diff options
Diffstat (limited to 'include/net')
43 files changed, 1634 insertions, 643 deletions
diff --git a/include/net/6lowpan.h b/include/net/6lowpan.h index da3a77d25fcb..da84cf920b78 100644 --- a/include/net/6lowpan.h +++ b/include/net/6lowpan.h @@ -58,6 +58,9 @@ #include <net/ipv6.h> #include <net/net_namespace.h> +/* special link-layer handling */ +#include <net/mac802154.h> + #define EUI64_ADDR_LEN 8 #define LOWPAN_NHC_MAX_ID_LEN 1 @@ -93,7 +96,7 @@ static inline bool lowpan_is_iphc(u8 dispatch) } #define LOWPAN_PRIV_SIZE(llpriv_size) \ - (sizeof(struct lowpan_priv) + llpriv_size) + (sizeof(struct lowpan_dev) + llpriv_size) enum lowpan_lltypes { LOWPAN_LLTYPE_BTLE, @@ -129,7 +132,7 @@ lowpan_iphc_ctx_is_compression(const struct lowpan_iphc_ctx *ctx) return test_bit(LOWPAN_IPHC_CTX_FLAG_COMPRESSION, &ctx->flags); } -struct lowpan_priv { +struct lowpan_dev { enum lowpan_lltypes lltype; struct dentry *iface_debugfs; struct lowpan_iphc_ctx_table ctx; @@ -139,11 +142,23 @@ struct lowpan_priv { }; static inline -struct lowpan_priv *lowpan_priv(const struct net_device *dev) +struct lowpan_dev *lowpan_dev(const struct net_device *dev) { return netdev_priv(dev); } +/* private device info */ +struct lowpan_802154_dev { + struct net_device *wdev; /* wpan device ptr */ + u16 fragment_tag; +}; + +static inline struct +lowpan_802154_dev *lowpan_802154_dev(const struct net_device *dev) +{ + return (struct lowpan_802154_dev *)lowpan_dev(dev)->priv; +} + struct lowpan_802154_cb { u16 d_tag; unsigned int d_size; @@ -157,6 +172,22 @@ struct lowpan_802154_cb *lowpan_802154_cb(const struct sk_buff *skb) return (struct lowpan_802154_cb *)skb->cb; } +static inline void lowpan_iphc_uncompress_eui64_lladdr(struct in6_addr *ipaddr, + const void *lladdr) +{ + /* fe:80::XXXX:XXXX:XXXX:XXXX + * \_________________/ + * hwaddr + */ + ipaddr->s6_addr[0] = 0xFE; + ipaddr->s6_addr[1] = 0x80; + memcpy(&ipaddr->s6_addr[8], lladdr, EUI64_ADDR_LEN); + /* second bit-flip (Universe/Local) + * is done according RFC2464 + */ + ipaddr->s6_addr[8] ^= 0x02; +} + #ifdef DEBUG /* print data in line */ static inline void raw_dump_inline(const char *caller, char *msg, diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h index e797d45a5ae6..ac1bc3c49fbd 100644 --- a/include/net/af_rxrpc.h +++ b/include/net/af_rxrpc.h @@ -12,6 +12,7 @@ #ifndef _NET_RXRPC_H #define _NET_RXRPC_H +#include <linux/skbuff.h> #include <linux/rxrpc.h> struct rxrpc_call; @@ -19,11 +20,12 @@ struct rxrpc_call; /* * the mark applied to socket buffers that may be intercepted */ -enum { +enum rxrpc_skb_mark { RXRPC_SKB_MARK_DATA, /* data message */ RXRPC_SKB_MARK_FINAL_ACK, /* final ACK received message */ RXRPC_SKB_MARK_BUSY, /* server busy message */ RXRPC_SKB_MARK_REMOTE_ABORT, /* remote abort message */ + RXRPC_SKB_MARK_LOCAL_ABORT, /* local abort message */ RXRPC_SKB_MARK_NET_ERROR, /* network error message */ RXRPC_SKB_MARK_LOCAL_ERROR, /* local error message */ RXRPC_SKB_MARK_NEW_CALL, /* local error message */ diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 5d38d980b89d..eefcf3e96421 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -61,6 +61,8 @@ #define HCI_RS232 4 #define HCI_PCI 5 #define HCI_SDIO 6 +#define HCI_SPI 7 +#define HCI_I2C 8 /* HCI controller types */ #define HCI_BREDR 0x00 diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 9e1b24c29f0c..183916e168f1 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -68,26 +68,6 @@ struct wiphy; */ /** - * enum ieee80211_band - supported frequency bands - * - * The bands are assigned this way because the supported - * bitrates differ in these bands. - * - * @IEEE80211_BAND_2GHZ: 2.4GHz ISM band - * @IEEE80211_BAND_5GHZ: around 5GHz band (4.9-5.7) - * @IEEE80211_BAND_60GHZ: around 60 GHz band (58.32 - 64.80 GHz) - * @IEEE80211_NUM_BANDS: number of defined bands - */ -enum ieee80211_band { - IEEE80211_BAND_2GHZ = NL80211_BAND_2GHZ, - IEEE80211_BAND_5GHZ = NL80211_BAND_5GHZ, - IEEE80211_BAND_60GHZ = NL80211_BAND_60GHZ, - - /* keep last */ - IEEE80211_NUM_BANDS -}; - -/** * enum ieee80211_channel_flags - channel flags * * Channel flags set by the regulatory control code. @@ -167,7 +147,7 @@ enum ieee80211_channel_flags { * @dfs_cac_ms: DFS CAC time in milliseconds, this is valid for DFS channels. */ struct ieee80211_channel { - enum ieee80211_band band; + enum nl80211_band band; u16 center_freq; u16 hw_value; u32 flags; @@ -324,7 +304,7 @@ struct ieee80211_sta_vht_cap { struct ieee80211_supported_band { struct ieee80211_channel *channels; struct ieee80211_rate *bitrates; - enum ieee80211_band band; + enum nl80211_band band; int n_channels; int n_bitrates; struct ieee80211_sta_ht_cap ht_cap; @@ -816,6 +796,7 @@ enum station_parameters_apply_mask { * @supported_oper_classes_len: number of supported operating classes * @opmode_notif: operating mode field from Operating Mode Notification * @opmode_notif_used: information if operating mode field is used + * @support_p2p_ps: information if station supports P2P PS mechanism */ struct station_parameters { const u8 *supported_rates; @@ -841,6 +822,7 @@ struct station_parameters { u8 supported_oper_classes_len; u8 opmode_notif; bool opmode_notif_used; + int support_p2p_ps; }; /** @@ -1368,7 +1350,7 @@ struct mesh_setup { bool user_mpm; u8 dtim_period; u16 beacon_interval; - int mcast_rate[IEEE80211_NUM_BANDS]; + int mcast_rate[NUM_NL80211_BANDS]; u32 basic_rates; }; @@ -1455,6 +1437,7 @@ struct cfg80211_ssid { * @mac_addr_mask: MAC address mask used with randomisation, bits that * are 0 in the mask should be randomised, bits that are 1 should * be taken from the @mac_addr + * @bssid: BSSID to scan for (most commonly, the wildcard BSSID) */ struct cfg80211_scan_request { struct cfg80211_ssid *ssids; @@ -1465,12 +1448,13 @@ struct cfg80211_scan_request { size_t ie_len; u32 flags; - u32 rates[IEEE80211_NUM_BANDS]; + u32 rates[NUM_NL80211_BANDS]; struct wireless_dev *wdev; u8 mac_addr[ETH_ALEN] __aligned(2); u8 mac_addr_mask[ETH_ALEN] __aligned(2); + u8 bssid[ETH_ALEN] __aligned(2); /* internal */ struct wiphy *wiphy; @@ -1617,7 +1601,7 @@ struct cfg80211_inform_bss { }; /** - * struct cfg80211_bss_ie_data - BSS entry IE data + * struct cfg80211_bss_ies - BSS entry IE data * @tsf: TSF contained in the frame that carried these IEs * @rcu_head: internal use, for freeing * @len: length of the IEs @@ -1746,7 +1730,12 @@ enum cfg80211_assoc_req_flags { * @ie_len: Length of ie buffer in octets * @use_mfp: Use management frame protection (IEEE 802.11w) in this association * @crypto: crypto settings - * @prev_bssid: previous BSSID, if not %NULL use reassociate frame + * @prev_bssid: previous BSSID, if not %NULL use reassociate frame. This is used + * to indicate a request to reassociate within the ESS instead of a request + * do the initial association with the ESS. When included, this is set to + * the BSSID of the current association, i.e., to the value that is + * included in the Current AP address field of the Reassociation Request + * frame. * @flags: See &enum cfg80211_assoc_req_flags * @ht_capa: HT Capabilities over-rides. Values set in ht_capa_mask * will be used in ht_capa. Un-supported values will be ignored. @@ -1851,12 +1840,39 @@ struct cfg80211_ibss_params { bool privacy; bool control_port; bool userspace_handles_dfs; - int mcast_rate[IEEE80211_NUM_BANDS]; + int mcast_rate[NUM_NL80211_BANDS]; struct ieee80211_ht_cap ht_capa; struct ieee80211_ht_cap ht_capa_mask; }; /** + * struct cfg80211_bss_select_adjust - BSS selection with RSSI adjustment. + * + * @band: band of BSS which should match for RSSI level adjustment. + * @delta: value of RSSI level adjustment. + */ +struct cfg80211_bss_select_adjust { + enum nl80211_band band; + s8 delta; +}; + +/** + * struct cfg80211_bss_selection - connection parameters for BSS selection. + * + * @behaviour: requested BSS selection behaviour. + * @param: parameters for requestion behaviour. + * @band_pref: preferred band for %NL80211_BSS_SELECT_ATTR_BAND_PREF. + * @adjust: parameters for %NL80211_BSS_SELECT_ATTR_RSSI_ADJUST. + */ +struct cfg80211_bss_selection { + enum nl80211_bss_select_attr behaviour; + union { + enum nl80211_band band_pref; + struct cfg80211_bss_select_adjust adjust; + } param; +}; + +/** * struct cfg80211_connect_params - Connection parameters * * This structure provides information needed to complete IEEE 802.11 @@ -1893,6 +1909,13 @@ struct cfg80211_ibss_params { * @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. + * @bss_select: criteria to be used for BSS selection. + * @prev_bssid: previous BSSID, if not %NULL use reassociate frame. This is used + * to indicate a request to reassociate within the ESS instead of a request + * do the initial association with the ESS. When included, this is set to + * the BSSID of the current association, i.e., to the value that is + * included in the Current AP address field of the Reassociation Request + * frame. */ struct cfg80211_connect_params { struct ieee80211_channel *channel; @@ -1916,6 +1939,8 @@ struct cfg80211_connect_params { struct ieee80211_vht_cap vht_capa; struct ieee80211_vht_cap vht_capa_mask; bool pbss; + struct cfg80211_bss_selection bss_select; + const u8 *prev_bssid; }; /** @@ -1945,7 +1970,7 @@ struct cfg80211_bitrate_mask { u8 ht_mcs[IEEE80211_HT_MCS_MASK_LEN]; u16 vht_mcs[NL80211_VHT_NSS_MAX]; enum nl80211_txrate_gi gi; - } control[IEEE80211_NUM_BANDS]; + } control[NUM_NL80211_BANDS]; }; /** * struct cfg80211_pmksa - PMK Security Association @@ -2342,7 +2367,17 @@ struct cfg80211_qos_map { * @connect: Connect to the ESS with the specified parameters. When connected, * call cfg80211_connect_result() with status code %WLAN_STATUS_SUCCESS. * If the connection fails for some reason, call cfg80211_connect_result() - * with the status from the AP. + * with the status from the AP. The driver is allowed to roam to other + * BSSes within the ESS when the other BSS matches the connect parameters. + * When such roaming is initiated by the driver, the driver is expected to + * verify that the target matches the configured security parameters and + * to use Reassociation Request frame instead of Association Request frame. + * The connect function can also be used to request the driver to perform + * a specific roam when connected to an ESS. In that case, the prev_bssid + * parameter is set to the BSSID of the currently associated BSS as an + * indication of requesting reassociation. In both the driver-initiated and + * new connect() call initiated roaming cases, the result of roaming is + * indicated with a call to cfg80211_roamed() or cfg80211_roamed_bss(). * (invoked with the wireless_dev mutex held) * @disconnect: Disconnect from the BSS/ESS. * (invoked with the wireless_dev mutex held) @@ -2622,7 +2657,7 @@ struct cfg80211_ops { int (*leave_ibss)(struct wiphy *wiphy, struct net_device *dev); int (*set_mcast_rate)(struct wiphy *wiphy, struct net_device *dev, - int rate[IEEE80211_NUM_BANDS]); + int rate[NUM_NL80211_BANDS]); int (*set_wiphy_params)(struct wiphy *wiphy, u32 changed); @@ -3184,6 +3219,9 @@ struct wiphy_vendor_command { * low rssi when a frame is heard on different channel, then it should set * this variable to the maximal offset for which it can compensate. * This value should be set in MHz. + * @bss_select_support: bitmask indicating the BSS selection criteria supported + * by the driver in the .connect() callback. The bit position maps to the + * attribute indices defined in &enum nl80211_bss_select_attr. */ struct wiphy { /* assign these fields before you register the wiphy */ @@ -3265,7 +3303,7 @@ struct wiphy { * help determine whether you own this wiphy or not. */ const void *privid; - struct ieee80211_supported_band *bands[IEEE80211_NUM_BANDS]; + struct ieee80211_supported_band *bands[NUM_NL80211_BANDS]; /* Lets us get back the wiphy on the callback */ void (*reg_notifier)(struct wiphy *wiphy, @@ -3306,6 +3344,8 @@ struct wiphy { u8 max_num_csa_counters; u8 max_adj_channel_rssi_comp; + u32 bss_select_support; + char priv[0] __aligned(NETDEV_ALIGN); }; @@ -3598,7 +3638,7 @@ static inline void *wdev_priv(struct wireless_dev *wdev) * @band: band, necessary due to channel number overlap * Return: The corresponding frequency (in MHz), or 0 if the conversion failed. */ -int ieee80211_channel_to_frequency(int chan, enum ieee80211_band band); +int ieee80211_channel_to_frequency(int chan, enum nl80211_band band); /** * ieee80211_frequency_to_channel - convert frequency to channel number @@ -5029,7 +5069,7 @@ void cfg80211_ch_switch_started_notify(struct net_device *dev, * Returns %true if the conversion was successful, %false otherwise. */ bool ieee80211_operating_class_to_band(u8 operating_class, - enum ieee80211_band *band); + enum nl80211_band *band); /** * ieee80211_chandef_to_operating_class - convert chandef to operation class diff --git a/include/net/codel.h b/include/net/codel.h index d168aca115cc..a6e428f80135 100644 --- a/include/net/codel.h +++ b/include/net/codel.h @@ -87,27 +87,6 @@ static inline codel_time_t codel_get_time(void) ((s32)((a) - (b)) >= 0)) #define codel_time_before_eq(a, b) codel_time_after_eq(b, a) -/* Qdiscs using codel plugin must use codel_skb_cb in their own cb[] */ -struct codel_skb_cb { - codel_time_t enqueue_time; -}; - -static struct codel_skb_cb *get_codel_cb(const struct sk_buff *skb) -{ - qdisc_cb_private_validate(skb, sizeof(struct codel_skb_cb)); - return (struct codel_skb_cb *)qdisc_skb_cb(skb)->data; -} - -static codel_time_t codel_get_enqueue_time(const struct sk_buff *skb) -{ - return get_codel_cb(skb)->enqueue_time; -} - -static void codel_set_enqueue_time(struct sk_buff *skb) -{ - get_codel_cb(skb)->enqueue_time = codel_get_time(); -} - static inline u32 codel_time_to_us(codel_time_t val) { u64 valns = ((u64)val << CODEL_SHIFT); @@ -176,198 +155,10 @@ struct codel_stats { #define CODEL_DISABLED_THRESHOLD INT_MAX -static void codel_params_init(struct codel_params *params, - const struct Qdisc *sch) -{ - params->interval = MS2TIME(100); - params->target = MS2TIME(5); - params->mtu = psched_mtu(qdisc_dev(sch)); - params->ce_threshold = CODEL_DISABLED_THRESHOLD; - params->ecn = false; -} - -static void codel_vars_init(struct codel_vars *vars) -{ - memset(vars, 0, sizeof(*vars)); -} - -static void codel_stats_init(struct codel_stats *stats) -{ - stats->maxpacket = 0; -} - -/* - * http://en.wikipedia.org/wiki/Methods_of_computing_square_roots#Iterative_methods_for_reciprocal_square_roots - * new_invsqrt = (invsqrt / 2) * (3 - count * invsqrt^2) - * - * Here, invsqrt is a fixed point number (< 1.0), 32bit mantissa, aka Q0.32 - */ -static void codel_Newton_step(struct codel_vars *vars) -{ - u32 invsqrt = ((u32)vars->rec_inv_sqrt) << REC_INV_SQRT_SHIFT; - u32 invsqrt2 = ((u64)invsqrt * invsqrt) >> 32; - u64 val = (3LL << 32) - ((u64)vars->count * invsqrt2); - - val >>= 2; /* avoid overflow in following multiply */ - val = (val * invsqrt) >> (32 - 2 + 1); - - vars->rec_inv_sqrt = val >> REC_INV_SQRT_SHIFT; -} - -/* - * CoDel control_law is t + interval/sqrt(count) - * We maintain in rec_inv_sqrt the reciprocal value of sqrt(count) to avoid - * both sqrt() and divide operation. - */ -static codel_time_t codel_control_law(codel_time_t t, - codel_time_t interval, - u32 rec_inv_sqrt) -{ - return t + reciprocal_scale(interval, rec_inv_sqrt << REC_INV_SQRT_SHIFT); -} - -static bool codel_should_drop(const struct sk_buff *skb, - struct Qdisc *sch, - struct codel_vars *vars, - struct codel_params *params, - struct codel_stats *stats, - codel_time_t now) -{ - bool ok_to_drop; - - if (!skb) { - vars->first_above_time = 0; - return false; - } - - vars->ldelay = now - codel_get_enqueue_time(skb); - sch->qstats.backlog -= qdisc_pkt_len(skb); - - if (unlikely(qdisc_pkt_len(skb) > stats->maxpacket)) - stats->maxpacket = qdisc_pkt_len(skb); - - if (codel_time_before(vars->ldelay, params->target) || - sch->qstats.backlog <= params->mtu) { - /* went below - stay below for at least interval */ - vars->first_above_time = 0; - return false; - } - ok_to_drop = false; - if (vars->first_above_time == 0) { - /* just went above from below. If we stay above - * for at least interval we'll say it's ok to drop - */ - vars->first_above_time = now + params->interval; - } else if (codel_time_after(now, vars->first_above_time)) { - ok_to_drop = true; - } - return ok_to_drop; -} - +typedef u32 (*codel_skb_len_t)(const struct sk_buff *skb); +typedef codel_time_t (*codel_skb_time_t)(const struct sk_buff *skb); +typedef void (*codel_skb_drop_t)(struct sk_buff *skb, void *ctx); typedef struct sk_buff * (*codel_skb_dequeue_t)(struct codel_vars *vars, - struct Qdisc *sch); + void *ctx); -static struct sk_buff *codel_dequeue(struct Qdisc *sch, - struct codel_params *params, - struct codel_vars *vars, - struct codel_stats *stats, - codel_skb_dequeue_t dequeue_func) -{ - struct sk_buff *skb = dequeue_func(vars, sch); - codel_time_t now; - bool drop; - - if (!skb) { - vars->dropping = false; - return skb; - } - now = codel_get_time(); - drop = codel_should_drop(skb, sch, vars, params, stats, now); - if (vars->dropping) { - if (!drop) { - /* sojourn time below target - leave dropping state */ - vars->dropping = false; - } else if (codel_time_after_eq(now, vars->drop_next)) { - /* It's time for the next drop. Drop the current - * packet and dequeue the next. The dequeue might - * take us out of dropping state. - * If not, schedule the next drop. - * A large backlog might result in drop rates so high - * that the next drop should happen now, - * hence the while loop. - */ - while (vars->dropping && - codel_time_after_eq(now, vars->drop_next)) { - vars->count++; /* dont care of possible wrap - * since there is no more divide - */ - codel_Newton_step(vars); - if (params->ecn && INET_ECN_set_ce(skb)) { - stats->ecn_mark++; - vars->drop_next = - codel_control_law(vars->drop_next, - params->interval, - 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); - if (!codel_should_drop(skb, sch, - vars, params, stats, now)) { - /* leave dropping state */ - vars->dropping = false; - } else { - /* and schedule the next drop */ - vars->drop_next = - codel_control_law(vars->drop_next, - params->interval, - vars->rec_inv_sqrt); - } - } - } - } else if (drop) { - u32 delta; - - 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++; - - skb = dequeue_func(vars, sch); - drop = codel_should_drop(skb, sch, vars, params, - stats, now); - } - vars->dropping = true; - /* if min went above target close to when we last went below it - * assume that the drop rate that controlled the queue on the - * last cycle is a good starting point to control it now. - */ - delta = vars->count - vars->lastcount; - if (delta > 1 && - codel_time_before(now - vars->drop_next, - 16 * params->interval)) { - vars->count = delta; - /* we dont care if rec_inv_sqrt approximation - * is not very precise : - * Next Newton steps will correct it quadratically. - */ - codel_Newton_step(vars); - } else { - vars->count = 1; - vars->rec_inv_sqrt = ~0U >> REC_INV_SQRT_SHIFT; - } - vars->lastcount = vars->count; - vars->drop_next = codel_control_law(now, params->interval, - vars->rec_inv_sqrt); - } -end: - if (skb && codel_time_after(vars->ldelay, params->ce_threshold) && - INET_ECN_set_ce(skb)) - stats->ce_mark++; - return skb; -} #endif diff --git a/include/net/codel_impl.h b/include/net/codel_impl.h new file mode 100644 index 000000000000..d289b91dcd65 --- /dev/null +++ b/include/net/codel_impl.h @@ -0,0 +1,255 @@ +#ifndef __NET_SCHED_CODEL_IMPL_H +#define __NET_SCHED_CODEL_IMPL_H + +/* + * Codel - The Controlled-Delay Active Queue Management algorithm + * + * Copyright (C) 2011-2012 Kathleen Nichols <nichols@pollere.com> + * Copyright (C) 2011-2012 Van Jacobson <van@pollere.net> + * Copyright (C) 2012 Michael D. Taht <dave.taht@bufferbloat.net> + * Copyright (C) 2012,2015 Eric Dumazet <edumazet@google.com> + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions, and the following disclaimer, + * without modification. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. The names of the authors may not be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * Alternatively, provided that this notice is retained in full, this + * software may be distributed under the terms of the GNU General + * Public License ("GPL") version 2, in which case the provisions of the + * GPL apply INSTEAD OF those given above. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH + * DAMAGE. + * + */ + +/* Controlling Queue Delay (CoDel) algorithm + * ========================================= + * Source : Kathleen Nichols and Van Jacobson + * http://queue.acm.org/detail.cfm?id=2209336 + * + * Implemented on linux by Dave Taht and Eric Dumazet + */ + +static void codel_params_init(struct codel_params *params) +{ + params->interval = MS2TIME(100); + params->target = MS2TIME(5); + params->ce_threshold = CODEL_DISABLED_THRESHOLD; + params->ecn = false; +} + +static void codel_vars_init(struct codel_vars *vars) +{ + memset(vars, 0, sizeof(*vars)); +} + +static void codel_stats_init(struct codel_stats *stats) +{ + stats->maxpacket = 0; +} + +/* + * http://en.wikipedia.org/wiki/Methods_of_computing_square_roots#Iterative_methods_for_reciprocal_square_roots + * new_invsqrt = (invsqrt / 2) * (3 - count * invsqrt^2) + * + * Here, invsqrt is a fixed point number (< 1.0), 32bit mantissa, aka Q0.32 + */ +static void codel_Newton_step(struct codel_vars *vars) +{ + u32 invsqrt = ((u32)vars->rec_inv_sqrt) << REC_INV_SQRT_SHIFT; + u32 invsqrt2 = ((u64)invsqrt * invsqrt) >> 32; + u64 val = (3LL << 32) - ((u64)vars->count * invsqrt2); + + val >>= 2; /* avoid overflow in following multiply */ + val = (val * invsqrt) >> (32 - 2 + 1); + + vars->rec_inv_sqrt = val >> REC_INV_SQRT_SHIFT; +} + +/* + * CoDel control_law is t + interval/sqrt(count) + * We maintain in rec_inv_sqrt the reciprocal value of sqrt(count) to avoid + * both sqrt() and divide operation. + */ +static codel_time_t codel_control_law(codel_time_t t, + codel_time_t interval, + u32 rec_inv_sqrt) +{ + return t + reciprocal_scale(interval, rec_inv_sqrt << REC_INV_SQRT_SHIFT); +} + +static bool codel_should_drop(const struct sk_buff *skb, + void *ctx, + struct codel_vars *vars, + struct codel_params *params, + struct codel_stats *stats, + codel_skb_len_t skb_len_func, + codel_skb_time_t skb_time_func, + u32 *backlog, + codel_time_t now) +{ + bool ok_to_drop; + u32 skb_len; + + if (!skb) { + vars->first_above_time = 0; + return false; + } + + skb_len = skb_len_func(skb); + vars->ldelay = now - skb_time_func(skb); + + if (unlikely(skb_len > stats->maxpacket)) + stats->maxpacket = skb_len; + + if (codel_time_before(vars->ldelay, params->target) || + *backlog <= params->mtu) { + /* went below - stay below for at least interval */ + vars->first_above_time = 0; + return false; + } + ok_to_drop = false; + if (vars->first_above_time == 0) { + /* just went above from below. If we stay above + * for at least interval we'll say it's ok to drop + */ + vars->first_above_time = now + params->interval; + } else if (codel_time_after(now, vars->first_above_time)) { + ok_to_drop = true; + } + return ok_to_drop; +} + +static struct sk_buff *codel_dequeue(void *ctx, + u32 *backlog, + struct codel_params *params, + struct codel_vars *vars, + struct codel_stats *stats, + codel_skb_len_t skb_len_func, + codel_skb_time_t skb_time_func, + codel_skb_drop_t drop_func, + codel_skb_dequeue_t dequeue_func) +{ + struct sk_buff *skb = dequeue_func(vars, ctx); + codel_time_t now; + bool drop; + + if (!skb) { + vars->dropping = false; + return skb; + } + now = codel_get_time(); + drop = codel_should_drop(skb, ctx, vars, params, stats, + skb_len_func, skb_time_func, backlog, now); + if (vars->dropping) { + if (!drop) { + /* sojourn time below target - leave dropping state */ + vars->dropping = false; + } else if (codel_time_after_eq(now, vars->drop_next)) { + /* It's time for the next drop. Drop the current + * packet and dequeue the next. The dequeue might + * take us out of dropping state. + * If not, schedule the next drop. + * A large backlog might result in drop rates so high + * that the next drop should happen now, + * hence the while loop. + */ + while (vars->dropping && + codel_time_after_eq(now, vars->drop_next)) { + vars->count++; /* dont care of possible wrap + * since there is no more divide + */ + codel_Newton_step(vars); + if (params->ecn && INET_ECN_set_ce(skb)) { + stats->ecn_mark++; + vars->drop_next = + codel_control_law(vars->drop_next, + params->interval, + vars->rec_inv_sqrt); + goto end; + } + stats->drop_len += skb_len_func(skb); + drop_func(skb, ctx); + stats->drop_count++; + skb = dequeue_func(vars, ctx); + if (!codel_should_drop(skb, ctx, + vars, params, stats, + skb_len_func, + skb_time_func, + backlog, now)) { + /* leave dropping state */ + vars->dropping = false; + } else { + /* and schedule the next drop */ + vars->drop_next = + codel_control_law(vars->drop_next, + params->interval, + vars->rec_inv_sqrt); + } + } + } + } else if (drop) { + u32 delta; + + if (params->ecn && INET_ECN_set_ce(skb)) { + stats->ecn_mark++; + } else { + stats->drop_len += skb_len_func(skb); + drop_func(skb, ctx); + stats->drop_count++; + + skb = dequeue_func(vars, ctx); + drop = codel_should_drop(skb, ctx, vars, params, + stats, skb_len_func, + skb_time_func, backlog, now); + } + vars->dropping = true; + /* if min went above target close to when we last went below it + * assume that the drop rate that controlled the queue on the + * last cycle is a good starting point to control it now. + */ + delta = vars->count - vars->lastcount; + if (delta > 1 && + codel_time_before(now - vars->drop_next, + 16 * params->interval)) { + vars->count = delta; + /* we dont care if rec_inv_sqrt approximation + * is not very precise : + * Next Newton steps will correct it quadratically. + */ + codel_Newton_step(vars); + } else { + vars->count = 1; + vars->rec_inv_sqrt = ~0U >> REC_INV_SQRT_SHIFT; + } + vars->lastcount = vars->count; + vars->drop_next = codel_control_law(now, params->interval, + vars->rec_inv_sqrt); + } +end: + if (skb && codel_time_after(vars->ldelay, params->ce_threshold) && + INET_ECN_set_ce(skb)) + stats->ce_mark++; + return skb; +} + +#endif diff --git a/include/net/codel_qdisc.h b/include/net/codel_qdisc.h new file mode 100644 index 000000000000..8144d9cd2908 --- /dev/null +++ b/include/net/codel_qdisc.h @@ -0,0 +1,73 @@ +#ifndef __NET_SCHED_CODEL_QDISC_H +#define __NET_SCHED_CODEL_QDISC_H + +/* + * Codel - The Controlled-Delay Active Queue Management algorithm + * + * Copyright (C) 2011-2012 Kathleen Nichols <nichols@pollere.com> + * Copyright (C) 2011-2012 Van Jacobson <van@pollere.net> + * Copyright (C) 2012 Michael D. Taht <dave.taht@bufferbloat.net> + * Copyright (C) 2012,2015 Eric Dumazet <edumazet@google.com> + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions, and the following disclaimer, + * without modification. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. The names of the authors may not be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * Alternatively, provided that this notice is retained in full, this + * software may be distributed under the terms of the GNU General + * Public License ("GPL") version 2, in which case the provisions of the + * GPL apply INSTEAD OF those given above. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH + * DAMAGE. + * + */ + +/* Controlling Queue Delay (CoDel) algorithm + * ========================================= + * Source : Kathleen Nichols and Van Jacobson + * http://queue.acm.org/detail.cfm?id=2209336 + * + * Implemented on linux by Dave Taht and Eric Dumazet + */ + +/* Qdiscs using codel plugin must use codel_skb_cb in their own cb[] */ +struct codel_skb_cb { + codel_time_t enqueue_time; +}; + +static struct codel_skb_cb *get_codel_cb(const struct sk_buff *skb) +{ + qdisc_cb_private_validate(skb, sizeof(struct codel_skb_cb)); + return (struct codel_skb_cb *)qdisc_skb_cb(skb)->data; +} + +static codel_time_t codel_get_enqueue_time(const struct sk_buff *skb) +{ + return get_codel_cb(skb)->enqueue_time; +} + +static void codel_set_enqueue_time(struct sk_buff *skb) +{ + get_codel_cb(skb)->enqueue_time = codel_get_time(); +} + +#endif diff --git a/include/net/devlink.h b/include/net/devlink.h index c37d257891d6..1d45b61cb320 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -24,6 +24,7 @@ struct devlink_ops; struct devlink { struct list_head list; struct list_head port_list; + struct list_head sb_list; const struct devlink_ops *ops; struct device *dev; possible_net_t _net; @@ -42,6 +43,12 @@ struct devlink_port { u32 split_group; }; +struct devlink_sb_pool_info { + enum devlink_sb_pool_type pool_type; + u32 size; + enum devlink_sb_threshold_type threshold_type; +}; + struct devlink_ops { size_t priv_size; int (*port_type_set)(struct devlink_port *devlink_port, @@ -49,6 +56,40 @@ struct devlink_ops { int (*port_split)(struct devlink *devlink, unsigned int port_index, unsigned int count); int (*port_unsplit)(struct devlink *devlink, unsigned int port_index); + int (*sb_pool_get)(struct devlink *devlink, unsigned int sb_index, + u16 pool_index, + struct devlink_sb_pool_info *pool_info); + int (*sb_pool_set)(struct devlink *devlink, unsigned int sb_index, + u16 pool_index, u32 size, + enum devlink_sb_threshold_type threshold_type); + int (*sb_port_pool_get)(struct devlink_port *devlink_port, + unsigned int sb_index, u16 pool_index, + u32 *p_threshold); + int (*sb_port_pool_set)(struct devlink_port *devlink_port, + unsigned int sb_index, u16 pool_index, + u32 threshold); + int (*sb_tc_pool_bind_get)(struct devlink_port *devlink_port, + unsigned int sb_index, + u16 tc_index, + enum devlink_sb_pool_type pool_type, + u16 *p_pool_index, u32 *p_threshold); + int (*sb_tc_pool_bind_set)(struct devlink_port *devlink_port, + unsigned int sb_index, + u16 tc_index, + enum devlink_sb_pool_type pool_type, + u16 pool_index, u32 threshold); + int (*sb_occ_snapshot)(struct devlink *devlink, + unsigned int sb_index); + int (*sb_occ_max_clear)(struct devlink *devlink, + unsigned int sb_index); + int (*sb_occ_port_pool_get)(struct devlink_port *devlink_port, + unsigned int sb_index, u16 pool_index, + u32 *p_cur, u32 *p_max); + int (*sb_occ_tc_port_bind_get)(struct devlink_port *devlink_port, + unsigned int sb_index, + u16 tc_index, + enum devlink_sb_pool_type pool_type, + u32 *p_cur, u32 *p_max); }; static inline void *devlink_priv(struct devlink *devlink) @@ -82,6 +123,11 @@ void devlink_port_type_ib_set(struct devlink_port *devlink_port, void devlink_port_type_clear(struct devlink_port *devlink_port); void devlink_port_split_set(struct devlink_port *devlink_port, u32 split_group); +int devlink_sb_register(struct devlink *devlink, unsigned int sb_index, + u32 size, u16 ingress_pools_count, + u16 egress_pools_count, u16 ingress_tc_count, + u16 egress_tc_count); +void devlink_sb_unregister(struct devlink *devlink, unsigned int sb_index); #else @@ -135,6 +181,21 @@ static inline void devlink_port_split_set(struct devlink_port *devlink_port, { } +static inline int devlink_sb_register(struct devlink *devlink, + unsigned int sb_index, u32 size, + u16 ingress_pools_count, + u16 egress_pools_count, + u16 ingress_tc_count, + u16 egress_tc_count) +{ + return 0; +} + +static inline void devlink_sb_unregister(struct devlink *devlink, + unsigned int sb_index) +{ +} + #endif #endif /* _NET_DEVLINK_H_ */ diff --git a/include/net/dsa.h b/include/net/dsa.h index 6463bb2863ac..8e86af87c84f 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -111,6 +111,11 @@ struct dsa_switch_tree { enum dsa_tag_protocol tag_protocol; /* + * Original copy of the master netdev ethtool_ops + */ + struct ethtool_ops master_ethtool_ops; + + /* * The switch and port to which the CPU is attached. */ s8 cpu_switch; @@ -130,9 +135,10 @@ struct dsa_switch { int index; /* - * Tagging protocol understood by this switch + * Give the switch driver somewhere to hang its private data + * structure. */ - enum dsa_tag_protocol tag_protocol; + void *priv; /* * Configuration data for this switch. @@ -161,7 +167,7 @@ struct dsa_switch { * Slave mii_bus and devices for the individual ports. */ u32 dsa_port_mask; - u32 phys_port_mask; + u32 enabled_port_mask; u32 phys_mii_mask; struct mii_bus *slave_mii_bus; struct net_device *ports[DSA_MAX_PORTS]; @@ -179,7 +185,7 @@ static inline bool dsa_is_dsa_port(struct dsa_switch *ds, int p) static inline bool dsa_is_port_initialized(struct dsa_switch *ds, int p) { - return ds->phys_port_mask & (1 << p) && ds->ports[p]; + return ds->enabled_port_mask & (1 << p) && ds->ports[p]; } static inline u8 dsa_upstream_port(struct dsa_switch *ds) @@ -207,12 +213,13 @@ struct dsa_switch_driver { struct list_head list; enum dsa_tag_protocol tag_protocol; - int priv_size; /* * Probing and setup. */ - char *(*probe)(struct device *host_dev, int sw_addr); + const char *(*probe)(struct device *dsa_dev, + struct device *host_dev, int sw_addr, + void **priv); int (*setup)(struct dsa_switch *ds); int (*set_addr)(struct dsa_switch *ds, u8 *addr); u32 (*get_phy_flags)(struct dsa_switch *ds, int port); @@ -299,8 +306,8 @@ struct dsa_switch_driver { int (*port_bridge_join)(struct dsa_switch *ds, int port, struct net_device *bridge); void (*port_bridge_leave)(struct dsa_switch *ds, int port); - int (*port_stp_update)(struct dsa_switch *ds, int port, - u8 state); + void (*port_stp_state_set)(struct dsa_switch *ds, int port, + u8 state); /* * VLAN support @@ -310,7 +317,7 @@ struct dsa_switch_driver { int (*port_vlan_prepare)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan, struct switchdev_trans *trans); - int (*port_vlan_add)(struct dsa_switch *ds, int port, + void (*port_vlan_add)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan, struct switchdev_trans *trans); int (*port_vlan_del)(struct dsa_switch *ds, int port, @@ -325,7 +332,7 @@ struct dsa_switch_driver { int (*port_fdb_prepare)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_fdb *fdb, struct switchdev_trans *trans); - int (*port_fdb_add)(struct dsa_switch *ds, int port, + void (*port_fdb_add)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_fdb *fdb, struct switchdev_trans *trans); int (*port_fdb_del)(struct dsa_switch *ds, int port, @@ -341,7 +348,7 @@ struct mii_bus *dsa_host_dev_to_mii_bus(struct device *dev); static inline void *ds_to_priv(struct dsa_switch *ds) { - return (void *)(ds + 1); + return ds->priv; } static inline bool dsa_uses_tagged_protocol(struct dsa_switch_tree *dst) diff --git a/include/net/dst.h b/include/net/dst.h index 5c98443c1c9e..6835d224d47b 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -85,12 +85,11 @@ struct dst_entry { #endif #ifdef CONFIG_64BIT - struct lwtunnel_state *lwtstate; /* * Align __refcnt to a 64 bytes alignment * (L1_CACHE_SIZE would be too much) */ - long __pad_to_align_refcnt[1]; + long __pad_to_align_refcnt[2]; #endif /* * __refcnt wants to be on a different cache line from @@ -99,9 +98,7 @@ struct dst_entry { atomic_t __refcnt; /* client references */ int __use; unsigned long lastuse; -#ifndef CONFIG_64BIT struct lwtunnel_state *lwtstate; -#endif union { struct dst_entry *next; struct rtable __rcu *rt_next; diff --git a/include/net/fq.h b/include/net/fq.h new file mode 100644 index 000000000000..268b49049c37 --- /dev/null +++ b/include/net/fq.h @@ -0,0 +1,95 @@ +/* + * Copyright (c) 2016 Qualcomm Atheros, Inc + * + * GPL v2 + * + * Based on net/sched/sch_fq_codel.c + */ +#ifndef __NET_SCHED_FQ_H +#define __NET_SCHED_FQ_H + +struct fq_tin; + +/** + * struct fq_flow - per traffic flow queue + * + * @tin: owner of this flow. Used to manage collisions, i.e. when a packet + * hashes to an index which points to a flow that is already owned by a + * different tin the packet is destined to. In such case the implementer + * must provide a fallback flow + * @flowchain: can be linked to fq_tin's new_flows or old_flows. Used for DRR++ + * (deficit round robin) based round robin queuing similar to the one + * found in net/sched/sch_fq_codel.c + * @backlogchain: can be linked to other fq_flow and fq. Used to keep track of + * fat flows and efficient head-dropping if packet limit is reached + * @queue: sk_buff queue to hold packets + * @backlog: number of bytes pending in the queue. The number of packets can be + * found in @queue.qlen + * @deficit: used for DRR++ + */ +struct fq_flow { + struct fq_tin *tin; + struct list_head flowchain; + struct list_head backlogchain; + struct sk_buff_head queue; + u32 backlog; + int deficit; +}; + +/** + * struct fq_tin - a logical container of fq_flows + * + * Used to group fq_flows into a logical aggregate. DRR++ scheme is used to + * pull interleaved packets out of the associated flows. + * + * @new_flows: linked list of fq_flow + * @old_flows: linked list of fq_flow + */ +struct fq_tin { + struct list_head new_flows; + struct list_head old_flows; + u32 backlog_bytes; + u32 backlog_packets; + u32 overlimit; + u32 collisions; + u32 flows; + u32 tx_bytes; + u32 tx_packets; +}; + +/** + * struct fq - main container for fair queuing purposes + * + * @backlogs: linked to fq_flows. Used to maintain fat flows for efficient + * head-dropping when @backlog reaches @limit + * @limit: max number of packets that can be queued across all flows + * @backlog: number of packets queued across all flows + */ +struct fq { + struct fq_flow *flows; + struct list_head backlogs; + spinlock_t lock; + u32 flows_cnt; + u32 perturbation; + u32 limit; + u32 quantum; + u32 backlog; + u32 overlimit; + u32 collisions; +}; + +typedef struct sk_buff *fq_tin_dequeue_t(struct fq *, + struct fq_tin *, + struct fq_flow *flow); + +typedef void fq_skb_free_t(struct fq *, + struct fq_tin *, + struct fq_flow *, + struct sk_buff *); + +typedef struct fq_flow *fq_flow_get_default_t(struct fq *, + struct fq_tin *, + int idx, + struct sk_buff *); + +#endif diff --git a/include/net/fq_impl.h b/include/net/fq_impl.h new file mode 100644 index 000000000000..163f3ed0f05a --- /dev/null +++ b/include/net/fq_impl.h @@ -0,0 +1,277 @@ +/* + * Copyright (c) 2016 Qualcomm Atheros, Inc + * + * GPL v2 + * + * Based on net/sched/sch_fq_codel.c + */ +#ifndef __NET_SCHED_FQ_IMPL_H +#define __NET_SCHED_FQ_IMPL_H + +#include <net/fq.h> + +/* functions that are embedded into includer */ + +static struct sk_buff *fq_flow_dequeue(struct fq *fq, + struct fq_flow *flow) +{ + struct fq_tin *tin = flow->tin; + struct fq_flow *i; + struct sk_buff *skb; + + lockdep_assert_held(&fq->lock); + + skb = __skb_dequeue(&flow->queue); + if (!skb) + return NULL; + + tin->backlog_bytes -= skb->len; + tin->backlog_packets--; + flow->backlog -= skb->len; + fq->backlog--; + + if (flow->backlog == 0) { + list_del_init(&flow->backlogchain); + } else { + i = flow; + + list_for_each_entry_continue(i, &fq->backlogs, backlogchain) + if (i->backlog < flow->backlog) + break; + + list_move_tail(&flow->backlogchain, + &i->backlogchain); + } + + return skb; +} + +static struct sk_buff *fq_tin_dequeue(struct fq *fq, + struct fq_tin *tin, + fq_tin_dequeue_t dequeue_func) +{ + struct fq_flow *flow; + struct list_head *head; + struct sk_buff *skb; + + lockdep_assert_held(&fq->lock); + +begin: + head = &tin->new_flows; + if (list_empty(head)) { + head = &tin->old_flows; + if (list_empty(head)) + return NULL; + } + + flow = list_first_entry(head, struct fq_flow, flowchain); + + if (flow->deficit <= 0) { + flow->deficit += fq->quantum; + list_move_tail(&flow->flowchain, + &tin->old_flows); + goto begin; + } + + skb = dequeue_func(fq, tin, flow); + if (!skb) { + /* force a pass through old_flows to prevent starvation */ + if ((head == &tin->new_flows) && + !list_empty(&tin->old_flows)) { + list_move_tail(&flow->flowchain, &tin->old_flows); + } else { + list_del_init(&flow->flowchain); + flow->tin = NULL; + } + goto begin; + } + + flow->deficit -= skb->len; + tin->tx_bytes += skb->len; + tin->tx_packets++; + + return skb; +} + +static struct fq_flow *fq_flow_classify(struct fq *fq, + struct fq_tin *tin, + struct sk_buff *skb, + fq_flow_get_default_t get_default_func) +{ + struct fq_flow *flow; + u32 hash; + u32 idx; + + lockdep_assert_held(&fq->lock); + + hash = skb_get_hash_perturb(skb, fq->perturbation); + idx = reciprocal_scale(hash, fq->flows_cnt); + flow = &fq->flows[idx]; + + if (flow->tin && flow->tin != tin) { + flow = get_default_func(fq, tin, idx, skb); + tin->collisions++; + fq->collisions++; + } + + if (!flow->tin) + tin->flows++; + + return flow; +} + +static void fq_recalc_backlog(struct fq *fq, + struct fq_tin *tin, + struct fq_flow *flow) +{ + struct fq_flow *i; + + if (list_empty(&flow->backlogchain)) + list_add_tail(&flow->backlogchain, &fq->backlogs); + + i = flow; + list_for_each_entry_continue_reverse(i, &fq->backlogs, + backlogchain) + if (i->backlog > flow->backlog) + break; + + list_move(&flow->backlogchain, &i->backlogchain); +} + +static void fq_tin_enqueue(struct fq *fq, + struct fq_tin *tin, + struct sk_buff *skb, + fq_skb_free_t free_func, + fq_flow_get_default_t get_default_func) +{ + struct fq_flow *flow; + + lockdep_assert_held(&fq->lock); + + flow = fq_flow_classify(fq, tin, skb, get_default_func); + + flow->tin = tin; + flow->backlog += skb->len; + tin->backlog_bytes += skb->len; + tin->backlog_packets++; + fq->backlog++; + + fq_recalc_backlog(fq, tin, flow); + + if (list_empty(&flow->flowchain)) { + flow->deficit = fq->quantum; + list_add_tail(&flow->flowchain, + &tin->new_flows); + } + + __skb_queue_tail(&flow->queue, skb); + + if (fq->backlog > fq->limit) { + flow = list_first_entry_or_null(&fq->backlogs, + struct fq_flow, + backlogchain); + if (!flow) + return; + + skb = fq_flow_dequeue(fq, flow); + if (!skb) + return; + + free_func(fq, flow->tin, flow, skb); + + flow->tin->overlimit++; + fq->overlimit++; + } +} + +static void fq_flow_reset(struct fq *fq, + struct fq_flow *flow, + fq_skb_free_t free_func) +{ + struct sk_buff *skb; + + while ((skb = fq_flow_dequeue(fq, flow))) + free_func(fq, flow->tin, flow, skb); + + if (!list_empty(&flow->flowchain)) + list_del_init(&flow->flowchain); + + if (!list_empty(&flow->backlogchain)) + list_del_init(&flow->backlogchain); + + flow->tin = NULL; + + WARN_ON_ONCE(flow->backlog); +} + +static void fq_tin_reset(struct fq *fq, + struct fq_tin *tin, + fq_skb_free_t free_func) +{ + struct list_head *head; + struct fq_flow *flow; + + for (;;) { + head = &tin->new_flows; + if (list_empty(head)) { + head = &tin->old_flows; + if (list_empty(head)) + break; + } + + flow = list_first_entry(head, struct fq_flow, flowchain); + fq_flow_reset(fq, flow, free_func); + } + + WARN_ON_ONCE(tin->backlog_bytes); + WARN_ON_ONCE(tin->backlog_packets); +} + +static void fq_flow_init(struct fq_flow *flow) +{ + INIT_LIST_HEAD(&flow->flowchain); + INIT_LIST_HEAD(&flow->backlogchain); + __skb_queue_head_init(&flow->queue); +} + +static void fq_tin_init(struct fq_tin *tin) +{ + INIT_LIST_HEAD(&tin->new_flows); + INIT_LIST_HEAD(&tin->old_flows); +} + +static int fq_init(struct fq *fq, int flows_cnt) +{ + int i; + + memset(fq, 0, sizeof(fq[0])); + INIT_LIST_HEAD(&fq->backlogs); + spin_lock_init(&fq->lock); + fq->flows_cnt = max_t(u32, flows_cnt, 1); + fq->perturbation = prandom_u32(); + fq->quantum = 300; + fq->limit = 8192; + + fq->flows = kcalloc(fq->flows_cnt, sizeof(fq->flows[0]), GFP_KERNEL); + if (!fq->flows) + return -ENOMEM; + + for (i = 0; i < fq->flows_cnt; i++) + fq_flow_init(&fq->flows[i]); + + return 0; +} + +static void fq_reset(struct fq *fq, + fq_skb_free_t free_func) +{ + int i; + + for (i = 0; i < fq->flows_cnt; i++) + fq_flow_reset(fq, &fq->flows[i], free_func); + + kfree(fq->flows); + fq->flows = NULL; +} + +#endif diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h index cbafa3768d48..610cd397890e 100644 --- a/include/net/gen_stats.h +++ b/include/net/gen_stats.h @@ -19,17 +19,19 @@ struct gnet_dump { /* Backward compatibility */ int compat_tc_stats; int compat_xstats; + int padattr; void * xstats; int xstats_len; struct tc_stats tc_stats; }; int gnet_stats_start_copy(struct sk_buff *skb, int type, spinlock_t *lock, - struct gnet_dump *d); + struct gnet_dump *d, int padattr); int gnet_stats_start_copy_compat(struct sk_buff *skb, int type, int tc_stats_type, int xstats_type, - spinlock_t *lock, struct gnet_dump *d); + spinlock_t *lock, struct gnet_dump *d, + int padattr); int gnet_stats_copy_basic(struct gnet_dump *d, struct gnet_stats_basic_cpu __percpu *cpu, diff --git a/include/net/geneve.h b/include/net/geneve.h index e6c23dc765f7..cb544a530146 100644 --- a/include/net/geneve.h +++ b/include/net/geneve.h @@ -62,13 +62,11 @@ struct genevehdr { struct geneve_opt options[]; }; -#if IS_ENABLED(CONFIG_GENEVE) -void geneve_get_rx_port(struct net_device *netdev); -#else static inline void geneve_get_rx_port(struct net_device *netdev) { + ASSERT_RTNL(); + call_netdevice_notifiers(NETDEV_OFFLOAD_PUSH_GENEVE, netdev); } -#endif #ifdef CONFIG_INET struct net_device *geneve_dev_create_fb(struct net *net, const char *name, diff --git a/include/net/gre.h b/include/net/gre.h index 97eafdc47eea..29e37322c06e 100644 --- a/include/net/gre.h +++ b/include/net/gre.h @@ -25,4 +25,108 @@ int gre_del_protocol(const struct gre_protocol *proto, u8 version); struct net_device *gretap_fb_dev_create(struct net *net, const char *name, u8 name_assign_type); +int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, + bool *csum_err, int *hdr_len); + +static inline int gre_calc_hlen(__be16 o_flags) +{ + int addend = 4; + + if (o_flags & TUNNEL_CSUM) + addend += 4; + if (o_flags & TUNNEL_KEY) + addend += 4; + if (o_flags & TUNNEL_SEQ) + addend += 4; + return addend; +} + +static inline __be16 gre_flags_to_tnl_flags(__be16 flags) +{ + __be16 tflags = 0; + + if (flags & GRE_CSUM) + tflags |= TUNNEL_CSUM; + if (flags & GRE_ROUTING) + tflags |= TUNNEL_ROUTING; + if (flags & GRE_KEY) + tflags |= TUNNEL_KEY; + if (flags & GRE_SEQ) + tflags |= TUNNEL_SEQ; + if (flags & GRE_STRICT) + tflags |= TUNNEL_STRICT; + if (flags & GRE_REC) + tflags |= TUNNEL_REC; + if (flags & GRE_VERSION) + tflags |= TUNNEL_VERSION; + + return tflags; +} + +static inline __be16 gre_tnl_flags_to_gre_flags(__be16 tflags) +{ + __be16 flags = 0; + + if (tflags & TUNNEL_CSUM) + flags |= GRE_CSUM; + if (tflags & TUNNEL_ROUTING) + flags |= GRE_ROUTING; + if (tflags & TUNNEL_KEY) + flags |= GRE_KEY; + if (tflags & TUNNEL_SEQ) + flags |= GRE_SEQ; + if (tflags & TUNNEL_STRICT) + flags |= GRE_STRICT; + if (tflags & TUNNEL_REC) + flags |= GRE_REC; + if (tflags & TUNNEL_VERSION) + flags |= GRE_VERSION; + + return flags; +} + +static inline __sum16 gre_checksum(struct sk_buff *skb) +{ + __wsum csum; + + if (skb->ip_summed == CHECKSUM_PARTIAL) + csum = lco_csum(skb); + else + csum = skb_checksum(skb, 0, skb->len, 0); + return csum_fold(csum); +} + +static inline void gre_build_header(struct sk_buff *skb, int hdr_len, + __be16 flags, __be16 proto, + __be32 key, __be32 seq) +{ + struct gre_base_hdr *greh; + + skb_push(skb, hdr_len); + + skb_reset_transport_header(skb); + greh = (struct gre_base_hdr *)skb->data; + greh->flags = gre_tnl_flags_to_gre_flags(flags); + greh->protocol = proto; + + if (flags & (TUNNEL_KEY | TUNNEL_CSUM | TUNNEL_SEQ)) { + __be32 *ptr = (__be32 *)(((u8 *)greh) + hdr_len - 4); + + if (flags & TUNNEL_SEQ) { + *ptr = seq; + ptr--; + } + if (flags & TUNNEL_KEY) { + *ptr = key; + ptr--; + } + if (flags & TUNNEL_CSUM && + !(skb_shinfo(skb)->gso_type & + (SKB_GSO_GRE | SKB_GSO_GRE_CSUM))) { + *ptr = 0; + *(__sum16 *)ptr = gre_checksum(skb); + } + } +} + #endif diff --git a/include/net/icmp.h b/include/net/icmp.h index 970028e13382..3ef2743a8eec 100644 --- a/include/net/icmp.h +++ b/include/net/icmp.h @@ -30,9 +30,9 @@ struct icmp_err { extern const struct icmp_err icmp_err_convert[]; #define ICMP_INC_STATS(net, field) SNMP_INC_STATS((net)->mib.icmp_statistics, field) -#define ICMP_INC_STATS_BH(net, field) SNMP_INC_STATS_BH((net)->mib.icmp_statistics, field) +#define __ICMP_INC_STATS(net, field) __SNMP_INC_STATS((net)->mib.icmp_statistics, field) #define ICMPMSGOUT_INC_STATS(net, field) SNMP_INC_STATS_ATOMIC_LONG((net)->mib.icmpmsg_statistics, field+256) -#define ICMPMSGIN_INC_STATS_BH(net, field) SNMP_INC_STATS_ATOMIC_LONG((net)->mib.icmpmsg_statistics, field) +#define ICMPMSGIN_INC_STATS(net, field) SNMP_INC_STATS_ATOMIC_LONG((net)->mib.icmpmsg_statistics, field) struct dst_entry; struct net_proto_family; diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index 28332bdac333..b87becacd9d3 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -66,13 +66,15 @@ static inline struct sock *__inet6_lookup(struct net *net, const __be16 sport, const struct in6_addr *daddr, const u16 hnum, - const int dif) + const int dif, + bool *refcounted) { struct sock *sk = __inet6_lookup_established(net, hashinfo, saddr, sport, daddr, hnum, dif); + *refcounted = true; if (sk) return sk; - + *refcounted = false; return inet6_lookup_listener(net, hashinfo, skb, doff, saddr, sport, daddr, hnum, dif); } @@ -81,17 +83,19 @@ static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const __be16 sport, const __be16 dport, - int iif) + int iif, + bool *refcounted) { struct sock *sk = skb_steal_sock(skb); + *refcounted = true; if (sk) return sk; return __inet6_lookup(dev_net(skb_dst(skb)->dev), hashinfo, skb, doff, &ipv6_hdr(skb)->saddr, sport, &ipv6_hdr(skb)->daddr, ntohs(dport), - iif); + iif, refcounted); } struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 50f635c2c536..0574493e3899 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -100,14 +100,10 @@ struct inet_bind_hashbucket { /* * Sockets can be hashed in established or listening table - * We must use different 'nulls' end-of-chain value for listening - * hash table, or we might find a socket that was closed and - * reallocated/inserted into established hash table */ -#define LISTENING_NULLS_BASE (1U << 29) struct inet_listen_hashbucket { spinlock_t lock; - struct hlist_nulls_head head; + struct hlist_head head; }; /* This is for listening sockets, thus all sockets which possess wildcards. */ @@ -280,11 +276,8 @@ static inline struct sock *inet_lookup_listener(struct net *net, net_eq(sock_net(__sk), (__net))) #endif /* 64-bit arch */ -/* - * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so we need +/* Sockets in TCP_CLOSE state are _always_ taken out of the hash, so we need * not check it for lookups anymore, thanks Alexey. -DaveM - * - * Local BH must be disabled here. */ struct sock *__inet_lookup_established(struct net *net, struct inet_hashinfo *hashinfo, @@ -307,14 +300,20 @@ static inline struct sock *__inet_lookup(struct net *net, struct sk_buff *skb, int doff, const __be32 saddr, const __be16 sport, const __be32 daddr, const __be16 dport, - const int dif) + const int dif, + bool *refcounted) { u16 hnum = ntohs(dport); - struct sock *sk = __inet_lookup_established(net, hashinfo, - saddr, sport, daddr, hnum, dif); + struct sock *sk; - return sk ? : __inet_lookup_listener(net, hashinfo, skb, doff, saddr, - sport, daddr, hnum, dif); + sk = __inet_lookup_established(net, hashinfo, saddr, sport, + daddr, hnum, dif); + *refcounted = true; + if (sk) + return sk; + *refcounted = false; + return __inet_lookup_listener(net, hashinfo, skb, doff, saddr, + sport, daddr, hnum, dif); } static inline struct sock *inet_lookup(struct net *net, @@ -325,12 +324,13 @@ static inline struct sock *inet_lookup(struct net *net, const int dif) { struct sock *sk; + bool refcounted; - local_bh_disable(); sk = __inet_lookup(net, hashinfo, skb, doff, saddr, sport, daddr, - dport, dif); - local_bh_enable(); + dport, dif, &refcounted); + if (sk && !refcounted && !atomic_inc_not_zero(&sk->sk_refcnt)) + sk = NULL; return sk; } @@ -338,17 +338,20 @@ static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const __be16 sport, - const __be16 dport) + const __be16 dport, + bool *refcounted) { struct sock *sk = skb_steal_sock(skb); const struct iphdr *iph = ip_hdr(skb); + *refcounted = true; if (sk) return sk; - else - return __inet_lookup(dev_net(skb_dst(skb)->dev), hashinfo, skb, - doff, iph->saddr, sport, - iph->daddr, dport, inet_iif(skb)); + + return __inet_lookup(dev_net(skb_dst(skb)->dev), hashinfo, skb, + doff, iph->saddr, sport, + iph->daddr, dport, inet_iif(skb), + refcounted); } u32 sk_ehashfn(const struct sock *sk); diff --git a/include/net/ip.h b/include/net/ip.h index fad74d323bd6..247ac82e9cf2 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -56,6 +56,7 @@ static inline unsigned int ip_hdrlen(const struct sk_buff *skb) } struct ipcm_cookie { + struct sockcm_cookie sockc; __be32 addr; int oif; struct ip_options_rcu *opt; @@ -186,17 +187,15 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, unsigned int len); #define IP_INC_STATS(net, field) SNMP_INC_STATS64((net)->mib.ip_statistics, field) -#define IP_INC_STATS_BH(net, field) SNMP_INC_STATS64_BH((net)->mib.ip_statistics, field) +#define __IP_INC_STATS(net, field) __SNMP_INC_STATS64((net)->mib.ip_statistics, field) #define IP_ADD_STATS(net, field, val) SNMP_ADD_STATS64((net)->mib.ip_statistics, field, val) -#define IP_ADD_STATS_BH(net, field, val) SNMP_ADD_STATS64_BH((net)->mib.ip_statistics, field, val) +#define __IP_ADD_STATS(net, field, val) __SNMP_ADD_STATS64((net)->mib.ip_statistics, field, val) #define IP_UPD_PO_STATS(net, field, val) SNMP_UPD_PO_STATS64((net)->mib.ip_statistics, field, val) -#define IP_UPD_PO_STATS_BH(net, field, val) SNMP_UPD_PO_STATS64_BH((net)->mib.ip_statistics, field, val) +#define __IP_UPD_PO_STATS(net, field, val) __SNMP_UPD_PO_STATS64((net)->mib.ip_statistics, field, val) #define NET_INC_STATS(net, field) SNMP_INC_STATS((net)->mib.net_statistics, field) -#define NET_INC_STATS_BH(net, field) SNMP_INC_STATS_BH((net)->mib.net_statistics, field) -#define NET_INC_STATS_USER(net, field) SNMP_INC_STATS_USER((net)->mib.net_statistics, field) +#define __NET_INC_STATS(net, field) __SNMP_INC_STATS((net)->mib.net_statistics, field) #define NET_ADD_STATS(net, field, adnd) SNMP_ADD_STATS((net)->mib.net_statistics, field, adnd) -#define NET_ADD_STATS_BH(net, field, adnd) SNMP_ADD_STATS_BH((net)->mib.net_statistics, field, adnd) -#define NET_ADD_STATS_USER(net, field, adnd) SNMP_ADD_STATS_USER((net)->mib.net_statistics, field, adnd) +#define __NET_ADD_STATS(net, field, adnd) __SNMP_ADD_STATS((net)->mib.net_statistics, field, adnd) u64 snmp_get_cpu_field(void __percpu *mib, int cpu, int offct); unsigned long snmp_fold_field(void __percpu *mib, int offt); @@ -550,7 +549,7 @@ int ip_options_rcv_srr(struct sk_buff *skb); void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb); void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb, int offset); -int ip_cmsg_send(struct net *net, struct msghdr *msg, +int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, bool allow_ipv6); int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen); diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index 499a707765ea..fb9e0153f4f2 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -42,6 +42,7 @@ struct ip6_tnl { struct __ip6_tnl_parm parms; /* tunnel configuration parameters */ struct flowi fl; /* flowi template for xmit */ struct dst_cache dst_cache; /* cached dst */ + struct gro_cells gro_cells; int err_count; unsigned long err_time; @@ -49,8 +50,10 @@ struct ip6_tnl { /* These fields used only by GRE */ __u32 i_seqno; /* The last seen seqno */ __u32 o_seqno; /* The last output seqno */ - int hlen; /* Precalculated GRE header length */ + int hlen; /* tun_hlen + encap_hlen */ + int tun_hlen; /* Precalculated header length */ int mlink; + }; /* Tunnel encapsulation limit destination sub-option */ @@ -63,13 +66,19 @@ struct ipv6_tlv_tnl_enc_lim { int ip6_tnl_rcv_ctl(struct ip6_tnl *t, const struct in6_addr *laddr, const struct in6_addr *raddr); +int ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, + const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst, + bool log_ecn_error); int ip6_tnl_xmit_ctl(struct ip6_tnl *t, const struct in6_addr *laddr, const struct in6_addr *raddr); +int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, + struct flowi6 *fl6, int encap_limit, __u32 *pmtu, __u8 proto); __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw); __u32 ip6_tnl_get_cap(struct ip6_tnl *t, const struct in6_addr *laddr, const struct in6_addr *raddr); struct net *ip6_tnl_get_link_net(const struct net_device *dev); int ip6_tnl_get_iflink(const struct net_device *dev); +int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu); #ifdef CONFIG_INET static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb, diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 56050f913339..6d790910ebdf 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -105,24 +105,23 @@ struct ip_tunnel { struct net_device *dev; struct net *net; /* netns for packet i/o */ - int err_count; /* Number of arrived ICMP errors */ unsigned long err_time; /* Time when the last ICMP error * arrived */ + int err_count; /* Number of arrived ICMP errors */ /* These four fields used only by GRE */ u32 i_seqno; /* The last seen seqno */ u32 o_seqno; /* The last output seqno */ int tun_hlen; /* Precalculated header length */ - int mlink; struct dst_cache dst_cache; struct ip_tunnel_parm parms; + int mlink; int encap_hlen; /* Encap header length (FOU,GUE) */ - struct ip_tunnel_encap encap; - int hlen; /* tun_hlen + encap_hlen */ + struct ip_tunnel_encap encap; /* for SIT */ #ifdef CONFIG_IPV6_SIT_6RD @@ -295,15 +294,22 @@ 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, - bool xnet); +int __iptunnel_pull_header(struct sk_buff *skb, int hdr_len, + __be16 inner_proto, bool raw_proto, bool xnet); + +static inline int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, + __be16 inner_proto, bool xnet) +{ + return __iptunnel_pull_header(skb, hdr_len, inner_proto, false, 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); struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md, gfp_t flags); -struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb, int gso_type_mask); +int iptunnel_handle_offloads(struct sk_buff *skb, int gso_type_mask); static inline int iptunnel_pull_offloads(struct sk_buff *skb) { diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 1be050ada8c5..11a045281948 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -121,21 +121,21 @@ struct frag_hdr { extern int sysctl_mld_max_msf; extern int sysctl_mld_qrv; -#define _DEVINC(net, statname, modifier, idev, field) \ +#define _DEVINC(net, statname, mod, idev, field) \ ({ \ struct inet6_dev *_idev = (idev); \ if (likely(_idev != NULL)) \ - SNMP_INC_STATS##modifier((_idev)->stats.statname, (field)); \ - SNMP_INC_STATS##modifier((net)->mib.statname##_statistics, (field));\ + mod##SNMP_INC_STATS64((_idev)->stats.statname, (field));\ + mod##SNMP_INC_STATS64((net)->mib.statname##_statistics, (field));\ }) /* per device counters are atomic_long_t */ -#define _DEVINCATOMIC(net, statname, modifier, idev, field) \ +#define _DEVINCATOMIC(net, statname, mod, idev, field) \ ({ \ struct inet6_dev *_idev = (idev); \ if (likely(_idev != NULL)) \ SNMP_INC_STATS_ATOMIC_LONG((_idev)->stats.statname##dev, (field)); \ - SNMP_INC_STATS##modifier((net)->mib.statname##_statistics, (field));\ + mod##SNMP_INC_STATS((net)->mib.statname##_statistics, (field));\ }) /* per device and per net counters are atomic_long_t */ @@ -147,46 +147,44 @@ extern int sysctl_mld_qrv; SNMP_INC_STATS_ATOMIC_LONG((net)->mib.statname##_statistics, (field));\ }) -#define _DEVADD(net, statname, modifier, idev, field, val) \ +#define _DEVADD(net, statname, mod, idev, field, val) \ ({ \ struct inet6_dev *_idev = (idev); \ if (likely(_idev != NULL)) \ - SNMP_ADD_STATS##modifier((_idev)->stats.statname, (field), (val)); \ - SNMP_ADD_STATS##modifier((net)->mib.statname##_statistics, (field), (val));\ + mod##SNMP_ADD_STATS((_idev)->stats.statname, (field), (val)); \ + mod##SNMP_ADD_STATS((net)->mib.statname##_statistics, (field), (val));\ }) -#define _DEVUPD(net, statname, modifier, idev, field, val) \ +#define _DEVUPD(net, statname, mod, idev, field, val) \ ({ \ struct inet6_dev *_idev = (idev); \ if (likely(_idev != NULL)) \ - SNMP_UPD_PO_STATS##modifier((_idev)->stats.statname, field, (val)); \ - SNMP_UPD_PO_STATS##modifier((net)->mib.statname##_statistics, field, (val));\ + mod##SNMP_UPD_PO_STATS((_idev)->stats.statname, field, (val)); \ + mod##SNMP_UPD_PO_STATS((net)->mib.statname##_statistics, field, (val));\ }) /* MIBs */ #define IP6_INC_STATS(net, idev,field) \ - _DEVINC(net, ipv6, 64, idev, field) -#define IP6_INC_STATS_BH(net, idev,field) \ - _DEVINC(net, ipv6, 64_BH, idev, field) + _DEVINC(net, ipv6, , idev, field) +#define __IP6_INC_STATS(net, idev,field) \ + _DEVINC(net, ipv6, __, idev, field) #define IP6_ADD_STATS(net, idev,field,val) \ - _DEVADD(net, ipv6, 64, idev, field, val) -#define IP6_ADD_STATS_BH(net, idev,field,val) \ - _DEVADD(net, ipv6, 64_BH, idev, field, val) + _DEVADD(net, ipv6, , idev, field, val) +#define __IP6_ADD_STATS(net, idev,field,val) \ + _DEVADD(net, ipv6, __, idev, field, val) #define IP6_UPD_PO_STATS(net, idev,field,val) \ - _DEVUPD(net, ipv6, 64, idev, field, val) -#define IP6_UPD_PO_STATS_BH(net, idev,field,val) \ - _DEVUPD(net, ipv6, 64_BH, idev, field, val) + _DEVUPD(net, ipv6, , idev, field, val) +#define __IP6_UPD_PO_STATS(net, idev,field,val) \ + _DEVUPD(net, ipv6, __, idev, field, val) #define ICMP6_INC_STATS(net, idev, field) \ _DEVINCATOMIC(net, icmpv6, , idev, field) -#define ICMP6_INC_STATS_BH(net, idev, field) \ - _DEVINCATOMIC(net, icmpv6, _BH, idev, field) +#define __ICMP6_INC_STATS(net, idev, field) \ + _DEVINCATOMIC(net, icmpv6, __, idev, field) #define ICMP6MSGOUT_INC_STATS(net, idev, field) \ _DEVINC_ATOMIC_ATOMIC(net, icmpv6msg, idev, field +256) -#define ICMP6MSGOUT_INC_STATS_BH(net, idev, field) \ - _DEVINC_ATOMIC_ATOMIC(net, icmpv6msg, idev, field +256) -#define ICMP6MSGIN_INC_STATS_BH(net, idev, field) \ +#define ICMP6MSGIN_INC_STATS(net, idev, field) \ _DEVINC_ATOMIC_ATOMIC(net, icmpv6msg, idev, field) struct ip6_ra_chain { @@ -253,6 +251,13 @@ struct ipv6_fl_socklist { struct rcu_head rcu; }; +struct ipcm6_cookie { + __s16 hlimit; + __s16 tclass; + __s8 dontfrag; + struct ipv6_txoptions *opt; +}; + static inline struct ipv6_txoptions *txopt_get(const struct ipv6_pinfo *np) { struct ipv6_txoptions *opt; @@ -865,9 +870,10 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr); int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), - void *from, int length, int transhdrlen, int hlimit, - int tclass, struct ipv6_txoptions *opt, struct flowi6 *fl6, - struct rt6_info *rt, unsigned int flags, int dontfrag); + void *from, int length, int transhdrlen, + struct ipcm6_cookie *ipc6, struct flowi6 *fl6, + struct rt6_info *rt, unsigned int flags, + const struct sockcm_cookie *sockc); int ip6_push_pending_frames(struct sock *sk); @@ -882,9 +888,9 @@ struct sk_buff *ip6_make_skb(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, - int hlimit, int tclass, struct ipv6_txoptions *opt, - struct flowi6 *fl6, struct rt6_info *rt, - unsigned int flags, int dontfrag); + struct ipcm6_cookie *ipc6, struct flowi6 *fl6, + struct rt6_info *rt, unsigned int flags, + const struct sockcm_cookie *sockc); static inline struct sk_buff *ip6_finish_skb(struct sock *sk) { diff --git a/include/net/mac80211.h b/include/net/mac80211.h index e385eb3076a1..07ef9378df2b 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -291,7 +291,7 @@ struct ieee80211_vif_chanctx_switch { * @BSS_CHANGED_PS: PS changed for this BSS (STA mode) * @BSS_CHANGED_TXPOWER: TX power setting changed for this interface * @BSS_CHANGED_P2P_PS: P2P powersave settings (CTWindow, opportunistic PS) - * changed (currently only in P2P client mode, GO mode will be later) + * changed * @BSS_CHANGED_BEACON_INFO: Data from the AP's beacon became available: * currently dtim_period only is under consideration. * @BSS_CHANGED_BANDWIDTH: The bandwidth used by this interface changed, @@ -526,6 +526,9 @@ struct ieee80211_mu_group_data { * userspace), whereas TPC is disabled if %txpower_type is set to * NL80211_TX_POWER_FIXED (use value configured from userspace) * @p2p_noa_attr: P2P NoA attribute for P2P powersave + * @allow_p2p_go_ps: indication for AP or P2P GO interface, whether it's allowed + * to use P2P PS mechanism or not. AP/P2P GO is not allowed to use P2P PS + * if it has associated clients without P2P PS support. */ struct ieee80211_bss_conf { const u8 *bssid; @@ -546,7 +549,7 @@ struct ieee80211_bss_conf { u8 sync_dtim_count; u32 basic_rates; struct ieee80211_rate *beacon_rate; - int mcast_rate[IEEE80211_NUM_BANDS]; + int mcast_rate[NUM_NL80211_BANDS]; u16 ht_operation_mode; s32 cqm_rssi_thold; u32 cqm_rssi_hyst; @@ -563,6 +566,7 @@ struct ieee80211_bss_conf { int txpower; enum nl80211_tx_power_setting txpower_type; struct ieee80211_p2p_noa_attr p2p_noa_attr; + bool allow_p2p_go_ps; }; /** @@ -709,6 +713,7 @@ enum mac80211_tx_info_flags { * @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 + * @IEEE80211_TX_CTRL_AMSDU: This frame is an A-MSDU frame * * These flags are used in tx_info->control.flags. */ @@ -716,6 +721,7 @@ 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), + IEEE80211_TX_CTRL_AMSDU = BIT(3), }; /* @@ -932,8 +938,8 @@ struct ieee80211_tx_info { * @common_ie_len: length of the common_ies */ struct ieee80211_scan_ies { - const u8 *ies[IEEE80211_NUM_BANDS]; - size_t len[IEEE80211_NUM_BANDS]; + const u8 *ies[NUM_NL80211_BANDS]; + size_t len[NUM_NL80211_BANDS]; const u8 *common_ies; size_t common_ie_len; }; @@ -1036,6 +1042,8 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) * on this subframe * @RX_FLAG_AMPDU_DELIM_CRC_KNOWN: The delimiter CRC field is known (the CRC * is stored in the @ampdu_delimiter_crc field) + * @RX_FLAG_MIC_STRIPPED: The mic was stripped of this packet. Decryption was + * done by the hardware * @RX_FLAG_LDPC: LDPC was used * @RX_FLAG_ONLY_MONITOR: Report frame only to monitor interfaces without * processing it in any regular way. @@ -1093,6 +1101,7 @@ enum mac80211_rx_flags { RX_FLAG_5MHZ = BIT(29), RX_FLAG_AMSDU_MORE = BIT(30), RX_FLAG_RADIOTAP_VENDOR_DATA = BIT(31), + RX_FLAG_MIC_STRIPPED = BIT_ULL(32), }; #define RX_FLAG_STBC_SHIFT 26 @@ -1122,6 +1131,8 @@ enum mac80211_rx_vht_flags { * * @mactime: value in microseconds of the 64-bit Time Synchronization Function * (TSF) timer when the first data symbol (MPDU) arrived at the hardware. + * @boottime_ns: CLOCK_BOOTTIME timestamp the frame was received at, this is + * needed only for beacons and probe responses that update the scan cache. * @device_timestamp: arbitrary timestamp for the device, mac80211 doesn't use * it but can store it and pass it back to the driver for synchronisation * @band: the active band when this frame was received @@ -1148,9 +1159,10 @@ enum mac80211_rx_vht_flags { */ struct ieee80211_rx_status { u64 mactime; + u64 boottime_ns; u32 device_timestamp; u32 ampdu_reference; - u32 flag; + u64 flag; u16 freq; u8 vht_flag; u8 rate_idx; @@ -1737,10 +1749,12 @@ struct ieee80211_sta_rates { * 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). + * @support_p2p_ps: indicates whether the STA supports P2P PS mechanism or not. + * @max_rc_amsdu_len: Maximum A-MSDU size in bytes recommended by rate control. * @txq: per-TID data TX queues (if driver uses the TXQ abstraction) */ struct ieee80211_sta { - u32 supp_rates[IEEE80211_NUM_BANDS]; + u32 supp_rates[NUM_NL80211_BANDS]; u8 addr[ETH_ALEN]; u16 aid; struct ieee80211_sta_ht_cap ht_cap; @@ -1757,6 +1771,8 @@ struct ieee80211_sta { bool mfp; u8 max_amsdu_subframes; u16 max_amsdu_len; + bool support_p2p_ps; + u16 max_rc_amsdu_len; struct ieee80211_txq *txq[IEEE80211_NUM_TIDS]; @@ -1970,6 +1986,18 @@ struct ieee80211_txq { * order and does not need to manage its own reorder buffer or BA session * timeout. * + * @IEEE80211_HW_USES_RSS: The device uses RSS and thus requires parallel RX, + * which implies using per-CPU station statistics. + * + * @IEEE80211_HW_TX_AMSDU: Hardware (or driver) supports software aggregated + * A-MSDU frames. Requires software tx queueing and fast-xmit support. + * When not using minstrel/minstrel_ht rate control, the driver must + * limit the maximum A-MSDU size based on the current tx rate by setting + * max_rc_amsdu_len in struct ieee80211_sta. + * + * @IEEE80211_HW_TX_FRAG_LIST: Hardware (or driver) supports sending frag_list + * skbs, needed for zero-copy software A-MSDU. + * * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ enum ieee80211_hw_flags { @@ -2007,6 +2035,9 @@ enum ieee80211_hw_flags { IEEE80211_HW_BEACON_TX_STATUS, IEEE80211_HW_NEEDS_UNIQUE_STA_ADDR, IEEE80211_HW_SUPPORTS_REORDERING_BUFFER, + IEEE80211_HW_USES_RSS, + IEEE80211_HW_TX_AMSDU, + IEEE80211_HW_TX_FRAG_LIST, /* keep last, obviously */ NUM_IEEE80211_HW_FLAGS @@ -2079,6 +2110,9 @@ enum ieee80211_hw_flags { * size is smaller (an example is LinkSys WRT120N with FW v1.0.07 * build 002 Jun 18 2012). * + * @max_tx_fragments: maximum number of tx buffers per (A)-MSDU, sum + * of 1 + skb_shinfo(skb)->nr_frags for each skb in the frag_list. + * * @offchannel_tx_hw_queue: HW queue ID to use for offchannel TX * (if %IEEE80211_HW_QUEUE_CONTROL is set) * @@ -2133,6 +2167,7 @@ struct ieee80211_hw { u8 max_rate_tries; u8 max_rx_aggregation_subframes; u8 max_tx_aggregation_subframes; + u8 max_tx_fragments; u8 offchannel_tx_hw_queue; u8 radiotap_mcs_details; u16 radiotap_vht_details; @@ -3350,6 +3385,10 @@ enum ieee80211_reconfig_type { * the function call. * * @wake_tx_queue: Called when new packets have been added to the queue. + * @sync_rx_queues: Process all pending frames in RSS queues. This is a + * synchronization which is needed in case driver has in its RSS queues + * pending frames that were received prior to the control path action + * currently taken (e.g. disassociation) but are not processed yet. */ struct ieee80211_ops { void (*tx)(struct ieee80211_hw *hw, @@ -3587,6 +3626,7 @@ struct ieee80211_ops { void (*wake_tx_queue)(struct ieee80211_hw *hw, struct ieee80211_txq *txq); + void (*sync_rx_queues)(struct ieee80211_hw *hw); }; /** @@ -3840,11 +3880,12 @@ void ieee80211_restart_hw(struct ieee80211_hw *hw); * This function must be called with BHs disabled. * * @hw: the hardware this frame came in on + * @sta: the station the frame was received from, or %NULL * @skb: the buffer to receive, owned by mac80211 after this call * @napi: the NAPI context */ -void ieee80211_rx_napi(struct ieee80211_hw *hw, struct sk_buff *skb, - struct napi_struct *napi); +void ieee80211_rx_napi(struct ieee80211_hw *hw, struct ieee80211_sta *sta, + struct sk_buff *skb, struct napi_struct *napi); /** * ieee80211_rx - receive frame @@ -3868,7 +3909,7 @@ void ieee80211_rx_napi(struct ieee80211_hw *hw, struct sk_buff *skb, */ static inline void ieee80211_rx(struct ieee80211_hw *hw, struct sk_buff *skb) { - ieee80211_rx_napi(hw, skb, NULL); + ieee80211_rx_napi(hw, NULL, skb, NULL); } /** @@ -4363,7 +4404,7 @@ __le16 ieee80211_ctstoself_duration(struct ieee80211_hw *hw, */ __le16 ieee80211_generic_frame_duration(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_band band, + enum nl80211_band band, size_t frame_len, struct ieee80211_rate *rate); @@ -5316,7 +5357,7 @@ struct rate_control_ops { }; static inline int rate_supported(struct ieee80211_sta *sta, - enum ieee80211_band band, + enum nl80211_band band, int index) { return (sta == NULL || sta->supp_rates[band] & BIT(index)); diff --git a/include/net/mac802154.h b/include/net/mac802154.h index 6cd7a70706a9..e465c8551ac3 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -288,6 +288,16 @@ static inline void ieee802154_le16_to_be16(void *be16_dst, const void *le16_src) } /** + * ieee802154_be16_to_le16 - copies and convert be16 to le16 + * @le16_dst: le16 destination pointer + * @be16_src: be16 source pointer + */ +static inline void ieee802154_be16_to_le16(void *le16_dst, const void *be16_src) +{ + put_unaligned_le16(get_unaligned_be16(be16_src), le16_dst); +} + +/** * ieee802154_alloc_hw - Allocate a new hardware device * * This must be called once for each hardware device. The returned pointer diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h index 57c880378443..fa36447371c6 100644 --- a/include/net/netfilter/nf_conntrack_ecache.h +++ b/include/net/netfilter/nf_conntrack_ecache.h @@ -73,6 +73,8 @@ void nf_conntrack_unregister_notifier(struct net *net, struct nf_ct_event_notifier *nb); void nf_ct_deliver_cached_events(struct nf_conn *ct); +int nf_conntrack_eventmask_report(unsigned int eventmask, struct nf_conn *ct, + u32 portid, int report); static inline void nf_conntrack_event_cache(enum ip_conntrack_events event, struct nf_conn *ct) @@ -91,69 +93,25 @@ nf_conntrack_event_cache(enum ip_conntrack_events event, struct nf_conn *ct) } static inline int -nf_conntrack_eventmask_report(unsigned int eventmask, - struct nf_conn *ct, - u32 portid, - int report) -{ - int ret = 0; - struct net *net = nf_ct_net(ct); - struct nf_ct_event_notifier *notify; - struct nf_conntrack_ecache *e; - - rcu_read_lock(); - notify = rcu_dereference(net->ct.nf_conntrack_event_cb); - if (notify == NULL) - goto out_unlock; - - e = nf_ct_ecache_find(ct); - if (e == NULL) - goto out_unlock; - - if (nf_ct_is_confirmed(ct) && !nf_ct_is_dying(ct)) { - struct nf_ct_event item = { - .ct = ct, - .portid = e->portid ? e->portid : portid, - .report = report - }; - /* This is a resent of a destroy event? If so, skip missed */ - unsigned long missed = e->portid ? 0 : e->missed; - - if (!((eventmask | missed) & e->ctmask)) - goto out_unlock; - - ret = notify->fcn(eventmask | missed, &item); - if (unlikely(ret < 0 || missed)) { - spin_lock_bh(&ct->lock); - if (ret < 0) { - /* This is a destroy event that has been - * triggered by a process, we store the PORTID - * to include it in the retransmission. */ - if (eventmask & (1 << IPCT_DESTROY) && - e->portid == 0 && portid != 0) - e->portid = portid; - else - e->missed |= eventmask; - } else - e->missed &= ~missed; - spin_unlock_bh(&ct->lock); - } - } -out_unlock: - rcu_read_unlock(); - return ret; -} - -static inline int nf_conntrack_event_report(enum ip_conntrack_events event, struct nf_conn *ct, u32 portid, int report) { + const struct net *net = nf_ct_net(ct); + + if (!rcu_access_pointer(net->ct.nf_conntrack_event_cb)) + return 0; + return nf_conntrack_eventmask_report(1 << event, ct, portid, report); } static inline int nf_conntrack_event(enum ip_conntrack_events event, struct nf_conn *ct) { + const struct net *net = nf_ct_net(ct); + + if (!rcu_access_pointer(net->ct.nf_conntrack_event_cb)) + return 0; + return nf_conntrack_eventmask_report(1 << event, ct, 0, 0); } @@ -172,43 +130,9 @@ int nf_ct_expect_register_notifier(struct net *net, void nf_ct_expect_unregister_notifier(struct net *net, struct nf_exp_event_notifier *nb); -static inline void -nf_ct_expect_event_report(enum ip_conntrack_expect_events event, - struct nf_conntrack_expect *exp, - u32 portid, - int report) -{ - struct net *net = nf_ct_exp_net(exp); - struct nf_exp_event_notifier *notify; - struct nf_conntrack_ecache *e; - - rcu_read_lock(); - notify = rcu_dereference(net->ct.nf_expect_event_cb); - if (notify == NULL) - goto out_unlock; - - e = nf_ct_ecache_find(exp->master); - if (e == NULL) - goto out_unlock; - - if (e->expmask & (1 << event)) { - struct nf_exp_event item = { - .exp = exp, - .portid = portid, - .report = report - }; - notify->fcn(1 << event, &item); - } -out_unlock: - rcu_read_unlock(); -} - -static inline void -nf_ct_expect_event(enum ip_conntrack_expect_events event, - struct nf_conntrack_expect *exp) -{ - nf_ct_expect_event_report(event, exp, 0, 0); -} +void nf_ct_expect_event_report(enum ip_conntrack_expect_events event, + struct nf_conntrack_expect *exp, + u32 portid, int report); int nf_conntrack_ecache_pernet_init(struct net *net); void nf_conntrack_ecache_pernet_fini(struct net *net); @@ -245,8 +169,6 @@ static inline int nf_conntrack_event_report(enum ip_conntrack_events event, u32 portid, int report) { return 0; } static inline void nf_ct_deliver_cached_events(const struct nf_conn *ct) {} -static inline void nf_ct_expect_event(enum ip_conntrack_expect_events event, - struct nf_conntrack_expect *exp) {} static inline void nf_ct_expect_event_report(enum ip_conntrack_expect_events e, struct nf_conntrack_expect *exp, u32 portid, diff --git a/include/net/netfilter/nf_conntrack_labels.h b/include/net/netfilter/nf_conntrack_labels.h index 7e2b1d025f50..c5f8fc736b3d 100644 --- a/include/net/netfilter/nf_conntrack_labels.h +++ b/include/net/netfilter/nf_conntrack_labels.h @@ -45,7 +45,6 @@ static inline struct nf_conn_labels *nf_ct_labels_ext_add(struct nf_conn *ct) #endif } -bool nf_connlabel_match(const struct nf_conn *ct, u16 bit); int nf_connlabel_set(struct nf_conn *ct, u16 bit); int nf_connlabels_replace(struct nf_conn *ct, @@ -54,11 +53,11 @@ int nf_connlabels_replace(struct nf_conn *ct, #ifdef CONFIG_NF_CONNTRACK_LABELS int nf_conntrack_labels_init(void); void nf_conntrack_labels_fini(void); -int nf_connlabels_get(struct net *net, unsigned int n_bits); +int nf_connlabels_get(struct net *net, unsigned int bit); void nf_connlabels_put(struct net *net); #else static inline int nf_conntrack_labels_init(void) { return 0; } static inline void nf_conntrack_labels_fini(void) {} -static inline int nf_connlabels_get(struct net *net, unsigned int n_bits) { return 0; } +static inline int nf_connlabels_get(struct net *net, unsigned int bit) { return 0; } static inline void nf_connlabels_put(struct net *net) {} #endif diff --git a/include/net/netlink.h b/include/net/netlink.h index 0e3172751755..e589cb3dccee 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -102,10 +102,12 @@ * nla_put_s8(skb, type, value) add s8 attribute to skb * nla_put_s16(skb, type, value) add s16 attribute to skb * nla_put_s32(skb, type, value) add s32 attribute to skb - * nla_put_s64(skb, type, value) add s64 attribute to skb + * nla_put_s64(skb, type, value, + * padattr) add s64 attribute to skb * nla_put_string(skb, type, str) add string attribute to skb * nla_put_flag(skb, type) add flag attribute to skb - * nla_put_msecs(skb, type, jiffies) add msecs attribute to skb + * nla_put_msecs(skb, type, jiffies, + * padattr) add msecs attribute to skb * nla_put_in_addr(skb, type, addr) add IPv4 address attribute to skb * nla_put_in6_addr(skb, type, addr) add IPv6 address attribute to skb * @@ -244,13 +246,21 @@ int nla_memcpy(void *dest, const struct nlattr *src, int count); int nla_memcmp(const struct nlattr *nla, const void *data, size_t size); int nla_strcmp(const struct nlattr *nla, const char *str); struct nlattr *__nla_reserve(struct sk_buff *skb, int attrtype, int attrlen); +struct nlattr *__nla_reserve_64bit(struct sk_buff *skb, int attrtype, + int attrlen, int padattr); void *__nla_reserve_nohdr(struct sk_buff *skb, int attrlen); struct nlattr *nla_reserve(struct sk_buff *skb, int attrtype, int attrlen); +struct nlattr *nla_reserve_64bit(struct sk_buff *skb, int attrtype, + int attrlen, int padattr); void *nla_reserve_nohdr(struct sk_buff *skb, int attrlen); void __nla_put(struct sk_buff *skb, int attrtype, int attrlen, const void *data); +void __nla_put_64bit(struct sk_buff *skb, int attrtype, int attrlen, + const void *data, int padattr); void __nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data); int nla_put(struct sk_buff *skb, int attrtype, int attrlen, const void *data); +int nla_put_64bit(struct sk_buff *skb, int attrtype, int attrlen, + const void *data, int padattr); int nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data); int nla_append(struct sk_buff *skb, int attrlen, const void *data); @@ -848,36 +858,56 @@ static inline int nla_put_u64(struct sk_buff *skb, int attrtype, u64 value) } /** - * nla_put_be64 - Add a __be64 netlink attribute to a socket buffer + * nla_put_u64_64bit - Add a u64 netlink attribute to a skb and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value + * @padattr: attribute type for the padding */ -static inline int nla_put_be64(struct sk_buff *skb, int attrtype, __be64 value) +static inline int nla_put_u64_64bit(struct sk_buff *skb, int attrtype, + u64 value, int padattr) { - return nla_put(skb, attrtype, sizeof(__be64), &value); + return nla_put_64bit(skb, attrtype, sizeof(u64), &value, padattr); } /** - * nla_put_net64 - Add 64-bit network byte order netlink attribute to a socket buffer + * nla_put_be64 - Add a __be64 netlink attribute to a socket buffer and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value + * @padattr: attribute type for the padding */ -static inline int nla_put_net64(struct sk_buff *skb, int attrtype, __be64 value) +static inline int nla_put_be64(struct sk_buff *skb, int attrtype, __be64 value, + int padattr) { - return nla_put_be64(skb, attrtype | NLA_F_NET_BYTEORDER, value); + return nla_put_64bit(skb, attrtype, sizeof(__be64), &value, padattr); } /** - * nla_put_le64 - Add a __le64 netlink attribute to a socket buffer + * nla_put_net64 - Add 64-bit network byte order nlattr to a skb and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value + * @padattr: attribute type for the padding */ -static inline int nla_put_le64(struct sk_buff *skb, int attrtype, __le64 value) +static inline int nla_put_net64(struct sk_buff *skb, int attrtype, __be64 value, + int padattr) { - return nla_put(skb, attrtype, sizeof(__le64), &value); + return nla_put_be64(skb, attrtype | NLA_F_NET_BYTEORDER, value, + padattr); +} + +/** + * nla_put_le64 - Add a __le64 netlink attribute to a socket buffer and align it + * @skb: socket buffer to add attribute to + * @attrtype: attribute type + * @value: numeric value + * @padattr: attribute type for the padding + */ +static inline int nla_put_le64(struct sk_buff *skb, int attrtype, __le64 value, + int padattr) +{ + return nla_put_64bit(skb, attrtype, sizeof(__le64), &value, padattr); } /** @@ -914,14 +944,16 @@ static inline int nla_put_s32(struct sk_buff *skb, int attrtype, s32 value) } /** - * nla_put_s64 - Add a s64 netlink attribute to a socket buffer + * nla_put_s64 - Add a s64 netlink attribute to a socket buffer and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value + * @padattr: attribute type for the padding */ -static inline int nla_put_s64(struct sk_buff *skb, int attrtype, s64 value) +static inline int nla_put_s64(struct sk_buff *skb, int attrtype, s64 value, + int padattr) { - return nla_put(skb, attrtype, sizeof(s64), &value); + return nla_put_64bit(skb, attrtype, sizeof(s64), &value, padattr); } /** @@ -947,16 +979,18 @@ static inline int nla_put_flag(struct sk_buff *skb, int attrtype) } /** - * nla_put_msecs - Add a msecs netlink attribute to a socket buffer + * nla_put_msecs - Add a msecs netlink attribute to a skb and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @njiffies: number of jiffies to convert to msecs + * @padattr: attribute type for the padding */ static inline int nla_put_msecs(struct sk_buff *skb, int attrtype, - unsigned long njiffies) + unsigned long njiffies, int padattr) { u64 tmp = jiffies_to_msecs(njiffies); - return nla_put(skb, attrtype, sizeof(u64), &tmp); + + return nla_put_64bit(skb, attrtype, sizeof(u64), &tmp, padattr); } /** @@ -1231,6 +1265,61 @@ static inline int nla_validate_nested(const struct nlattr *start, int maxtype, } /** + * nla_need_padding_for_64bit - test 64-bit alignment of the next attribute + * @skb: socket buffer the message is stored in + * + * Return true if padding is needed to align the next attribute (nla_data()) to + * a 64-bit aligned area. + */ +static inline bool nla_need_padding_for_64bit(struct sk_buff *skb) +{ +#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS + /* The nlattr header is 4 bytes in size, that's why we test + * if the skb->data _is_ aligned. A NOP attribute, plus + * nlattr header for next attribute, will make nla_data() + * 8-byte aligned. + */ + if (IS_ALIGNED((unsigned long)skb_tail_pointer(skb), 8)) + return true; +#endif + return false; +} + +/** + * nla_align_64bit - 64-bit align the nla_data() of next attribute + * @skb: socket buffer the message is stored in + * @padattr: attribute type for the padding + * + * Conditionally emit a padding netlink attribute in order to make + * the next attribute we emit have a 64-bit aligned nla_data() area. + * This will only be done in architectures which do not have + * CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS defined. + * + * Returns zero on success or a negative error code. + */ +static inline int nla_align_64bit(struct sk_buff *skb, int padattr) +{ + if (nla_need_padding_for_64bit(skb) && + !nla_reserve(skb, padattr, 0)) + return -EMSGSIZE; + + return 0; +} + +/** + * nla_total_size_64bit - total length of attribute including padding + * @payload: length of payload + */ +static inline int nla_total_size_64bit(int payload) +{ + return NLA_ALIGN(nla_attr_size(payload)) +#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS + + NLA_ALIGN(nla_attr_size(0)) +#endif + ; +} + +/** * nla_for_each_attr - iterate over a stream of attributes * @pos: loop counter, set to current attribute * @head: head of attribute stream diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index a69cde3ce460..d061ffeb1e71 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -133,6 +133,9 @@ struct netns_ipv4 { struct fib_rules_ops *mr_rules_ops; #endif #endif +#ifdef CONFIG_IP_ROUTE_MULTIPATH + int sysctl_fib_multipath_use_neigh; +#endif atomic_t rt_genid; }; #endif diff --git a/include/net/nl802154.h b/include/net/nl802154.h index 32cb3e591e07..fcab4de49951 100644 --- a/include/net/nl802154.h +++ b/include/net/nl802154.h @@ -138,6 +138,8 @@ enum nl802154_attrs { NL802154_ATTR_SEC_KEY, #endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ + NL802154_ATTR_PAD, + __NL802154_ATTR_AFTER_LAST, NL802154_ATTR_MAX = __NL802154_ATTR_AFTER_LAST - 1 }; @@ -295,6 +297,7 @@ enum nl802154_dev_addr_attrs { NL802154_DEV_ADDR_ATTR_MODE, NL802154_DEV_ADDR_ATTR_SHORT, NL802154_DEV_ADDR_ATTR_EXTENDED, + NL802154_DEV_ADDR_ATTR_PAD, /* keep last */ __NL802154_DEV_ADDR_ATTR_AFTER_LAST, @@ -320,6 +323,7 @@ enum nl802154_key_id_attrs { NL802154_KEY_ID_ATTR_IMPLICIT, NL802154_KEY_ID_ATTR_SOURCE_SHORT, NL802154_KEY_ID_ATTR_SOURCE_EXTENDED, + NL802154_KEY_ID_ATTR_PAD, /* keep last */ __NL802154_KEY_ID_ATTR_AFTER_LAST, @@ -402,6 +406,7 @@ enum nl802154_dev { NL802154_DEV_ATTR_EXTENDED_ADDR, NL802154_DEV_ATTR_SECLEVEL_EXEMPT, NL802154_DEV_ATTR_KEY_MODE, + NL802154_DEV_ATTR_PAD, /* keep last */ __NL802154_DEV_ATTR_AFTER_LAST, @@ -414,6 +419,7 @@ enum nl802154_devkey { NL802154_DEVKEY_ATTR_FRAME_COUNTER, NL802154_DEVKEY_ATTR_EXTENDED_ADDR, NL802154_DEVKEY_ATTR_ID, + NL802154_DEVKEY_ATTR_PAD, /* keep last */ __NL802154_DEVKEY_ATTR_AFTER_LAST, diff --git a/include/net/protocol.h b/include/net/protocol.h index da689f5432de..bf36ca34af7a 100644 --- a/include/net/protocol.h +++ b/include/net/protocol.h @@ -107,9 +107,6 @@ int inet_del_offload(const struct net_offload *prot, unsigned char num); void inet_register_protosw(struct inet_protosw *p); void inet_unregister_protosw(struct inet_protosw *p); -int udp_add_offload(struct net *net, struct udp_offload *prot); -void udp_del_offload(struct udp_offload *prot); - #if IS_ENABLED(CONFIG_IPV6) int inet6_add_protocol(const struct inet6_protocol *prot, unsigned char num); int inet6_del_protocol(const struct inet6_protocol *prot, unsigned char num); diff --git a/include/net/request_sock.h b/include/net/request_sock.h index f49759decb28..6ebe13eb1c4c 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -85,24 +85,23 @@ reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener, struct request_sock *req; req = kmem_cache_alloc(ops->slab, GFP_ATOMIC | __GFP_NOWARN); - - if (req) { - req->rsk_ops = ops; - if (attach_listener) { - sock_hold(sk_listener); - req->rsk_listener = sk_listener; - } else { - req->rsk_listener = NULL; + if (!req) + return NULL; + req->rsk_listener = NULL; + if (attach_listener) { + if (unlikely(!atomic_inc_not_zero(&sk_listener->sk_refcnt))) { + kmem_cache_free(ops->slab, req); + return NULL; } - req_to_sk(req)->sk_prot = sk_listener->sk_prot; - sk_node_init(&req_to_sk(req)->sk_node); - sk_tx_queue_clear(req_to_sk(req)); - req->saved_syn = NULL; - /* Following is temporary. It is coupled with debugging - * helpers in reqsk_put() & reqsk_free() - */ - atomic_set(&req->rsk_refcnt, 0); + req->rsk_listener = sk_listener; } + req->rsk_ops = ops; + req_to_sk(req)->sk_prot = sk_listener->sk_prot; + sk_node_init(&req_to_sk(req)->sk_node); + sk_tx_queue_clear(req_to_sk(req)); + req->saved_syn = NULL; + atomic_set(&req->rsk_refcnt, 0); + return req; } diff --git a/include/net/route.h b/include/net/route.h index 6de665bf1750..ad777d79af94 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -325,10 +325,11 @@ static inline struct rtable *ip_route_newports(struct flowi4 *fl4, struct rtable static inline int inet_iif(const struct sk_buff *skb) { - int iif = skb_rtable(skb)->rt_iif; + struct rtable *rt = skb_rtable(skb); + + if (rt && rt->rt_iif) + return rt->rt_iif; - if (iif) - return iif; return skb->skb_iif; } diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 2f87c1ba13de..006a7b81d758 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -47,6 +47,9 @@ static inline int rtnl_msg_family(const struct nlmsghdr *nlh) * @get_num_rx_queues: Function to determine number of receive queues * to create when creating a new device. * @get_link_net: Function to get the i/o netns of the device + * @get_linkxstats_size: Function to calculate the required room for + * dumping device-specific extended link stats + * @fill_linkxstats: Function to dump device-specific extended link stats */ struct rtnl_link_ops { struct list_head list; @@ -95,6 +98,10 @@ struct rtnl_link_ops { const struct net_device *dev, const struct net_device *slave_dev); struct net *(*get_link_net)(const struct net_device *dev); + size_t (*get_linkxstats_size)(const struct net_device *dev); + int (*fill_linkxstats)(struct sk_buff *skb, + const struct net_device *dev, + int *prividx); }; int __rtnl_link_register(struct rtnl_link_ops *ops); diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 03fb33efcae2..b392ac8382f2 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -116,6 +116,22 @@ extern struct percpu_counter sctp_sockets_allocated; int sctp_asconf_mgmt(struct sctp_sock *, struct sctp_sockaddr_entry *); struct sk_buff *sctp_skb_recv_datagram(struct sock *, int, int, int *); +int sctp_transport_walk_start(struct rhashtable_iter *iter); +void sctp_transport_walk_stop(struct rhashtable_iter *iter); +struct sctp_transport *sctp_transport_get_next(struct net *net, + struct rhashtable_iter *iter); +struct sctp_transport *sctp_transport_get_idx(struct net *net, + struct rhashtable_iter *iter, int pos); +int sctp_transport_lookup_process(int (*cb)(struct sctp_transport *, void *), + struct net *net, + const union sctp_addr *laddr, + const union sctp_addr *paddr, void *p); +int sctp_for_each_transport(int (*cb)(struct sctp_transport *, void *), + struct net *net, int pos, void *p); +int sctp_for_each_endpoint(int (*cb)(struct sctp_endpoint *, void *), void *p); +int sctp_get_sctp_info(struct sock *sk, struct sctp_association *asoc, + struct sctp_info *info); + /* * sctp/primitive.c */ @@ -189,10 +205,9 @@ extern int sysctl_sctp_wmem[3]; */ /* SCTP SNMP MIB stats handlers */ -#define SCTP_INC_STATS(net, field) SNMP_INC_STATS((net)->sctp.sctp_statistics, field) -#define SCTP_INC_STATS_BH(net, field) SNMP_INC_STATS_BH((net)->sctp.sctp_statistics, field) -#define SCTP_INC_STATS_USER(net, field) SNMP_INC_STATS_USER((net)->sctp.sctp_statistics, field) -#define SCTP_DEC_STATS(net, field) SNMP_DEC_STATS((net)->sctp.sctp_statistics, field) +#define SCTP_INC_STATS(net, field) SNMP_INC_STATS((net)->sctp.sctp_statistics, field) +#define __SCTP_INC_STATS(net, field) __SNMP_INC_STATS((net)->sctp.sctp_statistics, field) +#define SCTP_DEC_STATS(net, field) SNMP_DEC_STATS((net)->sctp.sctp_statistics, field) /* sctp mib definitions */ enum { @@ -359,21 +374,6 @@ int sctp_do_peeloff(struct sock *sk, sctp_assoc_t id, struct socket **sockp); #define sctp_skb_for_each(pos, head, tmp) \ skb_queue_walk_safe(head, pos, tmp) -/* A helper to append an entire skb list (list) to another (head). */ -static inline void sctp_skb_list_tail(struct sk_buff_head *list, - struct sk_buff_head *head) -{ - unsigned long flags; - - spin_lock_irqsave(&head->lock, flags); - spin_lock(&list->lock); - - skb_queue_splice_tail_init(list, head); - - spin_unlock(&list->lock); - spin_unlock_irqrestore(&head->lock, flags); -} - /** * sctp_list_dequeue - remove from the head of the queue * @list: list to dequeue from diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 5a404c354f4c..16b013a6191c 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -210,14 +210,15 @@ struct sctp_sock { int user_frag; __u32 autoclose; - __u8 nodelay; - __u8 disable_fragments; - __u8 v4mapped; - __u8 frag_interleave; __u32 adaptation_ind; __u32 pd_point; - __u8 recvrcvinfo; - __u8 recvnxtinfo; + __u16 nodelay:1, + disable_fragments:1, + v4mapped:1, + frag_interleave:1, + recvrcvinfo:1, + recvnxtinfo:1, + data_ready_signalled:1; atomic_t pd_mode; /* Receive to here while partial delivery is in effect. */ diff --git a/include/net/snmp.h b/include/net/snmp.h index 35512ac6dcfb..c9228ad7ee91 100644 --- a/include/net/snmp.h +++ b/include/net/snmp.h @@ -123,12 +123,9 @@ struct linux_xfrm_mib { #define DECLARE_SNMP_STAT(type, name) \ extern __typeof__(type) __percpu *name -#define SNMP_INC_STATS_BH(mib, field) \ +#define __SNMP_INC_STATS(mib, field) \ __this_cpu_inc(mib->mibs[field]) -#define SNMP_INC_STATS_USER(mib, field) \ - this_cpu_inc(mib->mibs[field]) - #define SNMP_INC_STATS_ATOMIC_LONG(mib, field) \ atomic_long_inc(&mib->mibs[field]) @@ -138,12 +135,9 @@ struct linux_xfrm_mib { #define SNMP_DEC_STATS(mib, field) \ this_cpu_dec(mib->mibs[field]) -#define SNMP_ADD_STATS_BH(mib, field, addend) \ +#define __SNMP_ADD_STATS(mib, field, addend) \ __this_cpu_add(mib->mibs[field], addend) -#define SNMP_ADD_STATS_USER(mib, field, addend) \ - this_cpu_add(mib->mibs[field], addend) - #define SNMP_ADD_STATS(mib, field, addend) \ this_cpu_add(mib->mibs[field], addend) #define SNMP_UPD_PO_STATS(mib, basefield, addend) \ @@ -152,7 +146,7 @@ struct linux_xfrm_mib { this_cpu_inc(ptr[basefield##PKTS]); \ this_cpu_add(ptr[basefield##OCTETS], addend); \ } while (0) -#define SNMP_UPD_PO_STATS_BH(mib, basefield, addend) \ +#define __SNMP_UPD_PO_STATS(mib, basefield, addend) \ do { \ __typeof__((mib->mibs) + 0) ptr = mib->mibs; \ __this_cpu_inc(ptr[basefield##PKTS]); \ @@ -162,7 +156,7 @@ struct linux_xfrm_mib { #if BITS_PER_LONG==32 -#define SNMP_ADD_STATS64_BH(mib, field, addend) \ +#define __SNMP_ADD_STATS64(mib, field, addend) \ do { \ __typeof__(*mib) *ptr = raw_cpu_ptr(mib); \ u64_stats_update_begin(&ptr->syncp); \ @@ -170,20 +164,16 @@ struct linux_xfrm_mib { u64_stats_update_end(&ptr->syncp); \ } while (0) -#define SNMP_ADD_STATS64_USER(mib, field, addend) \ +#define SNMP_ADD_STATS64(mib, field, addend) \ do { \ local_bh_disable(); \ - SNMP_ADD_STATS64_BH(mib, field, addend); \ - local_bh_enable(); \ + __SNMP_ADD_STATS64(mib, field, addend); \ + local_bh_enable(); \ } while (0) -#define SNMP_ADD_STATS64(mib, field, addend) \ - SNMP_ADD_STATS64_USER(mib, field, addend) - -#define SNMP_INC_STATS64_BH(mib, field) SNMP_ADD_STATS64_BH(mib, field, 1) -#define SNMP_INC_STATS64_USER(mib, field) SNMP_ADD_STATS64_USER(mib, field, 1) +#define __SNMP_INC_STATS64(mib, field) SNMP_ADD_STATS64(mib, field, 1) #define SNMP_INC_STATS64(mib, field) SNMP_ADD_STATS64(mib, field, 1) -#define SNMP_UPD_PO_STATS64_BH(mib, basefield, addend) \ +#define __SNMP_UPD_PO_STATS64(mib, basefield, addend) \ do { \ __typeof__(*mib) *ptr; \ ptr = raw_cpu_ptr((mib)); \ @@ -195,19 +185,17 @@ struct linux_xfrm_mib { #define SNMP_UPD_PO_STATS64(mib, basefield, addend) \ do { \ local_bh_disable(); \ - SNMP_UPD_PO_STATS64_BH(mib, basefield, addend); \ - local_bh_enable(); \ + __SNMP_UPD_PO_STATS64(mib, basefield, addend); \ + local_bh_enable(); \ } while (0) #else -#define SNMP_INC_STATS64_BH(mib, field) SNMP_INC_STATS_BH(mib, field) -#define SNMP_INC_STATS64_USER(mib, field) SNMP_INC_STATS_USER(mib, field) +#define __SNMP_INC_STATS64(mib, field) __SNMP_INC_STATS(mib, field) #define SNMP_INC_STATS64(mib, field) SNMP_INC_STATS(mib, field) #define SNMP_DEC_STATS64(mib, field) SNMP_DEC_STATS(mib, field) -#define SNMP_ADD_STATS64_BH(mib, field, addend) SNMP_ADD_STATS_BH(mib, field, addend) -#define SNMP_ADD_STATS64_USER(mib, field, addend) SNMP_ADD_STATS_USER(mib, field, addend) +#define __SNMP_ADD_STATS64(mib, field, addend) __SNMP_ADD_STATS(mib, field, addend) #define SNMP_ADD_STATS64(mib, field, addend) SNMP_ADD_STATS(mib, field, addend) #define SNMP_UPD_PO_STATS64(mib, basefield, addend) SNMP_UPD_PO_STATS(mib, basefield, addend) -#define SNMP_UPD_PO_STATS64_BH(mib, basefield, addend) SNMP_UPD_PO_STATS_BH(mib, basefield, addend) +#define __SNMP_UPD_PO_STATS64(mib, basefield, addend) __SNMP_UPD_PO_STATS(mib, basefield, addend) #endif #endif diff --git a/include/net/sock.h b/include/net/sock.h index 121ffc115c4f..45f5b492c658 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -178,7 +178,7 @@ struct sock_common { int skc_bound_dev_if; union { struct hlist_node skc_bind_node; - struct hlist_nulls_node skc_portaddr_node; + struct hlist_node skc_portaddr_node; }; struct proto *skc_prot; possible_net_t skc_net; @@ -438,6 +438,7 @@ struct sock { struct sk_buff *skb); void (*sk_destruct)(struct sock *sk); struct sock_reuseport __rcu *sk_reuseport_cb; + struct rcu_head sk_rcu; }; #define __sk_user_data(sk) ((*((void __rcu **)&(sk)->sk_user_data))) @@ -456,28 +457,32 @@ struct sock { #define SK_CAN_REUSE 1 #define SK_FORCE_REUSE 2 +int sk_set_peek_off(struct sock *sk, int val); + static inline int sk_peek_offset(struct sock *sk, int flags) { - if ((flags & MSG_PEEK) && (sk->sk_peek_off >= 0)) - return sk->sk_peek_off; - else - return 0; + if (unlikely(flags & MSG_PEEK)) { + s32 off = READ_ONCE(sk->sk_peek_off); + if (off >= 0) + return off; + } + + return 0; } static inline void sk_peek_offset_bwd(struct sock *sk, int val) { - if (sk->sk_peek_off >= 0) { - if (sk->sk_peek_off >= val) - sk->sk_peek_off -= val; - else - sk->sk_peek_off = 0; + s32 off = READ_ONCE(sk->sk_peek_off); + + if (unlikely(off >= 0)) { + off = max_t(s32, off - val, 0); + WRITE_ONCE(sk->sk_peek_off, off); } } static inline void sk_peek_offset_fwd(struct sock *sk, int val) { - if (sk->sk_peek_off >= 0) - sk->sk_peek_off += val; + sk_peek_offset_bwd(sk, -val); } /* @@ -564,7 +569,7 @@ static inline bool __sk_del_node_init(struct sock *sk) modifications. */ -static inline void sock_hold(struct sock *sk) +static __always_inline void sock_hold(struct sock *sk) { atomic_inc(&sk->sk_refcnt); } @@ -572,7 +577,7 @@ static inline void sock_hold(struct sock *sk) /* Ungrab socket in the context, which assumes that socket refcnt cannot hit zero, f.e. it is true in context of any socketcall. */ -static inline void __sock_put(struct sock *sk) +static __always_inline void __sock_put(struct sock *sk) { atomic_dec(&sk->sk_refcnt); } @@ -625,7 +630,11 @@ static inline void sk_add_node(struct sock *sk, struct hlist_head *list) static inline void sk_add_node_rcu(struct sock *sk, struct hlist_head *list) { sock_hold(sk); - hlist_add_head_rcu(&sk->sk_node, list); + if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport && + sk->sk_family == AF_INET6) + hlist_add_tail_rcu(&sk->sk_node, list); + else + hlist_add_head_rcu(&sk->sk_node, list); } static inline void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list) @@ -673,18 +682,18 @@ static inline void sk_add_bind_node(struct sock *sk, hlist_for_each_entry(__sk, list, sk_bind_node) /** - * sk_nulls_for_each_entry_offset - iterate over a list at a given struct offset + * sk_for_each_entry_offset_rcu - iterate over a list at a given struct offset * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_node to use as a loop cursor. * @head: the head for your list. * @offset: offset of hlist_node within the struct. * */ -#define sk_nulls_for_each_entry_offset(tpos, pos, head, offset) \ - for (pos = (head)->first; \ - (!is_a_nulls(pos)) && \ +#define sk_for_each_entry_offset_rcu(tpos, pos, head, offset) \ + for (pos = rcu_dereference((head)->first); \ + pos != NULL && \ ({ tpos = (typeof(*tpos) *)((void *)pos - offset); 1;}); \ - pos = pos->next) + pos = rcu_dereference(pos->next)) static inline struct user_namespace *sk_user_ns(struct sock *sk) { @@ -724,6 +733,7 @@ enum sock_flags { */ SOCK_FILTER_LOCKED, /* Filter cannot be changed anymore */ SOCK_SELECT_ERR_QUEUE, /* Wake select on error queue */ + SOCK_RCU_FREE, /* wait rcu grace period in sk_destruct() */ }; #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) @@ -916,6 +926,17 @@ void sk_stream_kill_queues(struct sock *sk); void sk_set_memalloc(struct sock *sk); void sk_clear_memalloc(struct sock *sk); +void __sk_flush_backlog(struct sock *sk); + +static inline bool sk_flush_backlog(struct sock *sk) +{ + if (unlikely(READ_ONCE(sk->sk_backlog.tail))) { + __sk_flush_backlog(sk); + return true; + } + return false; +} + int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb); struct request_sock_ops; @@ -1314,24 +1335,14 @@ static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb) __kfree_skb(skb); } -/* Used by processes to "lock" a socket state, so that - * interrupts and bottom half handlers won't change it - * from under us. It essentially blocks any incoming - * packets, so that we won't get any new data or any - * packets that change the state of the socket. - * - * While locked, BH processing will add new packets to - * the backlog queue. This queue is processed by the - * owner of the socket lock right before it is released. - * - * Since ~2.3.5 it is also exclusive sleep lock serializing - * accesses from user process context. - */ -#define sock_owned_by_user(sk) ((sk)->sk_lock.owned) - static inline void sock_release_ownership(struct sock *sk) { - sk->sk_lock.owned = 0; + if (sk->sk_lock.owned) { + sk->sk_lock.owned = 0; + + /* The sk_lock has mutex_unlock() semantics: */ + mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_); + } } /* @@ -1353,6 +1364,16 @@ do { \ lockdep_init_map(&(sk)->sk_lock.dep_map, (name), (key), 0); \ } while (0) +#ifdef CONFIG_LOCKDEP +static inline bool lockdep_sock_is_held(const struct sock *csk) +{ + struct sock *sk = (struct sock *)csk; + + return lockdep_is_held(&sk->sk_lock) || + lockdep_is_held(&sk->sk_lock.slock); +} +#endif + void lock_sock_nested(struct sock *sk, int subclass); static inline void lock_sock(struct sock *sk) @@ -1386,6 +1407,35 @@ static inline void unlock_sock_fast(struct sock *sk, bool slow) spin_unlock_bh(&sk->sk_lock.slock); } +/* Used by processes to "lock" a socket state, so that + * interrupts and bottom half handlers won't change it + * from under us. It essentially blocks any incoming + * packets, so that we won't get any new data or any + * packets that change the state of the socket. + * + * While locked, BH processing will add new packets to + * the backlog queue. This queue is processed by the + * owner of the socket lock right before it is released. + * + * Since ~2.3.5 it is also exclusive sleep lock serializing + * accesses from user process context. + */ + +static inline bool sock_owned_by_user(const struct sock *sk) +{ +#ifdef CONFIG_LOCKDEP + WARN_ON_ONCE(!lockdep_sock_is_held(sk) && debug_locks); +#endif + return sk->sk_lock.owned; +} + +/* no reclassification while locks are held */ +static inline bool sock_allow_reclassification(const struct sock *csk) +{ + struct sock *sk = (struct sock *)csk; + + return !sk->sk_lock.owned && !spin_is_locked(&sk->sk_lock.slock); +} struct sock *sk_alloc(struct net *net, int family, gfp_t priority, struct proto *prot, int kern); @@ -1395,6 +1445,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority); struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, gfp_t priority); +void __sock_wfree(struct sk_buff *skb); void sock_wfree(struct sk_buff *skb); void skb_orphan_partial(struct sk_buff *skb); void sock_rfree(struct sk_buff *skb); @@ -1422,8 +1473,11 @@ void sk_send_sigurg(struct sock *sk); struct sockcm_cookie { u32 mark; + u16 tsflags; }; +int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg, + struct sockcm_cookie *sockc); int sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct sockcm_cookie *sockc); @@ -1588,8 +1642,8 @@ static inline void sk_rethink_txhash(struct sock *sk) static inline struct dst_entry * __sk_dst_get(struct sock *sk) { - return rcu_dereference_check(sk->sk_dst_cache, sock_owned_by_user(sk) || - lockdep_is_held(&sk->sk_lock.slock)); + return rcu_dereference_check(sk->sk_dst_cache, + lockdep_sock_is_held(sk)); } static inline struct dst_entry * @@ -1861,6 +1915,7 @@ void sk_reset_timer(struct sock *sk, struct timer_list *timer, void sk_stop_timer(struct sock *sk, struct timer_list *timer); +int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb); @@ -1897,11 +1952,19 @@ static inline unsigned long sock_wspace(struct sock *sk) */ static inline void sk_set_bit(int nr, struct sock *sk) { + if ((nr == SOCKWQ_ASYNC_NOSPACE || nr == SOCKWQ_ASYNC_WAITDATA) && + !sock_flag(sk, SOCK_FASYNC)) + return; + set_bit(nr, &sk->sk_wq_raw->flags); } static inline void sk_clear_bit(int nr, struct sock *sk) { + if ((nr == SOCKWQ_ASYNC_NOSPACE || nr == SOCKWQ_ASYNC_WAITDATA) && + !sock_flag(sk, SOCK_FASYNC)) + return; + clear_bit(nr, &sk->sk_wq_raw->flags); } @@ -2011,6 +2074,13 @@ sock_skb_set_dropcount(const struct sock *sk, struct sk_buff *skb) SOCK_SKB_CB(skb)->dropcount = atomic_read(&sk->sk_drops); } +static inline void sk_drops_add(struct sock *sk, const struct sk_buff *skb) +{ + int segs = max_t(u16, 1, skb_shinfo(skb)->gso_segs); + + atomic_add(segs, &sk->sk_drops); +} + void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb); void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk, @@ -2058,19 +2128,21 @@ static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, sk->sk_stamp = skb->tstamp; } -void __sock_tx_timestamp(const struct sock *sk, __u8 *tx_flags); +void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags); /** * sock_tx_timestamp - checks whether the outgoing packet is to be time stamped * @sk: socket sending this packet + * @tsflags: timestamping flags to use * @tx_flags: completed with instructions for time stamping * * Note : callers should take care of initial *tx_flags value (usually 0) */ -static inline void sock_tx_timestamp(const struct sock *sk, __u8 *tx_flags) +static inline void sock_tx_timestamp(const struct sock *sk, __u16 tsflags, + __u8 *tx_flags) { - if (unlikely(sk->sk_tsflags)) - __sock_tx_timestamp(sk, tx_flags); + if (unlikely(tsflags)) + __sock_tx_timestamp(tsflags, tx_flags); if (unlikely(sock_flag(sk, SOCK_WIFI_STATUS))) *tx_flags |= SKBTX_WIFI_STATUS; } diff --git a/include/net/tcp.h b/include/net/tcp.h index 6db10228113f..24ec80483805 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -332,9 +332,8 @@ bool tcp_check_oom(struct sock *sk, int shift); extern struct proto tcp_prot; #define TCP_INC_STATS(net, field) SNMP_INC_STATS((net)->mib.tcp_statistics, field) -#define TCP_INC_STATS_BH(net, field) SNMP_INC_STATS_BH((net)->mib.tcp_statistics, field) +#define __TCP_INC_STATS(net, field) __SNMP_INC_STATS((net)->mib.tcp_statistics, field) #define TCP_DEC_STATS(net, field) SNMP_DEC_STATS((net)->mib.tcp_statistics, field) -#define TCP_ADD_STATS_USER(net, field, val) SNMP_ADD_STATS_USER((net)->mib.tcp_statistics, field, val) #define TCP_ADD_STATS(net, field, val) SNMP_ADD_STATS((net)->mib.tcp_statistics, field, val) void tcp_tasklet_init(void); @@ -452,10 +451,15 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb); int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); int tcp_connect(struct sock *sk); +enum tcp_synack_type { + TCP_SYNACK_NORMAL, + TCP_SYNACK_FASTOPEN, + TCP_SYNACK_COOKIE, +}; struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, struct request_sock *req, struct tcp_fastopen_cookie *foc, - bool attach_req); + enum tcp_synack_type synack_type); int tcp_disconnect(struct sock *sk, int flags); void tcp_finish_connect(struct sock *sk, struct sk_buff *skb); @@ -533,8 +537,8 @@ __u32 cookie_v6_init_sequence(const struct sk_buff *skb, __u16 *mss); void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss, int nonagle); bool tcp_may_send_now(struct sock *sk); -int __tcp_retransmit_skb(struct sock *, struct sk_buff *); -int tcp_retransmit_skb(struct sock *, struct sk_buff *); +int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs); +int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs); void tcp_retransmit_timer(struct sock *sk); void tcp_xmit_retransmit_queue(struct sock *); void tcp_simple_retransmit(struct sock *); @@ -756,7 +760,9 @@ struct tcp_skb_cb { TCPCB_REPAIRED) __u8 ip_dsfield; /* IPv4 tos or IPv6 dsfield */ - /* 1 byte hole */ + __u8 txstamp_ack:1, /* Record TX timestamp for ack? */ + eor:1, /* Is skb MSG_EOR marked? */ + unused:6; __u32 ack_seq; /* Sequence number ACK'd */ union { struct inet_skb_parm h4; @@ -803,6 +809,11 @@ static inline int tcp_skb_mss(const struct sk_buff *skb) return TCP_SKB_CB(skb)->tcp_gso_size; } +static inline bool tcp_skb_can_collapse_to(const struct sk_buff *skb) +{ + return likely(!TCP_SKB_CB(skb)->eor); +} + /* Events passed to congestion control interface */ enum tcp_ca_event { CA_EVENT_TX_START, /* first transmit when no packets in flight */ @@ -1041,17 +1052,6 @@ static inline __u32 tcp_max_tso_deferred_mss(const struct tcp_sock *tp) return 3; } -/* Slow start with delack produces 3 packets of burst, so that - * it is safe "de facto". This will be the default - same as - * the default reordering threshold - but if reordering increases, - * we must be able to allow cwnd to burst at least this much in order - * to not pull it back when holes are filled. - */ -static __inline__ __u32 tcp_max_burst(const struct tcp_sock *tp) -{ - return tp->reordering; -} - /* Returns end sequence number of the receiver's advertised window */ static inline u32 tcp_wnd_end(const struct tcp_sock *tp) { @@ -1303,10 +1303,10 @@ bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb, static inline void tcp_mib_init(struct net *net) { /* See RFC 2012 */ - TCP_ADD_STATS_USER(net, TCP_MIB_RTOALGORITHM, 1); - TCP_ADD_STATS_USER(net, TCP_MIB_RTOMIN, TCP_RTO_MIN*1000/HZ); - TCP_ADD_STATS_USER(net, TCP_MIB_RTOMAX, TCP_RTO_MAX*1000/HZ); - TCP_ADD_STATS_USER(net, TCP_MIB_MAXCONN, -1); + TCP_ADD_STATS(net, TCP_MIB_RTOALGORITHM, 1); + TCP_ADD_STATS(net, TCP_MIB_RTOMIN, TCP_RTO_MIN*1000/HZ); + TCP_ADD_STATS(net, TCP_MIB_RTOMAX, TCP_RTO_MAX*1000/HZ); + TCP_ADD_STATS(net, TCP_MIB_MAXCONN, -1); } /* from STCP */ @@ -1740,7 +1740,7 @@ struct tcp_request_sock_ops { int (*send_synack)(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, struct tcp_fastopen_cookie *foc, - bool attach_req); + enum tcp_synack_type synack_type); }; #ifdef CONFIG_SYN_COOKIES @@ -1749,7 +1749,7 @@ static inline __u32 cookie_init_sequence(const struct tcp_request_sock_ops *ops, __u16 *mss) { tcp_synq_overflow(sk); - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESSENT); + __NET_INC_STATS(sock_net(sk), LINUX_MIB_SYNCOOKIESSENT); return ops->cookie_init_seq(skb, mss); } #else @@ -1848,4 +1848,17 @@ static inline void tcp_segs_in(struct tcp_sock *tp, const struct sk_buff *skb) tp->data_segs_in += segs_in; } +/* + * TCP listen path runs lockless. + * We forced "struct sock" to be const qualified to make sure + * we don't modify one of its field by mistake. + * Here, we increment sk_drops which is an atomic_t, so we can safely + * make sock writable again. + */ +static inline void tcp_listendrop(const struct sock *sk) +{ + atomic_inc(&((struct sock *)sk)->sk_drops); + __NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENDROPS); +} + #endif /* _TCP_H */ diff --git a/include/net/transp_v6.h b/include/net/transp_v6.h index b927413dde86..276f9760ab56 100644 --- a/include/net/transp_v6.h +++ b/include/net/transp_v6.h @@ -41,8 +41,8 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb); int ip6_datagram_send_ctl(struct net *net, struct sock *sk, struct msghdr *msg, - struct flowi6 *fl6, struct ipv6_txoptions *opt, - int *hlimit, int *tclass, int *dontfrag); + struct flowi6 *fl6, struct ipcm6_cookie *ipc6, + struct sockcm_cookie *sockc); void ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp, __u16 srcp, __u16 destp, int bucket); diff --git a/include/net/udp.h b/include/net/udp.h index 92927f729ac8..ae07f375370d 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -59,7 +59,7 @@ struct udp_skb_cb { * @lock: spinlock protecting changes to head/count */ struct udp_hslot { - struct hlist_nulls_head head; + struct hlist_head head; int count; spinlock_t lock; } __attribute__((aligned(2 * sizeof(long)))); @@ -158,9 +158,21 @@ static inline __sum16 udp_v4_check(int len, __be32 saddr, void udp_set_csum(bool nocheck, struct sk_buff *skb, __be32 saddr, __be32 daddr, int len); +static inline void udp_csum_pull_header(struct sk_buff *skb) +{ + if (skb->ip_summed == CHECKSUM_NONE) + skb->csum = csum_partial(udp_hdr(skb), sizeof(struct udphdr), + skb->csum); + skb_pull_rcsum(skb, sizeof(struct udphdr)); + UDP_SKB_CB(skb)->cscov -= sizeof(struct udphdr); +} + +typedef struct sock *(*udp_lookup_t)(struct sk_buff *skb, __be16 sport, + __be16 dport); + struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb, - struct udphdr *uh); -int udp_gro_complete(struct sk_buff *skb, int nhoff); + struct udphdr *uh, udp_lookup_t lookup); +int udp_gro_complete(struct sk_buff *skb, int nhoff, udp_lookup_t lookup); static inline struct udphdr *udp_gro_udphdr(struct sk_buff *skb) { @@ -260,6 +272,8 @@ struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif, struct udp_table *tbl, struct sk_buff *skb); +struct sock *udp4_lib_lookup_skb(struct sk_buff *skb, + __be16 sport, __be16 dport); struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, @@ -269,36 +283,38 @@ struct sock *__udp6_lib_lookup(struct net *net, const struct in6_addr *daddr, __be16 dport, int dif, struct udp_table *tbl, struct sk_buff *skb); +struct sock *udp6_lib_lookup_skb(struct sk_buff *skb, + __be16 sport, __be16 dport); /* * SNMP statistics for UDP and UDP-Lite */ -#define UDP_INC_STATS_USER(net, field, is_udplite) do { \ - if (is_udplite) SNMP_INC_STATS_USER((net)->mib.udplite_statistics, field); \ - else SNMP_INC_STATS_USER((net)->mib.udp_statistics, field); } while(0) -#define UDP_INC_STATS_BH(net, field, is_udplite) do { \ - if (is_udplite) SNMP_INC_STATS_BH((net)->mib.udplite_statistics, field); \ - else SNMP_INC_STATS_BH((net)->mib.udp_statistics, field); } while(0) - -#define UDP6_INC_STATS_BH(net, field, is_udplite) do { \ - if (is_udplite) SNMP_INC_STATS_BH((net)->mib.udplite_stats_in6, field);\ - else SNMP_INC_STATS_BH((net)->mib.udp_stats_in6, field); \ +#define UDP_INC_STATS(net, field, is_udplite) do { \ + if (is_udplite) SNMP_INC_STATS((net)->mib.udplite_statistics, field); \ + else SNMP_INC_STATS((net)->mib.udp_statistics, field); } while(0) +#define __UDP_INC_STATS(net, field, is_udplite) do { \ + if (is_udplite) __SNMP_INC_STATS((net)->mib.udplite_statistics, field); \ + else __SNMP_INC_STATS((net)->mib.udp_statistics, field); } while(0) + +#define __UDP6_INC_STATS(net, field, is_udplite) do { \ + if (is_udplite) __SNMP_INC_STATS((net)->mib.udplite_stats_in6, field);\ + else __SNMP_INC_STATS((net)->mib.udp_stats_in6, field); \ } while(0) -#define UDP6_INC_STATS_USER(net, field, __lite) do { \ - if (__lite) SNMP_INC_STATS_USER((net)->mib.udplite_stats_in6, field); \ - else SNMP_INC_STATS_USER((net)->mib.udp_stats_in6, field); \ +#define UDP6_INC_STATS(net, field, __lite) do { \ + if (__lite) SNMP_INC_STATS((net)->mib.udplite_stats_in6, field); \ + else SNMP_INC_STATS((net)->mib.udp_stats_in6, field); \ } while(0) #if IS_ENABLED(CONFIG_IPV6) -#define UDPX_INC_STATS_BH(sk, field) \ +#define __UDPX_INC_STATS(sk, field) \ do { \ if ((sk)->sk_family == AF_INET) \ - UDP_INC_STATS_BH(sock_net(sk), field, 0); \ + __UDP_INC_STATS(sock_net(sk), field, 0); \ else \ - UDP6_INC_STATS_BH(sock_net(sk), field, 0); \ + __UDP6_INC_STATS(sock_net(sk), field, 0); \ } while (0) #else -#define UDPX_INC_STATS_BH(sk, field) UDP_INC_STATS_BH(sock_net(sk), field, 0) +#define __UDPX_INC_STATS(sk, field) __UDP_INC_STATS(sock_net(sk), field, 0) #endif /* /proc */ diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index b83114077cee..4f543262dd81 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -64,6 +64,11 @@ static inline int udp_sock_create(struct net *net, typedef int (*udp_tunnel_encap_rcv_t)(struct sock *sk, struct sk_buff *skb); typedef void (*udp_tunnel_encap_destroy_t)(struct sock *sk); +typedef struct sk_buff **(*udp_tunnel_gro_receive_t)(struct sock *sk, + struct sk_buff **head, + struct sk_buff *skb); +typedef int (*udp_tunnel_gro_complete_t)(struct sock *sk, struct sk_buff *skb, + int nhoff); struct udp_tunnel_sock_cfg { void *sk_user_data; /* user data used by encap_rcv call back */ @@ -71,6 +76,8 @@ struct udp_tunnel_sock_cfg { __u8 encap_type; udp_tunnel_encap_rcv_t encap_rcv; udp_tunnel_encap_destroy_t encap_destroy; + udp_tunnel_gro_receive_t gro_receive; + udp_tunnel_gro_complete_t gro_complete; }; /* Setup the given (UDP) sock to receive UDP encapsulated packets */ @@ -98,8 +105,7 @@ struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family, __be16 flags, __be64 tunnel_id, int md_size); -static inline struct sk_buff *udp_tunnel_handle_offloads(struct sk_buff *skb, - bool udp_csum) +static inline int udp_tunnel_handle_offloads(struct sk_buff *skb, bool udp_csum) { int type = udp_csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 35437c779da8..b8803165df91 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -119,6 +119,64 @@ struct vxlanhdr_gbp { #define VXLAN_GBP_POLICY_APPLIED (BIT(3) << 16) #define VXLAN_GBP_ID_MASK (0xFFFF) +/* + * VXLAN Generic Protocol Extension (VXLAN_F_GPE): + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * |R|R|Ver|I|P|R|O| Reserved |Next Protocol | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | VXLAN Network Identifier (VNI) | Reserved | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * + * Ver = Version. Indicates VXLAN GPE protocol version. + * + * P = Next Protocol Bit. The P bit is set to indicate that the + * Next Protocol field is present. + * + * O = OAM Flag Bit. The O bit is set to indicate that the packet + * is an OAM packet. + * + * Next Protocol = This 8 bit field indicates the protocol header + * immediately following the VXLAN GPE header. + * + * https://tools.ietf.org/html/draft-ietf-nvo3-vxlan-gpe-01 + */ + +struct vxlanhdr_gpe { +#if defined(__LITTLE_ENDIAN_BITFIELD) + u8 oam_flag:1, + reserved_flags1:1, + np_applied:1, + instance_applied:1, + version:2, +reserved_flags2:2; +#elif defined(__BIG_ENDIAN_BITFIELD) + u8 reserved_flags2:2, + version:2, + instance_applied:1, + np_applied:1, + reserved_flags1:1, + oam_flag:1; +#endif + u8 reserved_flags3; + u8 reserved_flags4; + u8 next_protocol; + __be32 vx_vni; +}; + +/* VXLAN-GPE header flags. */ +#define VXLAN_HF_VER cpu_to_be32(BIT(29) | BIT(28)) +#define VXLAN_HF_NP cpu_to_be32(BIT(26)) +#define VXLAN_HF_OAM cpu_to_be32(BIT(24)) + +#define VXLAN_GPE_USED_BITS (VXLAN_HF_VER | VXLAN_HF_NP | VXLAN_HF_OAM | \ + cpu_to_be32(0xff)) + +/* VXLAN-GPE header Next Protocol. */ +#define VXLAN_GPE_NP_IPV4 0x01 +#define VXLAN_GPE_NP_IPV6 0x02 +#define VXLAN_GPE_NP_ETHERNET 0x03 +#define VXLAN_GPE_NP_NSH 0x04 + struct vxlan_metadata { u32 gbp; }; @@ -126,12 +184,9 @@ struct vxlan_metadata { /* per UDP socket information */ struct vxlan_sock { struct hlist_node hlist; - struct work_struct del_work; struct socket *sock; - struct rcu_head rcu; struct hlist_head vni_list[VNI_HASH_SIZE]; atomic_t refcnt; - struct udp_offload udp_offloads; u32 flags; }; @@ -206,16 +261,26 @@ struct vxlan_dev { #define VXLAN_F_GBP 0x800 #define VXLAN_F_REMCSUM_NOPARTIAL 0x1000 #define VXLAN_F_COLLECT_METADATA 0x2000 +#define VXLAN_F_GPE 0x4000 /* Flags that are used in the receive path. These flags must match in * order for a socket to be shareable */ #define VXLAN_F_RCV_FLAGS (VXLAN_F_GBP | \ + VXLAN_F_GPE | \ VXLAN_F_UDP_ZERO_CSUM6_RX | \ VXLAN_F_REMCSUM_RX | \ VXLAN_F_REMCSUM_NOPARTIAL | \ VXLAN_F_COLLECT_METADATA) +/* Flags that can be set together with VXLAN_F_GPE. */ +#define VXLAN_F_ALLOWED_GPE (VXLAN_F_GPE | \ + VXLAN_F_IPV6 | \ + VXLAN_F_UDP_ZERO_CSUM_TX | \ + VXLAN_F_UDP_ZERO_CSUM6_TX | \ + VXLAN_F_UDP_ZERO_CSUM6_RX | \ + VXLAN_F_COLLECT_METADATA) + struct net_device *vxlan_dev_create(struct net *net, const char *name, u8 name_assign_type, struct vxlan_config *conf); @@ -327,13 +392,11 @@ static inline __be32 vxlan_compute_rco(unsigned int start, unsigned int offset) return vni_field; } -#if IS_ENABLED(CONFIG_VXLAN) -void vxlan_get_rx_port(struct net_device *netdev); -#else static inline void vxlan_get_rx_port(struct net_device *netdev) { + ASSERT_RTNL(); + call_netdevice_notifiers(NETDEV_OFFLOAD_PUSH_VXLAN, netdev); } -#endif static inline unsigned short vxlan_get_sk_family(struct vxlan_sock *vs) { diff --git a/include/net/xfrm.h b/include/net/xfrm.h index d6f6e5006ee9..adfebd6f243c 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -45,12 +45,8 @@ #ifdef CONFIG_XFRM_STATISTICS #define XFRM_INC_STATS(net, field) SNMP_INC_STATS((net)->mib.xfrm_statistics, field) -#define XFRM_INC_STATS_BH(net, field) SNMP_INC_STATS_BH((net)->mib.xfrm_statistics, field) -#define XFRM_INC_STATS_USER(net, field) SNMP_INC_STATS_USER((net)-mib.xfrm_statistics, field) #else #define XFRM_INC_STATS(net, field) ((void)(net)) -#define XFRM_INC_STATS_BH(net, field) ((void)(net)) -#define XFRM_INC_STATS_USER(net, field) ((void)(net)) #endif |