc, - __u8 type, __u8 flags, int paylen) + __u8 type, __u8 flags, int paylen, + gfp_t gfp) { - struct sctp_chunk *chunk = _sctp_make_chunk(asoc, type, flags, paylen); + struct sctp_chunk *chunk; + chunk = _sctp_make_chunk(asoc, type, flags, paylen, gfp); if (chunk) sctp_control_set_owner_w(chunk); @@ -2756,7 +2768,8 @@ static struct sctp_chunk *sctp_make_asconf(struct sctp_association *asoc, length += addrlen; /* Create the chunk. */ - retval = sctp_make_control(asoc, SCTP_CID_ASCONF, 0, length); + retval = sctp_make_control(asoc, SCTP_CID_ASCONF, 0, length, + GFP_ATOMIC); if (!retval) return NULL; @@ -2940,7 +2953,8 @@ static struct sctp_chunk *sctp_make_asconf_ack(const struct sctp_association *as int length = sizeof(asconf) + vparam_len; /* Create the chunk. */ - retval = sctp_make_control(asoc, SCTP_CID_ASCONF_ACK, 0, length); + retval = sctp_make_control(asoc, SCTP_CID_ASCONF_ACK, 0, length, + GFP_ATOMIC); if (!retval) return NULL; @@ -3500,7 +3514,7 @@ struct sctp_chunk *sctp_make_fwdtsn(const struct sctp_association *asoc, hint = (nstreams + 1) * sizeof(__u32); - retval = sctp_make_control(asoc, SCTP_CID_FWD_TSN, 0, hint); + retval = sctp_make_control(asoc, SCTP_CID_FWD_TSN, 0, hint, GFP_ATOMIC); if (!retval) return NULL; diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index b5327bb77458..3c22c41a2bc2 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -1019,13 +1019,13 @@ static void sctp_cmd_t1_timer_update(struct sctp_association *asoc, * encouraged for small fragments. */ static int sctp_cmd_send_msg(struct sctp_association *asoc, - struct sctp_datamsg *msg) + struct sctp_datamsg *msg, gfp_t gfp) { struct sctp_chunk *chunk; int error = 0; list_for_each_entry(chunk, &msg->chunks, frag_list) { - error = sctp_outq_tail(&asoc->outqueue, chunk); + error = sctp_outq_tail(&asoc->outqueue, chunk, gfp); if (error) break; } @@ -1249,7 +1249,7 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, case SCTP_CMD_NEW_ASOC: /* Register a new association. */ if (local_cork) { - sctp_outq_uncork(&asoc->outqueue); + sctp_outq_uncork(&asoc->outqueue, gfp); local_cork = 0; } @@ -1269,7 +1269,7 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, case SCTP_CMD_DELETE_TCB: if (local_cork) { - sctp_outq_uncork(&asoc->outqueue); + sctp_outq_uncork(&asoc->outqueue, gfp); local_cork = 0; } /* Delete the current association. */ @@ -1423,13 +1423,14 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, local_cork = 1; } /* Send a chunk to our peer. */ - error = sctp_outq_tail(&asoc->outqueue, cmd->obj.chunk); + error = sctp_outq_tail(&asoc->outqueue, cmd->obj.chunk, + gfp); break; case SCTP_CMD_SEND_PKT: /* Send a full packet to our peer. */ packet = cmd->obj.packet; - sctp_packet_transmit(packet); + sctp_packet_transmit(packet, gfp); sctp_ootb_pkt_free(packet); break; @@ -1639,7 +1640,7 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, */ chunk->pdiscard = 1; if (asoc) { - sctp_outq_uncork(&asoc->outqueue); + sctp_outq_uncork(&asoc->outqueue, gfp); local_cork = 0; } break; @@ -1677,7 +1678,7 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, case SCTP_CMD_FORCE_PRIM_RETRAN: t = asoc->peer.retran_path; asoc->peer.retran_path = asoc->peer.primary_path; - error = sctp_outq_uncork(&asoc->outqueue); + error = sctp_outq_uncork(&asoc->outqueue, gfp); local_cork = 0; asoc->peer.retran_path = t; break; @@ -1704,7 +1705,7 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, sctp_outq_cork(&asoc->outqueue); local_cork = 1; } - error = sctp_cmd_send_msg(asoc, cmd->obj.msg); + error = sctp_cmd_send_msg(asoc, cmd->obj.msg, gfp); break; case SCTP_CMD_SEND_NEXT_ASCONF: sctp_cmd_send_asconf(asoc); @@ -1734,9 +1735,9 @@ out: */ if (asoc && SCTP_EVENT_T_CHUNK == event_type && chunk) { if (chunk->end_of_packet || chunk->singleton) - error = sctp_outq_uncork(&asoc->outqueue); + error = sctp_outq_uncork(&asoc->outqueue, gfp); } else if (local_cork) - error = sctp_outq_uncork(&asoc->outqueue); + error = sctp_outq_uncork(&asoc->outqueue, gfp); return error; nomem: error = -ENOMEM; -- cgit v1.2.3-71-gd317 From 1e94082963747b551b129528714827f76a090e93 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 11 Mar 2016 14:05:41 -0800 Subject: ipv6: Pass proto to csum_ipv6_magic as __u8 instead of unsigned short This patch updates csum_ipv6_magic so that it correctly recognizes that protocol is a unsigned 8 bit value. This will allow us to better understand what limitations may or may not be present in how we handle the data. For example there are a number of places that call htonl on the protocol value. This is likely not necessary and can be replaced with a multiplication by ntohl(1) which will be converted to a shift by the compiler. Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- arch/alpha/include/asm/checksum.h | 3 +-- arch/arm/include/asm/checksum.h | 4 ++-- arch/frv/include/asm/checksum.h | 2 +- arch/ia64/include/asm/checksum.h | 4 ++-- arch/m68k/include/asm/checksum.h | 2 +- arch/mips/include/asm/checksum.h | 2 +- arch/parisc/include/asm/checksum.h | 2 +- arch/score/include/asm/checksum.h | 5 ++--- arch/sh/include/asm/checksum_32.h | 3 +-- arch/sparc/include/asm/checksum_32.h | 3 +-- arch/sparc/include/asm/checksum_64.h | 3 +-- arch/x86/include/asm/checksum_32.h | 3 +-- arch/x86/include/asm/checksum_64.h | 2 +- arch/x86/lib/csum-wrappers_64.c | 2 +- arch/x86/um/asm/checksum_32.h | 2 +- arch/xtensa/include/asm/checksum.h | 2 +- include/net/ip6_checksum.h | 3 +-- net/ipv6/ip6_checksum.c | 3 +-- 18 files changed, 21 insertions(+), 29 deletions(-) (limited to 'include/net') diff --git a/arch/alpha/include/asm/checksum.h b/arch/alpha/include/asm/checksum.h index cba34b1c738c..f2bbdd2ace51 100644 --- a/arch/alpha/include/asm/checksum.h +++ b/arch/alpha/include/asm/checksum.h @@ -67,6 +67,5 @@ static inline __sum16 csum_fold(__wsum csum) #define _HAVE_ARCH_IPV6_CSUM extern __sum16 csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr, - __u32 len, unsigned short proto, - __wsum sum); + __u32 len, __u8 proto, __wsum sum); #endif diff --git a/arch/arm/include/asm/checksum.h b/arch/arm/include/asm/checksum.h index 42d020b7dfba..524692f4acab 100644 --- a/arch/arm/include/asm/checksum.h +++ b/arch/arm/include/asm/checksum.h @@ -144,8 +144,8 @@ __csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr, __ __be32 proto, __wsum sum); static inline __sum16 -csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr, __u32 len, - unsigned short proto, __wsum sum) +csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr, + __u32 len, __u8 proto, __wsum sum) { return csum_fold(__csum_ipv6_magic(saddr, daddr, htonl(len), htonl(proto), sum)); diff --git a/arch/frv/include/asm/checksum.h b/arch/frv/include/asm/checksum.h index cd59cd4fd2d9..b77388c5901d 100644 --- a/arch/frv/include/asm/checksum.h +++ b/arch/frv/include/asm/checksum.h @@ -135,7 +135,7 @@ extern __sum16 ip_compute_csum(const void *buff, int len); #define _HAVE_ARCH_IPV6_CSUM static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr, - __u32 len, unsigned short proto, __wsum sum) + __u32 len, __u8 proto, __wsum sum) { unsigned long tmp, tmp2; diff --git a/arch/ia64/include/asm/checksum.h b/arch/ia64/include/asm/checksum.h index ac9c687e8384..7accf54162b2 100644 --- a/arch/ia64/include/asm/checksum.h +++ b/arch/ia64/include/asm/checksum.h @@ -69,7 +69,7 @@ static inline __sum16 csum_fold(__wsum csum) #define _HAVE_ARCH_IPV6_CSUM 1 struct in6_addr; extern __sum16 csum_ipv6_magic(const struct in6_addr *saddr, - const struct in6_addr *daddr, __u32 len, unsigned short proto, - __wsum csum); + const struct in6_addr *daddr, + __u32 len, __u8 proto, __wsum csum); #endif /* _ASM_IA64_CHECKSUM_H */ diff --git a/arch/m68k/include/asm/checksum.h b/arch/m68k/include/asm/checksum.h index 2f88d867c711..75e91f03b178 100644 --- a/arch/m68k/include/asm/checksum.h +++ b/arch/m68k/include/asm/checksum.h @@ -117,7 +117,7 @@ static inline __sum16 ip_compute_csum(const void *buff, int len) #define _HAVE_ARCH_IPV6_CSUM static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr, - __u32 len, unsigned short proto, __wsum sum) + __u32 len, __u8 proto, __wsum sum) { register unsigned long tmp; __asm__("addl %2@,%0\n\t" diff --git a/arch/mips/include/asm/checksum.h b/arch/mips/include/asm/checksum.h index c635541d40b8..bce1ce53149a 100644 --- a/arch/mips/include/asm/checksum.h +++ b/arch/mips/include/asm/checksum.h @@ -215,7 +215,7 @@ static inline __sum16 ip_compute_csum(const void *buff, int len) #define _HAVE_ARCH_IPV6_CSUM static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr, - __u32 len, unsigned short proto, + __u32 len, __u8 proto, __wsum sum) { __wsum tmp; diff --git a/arch/parisc/include/asm/checksum.h b/arch/parisc/include/asm/checksum.h index 9815ab1fc8aa..60c2c42619c9 100644 --- a/arch/parisc/include/asm/checksum.h +++ b/arch/parisc/include/asm/checksum.h @@ -122,7 +122,7 @@ static inline __sum16 ip_compute_csum(const void *buf, int len) #define _HAVE_ARCH_IPV6_CSUM static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr, - __u32 len, unsigned short proto, + __u32 len, __u8 proto, __wsum sum) { __asm__ __volatile__ ( diff --git a/arch/score/include/asm/checksum.h b/arch/score/include/asm/checksum.h index a375bc2700be..539d9fd45d21 100644 --- a/arch/score/include/asm/checksum.h +++ b/arch/score/include/asm/checksum.h @@ -179,9 +179,8 @@ static inline unsigned short ip_compute_csum(const void *buff, int len) #define _HAVE_ARCH_IPV6_CSUM static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr, - const struct in6_addr *daddr, - __u32 len, unsigned short proto, - __wsum sum) + const struct in6_addr *daddr, + __u32 len, __u8 proto, __wsum sum) { __asm__ __volatile__( ".set\tvolatile\t\t\t# csum_ipv6_magic\n\t" diff --git a/arch/sh/include/asm/checksum_32.h b/arch/sh/include/asm/checksum_32.h index fd730f140c06..9c84386d35cb 100644 --- a/arch/sh/include/asm/checksum_32.h +++ b/arch/sh/include/asm/checksum_32.h @@ -159,8 +159,7 @@ static inline __sum16 ip_compute_csum(const void *buff, int len) #define _HAVE_ARCH_IPV6_CSUM static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr, - __u32 len, unsigned short proto, - __wsum sum) + __u32 len, __u8 proto, __wsum sum) { unsigned int __dummy; __asm__("clrt\n\t" diff --git a/arch/sparc/include/asm/checksum_32.h b/arch/sparc/include/asm/checksum_32.h index 86ae655a3c0f..eff748c871ec 100644 --- a/arch/sparc/include/asm/checksum_32.h +++ b/arch/sparc/include/asm/checksum_32.h @@ -199,8 +199,7 @@ static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr, static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr, - __u32 len, unsigned short proto, - __wsum sum) + __u32 len, __u8 proto, __wsum sum) { __asm__ __volatile__ ( "addcc %3, %4, %%g4\n\t" diff --git a/arch/sparc/include/asm/checksum_64.h b/arch/sparc/include/asm/checksum_64.h index ef0c6f48189a..0395d75322e9 100644 --- a/arch/sparc/include/asm/checksum_64.h +++ b/arch/sparc/include/asm/checksum_64.h @@ -125,8 +125,7 @@ static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr, static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr, - __u32 len, unsigned short proto, - __wsum sum) + __u32 len, __u8 proto, __wsum sum) { __asm__ __volatile__ ( " addcc %3, %4, %%g7\n" diff --git a/arch/x86/include/asm/checksum_32.h b/arch/x86/include/asm/checksum_32.h index 6f380605403d..532f85e6651f 100644 --- a/arch/x86/include/asm/checksum_32.h +++ b/arch/x86/include/asm/checksum_32.h @@ -149,8 +149,7 @@ static inline __sum16 ip_compute_csum(const void *buff, int len) #define _HAVE_ARCH_IPV6_CSUM static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr, - __u32 len, unsigned short proto, - __wsum sum) + __u32 len, __u8 proto, __wsum sum) { asm("addl 0(%1), %0 ;\n" "adcl 4(%1), %0 ;\n" diff --git a/arch/x86/include/asm/checksum_64.h b/arch/x86/include/asm/checksum_64.h index 97b98e2039bc..c020ee75dce7 100644 --- a/arch/x86/include/asm/checksum_64.h +++ b/arch/x86/include/asm/checksum_64.h @@ -177,7 +177,7 @@ struct in6_addr; #define _HAVE_ARCH_IPV6_CSUM 1 extern __sum16 csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr, - __u32 len, unsigned short proto, __wsum sum); + __u32 len, __u8 proto, __wsum sum); static inline unsigned add32_with_carry(unsigned a, unsigned b) { diff --git a/arch/x86/lib/csum-wrappers_64.c b/arch/x86/lib/csum-wrappers_64.c index 1318f75d56e4..28a6654f0d08 100644 --- a/arch/x86/lib/csum-wrappers_64.c +++ b/arch/x86/lib/csum-wrappers_64.c @@ -135,7 +135,7 @@ EXPORT_SYMBOL(csum_partial_copy_nocheck); __sum16 csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr, - __u32 len, unsigned short proto, __wsum sum) + __u32 len, __u8 proto, __wsum sum) { __u64 rest, sum64; diff --git a/arch/x86/um/asm/checksum_32.h b/arch/x86/um/asm/checksum_32.h index ab77b6f9a4bf..83a75f8a1233 100644 --- a/arch/x86/um/asm/checksum_32.h +++ b/arch/x86/um/asm/checksum_32.h @@ -13,7 +13,7 @@ static inline __sum16 ip_compute_csum(const void *buff, int len) #define _HAVE_ARCH_IPV6_CSUM static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr, - __u32 len, unsigned short proto, + __u32 len, __u8 proto, __wsum sum) { __asm__( diff --git a/arch/xtensa/include/asm/checksum.h b/arch/xtensa/include/asm/checksum.h index 62254e6688f5..ec35074fcb03 100644 --- a/arch/xtensa/include/asm/checksum.h +++ b/arch/xtensa/include/asm/checksum.h @@ -175,7 +175,7 @@ static __inline__ __sum16 ip_compute_csum(const void *buff, int len) #define _HAVE_ARCH_IPV6_CSUM static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr, - __u32 len, unsigned short proto, + __u32 len, __u8 proto, __wsum sum) { unsigned int __dummy; diff --git a/include/net/ip6_checksum.h b/include/net/ip6_checksum.h index 1a49b73f7f6e..cca840584c88 100644 --- a/include/net/ip6_checksum.h +++ b/include/net/ip6_checksum.h @@ -37,8 +37,7 @@ #ifndef _HAVE_ARCH_IPV6_CSUM __sum16 csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr, - __u32 len, unsigned short proto, - __wsum csum); + __u32 len, __u8 proto, __wsum csum); #endif static inline __wsum ip6_compute_pseudo(struct sk_buff *skb, int proto) diff --git a/net/ipv6/ip6_checksum.c b/net/ipv6/ip6_checksum.c index 8f920580976f..b2025bf3da4a 100644 --- a/net/ipv6/ip6_checksum.c +++ b/net/ipv6/ip6_checksum.c @@ -6,8 +6,7 @@ #ifndef _HAVE_ARCH_IPV6_CSUM __sum16 csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr, - __u32 len, unsigned short proto, - __wsum csum) + __u32 len, __u8 proto, __wsum csum) { int carry; -- cgit v1.2.3-71-gd317 From 8cb2d8bf57e6e004c37db2fb4ce74f4d032b7cd0 Mon Sep 17 00:00:00 2001 From: Gregory CLEMENT Date: Mon, 14 Mar 2016 09:39:04 +0100 Subject: net: add a hardware buffer management helper API This basic implementation allows to share code between driver using hardware buffer management. As the code is hardware agnostic, there is few helpers, most of the optimization brought by the an HW BM has to be done at driver level. Tested-by: Sebastian Careba Signed-off-by: Gregory CLEMENT Signed-off-by: David S. Miller --- include/net/hwbm.h | 28 ++++++++++++++++++ net/Kconfig | 3 ++ net/core/Makefile | 1 + net/core/hwbm.c | 87 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 119 insertions(+) create mode 100644 include/net/hwbm.h create mode 100644 net/core/hwbm.c (limited to 'include/net') diff --git a/include/net/hwbm.h b/include/net/hwbm.h new file mode 100644 index 000000000000..47d08662501b --- /dev/null +++ b/include/net/hwbm.h @@ -0,0 +1,28 @@ +#ifndef _HWBM_H +#define _HWBM_H + +struct hwbm_pool { + /* Capacity of the pool */ + int size; + /* Size of the buffers managed */ + int frag_size; + /* Number of buffers currently used by this pool */ + int buf_num; + /* constructor called during alocation */ + int (*construct)(struct hwbm_pool *bm_pool, void *buf); + /* protect acces to the buffer counter*/ + spinlock_t lock; + /* private data */ + void *priv; +}; +#ifdef CONFIG_HWBM +void hwbm_buf_free(struct hwbm_pool *bm_pool, void *buf); +int hwbm_pool_refill(struct hwbm_pool *bm_pool, gfp_t gfp); +int hwbm_pool_add(struct hwbm_pool *bm_pool, unsigned int buf_num, gfp_t gfp); +#else +void hwbm_buf_free(struct hwbm_pool *bm_pool, void *buf) {} +int hwbm_pool_refill(struct hwbm_pool *bm_pool, gfp_t gfp) { return 0; } +int hwbm_pool_add(struct hwbm_pool *bm_pool, unsigned int buf_num, gfp_t gfp) +{ return 0; } +#endif /* CONFIG_HWBM */ +#endif /* _HWBM_H */ diff --git a/net/Kconfig b/net/Kconfig index 10640d5f8bee..e13449870d06 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -253,6 +253,9 @@ config XPS depends on SMP default y +config HWBM + bool + config SOCK_CGROUP_DATA bool default n diff --git a/net/core/Makefile b/net/core/Makefile index 014422e2561f..d6508c2ddca5 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -25,4 +25,5 @@ obj-$(CONFIG_CGROUP_NET_PRIO) += netprio_cgroup.o obj-$(CONFIG_CGROUP_NET_CLASSID) += netclassid_cgroup.o obj-$(CONFIG_LWTUNNEL) += lwtunnel.o obj-$(CONFIG_DST_CACHE) += dst_cache.o +obj-$(CONFIG_HWBM) += hwbm.o obj-$(CONFIG_NET_DEVLINK) += devlink.o diff --git a/net/core/hwbm.c b/net/core/hwbm.c new file mode 100644 index 000000000000..941c28486896 --- /dev/null +++ b/net/core/hwbm.c @@ -0,0 +1,87 @@ +/* Support for hardware buffer manager. + * + * Copyright (C) 2016 Marvell + * + * Gregory CLEMENT + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ +#include +#include +#include +#include + +void hwbm_buf_free(struct hwbm_pool *bm_pool, void *buf) +{ + if (likely(bm_pool->frag_size <= PAGE_SIZE)) + skb_free_frag(buf); + else + kfree(buf); +} +EXPORT_SYMBOL_GPL(hwbm_buf_free); + +/* Refill processing for HW buffer management */ +int hwbm_pool_refill(struct hwbm_pool *bm_pool, gfp_t gfp) +{ + int frag_size = bm_pool->frag_size; + void *buf; + + if (likely(frag_size <= PAGE_SIZE)) + buf = netdev_alloc_frag(frag_size); + else + buf = kmalloc(frag_size, gfp); + + if (!buf) + return -ENOMEM; + + if (bm_pool->construct) + if (bm_pool->construct(bm_pool, buf)) { + hwbm_buf_free(bm_pool, buf); + return -ENOMEM; + } + + return 0; +} +EXPORT_SYMBOL_GPL(hwbm_pool_refill); + +int hwbm_pool_add(struct hwbm_pool *bm_pool, unsigned int buf_num, gfp_t gfp) +{ + int err, i; + unsigned long flags; + + spin_lock_irqsave(&bm_pool->lock, flags); + if (bm_pool->buf_num == bm_pool->size) { + pr_warn("pool already filled\n"); + return bm_pool->buf_num; + } + + if (buf_num + bm_pool->buf_num > bm_pool->size) { + pr_warn("cannot allocate %d buffers for pool\n", + buf_num); + return 0; + } + + if ((buf_num + bm_pool->buf_num) < bm_pool->buf_num) { + pr_warn("Adding %d buffers to the %d current buffers will overflow\n", + buf_num, bm_pool->buf_num); + return 0; + } + + for (i = 0; i < buf_num; i++) { + err = hwbm_pool_refill(bm_pool, gfp); + if (err < 0) + break; + } + + /* Update BM driver with number of buffers added to pool */ + bm_pool->buf_num += i; + + pr_debug("hwpm pool: %d of %d buffers added\n", i, buf_num); + spin_unlock_irqrestore(&bm_pool->lock, flags); + + return i; +} +EXPORT_SYMBOL_GPL(hwbm_pool_add); -- cgit v1.2.3-71-gd317 From a44d6eacdaf56f74fad699af7f4925a5f5ac0e7f Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Mon, 14 Mar 2016 10:52:15 -0700 Subject: tcp: Add RFC4898 tcpEStatsPerfDataSegsOut/In Per RFC4898, they count segments sent/received containing a positive length data segment (that includes retransmission segments carrying data). Unlike tcpi_segs_out/in, tcpi_data_segs_out/in excludes segments carrying no data (e.g. pure ack). The patch also updates the segs_in in tcp_fastopen_add_skb() so that segs_in >= data_segs_in property is kept. Together with retransmission data, tcpi_data_segs_out gives a better signal on the rxmit rate. v6: Rebase on the latest net-next v5: Eric pointed out that checking skb->len is still needed in tcp_fastopen_add_skb() because skb can carry a FIN without data. Hence, instead of open coding segs_in and data_segs_in, tcp_segs_in() helper is used. Comment is added to the fastopen case to explain why segs_in has to be reset and tcp_segs_in() has to be called before __skb_pull(). v4: Add comment to the changes in tcp_fastopen_add_skb() and also add remark on this case in the commit message. v3: Add const modifier to the skb parameter in tcp_segs_in() v2: Rework based on recent fix by Eric: commit a9d99ce28ed3 ("tcp: fix tcpi_segs_in after connection establishment") Signed-off-by: Martin KaFai Lau Cc: Chris Rapier Cc: Eric Dumazet Cc: Marcelo Ricardo Leitner Cc: Neal Cardwell Cc: Yuchung Cheng Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 6 ++++++ include/net/tcp.h | 10 ++++++++++ include/uapi/linux/tcp.h | 2 ++ net/ipv4/tcp.c | 2 ++ net/ipv4/tcp_fastopen.c | 8 ++++++++ net/ipv4/tcp_ipv4.c | 2 +- net/ipv4/tcp_minisocks.c | 2 +- net/ipv4/tcp_output.c | 4 +++- net/ipv6/tcp_ipv6.c | 2 +- 9 files changed, 34 insertions(+), 4 deletions(-) (limited to 'include/net') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index bcbf51da4e1e..7be9b1242354 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -158,6 +158,9 @@ struct tcp_sock { u32 segs_in; /* RFC4898 tcpEStatsPerfSegsIn * total number of segments in. */ + u32 data_segs_in; /* RFC4898 tcpEStatsPerfDataSegsIn + * total number of data segments in. + */ u32 rcv_nxt; /* What we want to receive next */ u32 copied_seq; /* Head of yet unread data */ u32 rcv_wup; /* rcv_nxt on last window update sent */ @@ -165,6 +168,9 @@ struct tcp_sock { u32 segs_out; /* RFC4898 tcpEStatsPerfSegsOut * The total number of segments sent. */ + u32 data_segs_out; /* RFC4898 tcpEStatsPerfDataSegsOut + * total number of data segments sent. + */ u64 bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked * sum(delta(snd_una)), or how many bytes * were acked. diff --git a/include/net/tcp.h b/include/net/tcp.h index 0302636af98c..c8dbd293daae 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1840,4 +1840,14 @@ static inline int tcp_inq(struct sock *sk) return answ; } +static inline void tcp_segs_in(struct tcp_sock *tp, const struct sk_buff *skb) +{ + u16 segs_in; + + segs_in = max_t(u16, 1, skb_shinfo(skb)->gso_segs); + tp->segs_in += segs_in; + if (skb->len > tcp_hdrlen(skb)) + tp->data_segs_in += segs_in; +} + #endif /* _TCP_H */ diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index fe95446e9abf..53e8e3fe6b1b 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -199,6 +199,8 @@ struct tcp_info { __u32 tcpi_notsent_bytes; __u32 tcpi_min_rtt; + __u32 tcpi_data_segs_in; /* RFC4898 tcpEStatsDataSegsIn */ + __u32 tcpi_data_segs_out; /* RFC4898 tcpEStatsDataSegsOut */ }; /* for TCP_MD5SIG socket option */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index a265f00b9df9..992b3103ec3e 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2715,6 +2715,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_notsent_bytes = max(0, notsent_bytes); info->tcpi_min_rtt = tcp_min_rtt(tp); + info->tcpi_data_segs_in = tp->data_segs_in; + info->tcpi_data_segs_out = tp->data_segs_out; } EXPORT_SYMBOL_GPL(tcp_get_info); diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index fdb286ddba04..4fc0061bebf4 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -140,6 +140,14 @@ void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb) return; skb_dst_drop(skb); + /* segs_in has been initialized to 1 in tcp_create_openreq_child(). + * Hence, reset segs_in to 0 before calling tcp_segs_in() + * to avoid double counting. Also, tcp_segs_in() expects + * skb->len to include the tcp_hdrlen. Hence, it should + * be called before __skb_pull(). + */ + tp->segs_in = 0; + tcp_segs_in(tp, skb); __skb_pull(skb, tcp_hdrlen(skb)); skb_set_owner_r(skb, sk); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 4c8d58dfac9b..0b02ef773705 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1650,7 +1650,7 @@ process: sk_incoming_cpu_update(sk); bh_lock_sock_nested(sk); - tcp_sk(sk)->segs_in += max_t(u16, 1, skb_shinfo(skb)->gso_segs); + tcp_segs_in(tcp_sk(sk), skb); ret = 0; if (!sock_owned_by_user(sk)) { if (!tcp_prequeue(sk, skb)) diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index ae90e4b34bd3..acb366dd61e6 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -812,7 +812,7 @@ int tcp_child_process(struct sock *parent, struct sock *child, int ret = 0; int state = child->sk_state; - tcp_sk(child)->segs_in += max_t(u16, 1, skb_shinfo(skb)->gso_segs); + tcp_segs_in(tcp_sk(child), skb); if (!sock_owned_by_user(child)) { ret = tcp_rcv_state_process(child, skb); /* Wakeup parent, send SIGIO */ diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 7d2c7a400456..7d2dc015cd19 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1003,8 +1003,10 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, if (likely(tcb->tcp_flags & TCPHDR_ACK)) tcp_event_ack_sent(sk, tcp_skb_pcount(skb)); - if (skb->len != tcp_header_size) + if (skb->len != tcp_header_size) { tcp_event_data_sent(tp, sk); + tp->data_segs_out += tcp_skb_pcount(skb); + } if (after(tcb->end_seq, tp->snd_nxt) || tcb->seq == tcb->end_seq) TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS, diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 33f2820181f9..9c16565b70cc 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1443,7 +1443,7 @@ process: sk_incoming_cpu_update(sk); bh_lock_sock_nested(sk); - tcp_sk(sk)->segs_in += max_t(u16, 1, skb_shinfo(skb)->gso_segs); + tcp_segs_in(tcp_sk(sk), skb); ret = 0; if (!sock_owned_by_user(sk)) { if (!tcp_prequeue(sk, skb)) -- cgit v1.2.3-71-gd317 From 71327a4e7d997276d49db92fd3d30008389ee6d5 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Sun, 13 Mar 2016 16:21:32 -0400 Subject: net: dsa: rename port_*_bridge routines Rename DSA port_join_bridge and port_leave_bridge routines to respectively port_bridge_join and port_bridge_leave in order to respect an implicit Port::Bridge namespace. Signed-off-by: Vivien Didelot Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- Documentation/networking/dsa/dsa.txt | 4 ++-- drivers/net/dsa/bcm_sf2.c | 4 ++-- drivers/net/dsa/mv88e6171.c | 4 ++-- drivers/net/dsa/mv88e6352.c | 4 ++-- include/net/dsa.h | 4 ++-- net/dsa/slave.c | 8 ++++---- 6 files changed, 14 insertions(+), 14 deletions(-) (limited to 'include/net') diff --git a/Documentation/networking/dsa/dsa.txt b/Documentation/networking/dsa/dsa.txt index 974e9c387d1e..3b196c304b73 100644 --- a/Documentation/networking/dsa/dsa.txt +++ b/Documentation/networking/dsa/dsa.txt @@ -521,12 +521,12 @@ See Documentation/hwmon/sysfs-interface for details. Bridge layer ------------ -- port_join_bridge: bridge layer function invoked when a given switch port is +- port_bridge_join: bridge layer function invoked when a given switch port is added to a bridge, this function should be doing the necessary at the switch level to permit the joining port from being added to the relevant logical domain for it to ingress/egress traffic with other members of the bridge. -- port_leave_bridge: bridge layer function invoked when a given switch port is +- port_bridge_leave: bridge layer function invoked when a given switch port is removed from a bridge, this function should be doing the necessary at the switch level to deny the leaving port from ingress/egress traffic from the remaining bridge members. When the port leaves the bridge, it should be aged diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 3f627598f277..4bcc9ebf5e06 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -1387,8 +1387,8 @@ static struct dsa_switch_driver bcm_sf2_switch_driver = { .port_disable = bcm_sf2_port_disable, .get_eee = bcm_sf2_sw_get_eee, .set_eee = bcm_sf2_sw_set_eee, - .port_join_bridge = bcm_sf2_sw_br_join, - .port_leave_bridge = bcm_sf2_sw_br_leave, + .port_bridge_join = bcm_sf2_sw_br_join, + .port_bridge_leave = bcm_sf2_sw_br_leave, .port_stp_update = bcm_sf2_sw_br_set_stp_state, .port_fdb_prepare = bcm_sf2_sw_fdb_prepare, .port_fdb_add = bcm_sf2_sw_fdb_add, diff --git a/drivers/net/dsa/mv88e6171.c b/drivers/net/dsa/mv88e6171.c index d72ccbdf53ec..c0164b98fc08 100644 --- a/drivers/net/dsa/mv88e6171.c +++ b/drivers/net/dsa/mv88e6171.c @@ -103,8 +103,8 @@ struct dsa_switch_driver mv88e6171_switch_driver = { #endif .get_regs_len = mv88e6xxx_get_regs_len, .get_regs = mv88e6xxx_get_regs, - .port_join_bridge = mv88e6xxx_port_bridge_join, - .port_leave_bridge = mv88e6xxx_port_bridge_leave, + .port_bridge_join = mv88e6xxx_port_bridge_join, + .port_bridge_leave = mv88e6xxx_port_bridge_leave, .port_stp_update = mv88e6xxx_port_stp_update, .port_vlan_filtering = mv88e6xxx_port_vlan_filtering, .port_vlan_prepare = mv88e6xxx_port_vlan_prepare, diff --git a/drivers/net/dsa/mv88e6352.c b/drivers/net/dsa/mv88e6352.c index a41fa5043d77..5f528abc8af1 100644 --- a/drivers/net/dsa/mv88e6352.c +++ b/drivers/net/dsa/mv88e6352.c @@ -324,8 +324,8 @@ struct dsa_switch_driver mv88e6352_switch_driver = { .set_eeprom = mv88e6352_set_eeprom, .get_regs_len = mv88e6xxx_get_regs_len, .get_regs = mv88e6xxx_get_regs, - .port_join_bridge = mv88e6xxx_port_bridge_join, - .port_leave_bridge = mv88e6xxx_port_bridge_leave, + .port_bridge_join = mv88e6xxx_port_bridge_join, + .port_bridge_leave = mv88e6xxx_port_bridge_leave, .port_stp_update = mv88e6xxx_port_stp_update, .port_vlan_filtering = mv88e6xxx_port_vlan_filtering, .port_vlan_prepare = mv88e6xxx_port_vlan_prepare, diff --git a/include/net/dsa.h b/include/net/dsa.h index 26c0a3fa009a..004e034184c1 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -296,9 +296,9 @@ struct dsa_switch_driver { /* * Bridge integration */ - int (*port_join_bridge)(struct dsa_switch *ds, int port, + int (*port_bridge_join)(struct dsa_switch *ds, int port, struct net_device *bridge); - int (*port_leave_bridge)(struct dsa_switch *ds, int port); + int (*port_bridge_leave)(struct dsa_switch *ds, int port); int (*port_stp_update)(struct dsa_switch *ds, int port, u8 state); diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 49056d90b179..52653d715f64 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -448,8 +448,8 @@ static int dsa_slave_bridge_port_join(struct net_device *dev, p->bridge_dev = br; - if (ds->drv->port_join_bridge) - ret = ds->drv->port_join_bridge(ds, p->port, br); + if (ds->drv->port_bridge_join) + ret = ds->drv->port_bridge_join(ds, p->port, br); return ret; } @@ -461,8 +461,8 @@ static int dsa_slave_bridge_port_leave(struct net_device *dev) int ret = -EOPNOTSUPP; - if (ds->drv->port_leave_bridge) - ret = ds->drv->port_leave_bridge(ds, p->port); + if (ds->drv->port_bridge_leave) + ret = ds->drv->port_bridge_leave(ds, p->port); p->bridge_dev = NULL; -- cgit v1.2.3-71-gd317 From 16bfa7024eba5e36aff38ba62086b9027373007d Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Sun, 13 Mar 2016 16:21:33 -0400 Subject: net: dsa: make port_bridge_leave return void netdev_upper_dev_unlink() which notifies NETDEV_CHANGEUPPER, returns void, as well as del_nbp(). So there's no advantage to catch an eventual error from the port_bridge_leave routine at the DSA level. Make this routine void for the DSA layer and its existing drivers. Signed-off-by: Vivien Didelot Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/dsa/bcm_sf2.c | 4 +--- drivers/net/dsa/mv88e6xxx.c | 28 +++++++++------------------- drivers/net/dsa/mv88e6xxx.h | 2 +- include/net/dsa.h | 2 +- net/dsa/slave.c | 9 +++------ 5 files changed, 15 insertions(+), 30 deletions(-) (limited to 'include/net') diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 4bcc9ebf5e06..95944d5e3e22 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -516,7 +516,7 @@ static int bcm_sf2_sw_br_join(struct dsa_switch *ds, int port, return 0; } -static int bcm_sf2_sw_br_leave(struct dsa_switch *ds, int port) +static void bcm_sf2_sw_br_leave(struct dsa_switch *ds, int port) { struct bcm_sf2_priv *priv = ds_to_priv(ds); struct net_device *bridge = priv->port_sts[port].bridge_dev; @@ -543,8 +543,6 @@ static int bcm_sf2_sw_br_leave(struct dsa_switch *ds, int port) core_writel(priv, p_ctl, CORE_PORT_VLAN_CTL_PORT(port)); priv->port_sts[port].vlan_ctl_mask = p_ctl; priv->port_sts[port].bridge_dev = NULL; - - return 0; } static int bcm_sf2_sw_br_set_stp_state(struct dsa_switch *ds, int port, diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c index 5309c738ff00..fa086e09d6b7 100644 --- a/drivers/net/dsa/mv88e6xxx.c +++ b/drivers/net/dsa/mv88e6xxx.c @@ -2219,39 +2219,29 @@ unlock: return err; } -int mv88e6xxx_port_bridge_leave(struct dsa_switch *ds, int port) +void mv88e6xxx_port_bridge_leave(struct dsa_switch *ds, int port) { struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); struct net_device *bridge = ps->ports[port].bridge_dev; u16 fid; - int i, err; + int i; mutex_lock(&ps->smi_mutex); /* Give the port a fresh Filtering Information Database */ - err = _mv88e6xxx_fid_new(ds, &fid); - if (err) - goto unlock; - - err = _mv88e6xxx_port_fid_set(ds, port, fid); - if (err) - goto unlock; + if (_mv88e6xxx_fid_new(ds, &fid) || + _mv88e6xxx_port_fid_set(ds, port, fid)) + netdev_warn(ds->ports[port], "failed to assign a new FID\n"); /* Unassign the bridge and remap each port's VLANTable */ ps->ports[port].bridge_dev = NULL; - for (i = 0; i < ps->num_ports; ++i) { - if (i == port || ps->ports[i].bridge_dev == bridge) { - err = _mv88e6xxx_port_based_vlan_map(ds, i); - if (err) - break; - } - } + for (i = 0; i < ps->num_ports; ++i) + if (i == port || ps->ports[i].bridge_dev == bridge) + if (_mv88e6xxx_port_based_vlan_map(ds, i)) + netdev_warn(ds->ports[i], "failed to remap\n"); -unlock: mutex_unlock(&ps->smi_mutex); - - return err; } static void mv88e6xxx_bridge_work(struct work_struct *work) diff --git a/drivers/net/dsa/mv88e6xxx.h b/drivers/net/dsa/mv88e6xxx.h index 281cefe86afd..9a038aba48fb 100644 --- a/drivers/net/dsa/mv88e6xxx.h +++ b/drivers/net/dsa/mv88e6xxx.h @@ -488,7 +488,7 @@ int mv88e6xxx_set_eee(struct dsa_switch *ds, int port, struct phy_device *phydev, struct ethtool_eee *e); int mv88e6xxx_port_bridge_join(struct dsa_switch *ds, int port, struct net_device *bridge); -int mv88e6xxx_port_bridge_leave(struct dsa_switch *ds, int port); +void mv88e6xxx_port_bridge_leave(struct dsa_switch *ds, int port); int mv88e6xxx_port_stp_update(struct dsa_switch *ds, int port, u8 state); int mv88e6xxx_port_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering); diff --git a/include/net/dsa.h b/include/net/dsa.h index 004e034184c1..6463bb2863ac 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -298,7 +298,7 @@ struct dsa_switch_driver { */ int (*port_bridge_join)(struct dsa_switch *ds, int port, struct net_device *bridge); - int (*port_bridge_leave)(struct dsa_switch *ds, int port); + void (*port_bridge_leave)(struct dsa_switch *ds, int port); int (*port_stp_update)(struct dsa_switch *ds, int port, u8 state); diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 52653d715f64..8e00f1d83eb8 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -454,15 +454,14 @@ static int dsa_slave_bridge_port_join(struct net_device *dev, return ret; } -static int dsa_slave_bridge_port_leave(struct net_device *dev) +static void dsa_slave_bridge_port_leave(struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; - int ret = -EOPNOTSUPP; if (ds->drv->port_bridge_leave) - ret = ds->drv->port_bridge_leave(ds, p->port); + ds->drv->port_bridge_leave(ds, p->port); p->bridge_dev = NULL; @@ -470,8 +469,6 @@ static int dsa_slave_bridge_port_leave(struct net_device *dev) * so allow it to be in BR_STATE_FORWARDING to be kept functional */ dsa_slave_stp_update(dev, BR_STATE_FORWARDING); - - return ret; } static int dsa_slave_port_attr_get(struct net_device *dev, @@ -1156,7 +1153,7 @@ static int dsa_slave_master_changed(struct net_device *dev) !strcmp(master->rtnl_link_ops->kind, "bridge")) err = dsa_slave_bridge_port_join(dev, master); else if (dsa_port_is_bridged(p)) - err = dsa_slave_bridge_port_leave(dev); + dsa_slave_bridge_port_leave(dev); return err; } -- cgit v1.2.3-71-gd317 From 808c1b697c3c4dd2a7132882424c390b0d0acfb9 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 16 Mar 2016 01:42:50 +0100 Subject: bpf, dst: add and use dst_tclassid helper We can just add a small helper dst_tclassid() for retrieving the dst->tclassid value. It makes the code a bit better in that we can get rid of the ifdef from filter.c by moving this into the header. Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/net/dst.h | 12 ++++++++++++ net/core/filter.c | 9 +-------- 2 files changed, 13 insertions(+), 8 deletions(-) (limited to 'include/net') diff --git a/include/net/dst.h b/include/net/dst.h index c7329dcd90cc..5c98443c1c9e 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -398,6 +398,18 @@ static inline void skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev, __skb_tunnel_rx(skb, dev, net); } +static inline u32 dst_tclassid(const struct sk_buff *skb) +{ +#ifdef CONFIG_IP_ROUTE_CLASSID + const struct dst_entry *dst; + + dst = skb_dst(skb); + if (dst) + return dst->tclassid; +#endif + return 0; +} + int dst_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb); static inline int dst_discard(struct sk_buff *skb) { diff --git a/net/core/filter.c b/net/core/filter.c index 69c7b2fecf44..4c35d8325c34 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1682,14 +1682,7 @@ static const struct bpf_func_proto bpf_get_cgroup_classid_proto = { static u64 bpf_get_route_realm(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) { -#ifdef CONFIG_IP_ROUTE_CLASSID - const struct dst_entry *dst; - - dst = skb_dst((struct sk_buff *) (unsigned long) r1); - if (dst) - return dst->tclassid; -#endif - return 0; + return dst_tclassid((struct sk_buff *) (unsigned long) r1); } static const struct bpf_func_proto bpf_get_route_realm_proto = { -- cgit v1.2.3-71-gd317 From fca5fdf67de9e092fda23c9eb059ba968e7b5267 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 16 Mar 2016 01:42:51 +0100 Subject: ip_tunnels, bpf: define IP_TUNNEL_OPTS_MAX and use it eBPF defines this as BPF_TUNLEN_MAX and OVS just uses the hard-coded value inside struct sw_flow_key. Thus, add and use IP_TUNNEL_OPTS_MAX for this, which makes the code a bit more generic and allows to remove BPF_TUNLEN_MAX from eBPF code. Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/net/ip_tunnels.h | 7 +++++++ net/core/filter.c | 9 ++------- net/ipv4/ip_tunnel_core.c | 6 ++++++ net/openvswitch/flow.h | 2 +- 4 files changed, 16 insertions(+), 8 deletions(-) (limited to 'include/net') diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 5dc2e454f866..c35dda9ec991 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -7,6 +7,8 @@ #include #include #include +#include + #include #include #include @@ -57,6 +59,11 @@ struct ip_tunnel_key { #define IP_TUNNEL_INFO_TX 0x01 /* represents tx tunnel parameters */ #define IP_TUNNEL_INFO_IPV6 0x02 /* key contains IPv6 addresses */ +/* Maximum tunnel options length. */ +#define IP_TUNNEL_OPTS_MAX \ + GENMASK((FIELD_SIZEOF(struct ip_tunnel_info, \ + options_len) * BITS_PER_BYTE) - 1, 0) + struct ip_tunnel_info { struct ip_tunnel_key key; #ifdef CONFIG_DST_CACHE diff --git a/net/core/filter.c b/net/core/filter.c index 4c35d8325c34..b7177d01ecb0 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1904,8 +1904,6 @@ static const struct bpf_func_proto bpf_skb_set_tunnel_key_proto = { .arg4_type = ARG_ANYTHING, }; -#define BPF_TUNLEN_MAX 255 - static u64 bpf_skb_set_tunnel_opt(u64 r1, u64 r2, u64 size, u64 r4, u64 r5) { struct sk_buff *skb = (struct sk_buff *) (long) r1; @@ -1915,7 +1913,7 @@ static u64 bpf_skb_set_tunnel_opt(u64 r1, u64 r2, u64 size, u64 r4, u64 r5) if (unlikely(info != &md->u.tun_info || (size & (sizeof(u32) - 1)))) return -EINVAL; - if (unlikely(size > BPF_TUNLEN_MAX)) + if (unlikely(size > IP_TUNNEL_OPTS_MAX)) return -ENOMEM; ip_tunnel_info_opts_set(info, from, size); @@ -1936,13 +1934,10 @@ static const struct bpf_func_proto * bpf_get_skb_set_tunnel_proto(enum bpf_func_id which) { if (!md_dst) { - BUILD_BUG_ON(FIELD_SIZEOF(struct ip_tunnel_info, - options_len) != 1); - /* Race is not possible, since it's called from verifier * that is holding verifier mutex. */ - md_dst = metadata_dst_alloc_percpu(BPF_TUNLEN_MAX, + md_dst = metadata_dst_alloc_percpu(IP_TUNNEL_OPTS_MAX, GFP_KERNEL); if (!md_dst) return NULL; diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index eaca2449a09a..d27276f6f8dd 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -398,6 +398,12 @@ static const struct lwtunnel_encap_ops ip6_tun_lwt_ops = { void __init ip_tunnel_core_init(void) { + /* If you land here, make sure whether increasing ip_tunnel_info's + * options_len is a reasonable choice with its usage in front ends + * (f.e., it's part of flow keys, etc). + */ + BUILD_BUG_ON(IP_TUNNEL_OPTS_MAX != 255); + lwtunnel_encap_add_ops(&ip_tun_lwt_ops, LWTUNNEL_ENCAP_IP); lwtunnel_encap_add_ops(&ip6_tun_lwt_ops, LWTUNNEL_ENCAP_IP6); } diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index 1d055c559eaf..03378e75a67c 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -55,7 +55,7 @@ struct ovs_tunnel_info { FIELD_SIZEOF(struct sw_flow_key, recirc_id)) struct sw_flow_key { - u8 tun_opts[255]; + u8 tun_opts[IP_TUNNEL_OPTS_MAX]; u8 tun_opts_len; struct ip_tunnel_key tun_key; /* Encapsulating tunnel key. */ struct { -- cgit v1.2.3-71-gd317 From fe30937b65354c7fec244caebbdaae68e28ca797 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 17 Mar 2016 17:23:36 -0700 Subject: bonding: fix bond_get_stats() bond_get_stats() can be called from rtnetlink (with RTNL held) or from /proc/net/dev seq handler (with RCU held) The logic added in commit 5f0c5f73e5ef ("bonding: make global bonding stats more reliable") kind of assumed only one cpu could run there. If multiple threads are reading /proc/net/dev, stats can be really messed up after a while. A second problem is that some fields are 32bit, so we need to properly handle the wrap around problem. Given that RTNL is not always held, we need to use bond_for_each_slave_rcu(). Fixes: 5f0c5f73e5ef ("bonding: make global bonding stats more reliable") Signed-off-by: Eric Dumazet Cc: Andy Gospodarek Cc: Jay Vosburgh Cc: Veaceslav Falico Reviewed-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 66 ++++++++++++++++++++++------------------- include/net/bonding.h | 1 + 2 files changed, 36 insertions(+), 31 deletions(-) (limited to 'include/net') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 270b39c8357f..941ec99cd3b6 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3301,6 +3301,30 @@ static int bond_close(struct net_device *bond_dev) return 0; } +/* fold stats, assuming all rtnl_link_stats64 fields are u64, but + * that some drivers can provide 32bit values only. + */ +static void bond_fold_stats(struct rtnl_link_stats64 *_res, + const struct rtnl_link_stats64 *_new, + const struct rtnl_link_stats64 *_old) +{ + const u64 *new = (const u64 *)_new; + const u64 *old = (const u64 *)_old; + u64 *res = (u64 *)_res; + int i; + + for (i = 0; i < sizeof(*_res) / sizeof(u64); i++) { + u64 nv = new[i]; + u64 ov = old[i]; + + /* detects if this particular field is 32bit only */ + if (((nv | ov) >> 32) == 0) + res[i] += (u32)nv - (u32)ov; + else + res[i] += nv - ov; + } +} + static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev, struct rtnl_link_stats64 *stats) { @@ -3309,44 +3333,23 @@ static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev, struct list_head *iter; struct slave *slave; + spin_lock(&bond->stats_lock); memcpy(stats, &bond->bond_stats, sizeof(*stats)); - bond_for_each_slave(bond, slave, iter) { - const struct rtnl_link_stats64 *sstats = + rcu_read_lock(); + bond_for_each_slave_rcu(bond, slave, iter) { + const struct rtnl_link_stats64 *new = dev_get_stats(slave->dev, &temp); - struct rtnl_link_stats64 *pstats = &slave->slave_stats; - - stats->rx_packets += sstats->rx_packets - pstats->rx_packets; - stats->rx_bytes += sstats->rx_bytes - pstats->rx_bytes; - stats->rx_errors += sstats->rx_errors - pstats->rx_errors; - stats->rx_dropped += sstats->rx_dropped - pstats->rx_dropped; - stats->rx_nohandler += sstats->rx_nohandler - pstats->rx_nohandler; - - stats->tx_packets += sstats->tx_packets - pstats->tx_packets;; - stats->tx_bytes += sstats->tx_bytes - pstats->tx_bytes; - stats->tx_errors += sstats->tx_errors - pstats->tx_errors; - stats->tx_dropped += sstats->tx_dropped - pstats->tx_dropped; - - stats->multicast += sstats->multicast - pstats->multicast; - stats->collisions += sstats->collisions - pstats->collisions; - - stats->rx_length_errors += sstats->rx_length_errors - pstats->rx_length_errors; - stats->rx_over_errors += sstats->rx_over_errors - pstats->rx_over_errors; - stats->rx_crc_errors += sstats->rx_crc_errors - pstats->rx_crc_errors; - stats->rx_frame_errors += sstats->rx_frame_errors - pstats->rx_frame_errors; - stats->rx_fifo_errors += sstats->rx_fifo_errors - pstats->rx_fifo_errors; - stats->rx_missed_errors += sstats->rx_missed_errors - pstats->rx_missed_errors; - - stats->tx_aborted_errors += sstats->tx_aborted_errors - pstats->tx_aborted_errors; - stats->tx_carrier_errors += sstats->tx_carrier_errors - pstats->tx_carrier_errors; - stats->tx_fifo_errors += sstats->tx_fifo_errors - pstats->tx_fifo_errors; - stats->tx_heartbeat_errors += sstats->tx_heartbeat_errors - pstats->tx_heartbeat_errors; - stats->tx_window_errors += sstats->tx_window_errors - pstats->tx_window_errors; + + bond_fold_stats(stats, new, &slave->slave_stats); /* save off the slave stats for the next run */ - memcpy(pstats, sstats, sizeof(*sstats)); + memcpy(&slave->slave_stats, new, sizeof(*new)); } + rcu_read_unlock(); + memcpy(&bond->bond_stats, stats, sizeof(*stats)); + spin_unlock(&bond->stats_lock); return stats; } @@ -4160,6 +4163,7 @@ void bond_setup(struct net_device *bond_dev) struct bonding *bond = netdev_priv(bond_dev); spin_lock_init(&bond->mode_lock); + spin_lock_init(&bond->stats_lock); bond->params = bonding_defaults; /* Initialize pointers */ diff --git a/include/net/bonding.h b/include/net/bonding.h index ee6c52053aa3..791800ddd6d9 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -215,6 +215,7 @@ struct bonding { * ALB mode (6) - to sync the use and modifications of its hash table */ spinlock_t mode_lock; + spinlock_t stats_lock; u8 send_peer_notif; u8 igmp_retrans; #ifdef CONFIG_PROC_FS -- cgit v1.2.3-71-gd317