diff options
Diffstat (limited to 'include/net')
52 files changed, 1088 insertions, 480 deletions
diff --git a/include/net/act_api.h b/include/net/act_api.h index cb382a89ea58..87214927314a 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -166,8 +166,6 @@ int tcf_idr_create_from_flags(struct tc_action_net *tn, u32 index, struct nlattr *est, struct tc_action **a, const struct tc_action_ops *ops, int bind, u32 flags); -void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a); - void tcf_idr_cleanup(struct tc_action_net *tn, u32 index); int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index, struct tc_action **a, int bind); diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h index 91eacbdcf33d..f6abcc0bbd6e 100644 --- a/include/net/af_rxrpc.h +++ b/include/net/af_rxrpc.h @@ -59,7 +59,7 @@ bool rxrpc_kernel_abort_call(struct socket *, struct rxrpc_call *, void rxrpc_kernel_end_call(struct socket *, struct rxrpc_call *); void rxrpc_kernel_get_peer(struct socket *, struct rxrpc_call *, struct sockaddr_rxrpc *); -u32 rxrpc_kernel_get_srtt(struct socket *, struct rxrpc_call *); +bool rxrpc_kernel_get_srtt(struct socket *, struct rxrpc_call *, u32 *); int rxrpc_kernel_charge_accept(struct socket *, rxrpc_notify_rx_t, rxrpc_user_attach_call_t, unsigned long, gfp_t, unsigned int); diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 8caac20556b4..9873e1c8cd16 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -484,6 +484,9 @@ struct hci_dev { enum suspended_state suspend_state; bool scanning_paused; bool suspended; + u8 wake_reason; + bdaddr_t wake_addr; + u8 wake_addr_type; wait_queue_head_t suspend_wait_q; DECLARE_BITMAP(suspend_tasks, __SUSPEND_NUM_TASKS); @@ -1750,6 +1753,9 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, void mgmt_remote_name(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, s8 rssi, u8 *name, u8 name_len); void mgmt_discovering(struct hci_dev *hdev, u8 discovering); +void mgmt_suspending(struct hci_dev *hdev, u8 state); +void mgmt_resuming(struct hci_dev *hdev, u8 reason, bdaddr_t *bdaddr, + u8 addr_type); bool mgmt_powering_down(struct hci_dev *hdev); void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, bool persistent); void mgmt_new_irk(struct hci_dev *hdev, struct smp_irk *irk, bool persistent); diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 8f1e6a7a2df8..1d1232917de7 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -665,6 +665,8 @@ struct l2cap_ops { struct sk_buff *(*alloc_skb) (struct l2cap_chan *chan, unsigned long hdr_len, unsigned long len, int nb); + int (*filter) (struct l2cap_chan * chan, + struct sk_buff *skb); }; struct l2cap_conn { diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index beae5c3980f0..6b55155e05e9 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -572,6 +572,8 @@ struct mgmt_rp_add_advertising { #define MGMT_ADV_FLAG_SEC_1M BIT(7) #define MGMT_ADV_FLAG_SEC_2M BIT(8) #define MGMT_ADV_FLAG_SEC_CODED BIT(9) +#define MGMT_ADV_FLAG_CAN_SET_TX_POWER BIT(10) +#define MGMT_ADV_FLAG_HW_OFFLOAD BIT(11) #define MGMT_ADV_FLAG_SEC_MASK (MGMT_ADV_FLAG_SEC_1M | MGMT_ADV_FLAG_SEC_2M | \ MGMT_ADV_FLAG_SEC_CODED) @@ -840,6 +842,7 @@ struct mgmt_ev_device_connected { #define MGMT_DEV_DISCONN_LOCAL_HOST 0x02 #define MGMT_DEV_DISCONN_REMOTE 0x03 #define MGMT_DEV_DISCONN_AUTH_FAILURE 0x04 +#define MGMT_DEV_DISCONN_LOCAL_HOST_SUSPEND 0x05 #define MGMT_EV_DEVICE_DISCONNECTED 0x000C struct mgmt_ev_device_disconnected { @@ -1028,3 +1031,18 @@ struct mgmt_ev_adv_monitor_added { struct mgmt_ev_adv_monitor_removed { __le16 monitor_handle; } __packed; + +#define MGMT_EV_CONTROLLER_SUSPEND 0x002d +struct mgmt_ev_controller_suspend { + __u8 suspend_state; +} __packed; + +#define MGMT_EV_CONTROLLER_RESUME 0x002e +struct mgmt_ev_controller_resume { + __u8 wake_reason; + struct mgmt_addr_info addr; +} __packed; + +#define MGMT_WAKE_REASON_NON_BT_WAKE 0x0 +#define MGMT_WAKE_REASON_UNEXPECTED 0x1 +#define MGMT_WAKE_REASON_REMOTE_WAKE 0x2 diff --git a/include/net/bpf_sk_storage.h b/include/net/bpf_sk_storage.h index 5036c94c0503..3c516dd07caf 100644 --- a/include/net/bpf_sk_storage.h +++ b/include/net/bpf_sk_storage.h @@ -3,6 +3,17 @@ #ifndef _BPF_SK_STORAGE_H #define _BPF_SK_STORAGE_H +#include <linux/rculist.h> +#include <linux/list.h> +#include <linux/hash.h> +#include <linux/types.h> +#include <linux/spinlock.h> +#include <linux/bpf.h> +#include <net/sock.h> +#include <uapi/linux/sock_diag.h> +#include <uapi/linux/btf.h> +#include <linux/bpf_local_storage.h> + struct sock; void bpf_sk_storage_free(struct sock *sk); @@ -10,6 +21,7 @@ void bpf_sk_storage_free(struct sock *sk); extern const struct bpf_func_proto bpf_sk_storage_get_proto; extern const struct bpf_func_proto bpf_sk_storage_delete_proto; +struct bpf_local_storage_elem; struct bpf_sk_storage_diag; struct sk_buff; struct nlattr; diff --git a/include/net/caif/caif_spi.h b/include/net/caif/caif_spi.h deleted file mode 100644 index a0bf4cbce71b..000000000000 --- a/include/net/caif/caif_spi.h +++ /dev/null @@ -1,155 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) ST-Ericsson AB 2010 - * Author: Daniel Martensson / Daniel.Martensson@stericsson.com - */ - -#ifndef CAIF_SPI_H_ -#define CAIF_SPI_H_ - -#include <net/caif/caif_device.h> - -#define SPI_CMD_WR 0x00 -#define SPI_CMD_RD 0x01 -#define SPI_CMD_EOT 0x02 -#define SPI_CMD_IND 0x04 - -#define SPI_DMA_BUF_LEN 8192 - -#define WL_SZ 2 /* 16 bits. */ -#define SPI_CMD_SZ 4 /* 32 bits. */ -#define SPI_IND_SZ 4 /* 32 bits. */ - -#define SPI_XFER 0 -#define SPI_SS_ON 1 -#define SPI_SS_OFF 2 -#define SPI_TERMINATE 3 - -/* Minimum time between different levels is 50 microseconds. */ -#define MIN_TRANSITION_TIME_USEC 50 - -/* Defines for calculating duration of SPI transfers for a particular - * number of bytes. - */ -#define SPI_MASTER_CLK_MHZ 13 -#define SPI_XFER_TIME_USEC(bytes, clk) (((bytes) * 8) / clk) - -/* Normally this should be aligned on the modem in order to benefit from full - * duplex transfers. However a size of 8188 provokes errors when running with - * the modem. These errors occur when packet sizes approaches 4 kB of data. - */ -#define CAIF_MAX_SPI_FRAME 4092 - -/* Maximum number of uplink CAIF frames that can reside in the same SPI frame. - * This number should correspond with the modem setting. The application side - * CAIF accepts any number of embedded downlink CAIF frames. - */ -#define CAIF_MAX_SPI_PKTS 9 - -/* Decides if SPI buffers should be prefilled with 0xFF pattern for easier - * debugging. Both TX and RX buffers will be filled before the transfer. - */ -#define CFSPI_DBG_PREFILL 0 - -/* Structure describing a SPI transfer. */ -struct cfspi_xfer { - u16 tx_dma_len; - u16 rx_dma_len; - void *va_tx[2]; - dma_addr_t pa_tx[2]; - void *va_rx; - dma_addr_t pa_rx; -}; - -/* Structure implemented by the SPI interface. */ -struct cfspi_ifc { - void (*ss_cb) (bool assert, struct cfspi_ifc *ifc); - void (*xfer_done_cb) (struct cfspi_ifc *ifc); - void *priv; -}; - -/* Structure implemented by SPI clients. */ -struct cfspi_dev { - int (*init_xfer) (struct cfspi_xfer *xfer, struct cfspi_dev *dev); - void (*sig_xfer) (bool xfer, struct cfspi_dev *dev); - struct cfspi_ifc *ifc; - char *name; - u32 clk_mhz; - void *priv; -}; - -/* Enumeration describing the CAIF SPI state. */ -enum cfspi_state { - CFSPI_STATE_WAITING = 0, - CFSPI_STATE_AWAKE, - CFSPI_STATE_FETCH_PKT, - CFSPI_STATE_GET_NEXT, - CFSPI_STATE_INIT_XFER, - CFSPI_STATE_WAIT_ACTIVE, - CFSPI_STATE_SIG_ACTIVE, - CFSPI_STATE_WAIT_XFER_DONE, - CFSPI_STATE_XFER_DONE, - CFSPI_STATE_WAIT_INACTIVE, - CFSPI_STATE_SIG_INACTIVE, - CFSPI_STATE_DELIVER_PKT, - CFSPI_STATE_MAX, -}; - -/* Structure implemented by SPI physical interfaces. */ -struct cfspi { - struct caif_dev_common cfdev; - struct net_device *ndev; - struct platform_device *pdev; - struct sk_buff_head qhead; - struct sk_buff_head chead; - u16 cmd; - u16 tx_cpck_len; - u16 tx_npck_len; - u16 rx_cpck_len; - u16 rx_npck_len; - struct cfspi_ifc ifc; - struct cfspi_xfer xfer; - struct cfspi_dev *dev; - unsigned long state; - struct work_struct work; - struct workqueue_struct *wq; - struct list_head list; - int flow_off_sent; - u32 qd_low_mark; - u32 qd_high_mark; - struct completion comp; - wait_queue_head_t wait; - spinlock_t lock; - bool flow_stop; - bool slave; - bool slave_talked; -#ifdef CONFIG_DEBUG_FS - enum cfspi_state dbg_state; - u16 pcmd; - u16 tx_ppck_len; - u16 rx_ppck_len; - struct dentry *dbgfs_dir; - struct dentry *dbgfs_state; - struct dentry *dbgfs_frame; -#endif /* CONFIG_DEBUG_FS */ -}; - -extern int spi_frm_align; -extern int spi_up_head_align; -extern int spi_up_tail_align; -extern int spi_down_head_align; -extern int spi_down_tail_align; -extern struct platform_driver cfspi_spi_driver; - -void cfspi_dbg_state(struct cfspi *cfspi, int state); -int cfspi_xmitfrm(struct cfspi *cfspi, u8 *buf, size_t len); -int cfspi_xmitlen(struct cfspi *cfspi); -int cfspi_rxfrm(struct cfspi *cfspi, u8 *buf, size_t len); -int cfspi_spi_remove(struct platform_device *pdev); -int cfspi_spi_probe(struct platform_device *pdev); -int cfspi_xmitfrm(struct cfspi *cfspi, u8 *buf, size_t len); -int cfspi_xmitlen(struct cfspi *cfspi); -int cfspi_rxfrm(struct cfspi *cfspi, u8 *buf, size_t len); -void cfspi_xfer(struct work_struct *work); - -#endif /* CAIF_SPI_H_ */ diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index d9e6b9fbd95b..661edfc8722e 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -96,6 +96,16 @@ struct wiphy; * @IEEE80211_CHAN_NO_10MHZ: 10 MHz bandwidth is not permitted * on this channel. * @IEEE80211_CHAN_NO_HE: HE operation is not permitted on this channel. + * @IEEE80211_CHAN_1MHZ: 1 MHz bandwidth is permitted + * on this channel. + * @IEEE80211_CHAN_2MHZ: 2 MHz bandwidth is permitted + * on this channel. + * @IEEE80211_CHAN_4MHZ: 4 MHz bandwidth is permitted + * on this channel. + * @IEEE80211_CHAN_8MHZ: 8 MHz bandwidth is permitted + * on this channel. + * @IEEE80211_CHAN_16MHZ: 16 MHz bandwidth is permitted + * on this channel. * */ enum ieee80211_channel_flags { @@ -113,6 +123,11 @@ enum ieee80211_channel_flags { IEEE80211_CHAN_NO_20MHZ = 1<<11, IEEE80211_CHAN_NO_10MHZ = 1<<12, IEEE80211_CHAN_NO_HE = 1<<13, + IEEE80211_CHAN_1MHZ = 1<<14, + IEEE80211_CHAN_2MHZ = 1<<15, + IEEE80211_CHAN_4MHZ = 1<<16, + IEEE80211_CHAN_8MHZ = 1<<17, + IEEE80211_CHAN_16MHZ = 1<<18, }; #define IEEE80211_CHAN_NO_HT40 \ @@ -254,13 +269,23 @@ struct ieee80211_rate { * struct ieee80211_he_obss_pd - AP settings for spatial reuse * * @enable: is the feature enabled. + * @sr_ctrl: The SR Control field of SRP element. + * @non_srg_max_offset: non-SRG maximum tx power offset * @min_offset: minimal tx power offset an associated station shall use * @max_offset: maximum tx power offset an associated station shall use + * @bss_color_bitmap: bitmap that indicates the BSS color values used by + * members of the SRG + * @partial_bssid_bitmap: bitmap that indicates the partial BSSID values + * used by members of the SRG */ struct ieee80211_he_obss_pd { bool enable; + u8 sr_ctrl; + u8 non_srg_max_offset; u8 min_offset; u8 max_offset; + u8 bss_color_bitmap[8]; + u8 partial_bssid_bitmap[8]; }; /** @@ -449,7 +474,9 @@ struct ieee80211_sta_s1g_cap { * @n_bitrates: Number of bitrates in @bitrates * @ht_cap: HT capabilities in this band * @vht_cap: VHT capabilities in this band + * @s1g_cap: S1G capabilities in this band * @edmg_cap: EDMG capabilities in this band + * @s1g_cap: S1G capabilities in this band (S1B band only, of course) * @n_iftype_data: number of iftype data entries * @iftype_data: interface type data entries. Note that the bits in * @types_mask inside this structure cannot overlap (i.e. only @@ -678,7 +705,10 @@ struct cfg80211_bitrate_mask { u32 legacy; u8 ht_mcs[IEEE80211_HT_MCS_MASK_LEN]; u16 vht_mcs[NL80211_VHT_NSS_MAX]; + u16 he_mcs[NL80211_HE_NSS_MAX]; enum nl80211_txrate_gi gi; + enum nl80211_he_gi he_gi; + enum nl80211_he_ltf he_ltf; } control[NUM_NL80211_BANDS]; }; @@ -1065,6 +1095,39 @@ struct cfg80211_acl_data { }; /** + * struct cfg80211_fils_discovery - FILS discovery parameters from + * IEEE Std 802.11ai-2016, Annex C.3 MIB detail. + * + * @min_interval: Minimum packet interval in TUs (0 - 10000) + * @max_interval: Maximum packet interval in TUs (0 - 10000) + * @tmpl_len: Template length + * @tmpl: Template data for FILS discovery frame including the action + * frame headers. + */ +struct cfg80211_fils_discovery { + u32 min_interval; + u32 max_interval; + size_t tmpl_len; + const u8 *tmpl; +}; + +/** + * struct cfg80211_unsol_bcast_probe_resp - Unsolicited broadcast probe + * response parameters in 6GHz. + * + * @interval: Packet interval in TUs. Maximum allowed is 20 TU, as mentioned + * in IEEE P802.11ax/D6.0 26.17.2.3.2 - AP behavior for fast passive + * scanning + * @tmpl_len: Template length + * @tmpl: Template data for probe response + */ +struct cfg80211_unsol_bcast_probe_resp { + u32 interval; + size_t tmpl_len; + const u8 *tmpl; +}; + +/** * enum cfg80211_ap_settings_flags - AP settings flags * * Used by cfg80211_ap_settings @@ -1111,6 +1174,8 @@ enum cfg80211_ap_settings_flags { * @he_obss_pd: OBSS Packet Detection settings * @he_bss_color: BSS Color settings * @he_oper: HE operation IE (or %NULL if HE isn't enabled) + * @fils_discovery: FILS discovery transmission parameters + * @unsol_bcast_probe_resp: Unsolicited broadcast probe response parameters */ struct cfg80211_ap_settings { struct cfg80211_chan_def chandef; @@ -1141,6 +1206,8 @@ struct cfg80211_ap_settings { u32 flags; struct ieee80211_he_obss_pd he_obss_pd; struct cfg80211_he_bss_color he_bss_color; + struct cfg80211_fils_discovery fils_discovery; + struct cfg80211_unsol_bcast_probe_resp unsol_bcast_probe_resp; }; /** @@ -1784,6 +1851,7 @@ struct mpath_info { * (or NULL for no change) * @basic_rates_len: number of basic rates * @ap_isolate: do not forward packets between connected stations + * (0 = no, 1 = yes, -1 = do not change) * @ht_opmode: HT Operation mode * (u16 = opmode, -1 = do not change) * @p2p_ctwindow: P2P CT Window (-1 = no change) @@ -2039,6 +2107,27 @@ struct cfg80211_scan_info { }; /** + * struct cfg80211_scan_6ghz_params - relevant for 6 GHz only + * + * @short_bssid: short ssid to scan for + * @bssid: bssid to scan for + * @channel_idx: idx of the channel in the channel array in the scan request + * which the above info relvant to + * @unsolicited_probe: the AP transmits unsolicited probe response every 20 TU + * @short_ssid_valid: short_ssid is valid and can be used + * @psc_no_listen: when set, and the channel is a PSC channel, no need to wait + * 20 TUs before starting to send probe requests. + */ +struct cfg80211_scan_6ghz_params { + u32 short_ssid; + u32 channel_idx; + u8 bssid[ETH_ALEN]; + bool unsolicited_probe; + bool short_ssid_valid; + bool psc_no_listen; +}; + +/** * struct cfg80211_scan_request - scan request description * * @ssids: SSIDs to scan for (active scan only) @@ -2065,6 +2154,10 @@ struct cfg80211_scan_info { * @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 + * @scan_6ghz: relevant for split scan request only, + * true if this is the second scan request + * @n_6ghz_params: number of 6 GHz params + * @scan_6ghz_params: 6 GHz params * @bssid: BSSID to scan for (most commonly, the wildcard BSSID) */ struct cfg80211_scan_request { @@ -2092,6 +2185,9 @@ struct cfg80211_scan_request { struct cfg80211_scan_info info; bool notified; bool no_cck; + bool scan_6ghz; + u32 n_6ghz_params; + struct cfg80211_scan_6ghz_params *scan_6ghz_params; /* keep last */ struct ieee80211_channel *channels[]; @@ -2471,6 +2567,8 @@ enum cfg80211_assoc_req_flags { * @fils_nonces: FILS nonces (part of AAD) for protecting (Re)Association * Request/Response frame or %NULL if FILS is not used. This field starts * with 16 octets of STA Nonce followed by 16 octets of AP Nonce. + * @s1g_capa: S1G capability override + * @s1g_capa_mask: S1G capability override mask */ struct cfg80211_assoc_request { struct cfg80211_bss *bss; @@ -2485,6 +2583,7 @@ struct cfg80211_assoc_request { const u8 *fils_kek; size_t fils_kek_len; const u8 *fils_nonces; + struct ieee80211_s1g_cap s1g_capa, s1g_capa_mask; }; /** @@ -4160,6 +4259,8 @@ struct cfg80211_ops { /** * enum wiphy_flags - wiphy capability flags * + * @WIPHY_FLAG_SPLIT_SCAN_6GHZ: if set to true, the scan request will be split + * into two, first for legacy bands and second for UHB. * @WIPHY_FLAG_NETNS_OK: if not set, do not allow changing the netns of this * wiphy at all * @WIPHY_FLAG_PS_ON_BY_DEFAULT: if set to true, powersave will be enabled @@ -4203,7 +4304,7 @@ struct cfg80211_ops { enum wiphy_flags { WIPHY_FLAG_SUPPORTS_EXT_KEK_KCK = BIT(0), /* use hole at 1 */ - /* use hole at 2 */ + WIPHY_FLAG_SPLIT_SCAN_6GHZ = BIT(2), WIPHY_FLAG_NETNS_OK = BIT(3), WIPHY_FLAG_PS_ON_BY_DEFAULT = BIT(4), WIPHY_FLAG_4ADDR_AP = BIT(5), @@ -5276,6 +5377,16 @@ ieee80211_channel_to_khz(const struct ieee80211_channel *chan) } /** + * ieee80211_s1g_channel_width - get allowed channel width from @chan + * + * Only allowed for band NL80211_BAND_S1GHZ + * @chan: channel + * Return: The allowed channel width for this center_freq + */ +enum nl80211_chan_width +ieee80211_s1g_channel_width(const struct ieee80211_channel *chan); + +/** * ieee80211_channel_to_freq_khz - convert channel number to frequency * @chan: channel number * @band: band, necessary due to channel number overlap diff --git a/include/net/checksum.h b/include/net/checksum.h index 46754ba9d7b7..0d05b9e8690b 100644 --- a/include/net/checksum.h +++ b/include/net/checksum.h @@ -24,26 +24,32 @@ #ifndef _HAVE_ARCH_COPY_AND_CSUM_FROM_USER static inline __wsum csum_and_copy_from_user (const void __user *src, void *dst, - int len, __wsum sum, int *err_ptr) + int len) { if (copy_from_user(dst, src, len)) - *err_ptr = -EFAULT; - return csum_partial(dst, len, sum); + return 0; + return csum_partial(dst, len, ~0U); } #endif #ifndef HAVE_CSUM_COPY_USER static __inline__ __wsum csum_and_copy_to_user -(const void *src, void __user *dst, int len, __wsum sum, int *err_ptr) +(const void *src, void __user *dst, int len) { - sum = csum_partial(src, len, sum); + __wsum sum = csum_partial(src, len, ~0U); if (copy_to_user(dst, src, len) == 0) return sum; - if (len) - *err_ptr = -EFAULT; + return 0; +} +#endif - return (__force __wsum)-1; /* invalid checksum */ +#ifndef _HAVE_ARCH_CSUM_AND_COPY +static inline __wsum +csum_partial_copy_nocheck(const void *src, void *dst, int len) +{ + memcpy(dst, src, len); + return csum_partial(dst, len, 0); } #endif diff --git a/include/net/devlink.h b/include/net/devlink.h index 8f3c8a443238..b01bb9bca5a2 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -20,6 +20,14 @@ #include <uapi/linux/devlink.h> #include <linux/xarray.h> +#define DEVLINK_RELOAD_STATS_ARRAY_SIZE \ + (__DEVLINK_RELOAD_LIMIT_MAX * __DEVLINK_RELOAD_ACTION_MAX) + +struct devlink_dev_stats { + u32 reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; + u32 remote_reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; +}; + struct devlink_ops; struct devlink { @@ -38,6 +46,7 @@ struct devlink { struct list_head trap_policer_list; const struct devlink_ops *ops; struct xarray snapshot_ids; + struct devlink_dev_stats stats; struct device *dev; possible_net_t _net; struct mutex lock; /* Serializes access to devlink instance specific objects such as @@ -57,13 +66,30 @@ struct devlink_port_phys_attrs { u32 split_subport_number; /* If the port is split, this is the number of subport. */ }; +/** + * struct devlink_port_pci_pf_attrs - devlink port's PCI PF attributes + * @controller: Associated controller number + * @pf: Associated PCI PF number for this port. + * @external: when set, indicates if a port is for an external controller + */ struct devlink_port_pci_pf_attrs { - u16 pf; /* Associated PCI PF for this port. */ + u32 controller; + u16 pf; + u8 external:1; }; +/** + * struct devlink_port_pci_vf_attrs - devlink port's PCI VF attributes + * @controller: Associated controller number + * @pf: Associated PCI PF number for this port. + * @vf: Associated PCI VF for of the PCI PF for this port. + * @external: when set, indicates if a port is for an external controller + */ struct devlink_port_pci_vf_attrs { - u16 pf; /* Associated PCI PF for this port. */ - u16 vf; /* Associated PCI VF for of the PCI PF for this port. */ + u32 controller; + u16 pf; + u16 vf; + u8 external:1; }; /** @@ -73,6 +99,9 @@ struct devlink_port_pci_vf_attrs { * @splittable: indicates if the port can be split. * @lanes: maximum number of lanes the port supports. 0 value is not passed to netlink. * @switch_id: if the port is part of switch, this is buffer with ID, otherwise this is NULL + * @phys: physical port attributes + * @pci_pf: PCI PF port attributes + * @pci_vf: PCI VF port attributes */ struct devlink_port_attrs { u8 split:1, @@ -90,6 +119,7 @@ struct devlink_port_attrs { struct devlink_port { struct list_head list; struct list_head param_list; + struct list_head region_list; struct devlink *devlink; unsigned int index; bool registered; @@ -372,6 +402,25 @@ struct devlink_param_gset_ctx { }; /** + * struct devlink_flash_notify - devlink dev flash notify data + * @status_msg: current status string + * @component: firmware component being updated + * @done: amount of work completed of total amount + * @total: amount of work expected to be done + * @timeout: expected max timeout in seconds + * + * These are values to be given to userland to be displayed in order + * to show current activity in a firmware update process. + */ +struct devlink_flash_notify { + const char *status_msg; + const char *component; + unsigned long done; + unsigned long total; + unsigned long timeout; +}; + +/** * struct devlink_param - devlink configuration parameter data * @name: name of the parameter * @generic: indicates if the parameter is generic or driver specific @@ -420,6 +469,7 @@ enum devlink_param_generic_id { DEVLINK_PARAM_GENERIC_ID_FW_LOAD_POLICY, DEVLINK_PARAM_GENERIC_ID_RESET_DEV_ON_DRV_PROBE, DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE, + DEVLINK_PARAM_GENERIC_ID_ENABLE_REMOTE_DEV_RESET, /* add new param generic ids above here*/ __DEVLINK_PARAM_GENERIC_ID_MAX, @@ -457,6 +507,9 @@ enum devlink_param_generic_id { #define DEVLINK_PARAM_GENERIC_ENABLE_ROCE_NAME "enable_roce" #define DEVLINK_PARAM_GENERIC_ENABLE_ROCE_TYPE DEVLINK_PARAM_TYPE_BOOL +#define DEVLINK_PARAM_GENERIC_ENABLE_REMOTE_DEV_RESET_NAME "enable_remote_dev_reset" +#define DEVLINK_PARAM_GENERIC_ENABLE_REMOTE_DEV_RESET_TYPE DEVLINK_PARAM_TYPE_BOOL + #define DEVLINK_PARAM_GENERIC(_id, _cmodes, _get, _set, _validate) \ { \ .id = DEVLINK_PARAM_GENERIC_ID_##_id, \ @@ -511,6 +564,24 @@ enum devlink_param_generic_id { /* Firmware bundle identifier */ #define DEVLINK_INFO_VERSION_GENERIC_FW_BUNDLE_ID "fw.bundle_id" +/** + * struct devlink_flash_update_params - Flash Update parameters + * @file_name: the name of the flash firmware file to update from + * @component: the flash component to update + * + * With the exception of file_name, drivers must opt-in to parameters by + * setting the appropriate bit in the supported_flash_update_params field in + * their devlink_ops structure. + */ +struct devlink_flash_update_params { + const char *file_name; + const char *component; + u32 overwrite_mask; +}; + +#define DEVLINK_SUPPORT_FLASH_UPDATE_COMPONENT BIT(0) +#define DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK BIT(1) + struct devlink_region; struct devlink_info_req; @@ -522,12 +593,36 @@ struct devlink_info_req; * the data variable must be updated to point to the snapshot data. * The function will be called while the devlink instance lock is * held. + * @priv: Pointer to driver private data for the region operation */ struct devlink_region_ops { const char *name; void (*destructor)(const void *data); - int (*snapshot)(struct devlink *devlink, struct netlink_ext_ack *extack, + int (*snapshot)(struct devlink *devlink, + const struct devlink_region_ops *ops, + struct netlink_ext_ack *extack, u8 **data); + void *priv; +}; + +/** + * struct devlink_port_region_ops - Region operations for a port + * @name: region name + * @destructor: callback used to free snapshot memory when deleting + * @snapshot: callback to request an immediate snapshot. On success, + * the data variable must be updated to point to the snapshot data. + * The function will be called while the devlink instance lock is + * held. + * @priv: Pointer to driver private data for the region operation + */ +struct devlink_port_region_ops { + const char *name; + void (*destructor)(const void *data); + int (*snapshot)(struct devlink_port *port, + const struct devlink_port_region_ops *ops, + struct netlink_ext_ack *extack, + u8 **data); + void *priv; }; struct devlink_fmsg; @@ -546,6 +641,7 @@ enum devlink_health_reporter_state { * @dump: callback to dump an object * if priv_ctx is NULL, run a full dump * @diagnose: callback to diagnose the current status + * @test: callback to trigger a test event */ struct devlink_health_reporter_ops { @@ -558,6 +654,24 @@ struct devlink_health_reporter_ops { int (*diagnose)(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg, struct netlink_ext_ack *extack); + int (*test)(struct devlink_health_reporter *reporter, + struct netlink_ext_ack *extack); +}; + +/** + * struct devlink_trap_metadata - Packet trap metadata. + * @trap_name: Trap name. + * @trap_group_name: Trap group name. + * @input_dev: Input netdevice. + * @fa_cookie: Flow action user cookie. + * @trap_type: Trap type. + */ +struct devlink_trap_metadata { + const char *trap_name; + const char *trap_group_name; + struct net_device *input_dev; + const struct flow_action_cookie *fa_cookie; + enum devlink_trap_type trap_type; }; /** @@ -704,6 +818,22 @@ enum devlink_trap_generic_id { DEVLINK_TRAP_GENERIC_ID_FLOW_ACTION_SAMPLE, DEVLINK_TRAP_GENERIC_ID_FLOW_ACTION_TRAP, DEVLINK_TRAP_GENERIC_ID_EARLY_DROP, + DEVLINK_TRAP_GENERIC_ID_VXLAN_PARSING, + DEVLINK_TRAP_GENERIC_ID_LLC_SNAP_PARSING, + DEVLINK_TRAP_GENERIC_ID_VLAN_PARSING, + DEVLINK_TRAP_GENERIC_ID_PPPOE_PPP_PARSING, + DEVLINK_TRAP_GENERIC_ID_MPLS_PARSING, + DEVLINK_TRAP_GENERIC_ID_ARP_PARSING, + DEVLINK_TRAP_GENERIC_ID_IP_1_PARSING, + DEVLINK_TRAP_GENERIC_ID_IP_N_PARSING, + DEVLINK_TRAP_GENERIC_ID_GRE_PARSING, + DEVLINK_TRAP_GENERIC_ID_UDP_PARSING, + DEVLINK_TRAP_GENERIC_ID_TCP_PARSING, + DEVLINK_TRAP_GENERIC_ID_IPSEC_PARSING, + DEVLINK_TRAP_GENERIC_ID_SCTP_PARSING, + DEVLINK_TRAP_GENERIC_ID_DCCP_PARSING, + DEVLINK_TRAP_GENERIC_ID_GTP_PARSING, + DEVLINK_TRAP_GENERIC_ID_ESP_PARSING, /* Add new generic trap IDs above */ __DEVLINK_TRAP_GENERIC_ID_MAX, @@ -739,6 +869,7 @@ enum devlink_trap_group_generic_id { DEVLINK_TRAP_GROUP_GENERIC_ID_PTP_GENERAL, DEVLINK_TRAP_GROUP_GENERIC_ID_ACL_SAMPLE, DEVLINK_TRAP_GROUP_GENERIC_ID_ACL_TRAP, + DEVLINK_TRAP_GROUP_GENERIC_ID_PARSER_ERROR_DROPS, /* Add new generic trap group IDs above */ __DEVLINK_TRAP_GROUP_GENERIC_ID_MAX, @@ -894,6 +1025,39 @@ enum devlink_trap_group_generic_id { "flow_action_trap" #define DEVLINK_TRAP_GENERIC_NAME_EARLY_DROP \ "early_drop" +#define DEVLINK_TRAP_GENERIC_NAME_VXLAN_PARSING \ + "vxlan_parsing" +#define DEVLINK_TRAP_GENERIC_NAME_LLC_SNAP_PARSING \ + "llc_snap_parsing" +#define DEVLINK_TRAP_GENERIC_NAME_VLAN_PARSING \ + "vlan_parsing" +#define DEVLINK_TRAP_GENERIC_NAME_PPPOE_PPP_PARSING \ + "pppoe_ppp_parsing" +#define DEVLINK_TRAP_GENERIC_NAME_MPLS_PARSING \ + "mpls_parsing" +#define DEVLINK_TRAP_GENERIC_NAME_ARP_PARSING \ + "arp_parsing" +#define DEVLINK_TRAP_GENERIC_NAME_IP_1_PARSING \ + "ip_1_parsing" +#define DEVLINK_TRAP_GENERIC_NAME_IP_N_PARSING \ + "ip_n_parsing" +#define DEVLINK_TRAP_GENERIC_NAME_GRE_PARSING \ + "gre_parsing" +#define DEVLINK_TRAP_GENERIC_NAME_UDP_PARSING \ + "udp_parsing" +#define DEVLINK_TRAP_GENERIC_NAME_TCP_PARSING \ + "tcp_parsing" +#define DEVLINK_TRAP_GENERIC_NAME_IPSEC_PARSING \ + "ipsec_parsing" +#define DEVLINK_TRAP_GENERIC_NAME_SCTP_PARSING \ + "sctp_parsing" +#define DEVLINK_TRAP_GENERIC_NAME_DCCP_PARSING \ + "dccp_parsing" +#define DEVLINK_TRAP_GENERIC_NAME_GTP_PARSING \ + "gtp_parsing" +#define DEVLINK_TRAP_GENERIC_NAME_ESP_PARSING \ + "esp_parsing" + #define DEVLINK_TRAP_GROUP_GENERIC_NAME_L2_DROPS \ "l2_drops" @@ -945,6 +1109,8 @@ enum devlink_trap_group_generic_id { "acl_sample" #define DEVLINK_TRAP_GROUP_GENERIC_NAME_ACL_TRAP \ "acl_trap" +#define DEVLINK_TRAP_GROUP_GENERIC_NAME_PARSER_ERROR_DROPS \ + "parser_error_drops" #define DEVLINK_TRAP_GENERIC(_type, _init_action, _id, _group_id, \ _metadata_cap) \ @@ -991,9 +1157,20 @@ enum devlink_trap_group_generic_id { } struct devlink_ops { + /** + * @supported_flash_update_params: + * mask of parameters supported by the driver's .flash_update + * implemementation. + */ + u32 supported_flash_update_params; + unsigned long reload_actions; + unsigned long reload_limits; int (*reload_down)(struct devlink *devlink, bool netns_change, + enum devlink_reload_action action, + enum devlink_reload_limit limit, struct netlink_ext_ack *extack); - int (*reload_up)(struct devlink *devlink, + int (*reload_up)(struct devlink *devlink, enum devlink_reload_action action, + enum devlink_reload_limit limit, u32 *actions_performed, struct netlink_ext_ack *extack); int (*port_type_set)(struct devlink_port *devlink_port, enum devlink_port_type port_type); @@ -1051,8 +1228,15 @@ struct devlink_ops { struct netlink_ext_ack *extack); int (*info_get)(struct devlink *devlink, struct devlink_info_req *req, struct netlink_ext_ack *extack); - int (*flash_update)(struct devlink *devlink, const char *file_name, - const char *component, + /** + * @flash_update: Device flash update function + * + * Used to perform a flash update for the device. The set of + * parameters supported by the driver should be set in + * supported_flash_update_params. + */ + int (*flash_update)(struct devlink *devlink, + struct devlink_flash_update_params *params, struct netlink_ext_ack *extack); /** * @trap_init: Trap initialization function. @@ -1098,6 +1282,16 @@ struct devlink_ops { const struct devlink_trap_policer *policer, struct netlink_ext_ack *extack); /** + * @trap_group_action_set: Trap group action set function. + * + * If this callback is populated, it will take precedence over looping + * over all traps in a group and calling .trap_action_set(). + */ + int (*trap_group_action_set)(struct devlink *devlink, + const struct devlink_trap_group *group, + enum devlink_trap_action action, + struct netlink_ext_ack *extack); + /** * @trap_policer_init: Trap policer initialization function. * * Should be used by device drivers to initialize the trap policer in @@ -1203,9 +1397,10 @@ void devlink_port_type_ib_set(struct devlink_port *devlink_port, void devlink_port_type_clear(struct devlink_port *devlink_port); void devlink_port_attrs_set(struct devlink_port *devlink_port, struct devlink_port_attrs *devlink_port_attrs); -void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u16 pf); -void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, - u16 pf, u16 vf); +void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u32 controller, + u16 pf, bool external); +void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 controller, + u16 pf, u16 vf, bool external); 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, @@ -1289,7 +1484,13 @@ struct devlink_region * devlink_region_create(struct devlink *devlink, const struct devlink_region_ops *ops, u32 region_max_snapshots, u64 region_size); +struct devlink_region * +devlink_port_region_create(struct devlink_port *port, + const struct devlink_port_region_ops *ops, + u32 region_max_snapshots, u64 region_size); void devlink_region_destroy(struct devlink_region *region); +void devlink_port_region_destroy(struct devlink_region *region); + int devlink_region_snapshot_id_get(struct devlink *devlink, u32 *id); void devlink_region_snapshot_id_put(struct devlink *devlink, u32 id); int devlink_region_snapshot_create(struct devlink_region *region, @@ -1371,6 +1572,9 @@ void devlink_health_reporter_recovery_done(struct devlink_health_reporter *reporter); bool devlink_is_reload_failed(const struct devlink *devlink); +void devlink_remote_reload_actions_performed(struct devlink *devlink, + enum devlink_reload_limit limit, + u32 actions_performed); void devlink_flash_update_begin_notify(struct devlink *devlink); void devlink_flash_update_end_notify(struct devlink *devlink); @@ -1379,6 +1583,10 @@ void devlink_flash_update_status_notify(struct devlink *devlink, const char *component, unsigned long done, unsigned long total); +void devlink_flash_update_timeout_notify(struct devlink *devlink, + const char *status_msg, + const char *component, + unsigned long timeout); int devlink_traps_register(struct devlink *devlink, const struct devlink_trap *traps, diff --git a/include/net/drop_monitor.h b/include/net/drop_monitor.h deleted file mode 100644 index 3f5b6ddb3179..000000000000 --- a/include/net/drop_monitor.h +++ /dev/null @@ -1,36 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ - -#ifndef _NET_DROP_MONITOR_H_ -#define _NET_DROP_MONITOR_H_ - -#include <linux/ktime.h> -#include <linux/netdevice.h> -#include <linux/skbuff.h> -#include <net/flow_offload.h> - -/** - * struct net_dm_hw_metadata - Hardware-supplied packet metadata. - * @trap_group_name: Hardware trap group name. - * @trap_name: Hardware trap name. - * @input_dev: Input netdevice. - * @fa_cookie: Flow action user cookie. - */ -struct net_dm_hw_metadata { - const char *trap_group_name; - const char *trap_name; - struct net_device *input_dev; - const struct flow_action_cookie *fa_cookie; -}; - -#if IS_REACHABLE(CONFIG_NET_DROP_MONITOR) -void net_dm_hw_report(struct sk_buff *skb, - const struct net_dm_hw_metadata *hw_metadata); -#else -static inline void -net_dm_hw_report(struct sk_buff *skb, - const struct net_dm_hw_metadata *hw_metadata) -{ -} -#endif - -#endif /* _NET_DROP_MONITOR_H_ */ diff --git a/include/net/dsa.h b/include/net/dsa.h index 75c8fac82017..35429a140dfa 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -74,8 +74,8 @@ struct dsa_device_ops { struct sk_buff *(*xmit)(struct sk_buff *skb, struct net_device *dev); struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt); - int (*flow_dissect)(const struct sk_buff *skb, __be16 *proto, - int *offset); + void (*flow_dissect)(const struct sk_buff *skb, __be16 *proto, + int *offset); /* Used to determine which traffic should match the DSA filter in * eth_type_trans, and which, if any, should bypass it and be processed * as regular on the master net device. @@ -84,6 +84,13 @@ struct dsa_device_ops { unsigned int overhead; const char *name; enum dsa_tag_protocol proto; + /* Some tagging protocols either mangle or shift the destination MAC + * address, in which case the DSA master would drop packets on ingress + * if what it understands out of the destination MAC address is not in + * its RX filter. + */ + bool promisc_on_master; + bool tail_tag; }; /* This structure defines the control interfaces that are overlayed by the @@ -208,6 +215,7 @@ struct dsa_port { u8 stp_state; struct net_device *bridge_dev; struct devlink_port devlink_port; + bool devlink_port_setup; struct phylink *pl; struct phylink_config pl_config; @@ -301,6 +309,14 @@ struct dsa_switch { */ bool configure_vlan_while_not_filtering; + /* If the switch driver always programs the CPU port as egress tagged + * despite the VLAN configuration indicating otherwise, then setting + * @untag_bridge_pvid will force the DSA receive path to pop the bridge's + * default_pvid VLAN tagged frames to offer a consistent behavior + * between a vlan_filtering=0 and vlan_filtering=1 bridge device. + */ + bool untag_bridge_pvid; + /* In case vlan_filtering_is_global is set, the VLAN awareness state * should be retrieved from here and not from the per-port settings. */ @@ -536,7 +552,8 @@ struct dsa_switch_ops { * VLAN support */ int (*port_vlan_filtering)(struct dsa_switch *ds, int port, - bool vlan_filtering); + bool vlan_filtering, + struct switchdev_trans *trans); int (*port_vlan_prepare)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan); void (*port_vlan_add)(struct dsa_switch *ds, int port, @@ -612,11 +629,14 @@ struct dsa_switch_ops { bool (*port_rxtstamp)(struct dsa_switch *ds, int port, struct sk_buff *skb, unsigned int type); - /* Devlink parameters */ + /* Devlink parameters, etc */ int (*devlink_param_get)(struct dsa_switch *ds, u32 id, struct devlink_param_gset_ctx *ctx); int (*devlink_param_set)(struct dsa_switch *ds, u32 id, struct devlink_param_gset_ctx *ctx); + int (*devlink_info_get)(struct dsa_switch *ds, + struct devlink_info_req *req, + struct netlink_ext_ack *extack); /* * MTU change functionality. Switches can also adjust their MRU through @@ -658,12 +678,44 @@ void dsa_devlink_resource_occ_get_register(struct dsa_switch *ds, void *occ_get_priv); void dsa_devlink_resource_occ_get_unregister(struct dsa_switch *ds, u64 resource_id); +struct devlink_region * +dsa_devlink_region_create(struct dsa_switch *ds, + const struct devlink_region_ops *ops, + u32 region_max_snapshots, u64 region_size); +struct devlink_region * +dsa_devlink_port_region_create(struct dsa_switch *ds, + int port, + const struct devlink_port_region_ops *ops, + u32 region_max_snapshots, u64 region_size); +void dsa_devlink_region_destroy(struct devlink_region *region); + struct dsa_port *dsa_port_from_netdev(struct net_device *netdev); struct dsa_devlink_priv { struct dsa_switch *ds; }; +static inline struct dsa_switch *dsa_devlink_to_ds(struct devlink *dl) +{ + struct dsa_devlink_priv *dl_priv = devlink_priv(dl); + + return dl_priv->ds; +} + +static inline +struct dsa_switch *dsa_devlink_port_to_ds(struct devlink_port *port) +{ + struct devlink *dl = port->devlink; + struct dsa_devlink_priv *dl_priv = devlink_priv(dl); + + return dl_priv->ds; +} + +static inline int dsa_devlink_port_to_port(struct devlink_port *port) +{ + return port->index; +} + struct dsa_switch_driver { struct list_head list; const struct dsa_switch_ops *ops; @@ -689,6 +741,32 @@ static inline bool dsa_can_decode(const struct sk_buff *skb, return false; } +/* All DSA tags that push the EtherType to the right (basically all except tail + * tags, which don't break dissection) can be treated the same from the + * perspective of the flow dissector. + * + * We need to return: + * - offset: the (B - A) difference between: + * A. the position of the real EtherType and + * B. the current skb->data (aka ETH_HLEN bytes into the frame, aka 2 bytes + * after the normal EtherType was supposed to be) + * The offset in bytes is exactly equal to the tagger overhead (and half of + * that, in __be16 shorts). + * + * - proto: the value of the real EtherType. + */ +static inline void dsa_tag_generic_flow_dissect(const struct sk_buff *skb, + __be16 *proto, int *offset) +{ +#if IS_ENABLED(CONFIG_NET_DSA) + const struct dsa_device_ops *ops = skb->dev->dsa_ptr->tag_ops; + int tag_len = ops->overhead; + + *offset = tag_len; + *proto = ((__be16 *)skb->data)[(tag_len / 2) - 1]; +#endif +} + #if IS_ENABLED(CONFIG_NET_DSA) static inline int __dsa_netdevice_ops_check(struct net_device *dev) { diff --git a/include/net/dst.h b/include/net/dst.h index 6ae2e625050d..8ea8812b0b41 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -214,7 +214,7 @@ dst_allfrag(const struct dst_entry *dst) static inline int dst_metric_locked(const struct dst_entry *dst, int metric) { - return dst_metric(dst, RTAX_LOCK) & (1<<metric); + return dst_metric(dst, RTAX_LOCK) & (1 << metric); } static inline void dst_hold(struct dst_entry *dst) diff --git a/include/net/flow.h b/include/net/flow.h index 929d3ca614d0..b2531df3f65f 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -116,6 +116,7 @@ static inline void flowi4_init_output(struct flowi4 *fl4, int oif, fl4->saddr = saddr; fl4->fl4_dport = dport; fl4->fl4_sport = sport; + fl4->flowi4_multipath_hash = 0; } /* Reset some input parameters after previous lookup */ diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 6e5f1e1aa822..e55ec1597ce7 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -41,6 +41,8 @@ struct genl_info; * (private) * @ops: the operations supported by this family * @n_ops: number of operations supported by this family + * @small_ops: the small-struct operations supported by this family + * @n_small_ops: number of small-struct operations supported by this family */ struct genl_family { int id; /* private */ @@ -48,8 +50,12 @@ struct genl_family { char name[GENL_NAMSIZ]; unsigned int version; unsigned int maxattr; - bool netnsok; - bool parallel_ops; + unsigned int mcgrp_offset; /* private */ + u8 netnsok:1; + u8 parallel_ops:1; + u8 n_ops; + u8 n_small_ops; + u8 n_mcgrps; const struct nla_policy *policy; int (*pre_doit)(const struct genl_ops *ops, struct sk_buff *skb, @@ -58,10 +64,8 @@ struct genl_family { struct sk_buff *skb, struct genl_info *info); const struct genl_ops * ops; + const struct genl_small_ops *small_ops; const struct genl_multicast_group *mcgrps; - unsigned int n_ops; - unsigned int n_mcgrps; - unsigned int mcgrp_offset; /* private */ struct module *module; }; @@ -101,14 +105,6 @@ static inline void genl_info_net_set(struct genl_info *info, struct net *net) #define GENL_SET_ERR_MSG(info, msg) NL_SET_ERR_MSG((info)->extack, msg) -static inline int genl_err_attr(struct genl_info *info, int err, - const struct nlattr *attr) -{ - info->extack->bad_attr = attr; - - return err; -} - enum genl_validate_flags { GENL_DONT_VALIDATE_STRICT = BIT(0), GENL_DONT_VALIDATE_DUMP = BIT(1), @@ -116,28 +112,34 @@ enum genl_validate_flags { }; /** - * struct genl_info - info that is available during dumpit op call - * @family: generic netlink family - for internal genl code usage - * @ops: generic netlink ops - for internal genl code usage - * @attrs: netlink attributes + * struct genl_small_ops - generic netlink operations (small version) + * @cmd: command identifier + * @internal_flags: flags used by the family + * @flags: flags + * @validate: validation flags from enum genl_validate_flags + * @doit: standard command callback + * @dumpit: callback for dumpers + * + * This is a cut-down version of struct genl_ops for users who don't need + * most of the ancillary infra and want to save space. */ -struct genl_dumpit_info { - const struct genl_family *family; - const struct genl_ops *ops; - struct nlattr **attrs; +struct genl_small_ops { + int (*doit)(struct sk_buff *skb, struct genl_info *info); + int (*dumpit)(struct sk_buff *skb, struct netlink_callback *cb); + u8 cmd; + u8 internal_flags; + u8 flags; + u8 validate; }; -static inline const struct genl_dumpit_info * -genl_dumpit_info(struct netlink_callback *cb) -{ - return cb->data; -} - /** * struct genl_ops - generic netlink operations * @cmd: command identifier * @internal_flags: flags used by the family * @flags: flags + * @maxattr: maximum number of attributes supported + * @policy: netlink policy (takes precedence over family policy) + * @validate: validation flags from enum genl_validate_flags * @doit: standard command callback * @start: start callback for dumps * @dumpit: callback for dumpers @@ -150,12 +152,32 @@ struct genl_ops { int (*dumpit)(struct sk_buff *skb, struct netlink_callback *cb); int (*done)(struct netlink_callback *cb); + const struct nla_policy *policy; + unsigned int maxattr; u8 cmd; u8 internal_flags; u8 flags; u8 validate; }; +/** + * struct genl_info - info that is available during dumpit op call + * @family: generic netlink family - for internal genl code usage + * @ops: generic netlink ops - for internal genl code usage + * @attrs: netlink attributes + */ +struct genl_dumpit_info { + const struct genl_family *family; + struct genl_ops op; + struct nlattr **attrs; +}; + +static inline const struct genl_dumpit_info * +genl_dumpit_info(struct netlink_callback *cb) +{ + return cb->data; +} + int genl_register_family(struct genl_family *family); int genl_unregister_family(const struct genl_family *family); void genl_notify(const struct genl_family *family, struct sk_buff *skb, diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index aa8893c68c50..7338b3865a2a 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -86,6 +86,8 @@ struct inet_connection_sock { struct timer_list icsk_retransmit_timer; struct timer_list icsk_delack_timer; __u32 icsk_rto; + __u32 icsk_rto_min; + __u32 icsk_delack_max; __u32 icsk_pmtu_cookie; const struct tcp_congestion_ops *icsk_ca_ops; const struct inet_connection_sock_af_ops *icsk_af_ops; @@ -94,7 +96,8 @@ struct inet_connection_sock { void (*icsk_clean_acked)(struct sock *sk, u32 acked_seq); struct hlist_node icsk_listen_portaddr_node; unsigned int (*icsk_sync_mss)(struct sock *sk, u32 pmtu); - __u8 icsk_ca_state:6, + __u8 icsk_ca_state:5, + icsk_ca_initialized:1, icsk_ca_setsockopt:1, icsk_ca_dst_locked:1; __u8 icsk_retransmits; @@ -107,7 +110,7 @@ struct inet_connection_sock { __u8 pending; /* ACK is pending */ __u8 quick; /* Scheduled number of quick acks */ __u8 pingpong; /* The session is interactive */ - __u8 blocked; /* Delayed ACK was blocked by socket lock */ + __u8 retry; /* Number of attempts */ __u32 ato; /* Predicted tick of soft clock */ unsigned long timeout; /* Currently scheduled timeout */ __u32 lrcvtime; /* timestamp of last received data packet */ @@ -195,7 +198,8 @@ static inline void inet_csk_clear_xmit_timer(struct sock *sk, const int what) sk_stop_timer(sk, &icsk->icsk_retransmit_timer); #endif } else if (what == ICSK_TIME_DACK) { - icsk->icsk_ack.blocked = icsk->icsk_ack.pending = 0; + icsk->icsk_ack.pending = 0; + icsk->icsk_ack.retry = 0; #ifdef INET_CSK_CLEAR_TIMERS sk_stop_timer(sk, &icsk->icsk_delack_timer); #endif diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index a3702d1d4875..89163ef8cf4b 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -296,13 +296,6 @@ static inline void __inet_sk_copy_descendant(struct sock *sk_to, memcpy(inet_sk(sk_to) + 1, inet_sk(sk_from) + 1, sk_from->sk_prot->obj_size - ancestor_size); } -#if !(IS_ENABLED(CONFIG_IPV6)) -static inline void inet_sk_copy_descendant(struct sock *sk_to, - const struct sock *sk_from) -{ - __inet_sk_copy_descendant(sk_to, sk_from, sizeof(struct inet_sock)); -} -#endif int inet_sk_rebuild_header(struct sock *sk); diff --git a/include/net/ip.h b/include/net/ip.h index b09c48d862cc..2d6b985d11cc 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -151,7 +151,7 @@ int igmp_mc_init(void); int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, __be32 saddr, __be32 daddr, - struct ip_options_rcu *opt); + struct ip_options_rcu *opt, u8 tos); int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); void ip_list_rcv(struct list_head *head, struct packet_type *pt, @@ -436,12 +436,18 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst, bool forwarding) { struct net *net = dev_net(dst->dev); + unsigned int mtu; if (net->ipv4.sysctl_ip_fwd_use_pmtu || ip_mtu_locked(dst) || !forwarding) return dst_mtu(dst); + /* 'forwarding = true' case should always honour route mtu */ + mtu = dst_metric_raw(dst, RTAX_MTU); + if (mtu) + return mtu; + return min(READ_ONCE(dst->dev->mtu), IP_MAX_MTU); } diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 9a59a33787cb..d609e957a3ec 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -25,9 +25,6 @@ #include <linux/ip.h> #include <linux/ipv6.h> /* for struct ipv6hdr */ #include <net/ipv6.h> -#if IS_ENABLED(CONFIG_IP_VS_IPV6) -#include <linux/netfilter_ipv6/ip6_tables.h> -#endif #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <net/netfilter/nf_conntrack.h> #endif diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h index d7a7f7c81e7b..8fce558b5fea 100644 --- a/include/net/ipv6_stubs.h +++ b/include/net/ipv6_stubs.h @@ -63,6 +63,9 @@ struct ipv6_stub { int encap_type); #endif struct neigh_table *nd_tbl; + + int (*ipv6_fragment)(struct net *net, struct sock *sk, struct sk_buff *skb, + int (*output)(struct net *, struct sock *, struct sk_buff *)); }; extern const struct ipv6_stub *ipv6_stub __read_mostly; diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 66e2bfd165e8..e8e295dae744 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -317,6 +317,9 @@ struct ieee80211_vif_chanctx_switch { * @BSS_CHANGED_TWT: TWT status changed * @BSS_CHANGED_HE_OBSS_PD: OBSS Packet Detection status changed. * @BSS_CHANGED_HE_BSS_COLOR: BSS Color has changed + * @BSS_CHANGED_FILS_DISCOVERY: FILS discovery status changed. + * @BSS_CHANGED_UNSOL_BCAST_PROBE_RESP: Unsolicited broadcast probe response + * status changed. * */ enum ieee80211_bss_change { @@ -350,6 +353,8 @@ enum ieee80211_bss_change { BSS_CHANGED_TWT = 1<<27, BSS_CHANGED_HE_OBSS_PD = 1<<28, BSS_CHANGED_HE_BSS_COLOR = 1<<29, + BSS_CHANGED_FILS_DISCOVERY = 1<<30, + BSS_CHANGED_UNSOL_BCAST_PROBE_RESP = 1<<31, /* when adding here, make sure to change ieee80211_reconfig */ }; @@ -491,6 +496,18 @@ struct ieee80211_ftm_responder_params { }; /** + * struct ieee80211_fils_discovery - FILS discovery parameters from + * IEEE Std 802.11ai-2016, Annex C.3 MIB detail. + * + * @min_interval: Minimum packet interval in TUs (0 - 10000) + * @max_interval: Maximum packet interval in TUs (0 - 10000) + */ +struct ieee80211_fils_discovery { + u32 min_interval; + u32 max_interval; +}; + +/** * struct ieee80211_bss_conf - holds the BSS's changing parameters * * This structure keeps information about a BSS (and an association @@ -607,6 +624,12 @@ struct ieee80211_ftm_responder_params { * @he_oper: HE operation information of the AP we are connected to * @he_obss_pd: OBSS Packet Detection parameters. * @he_bss_color: BSS coloring settings, if BSS supports HE + * @fils_discovery: FILS discovery configuration + * @unsol_bcast_probe_resp_interval: Unsolicited broadcast probe response + * interval. + * @s1g: BSS is S1G BSS (affects Association Request format). + * @beacon_tx_rate: The configured beacon transmit rate that needs to be passed + * to driver when rate control is offloaded to firmware. */ struct ieee80211_bss_conf { const u8 *bssid; @@ -674,6 +697,10 @@ struct ieee80211_bss_conf { } he_oper; struct ieee80211_he_obss_pd he_obss_pd; struct cfg80211_he_bss_color he_bss_color; + struct ieee80211_fils_discovery fils_discovery; + u32 unsol_bcast_probe_resp_interval; + bool s1g; + struct cfg80211_bitrate_mask beacon_tx_rate; }; /** @@ -720,9 +747,8 @@ struct ieee80211_bss_conf { * @IEEE80211_TX_INTFL_OFFCHAN_TX_OK: Internal to mac80211. Used to indicate * that a frame can be transmitted while the queues are stopped for * off-channel operation. - * @IEEE80211_TX_INTFL_NEED_TXPROCESSING: completely internal to mac80211, - * used to indicate that a pending frame requires TX processing before - * it can be sent out. + * @IEEE80211_TX_CTL_HW_80211_ENCAP: This frame uses hardware encapsulation + * (header conversion) * @IEEE80211_TX_INTFL_RETRIED: completely internal to mac80211, * used to indicate that a frame was already retried due to PS * @IEEE80211_TX_INTFL_DONT_ENCRYPT: completely internal to mac80211, @@ -791,7 +817,7 @@ enum mac80211_tx_info_flags { IEEE80211_TX_STAT_AMPDU_NO_BACK = BIT(11), IEEE80211_TX_CTL_RATE_CTRL_PROBE = BIT(12), IEEE80211_TX_INTFL_OFFCHAN_TX_OK = BIT(13), - IEEE80211_TX_INTFL_NEED_TXPROCESSING = BIT(14), + IEEE80211_TX_CTL_HW_80211_ENCAP = BIT(14), IEEE80211_TX_INTFL_RETRIED = BIT(15), IEEE80211_TX_INTFL_DONT_ENCRYPT = BIT(16), IEEE80211_TX_CTL_NO_PS_BUFFER = BIT(17), @@ -812,6 +838,8 @@ enum mac80211_tx_info_flags { #define IEEE80211_TX_CTL_STBC_SHIFT 23 +#define IEEE80211_TX_RC_S1G_MCS IEEE80211_TX_RC_VHT_MCS + /** * enum mac80211_tx_control_flags - flags to describe transmit control * @@ -823,8 +851,9 @@ enum mac80211_tx_info_flags { * @IEEE80211_TX_CTRL_AMSDU: This frame is an A-MSDU frame * @IEEE80211_TX_CTRL_FAST_XMIT: This frame is going through the fast_xmit path * @IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP: This frame skips mesh path lookup - * @IEEE80211_TX_CTRL_HW_80211_ENCAP: This frame uses hardware encapsulation - * (header conversion) + * @IEEE80211_TX_INTCFL_NEED_TXPROCESSING: completely internal to mac80211, + * used to indicate that a pending frame requires TX processing before + * it can be sent out. * @IEEE80211_TX_CTRL_NO_SEQNO: Do not overwrite the sequence number that * has already been assigned to this frame. * @@ -837,7 +866,7 @@ enum mac80211_tx_control_flags { IEEE80211_TX_CTRL_AMSDU = BIT(3), IEEE80211_TX_CTRL_FAST_XMIT = BIT(4), IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP = BIT(5), - IEEE80211_TX_CTRL_HW_80211_ENCAP = BIT(6), + IEEE80211_TX_INTCFL_NEED_TXPROCESSING = BIT(6), IEEE80211_TX_CTRL_NO_SEQNO = BIT(7), }; @@ -1002,7 +1031,8 @@ ieee80211_rate_get_vht_nss(const struct ieee80211_tx_rate *rate) * @status.ampdu_ack_len: AMPDU ack length * @status.ampdu_len: AMPDU length * @status.antenna: (legacy, kept only for iwlegacy) - * @status.tx_time: airtime consumed for transmission + * @status.tx_time: airtime consumed for transmission; note this is only + * used for WMM AC, not for airtime fairness * @status.is_valid_ack_signal: ACK signal is valid * @status.status_driver_data: driver use area * @ack: union part for pure ACK data @@ -1095,12 +1125,14 @@ ieee80211_info_get_tx_time_est(struct ieee80211_tx_info *info) * @info: Basic tx status information * @skb: Packet skb (can be NULL if not provided by the driver) * @rate: The TX rate that was used when sending the packet + * @free_list: list where processed skbs are stored to be free'd by the driver */ struct ieee80211_tx_status { struct ieee80211_sta *sta; struct ieee80211_tx_info *info; struct sk_buff *skb; struct rate_info *rate; + struct list_head *free_list; }; /** @@ -1606,6 +1638,21 @@ enum ieee80211_vif_flags { IEEE80211_VIF_GET_NOA_UPDATE = BIT(3), }; + +/** + * enum ieee80211_offload_flags - virtual interface offload flags + * + * @IEEE80211_OFFLOAD_ENCAP_ENABLED: tx encapsulation offload is enabled + * The driver supports sending frames passed as 802.3 frames by mac80211. + * It must also support sending 802.11 packets for the same interface. + * @IEEE80211_OFFLOAD_ENCAP_4ADDR: support 4-address mode encapsulation offload + */ + +enum ieee80211_offload_flags { + IEEE80211_OFFLOAD_ENCAP_ENABLED = BIT(0), + IEEE80211_OFFLOAD_ENCAP_4ADDR = BIT(1), +}; + /** * struct ieee80211_vif - per-interface data * @@ -1626,6 +1673,11 @@ enum ieee80211_vif_flags { * these need to be set (or cleared) when the interface is added * or, if supported by the driver, the interface type is changed * at runtime, mac80211 will never touch this field + * @offloaad_flags: hardware offload capabilities/flags for this interface. + * These are initialized by mac80211 before calling .add_interface, + * .change_interface or .update_vif_offload and updated by the driver + * within these ops, based on supported features or runtime change + * restrictions. * @hw_queue: hardware queue for each AC * @cab_queue: content-after-beacon (DTIM beacon really) queue, AP mode only * @chanctx_conf: The channel context this interface is assigned to, or %NULL @@ -1645,6 +1697,8 @@ enum ieee80211_vif_flags { * @txq: the multicast data TX queue (if driver uses the TXQ abstraction) * @txqs_stopped: per AC flag to indicate that intermediate TXQs are stopped, * protected by fq->lock. + * @offload_flags: 802.3 -> 802.11 enapsulation offload flags, see + * &enum ieee80211_offload_flags. */ struct ieee80211_vif { enum nl80211_iftype type; @@ -1662,6 +1716,7 @@ struct ieee80211_vif { struct ieee80211_chanctx_conf __rcu *chanctx_conf; u32 driver_flags; + u32 offload_flags; #ifdef CONFIG_MAC80211_DEBUGFS struct dentry *debugfs_dir; @@ -2328,6 +2383,9 @@ struct ieee80211_txq { * aggregating MPDUs with the same keyid, allowing mac80211 to keep Tx * A-MPDU sessions active while rekeying with Extended Key ID. * + * @IEEE80211_HW_SUPPORTS_TX_ENCAP_OFFLOAD: Hardware supports tx encapsulation + * offload + * * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ enum ieee80211_hw_flags { @@ -2380,6 +2438,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_SUPPORTS_MULTI_BSSID, IEEE80211_HW_SUPPORTS_ONLY_HE_MULTI_BSSID, IEEE80211_HW_AMPDU_KEYBORDER_SUPPORT, + IEEE80211_HW_SUPPORTS_TX_ENCAP_OFFLOAD, /* keep last, obviously */ NUM_IEEE80211_HW_FLAGS @@ -3736,7 +3795,7 @@ enum ieee80211_reconfig_type { * decremented, and when they reach 1 the driver must call * ieee80211_csa_finish(). Drivers which use ieee80211_beacon_get() * get the csa counter decremented by mac80211, but must check if it is - * 1 using ieee80211_csa_is_complete() after the beacon has been + * 1 using ieee80211_beacon_counter_is_complete() after the beacon has been * transmitted and then call ieee80211_csa_finish(). * If the CSA count starts as zero or 1, this function will not be called, * since there won't be any time to beacon before the switch anyway. @@ -3814,6 +3873,10 @@ enum ieee80211_reconfig_type { * @set_tid_config: Apply TID specific configurations. This callback may sleep. * @reset_tid_config: Reset TID specific configuration for the peer. * This callback may sleep. + * @update_vif_offload: Update virtual interface offload flags + * This callback may sleep. + * @sta_set_4addr: Called to notify the driver when a station starts/stops using + * 4-address mode */ struct ieee80211_ops { void (*tx)(struct ieee80211_hw *hw, @@ -4125,6 +4188,10 @@ struct ieee80211_ops { int (*reset_tid_config)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, u8 tids); + void (*update_vif_offload)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif); + void (*sta_set_4addr)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + struct ieee80211_sta *sta, bool enabled); }; /** @@ -4763,21 +4830,21 @@ void ieee80211_tx_status_8023(struct ieee80211_hw *hw, */ void ieee80211_report_low_ack(struct ieee80211_sta *sta, u32 num_packets); -#define IEEE80211_MAX_CSA_COUNTERS_NUM 2 +#define IEEE80211_MAX_CNTDWN_COUNTERS_NUM 2 /** * struct ieee80211_mutable_offsets - mutable beacon offsets * @tim_offset: position of TIM element * @tim_length: size of TIM element - * @csa_counter_offs: array of IEEE80211_MAX_CSA_COUNTERS_NUM offsets - * to CSA counters. This array can contain zero values which + * @cntdwn_counter_offs: array of IEEE80211_MAX_CNTDWN_COUNTERS_NUM offsets + * to countdown counters. This array can contain zero values which * should be ignored. */ struct ieee80211_mutable_offsets { u16 tim_offset; u16 tim_length; - u16 csa_counter_offs[IEEE80211_MAX_CSA_COUNTERS_NUM]; + u16 cntdwn_counter_offs[IEEE80211_MAX_CNTDWN_COUNTERS_NUM]; }; /** @@ -4846,31 +4913,31 @@ static inline struct sk_buff *ieee80211_beacon_get(struct ieee80211_hw *hw, } /** - * ieee80211_csa_update_counter - request mac80211 to decrement the csa counter + * ieee80211_beacon_update_cntdwn - request mac80211 to decrement the beacon countdown * @vif: &struct ieee80211_vif pointer from the add_interface callback. * - * The csa counter should be updated after each beacon transmission. + * The beacon counter should be updated after each beacon transmission. * This function is called implicitly when * ieee80211_beacon_get/ieee80211_beacon_get_tim are called, however if the * beacon frames are generated by the device, the driver should call this - * function after each beacon transmission to sync mac80211's csa counters. + * function after each beacon transmission to sync mac80211's beacon countdown. * - * Return: new csa counter value + * Return: new countdown value */ -u8 ieee80211_csa_update_counter(struct ieee80211_vif *vif); +u8 ieee80211_beacon_update_cntdwn(struct ieee80211_vif *vif); /** - * ieee80211_csa_set_counter - request mac80211 to set csa counter + * ieee80211_beacon_set_cntdwn - request mac80211 to set beacon countdown * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @counter: the new value for the counter * - * The csa counter can be changed by the device, this API should be + * The beacon countdown can be changed by the device, this API should be * used by the device driver to update csa counter in mac80211. * - * It should never be used together with ieee80211_csa_update_counter(), + * It should never be used together with ieee80211_beacon_update_cntdwn(), * as it will cause a race condition around the counter value. */ -void ieee80211_csa_set_counter(struct ieee80211_vif *vif, u8 counter); +void ieee80211_beacon_set_cntdwn(struct ieee80211_vif *vif, u8 counter); /** * ieee80211_csa_finish - notify mac80211 about channel switch @@ -4883,13 +4950,12 @@ void ieee80211_csa_set_counter(struct ieee80211_vif *vif, u8 counter); void ieee80211_csa_finish(struct ieee80211_vif *vif); /** - * ieee80211_csa_is_complete - find out if counters reached 1 + * ieee80211_beacon_cntdwn_is_complete - find out if countdown reached 1 * @vif: &struct ieee80211_vif pointer from the add_interface callback. * - * This function returns whether the channel switch counters reached zero. + * This function returns whether the countdown reached zero. */ -bool ieee80211_csa_is_complete(struct ieee80211_vif *vif); - +bool ieee80211_beacon_cntdwn_is_complete(struct ieee80211_vif *vif); /** * ieee80211_proberesp_get - retrieve a Probe Response template @@ -5344,11 +5410,15 @@ void ieee80211_sched_scan_stopped(struct ieee80211_hw *hw); * @IEEE80211_IFACE_ITER_RESUME_ALL: During resume, iterate over all * interfaces, even if they haven't been re-added to the driver yet. * @IEEE80211_IFACE_ITER_ACTIVE: Iterate only active interfaces (netdev is up). + * @IEEE80211_IFACE_SKIP_SDATA_NOT_IN_DRIVER: Skip any interfaces where SDATA + * is not in the driver. This may fix crashes during firmware recovery + * for instance. */ enum ieee80211_interface_iteration_flags { IEEE80211_IFACE_ITER_NORMAL = 0, IEEE80211_IFACE_ITER_RESUME_ALL = BIT(0), IEEE80211_IFACE_ITER_ACTIVE = BIT(1), + IEEE80211_IFACE_SKIP_SDATA_NOT_IN_DRIVER = BIT(2), }; /** @@ -5648,7 +5718,7 @@ void ieee80211_send_eosp_nullfunc(struct ieee80211_sta *pubsta, int tid); /** * ieee80211_sta_register_airtime - register airtime usage for a sta/tid * - * Register airtime usage for a given sta on a given tid. The driver can call + * Register airtime usage for a given sta on a given tid. The driver must call * this function to notify mac80211 that a station used a certain amount of * airtime. This information will be used by the TXQ scheduler to schedule * stations in a way that ensures airtime fairness. @@ -6594,4 +6664,29 @@ u32 ieee80211_calc_tx_airtime(struct ieee80211_hw *hw, */ bool ieee80211_set_hw_80211_encap(struct ieee80211_vif *vif, bool enable); +/** + * ieee80211_get_fils_discovery_tmpl - Get FILS discovery template. + * @hw: pointer obtained from ieee80211_alloc_hw(). + * @vif: &struct ieee80211_vif pointer from the add_interface callback. + * + * The driver is responsible for freeing the returned skb. + * + * Return: FILS discovery template. %NULL on error. + */ +struct sk_buff *ieee80211_get_fils_discovery_tmpl(struct ieee80211_hw *hw, + struct ieee80211_vif *vif); + +/** + * ieee80211_get_unsol_bcast_probe_resp_tmpl - Get unsolicited broadcast + * probe response template. + * @hw: pointer obtained from ieee80211_alloc_hw(). + * @vif: &struct ieee80211_vif pointer from the add_interface callback. + * + * The driver is responsible for freeing the returned skb. + * + * Return: Unsolicited broadcast probe response template. %NULL on error. + */ +struct sk_buff * +ieee80211_get_unsol_bcast_probe_resp_tmpl(struct ieee80211_hw *hw, + struct ieee80211_vif *vif); #endif /* MAC80211_H */ diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 3525d2822abe..753ba7e755d6 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -85,8 +85,7 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size, bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, unsigned int *size, unsigned int remaining, struct mptcp_out_options *opts); -void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb, - struct tcp_options_received *opt_rx); +void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb); void mptcp_write_options(__be32 *ptr, struct mptcp_out_options *opts); @@ -185,8 +184,7 @@ static inline bool mptcp_established_options(struct sock *sk, } static inline void mptcp_incoming_options(struct sock *sk, - struct sk_buff *skb, - struct tcp_options_received *opt_rx) + struct sk_buff *skb) { } diff --git a/include/net/ndisc.h b/include/net/ndisc.h index 9205a76d967a..38e4094960ce 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -494,7 +494,7 @@ int igmp6_event_report(struct sk_buff *skb); #ifdef CONFIG_SYSCTL int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); + void *buffer, size_t *lenp, loff_t *ppos); int ndisc_ifinfo_sysctl_strategy(struct ctl_table *ctl, void __user *oldval, size_t __user *oldlenp, void __user *newval, size_t newlen); diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 2ee5901bec7a..22bc07f4b043 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -230,7 +230,7 @@ extern struct list_head net_namespace_list; struct net *get_net_ns_by_pid(pid_t pid); struct net *get_net_ns_by_fd(int fd); -u64 net_gen_cookie(struct net *net); +u64 __net_gen_cookie(struct net *net); #ifdef CONFIG_SYSCTL void ipx_register_sysctl(void); diff --git a/include/net/netfilter/nf_log.h b/include/net/netfilter/nf_log.h index 0d3920896d50..716db4a0fed8 100644 --- a/include/net/netfilter/nf_log.h +++ b/include/net/netfilter/nf_log.h @@ -108,6 +108,7 @@ int nf_log_dump_tcp_header(struct nf_log_buf *m, const struct sk_buff *skb, unsigned int logflags); void nf_log_dump_sk_uid_gid(struct net *net, struct nf_log_buf *m, struct sock *sk); +void nf_log_dump_vlan(struct nf_log_buf *m, const struct sk_buff *skb); void nf_log_dump_packet_common(struct nf_log_buf *m, u_int8_t pf, unsigned int hooknum, const struct sk_buff *skb, const struct net_device *in, diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index bf9491b77d16..55b4cadf290a 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -14,6 +14,8 @@ #include <net/netlink.h> #include <net/flow_offload.h> +#define NFT_MAX_HOOKS (NF_INET_INGRESS + 1) + struct module; #define NFT_JUMP_STACK_SIZE 16 @@ -143,16 +145,11 @@ static inline u64 nft_reg_load64(const u32 *sreg) static inline void nft_data_copy(u32 *dst, const struct nft_data *src, unsigned int len) { + if (len % NFT_REG32_SIZE) + dst[len / NFT_REG32_SIZE] = 0; memcpy(dst, src, len); } -static inline void nft_data_debug(const struct nft_data *data) -{ - pr_debug("data[0]=%x data[1]=%x data[2]=%x data[3]=%x\n", - data->data[0], data->data[1], - data->data[2], data->data[3]); -} - /** * struct nft_ctx - nf_tables rule/set context * @@ -894,6 +891,12 @@ static inline struct nft_expr *nft_expr_last(const struct nft_rule *rule) return (struct nft_expr *)&rule->data[rule->dlen]; } +static inline bool nft_expr_more(const struct nft_rule *rule, + const struct nft_expr *expr) +{ + return expr != nft_expr_last(rule) && expr->ops; +} + static inline struct nft_userdata *nft_userdata(const struct nft_rule *rule) { return (void *)&rule->data[rule->dlen]; @@ -950,6 +953,8 @@ struct nft_chain { bound:1, genmask:2; char *name; + u16 udlen; + u8 *udata; /* Only used during control plane commit phase: */ struct nft_rule **rules_next; @@ -982,7 +987,7 @@ struct nft_chain_type { int family; struct module *owner; unsigned int hook_mask; - nf_hookfn *hooks[NF_MAX_HOOKS]; + nf_hookfn *hooks[NFT_MAX_HOOKS]; int (*ops_register)(struct net *net, const struct nf_hook_ops *ops); void (*ops_unregister)(struct net *net, const struct nf_hook_ops *ops); }; @@ -1080,8 +1085,16 @@ struct nft_table { flags:8, genmask:2; char *name; + u16 udlen; + u8 *udata; }; +static inline bool nft_base_chain_netdev(int family, u32 hooknum) +{ + return family == NFPROTO_NETDEV || + (family == NFPROTO_INET && hooknum == NF_INET_INGRESS); +} + void nft_register_chain_type(const struct nft_chain_type *); void nft_unregister_chain_type(const struct nft_chain_type *); @@ -1121,6 +1134,8 @@ struct nft_object { u32 genmask:2, use:30; u64 handle; + u16 udlen; + u8 *udata; /* runtime data below here */ const struct nft_object_ops *ops ____cacheline_aligned; unsigned char data[] diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index 78516de14d31..8657e6815b07 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -23,10 +23,19 @@ extern struct nft_object_type nft_secmark_obj_type; int nf_tables_core_module_init(void); void nf_tables_core_module_exit(void); +struct nft_bitwise_fast_expr { + u32 mask; + u32 xor; + enum nft_registers sreg:8; + enum nft_registers dreg:8; +}; + struct nft_cmp_fast_expr { u32 data; + u32 mask; enum nft_registers sreg:8; u8 len; + bool inv; }; struct nft_immediate_expr { @@ -66,6 +75,8 @@ struct nft_payload_set { extern const struct nft_expr_ops nft_payload_fast_ops; +extern const struct nft_expr_ops nft_bitwise_fast_ops; + extern struct static_key_false nft_counters_enabled; extern struct static_key_false nft_trace_enabled; diff --git a/include/net/netfilter/nf_tables_ipv4.h b/include/net/netfilter/nf_tables_ipv4.h index ed7b511f0a59..1f7bea39ad1b 100644 --- a/include/net/netfilter/nf_tables_ipv4.h +++ b/include/net/netfilter/nf_tables_ipv4.h @@ -53,4 +53,37 @@ static inline void nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt, nft_set_pktinfo_unspec(pkt, skb); } +static inline int nft_set_pktinfo_ipv4_ingress(struct nft_pktinfo *pkt, + struct sk_buff *skb) +{ + struct iphdr *iph; + u32 len, thoff; + + if (!pskb_may_pull(skb, sizeof(*iph))) + return -1; + + iph = ip_hdr(skb); + if (iph->ihl < 5 || iph->version != 4) + goto inhdr_error; + + len = ntohs(iph->tot_len); + thoff = iph->ihl * 4; + if (skb->len < len) { + __IP_INC_STATS(nft_net(pkt), IPSTATS_MIB_INTRUNCATEDPKTS); + return -1; + } else if (len < thoff) { + goto inhdr_error; + } + + pkt->tprot_set = true; + pkt->tprot = iph->protocol; + pkt->xt.thoff = thoff; + pkt->xt.fragoff = ntohs(iph->frag_off) & IP_OFFSET; + + return 0; + +inhdr_error: + __IP_INC_STATS(nft_net(pkt), IPSTATS_MIB_INHDRERRORS); + return -1; +} #endif diff --git a/include/net/netfilter/nf_tables_ipv6.h b/include/net/netfilter/nf_tables_ipv6.h index d0f1c537b017..867de29f3f7a 100644 --- a/include/net/netfilter/nf_tables_ipv6.h +++ b/include/net/netfilter/nf_tables_ipv6.h @@ -70,4 +70,50 @@ static inline void nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt, nft_set_pktinfo_unspec(pkt, skb); } +static inline int nft_set_pktinfo_ipv6_ingress(struct nft_pktinfo *pkt, + struct sk_buff *skb) +{ +#if IS_ENABLED(CONFIG_IPV6) + unsigned int flags = IP6_FH_F_AUTH; + unsigned short frag_off; + unsigned int thoff = 0; + struct inet6_dev *idev; + struct ipv6hdr *ip6h; + int protohdr; + u32 pkt_len; + + if (!pskb_may_pull(skb, sizeof(*ip6h))) + return -1; + + ip6h = ipv6_hdr(skb); + if (ip6h->version != 6) + goto inhdr_error; + + pkt_len = ntohs(ip6h->payload_len); + if (pkt_len + sizeof(*ip6h) > skb->len) { + idev = __in6_dev_get(nft_in(pkt)); + __IP6_INC_STATS(nft_net(pkt), idev, IPSTATS_MIB_INTRUNCATEDPKTS); + return -1; + } + + protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, &flags); + if (protohdr < 0) + goto inhdr_error; + + pkt->tprot_set = true; + pkt->tprot = protohdr; + pkt->xt.thoff = thoff; + pkt->xt.fragoff = frag_off; + + return 0; + +inhdr_error: + idev = __in6_dev_get(nft_in(pkt)); + __IP6_INC_STATS(nft_net(pkt), idev, IPSTATS_MIB_INHDRERRORS); + return -1; +#else + return -1; +#endif +} + #endif diff --git a/include/net/netlink.h b/include/net/netlink.h index c0411f14fb53..7356f41d23ba 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -181,8 +181,6 @@ enum { NLA_S64, NLA_BITFIELD32, NLA_REJECT, - NLA_EXACT_LEN, - NLA_MIN_LEN, __NLA_TYPE_MAX, }; @@ -199,11 +197,12 @@ struct netlink_range_validation_signed { enum nla_policy_validation { NLA_VALIDATE_NONE, NLA_VALIDATE_RANGE, + NLA_VALIDATE_RANGE_WARN_TOO_LONG, NLA_VALIDATE_MIN, NLA_VALIDATE_MAX, + NLA_VALIDATE_MASK, NLA_VALIDATE_RANGE_PTR, NLA_VALIDATE_FUNCTION, - NLA_VALIDATE_WARN_TOO_LONG, }; /** @@ -222,7 +221,7 @@ enum nla_policy_validation { * NLA_NUL_STRING Maximum length of string (excluding NUL) * NLA_FLAG Unused * NLA_BINARY Maximum length of attribute payload - * NLA_MIN_LEN Minimum length of attribute payload + * (but see also below with the validation type) * NLA_NESTED, * NLA_NESTED_ARRAY Length verification is done by checking len of * nested header (or empty); len field is used if @@ -237,11 +236,6 @@ enum nla_policy_validation { * just like "All other" * NLA_BITFIELD32 Unused * NLA_REJECT Unused - * NLA_EXACT_LEN Attribute should have exactly this length, otherwise - * it is rejected or warned about, the latter happening - * if and only if the `validation_type' is set to - * NLA_VALIDATE_WARN_TOO_LONG. - * NLA_MIN_LEN Minimum length of attribute payload * All other Minimum length of attribute payload * * Meaning of validation union: @@ -296,6 +290,11 @@ enum nla_policy_validation { * pointer to a struct netlink_range_validation_signed * that indicates the min/max values. * Use NLA_POLICY_FULL_RANGE_SIGNED(). + * + * NLA_BINARY If the validation type is like the ones for integers + * above, then the min/max length (not value like for + * integers) of the attribute is enforced. + * * All other Unused - but note that it's a union * * Meaning of `validate' field, use via NLA_POLICY_VALIDATE_FN: @@ -309,7 +308,7 @@ enum nla_policy_validation { * static const struct nla_policy my_policy[ATTR_MAX+1] = { * [ATTR_FOO] = { .type = NLA_U16 }, * [ATTR_BAR] = { .type = NLA_STRING, .len = BARSIZ }, - * [ATTR_BAZ] = { .type = NLA_EXACT_LEN, .len = sizeof(struct mystruct) }, + * [ATTR_BAZ] = NLA_POLICY_EXACT_LEN(sizeof(struct mystruct)), * [ATTR_GOO] = NLA_POLICY_BITFIELD32(myvalidflags), * }; */ @@ -319,6 +318,7 @@ struct nla_policy { u16 len; union { const u32 bitfield32_valid; + const u32 mask; const char *reject_message; const struct nla_policy *nested_policy; struct netlink_range_validation *range; @@ -335,9 +335,10 @@ struct nla_policy { * nesting validation starts here. * * Additionally, it means that NLA_UNSPEC is actually NLA_REJECT - * for any types >= this, so need to use NLA_MIN_LEN to get the - * previous pure { .len = xyz } behaviour. The advantage of this - * is that types not specified in the policy will be rejected. + * for any types >= this, so need to use NLA_POLICY_MIN_LEN() to + * get the previous pure { .len = xyz } behaviour. The advantage + * of this is that types not specified in the policy will be + * rejected. * * For completely new families it should be set to 1 so that the * validation is enforced for all attributes. For existing ones @@ -349,12 +350,6 @@ struct nla_policy { }; }; -#define NLA_POLICY_EXACT_LEN(_len) { .type = NLA_EXACT_LEN, .len = _len } -#define NLA_POLICY_EXACT_LEN_WARN(_len) \ - { .type = NLA_EXACT_LEN, .len = _len, \ - .validation_type = NLA_VALIDATE_WARN_TOO_LONG, } -#define NLA_POLICY_MIN_LEN(_len) { .type = NLA_MIN_LEN, .len = _len } - #define NLA_POLICY_ETH_ADDR NLA_POLICY_EXACT_LEN(ETH_ALEN) #define NLA_POLICY_ETH_ADDR_COMPAT NLA_POLICY_EXACT_LEN_WARN(ETH_ALEN) @@ -369,20 +364,25 @@ struct nla_policy { #define NLA_POLICY_BITFIELD32(valid) \ { .type = NLA_BITFIELD32, .bitfield32_valid = valid } +#define __NLA_IS_UINT_TYPE(tp) \ + (tp == NLA_U8 || tp == NLA_U16 || tp == NLA_U32 || tp == NLA_U64) +#define __NLA_IS_SINT_TYPE(tp) \ + (tp == NLA_S8 || tp == NLA_S16 || tp == NLA_S32 || tp == NLA_S64) + #define __NLA_ENSURE(condition) BUILD_BUG_ON_ZERO(!(condition)) #define NLA_ENSURE_UINT_TYPE(tp) \ - (__NLA_ENSURE(tp == NLA_U8 || tp == NLA_U16 || \ - tp == NLA_U32 || tp == NLA_U64 || \ - tp == NLA_MSECS) + tp) + (__NLA_ENSURE(__NLA_IS_UINT_TYPE(tp)) + tp) +#define NLA_ENSURE_UINT_OR_BINARY_TYPE(tp) \ + (__NLA_ENSURE(__NLA_IS_UINT_TYPE(tp) || \ + tp == NLA_MSECS || \ + tp == NLA_BINARY) + tp) #define NLA_ENSURE_SINT_TYPE(tp) \ - (__NLA_ENSURE(tp == NLA_S8 || tp == NLA_S16 || \ - tp == NLA_S32 || tp == NLA_S64) + tp) -#define NLA_ENSURE_INT_TYPE(tp) \ - (__NLA_ENSURE(tp == NLA_S8 || tp == NLA_U8 || \ - tp == NLA_S16 || tp == NLA_U16 || \ - tp == NLA_S32 || tp == NLA_U32 || \ - tp == NLA_S64 || tp == NLA_U64 || \ - tp == NLA_MSECS) + tp) + (__NLA_ENSURE(__NLA_IS_SINT_TYPE(tp)) + tp) +#define NLA_ENSURE_INT_OR_BINARY_TYPE(tp) \ + (__NLA_ENSURE(__NLA_IS_UINT_TYPE(tp) || \ + __NLA_IS_SINT_TYPE(tp) || \ + tp == NLA_MSECS || \ + tp == NLA_BINARY) + tp) #define NLA_ENSURE_NO_VALIDATION_PTR(tp) \ (__NLA_ENSURE(tp != NLA_BITFIELD32 && \ tp != NLA_REJECT && \ @@ -390,14 +390,14 @@ struct nla_policy { tp != NLA_NESTED_ARRAY) + tp) #define NLA_POLICY_RANGE(tp, _min, _max) { \ - .type = NLA_ENSURE_INT_TYPE(tp), \ + .type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp), \ .validation_type = NLA_VALIDATE_RANGE, \ .min = _min, \ .max = _max \ } #define NLA_POLICY_FULL_RANGE(tp, _range) { \ - .type = NLA_ENSURE_UINT_TYPE(tp), \ + .type = NLA_ENSURE_UINT_OR_BINARY_TYPE(tp), \ .validation_type = NLA_VALIDATE_RANGE_PTR, \ .range = _range, \ } @@ -409,17 +409,23 @@ struct nla_policy { } #define NLA_POLICY_MIN(tp, _min) { \ - .type = NLA_ENSURE_INT_TYPE(tp), \ + .type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp), \ .validation_type = NLA_VALIDATE_MIN, \ .min = _min, \ } #define NLA_POLICY_MAX(tp, _max) { \ - .type = NLA_ENSURE_INT_TYPE(tp), \ + .type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp), \ .validation_type = NLA_VALIDATE_MAX, \ .max = _max, \ } +#define NLA_POLICY_MASK(tp, _mask) { \ + .type = NLA_ENSURE_UINT_TYPE(tp), \ + .validation_type = NLA_VALIDATE_MASK, \ + .mask = _mask, \ +} + #define NLA_POLICY_VALIDATE_FN(tp, fn, ...) { \ .type = NLA_ENSURE_NO_VALIDATION_PTR(tp), \ .validation_type = NLA_VALIDATE_FUNCTION, \ @@ -427,6 +433,15 @@ struct nla_policy { .len = __VA_ARGS__ + 0, \ } +#define NLA_POLICY_EXACT_LEN(_len) NLA_POLICY_RANGE(NLA_BINARY, _len, _len) +#define NLA_POLICY_EXACT_LEN_WARN(_len) { \ + .type = NLA_BINARY, \ + .validation_type = NLA_VALIDATE_RANGE_WARN_TOO_LONG, \ + .min = _len, \ + .max = _len \ +} +#define NLA_POLICY_MIN_LEN(_len) NLA_POLICY_MIN(NLA_BINARY, _len) + /** * struct nl_info - netlink source information * @nlh: Netlink message header of original request @@ -726,7 +741,6 @@ static inline int __nlmsg_parse(const struct nlmsghdr *nlh, int hdrlen, * @hdrlen: length of family specific header * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected - * @validate: validation strictness * @extack: extended ACK report struct * * See nla_parse() @@ -824,7 +838,6 @@ static inline int nla_validate_deprecated(const struct nlattr *head, int len, * @len: length of attribute stream * @maxtype: maximum attribute type to be expected * @policy: validation policy - * @validate: validation strictness * @extack: extended ACK report struct * * Validates all attributes in the specified attribute stream against the @@ -1933,10 +1946,21 @@ void nla_get_range_unsigned(const struct nla_policy *pt, void nla_get_range_signed(const struct nla_policy *pt, struct netlink_range_validation_signed *range); -int netlink_policy_dump_start(const struct nla_policy *policy, - unsigned int maxtype, - unsigned long *state); -bool netlink_policy_dump_loop(unsigned long *state); -int netlink_policy_dump_write(struct sk_buff *skb, unsigned long state); +struct netlink_policy_dump_state; + +int netlink_policy_dump_add_policy(struct netlink_policy_dump_state **pstate, + const struct nla_policy *policy, + unsigned int maxtype); +int netlink_policy_dump_get_policy_idx(struct netlink_policy_dump_state *state, + const struct nla_policy *policy, + unsigned int maxtype); +bool netlink_policy_dump_loop(struct netlink_policy_dump_state *state); +int netlink_policy_dump_write(struct sk_buff *skb, + struct netlink_policy_dump_state *state); +int netlink_policy_dump_attr_size_estimate(const struct nla_policy *pt); +int netlink_policy_dump_write_attr(struct sk_buff *skb, + const struct nla_policy *pt, + int nestattr); +void netlink_policy_dump_free(struct netlink_policy_dump_state *state); #endif diff --git a/include/net/netns/can.h b/include/net/netns/can.h index b6ab7d1530d7..52fbd8291a96 100644 --- a/include/net/netns/can.h +++ b/include/net/netns/can.h @@ -15,7 +15,6 @@ struct can_rcv_lists_stats; struct netns_can { #if IS_ENABLED(CONFIG_PROC_FS) struct proc_dir_entry *proc_dir; - struct proc_dir_entry *pde_version; struct proc_dir_entry *pde_stats; struct proc_dir_entry *pde_reset_stats; struct proc_dir_entry *pde_rcvlist_all; diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 9e36738c1fe1..8e4fcac4df72 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -183,6 +183,7 @@ struct netns_ipv4 { unsigned int sysctl_tcp_fastopen_blackhole_timeout; atomic_t tfo_active_disable_times; unsigned long tfo_active_disable_stamp; + int sysctl_tcp_reflect_tos; int sysctl_udp_wmem_min; int sysctl_udp_rmem_min; diff --git a/include/net/netns/nexthop.h b/include/net/netns/nexthop.h index 1937476c94a0..1849e77eb68a 100644 --- a/include/net/netns/nexthop.h +++ b/include/net/netns/nexthop.h @@ -14,6 +14,6 @@ struct netns_nexthop { unsigned int seq; /* protected by rtnl_mutex */ u32 last_id_allocated; - struct atomic_notifier_head notifier_chain; + struct blocking_notifier_head notifier_chain; }; #endif diff --git a/include/net/netns/nftables.h b/include/net/netns/nftables.h index a1a8d45adb42..6c0806bd8d1e 100644 --- a/include/net/netns/nftables.h +++ b/include/net/netns/nftables.h @@ -8,6 +8,7 @@ struct netns_nftables { struct list_head tables; struct list_head commit_list; struct list_head module_list; + struct list_head notify_list; struct mutex commit_mutex; unsigned int base_seq; u8 gencursor; diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 3a4f9e3b91a5..2fd76a9b6dc8 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -105,13 +105,9 @@ struct nexthop { }; enum nexthop_event_type { - NEXTHOP_EVENT_ADD, NEXTHOP_EVENT_DEL }; -int call_nexthop_notifier(struct notifier_block *nb, struct net *net, - enum nexthop_event_type event_type, - struct nexthop *nh); int register_nexthop_notifier(struct net *net, struct notifier_block *nb); int unregister_nexthop_notifier(struct net *net, struct notifier_block *nb); diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index ac8c890a2657..4ed32e6b0201 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -19,12 +19,9 @@ struct qdisc_walker { int (*fn)(struct Qdisc *, unsigned long cl, struct qdisc_walker *); }; -#define QDISC_ALIGNTO 64 -#define QDISC_ALIGN(len) (((len) + QDISC_ALIGNTO-1) & ~(QDISC_ALIGNTO-1)) - static inline void *qdisc_priv(struct Qdisc *q) { - return (char *) q + QDISC_ALIGN(sizeof(struct Qdisc)); + return &q->privdata; } /* diff --git a/include/net/request_sock.h b/include/net/request_sock.h index b2eb8b4ba697..29e41ff3ec93 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -41,6 +41,13 @@ struct request_sock_ops { int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req); +struct saved_syn { + u32 mac_hdrlen; + u32 network_hdrlen; + u32 tcp_hdrlen; + u8 data[]; +}; + /* struct request_sock - mini sock to represent a connection request */ struct request_sock { @@ -60,7 +67,7 @@ struct request_sock { struct timer_list rsk_timer; const struct request_sock_ops *rsk_ops; struct sock *sk; - u32 *saved_syn; + struct saved_syn *saved_syn; u32 secid; u32 peer_secid; }; diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index d60e7c39d60c..d8fd8676fc72 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -91,7 +91,7 @@ struct Qdisc { struct net_rate_estimator __rcu *rate_est; struct gnet_stats_basic_cpu __percpu *cpu_bstats; struct gnet_stats_queue __percpu *cpu_qstats; - int padded; + int pad; refcount_t refcnt; /* @@ -112,6 +112,9 @@ struct Qdisc { /* for NOLOCK qdisc, true if there are no enqueued skbs */ bool empty; struct rcu_head rcu; + + /* private data */ + long privdata[] ____cacheline_aligned; }; static inline void qdisc_refcount_inc(struct Qdisc *qdisc) @@ -1047,12 +1050,6 @@ static inline unsigned int __qdisc_queue_drop_head(struct Qdisc *sch, return 0; } -static inline unsigned int qdisc_queue_drop_head(struct Qdisc *sch, - struct sk_buff **to_free) -{ - return __qdisc_queue_drop_head(sch, &sch->q, to_free); -} - static inline struct sk_buff *qdisc_peek_head(struct Qdisc *sch) { const struct qdisc_skb_head *qh = &sch->q; diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index b33f1aefad09..0bdff38eb4bb 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -226,12 +226,14 @@ struct sctp_sock { data_ready_signalled:1; atomic_t pd_mode; + + /* Fields after this point will be skipped on copies, like on accept + * and peeloff operations + */ + /* Receive to here while partial delivery is in effect. */ struct sk_buff_head pd_lobby; - /* These must be the last fields, as they will skipped on copies, - * like on accept and peeloff operations - */ struct list_head auto_asconf_list; int do_auto_asconf; }; diff --git a/include/net/smc.h b/include/net/smc.h index 646feb4bc75f..e441aa97ad61 100644 --- a/include/net/smc.h +++ b/include/net/smc.h @@ -37,6 +37,8 @@ struct smcd_dmb { #define ISM_EVENT_GID 1 #define ISM_EVENT_SWR 2 +#define ISM_RESERVED_VLANID 0x1FFF + #define ISM_ERROR 0xFFFF struct smcd_event { @@ -63,6 +65,8 @@ struct smcd_ops { int (*move_data)(struct smcd_dev *dev, u64 dmb_tok, unsigned int idx, bool sf, unsigned int offset, void *data, unsigned int size); + void (*get_system_eid)(struct smcd_dev *dev, u8 **eid); + u16 (*get_chid)(struct smcd_dev *dev); }; struct smcd_dev { diff --git a/include/net/sock.h b/include/net/sock.h index 064637d1ddf6..a5c6ae78df77 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -246,7 +246,7 @@ struct sock_common { /* public: */ }; -struct bpf_sk_storage; +struct bpf_local_storage; /** * struct sock - network layer representation of sockets @@ -517,7 +517,7 @@ struct sock { void (*sk_destruct)(struct sock *sk); struct sock_reuseport __rcu *sk_reuseport_cb; #ifdef CONFIG_BPF_SYSCALL - struct bpf_sk_storage __rcu *sk_bpf_storage; + struct bpf_local_storage __rcu *sk_bpf_storage; #endif struct rcu_head sk_rcu; }; @@ -845,7 +845,6 @@ enum sock_flags { SOCK_RCVTSTAMP, /* %SO_TIMESTAMP setting */ SOCK_RCVTSTAMPNS, /* %SO_TIMESTAMPNS setting */ SOCK_LOCALROUTE, /* route locally only, %SO_DONTROUTE setting */ - SOCK_QUEUE_SHRUNK, /* write queue has been shrunk recently */ SOCK_MEMALLOC, /* VM depends on this socket for swapping */ SOCK_TIMESTAMPING_RX_SOFTWARE, /* %SOF_TIMESTAMPING_RX_SOFTWARE */ SOCK_FASYNC, /* fasync() active */ @@ -1478,7 +1477,7 @@ sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size) { if (!sk_has_account(sk)) return true; - return size<= sk->sk_forward_alloc || + return size <= sk->sk_forward_alloc || __sk_mem_schedule(sk, size, SK_MEM_RECV) || skb_pfmemalloc(skb); } @@ -1526,7 +1525,6 @@ static inline void sk_mem_uncharge(struct sock *sk, int size) DECLARE_STATIC_KEY_FALSE(tcp_tx_skb_cache_key); static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb) { - sock_set_flag(sk, SOCK_QUEUE_SHRUNK); sk_wmem_queued_add(sk, -skb->truesize); sk_mem_uncharge(sk, skb->truesize); if (static_branch_unlikely(&tcp_tx_skb_cache_key) && @@ -2197,6 +2195,8 @@ void sk_reset_timer(struct sock *sk, struct timer_list *timer, void sk_stop_timer(struct sock *sk, struct timer_list *timer); +void sk_stop_timer_sync(struct sock *sk, struct timer_list *timer); + int __sk_queue_drop_skb(struct sock *sk, struct sk_buff_head *sk_queue, struct sk_buff *skb, unsigned int flags, void (*destructor)(struct sock *sk, diff --git a/include/net/switchdev.h b/include/net/switchdev.h index ff2246914301..53e8b4994296 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -203,6 +203,7 @@ enum switchdev_notifier_type { SWITCHDEV_FDB_ADD_TO_DEVICE, SWITCHDEV_FDB_DEL_TO_DEVICE, SWITCHDEV_FDB_OFFLOADED, + SWITCHDEV_FDB_FLUSH_TO_BRIDGE, SWITCHDEV_PORT_OBJ_ADD, /* Blocking. */ SWITCHDEV_PORT_OBJ_DEL, /* Blocking. */ diff --git a/include/net/tc_act/tc_tunnel_key.h b/include/net/tc_act/tc_tunnel_key.h index e1057b255f69..879fe8cff581 100644 --- a/include/net/tc_act/tc_tunnel_key.h +++ b/include/net/tc_act/tc_tunnel_key.h @@ -56,7 +56,10 @@ static inline struct ip_tunnel_info *tcf_tunnel_info(const struct tc_action *a) { #ifdef CONFIG_NET_CLS_ACT struct tcf_tunnel_key *t = to_tunnel_key(a); - struct tcf_tunnel_key_params *params = rtnl_dereference(t->params); + struct tcf_tunnel_key_params *params; + + params = rcu_dereference_protected(t->params, + lockdep_is_held(&a->tcfa_lock)); return ¶ms->tcft_enc_metadata->u.tun_info; #else diff --git a/include/net/tc_act/tc_vlan.h b/include/net/tc_act/tc_vlan.h index 4e2502408c31..f051046ba034 100644 --- a/include/net/tc_act/tc_vlan.h +++ b/include/net/tc_act/tc_vlan.h @@ -11,6 +11,8 @@ struct tcf_vlan_params { int tcfv_action; + unsigned char tcfv_push_dst[ETH_ALEN]; + unsigned char tcfv_push_src[ETH_ALEN]; u16 tcfv_push_vid; __be16 tcfv_push_proto; u8 tcfv_push_prio; diff --git a/include/net/tcp.h b/include/net/tcp.h index eab6c7510b5b..d4ef5bf94168 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -394,7 +394,7 @@ void tcp_metrics_init(void); bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst); void tcp_close(struct sock *sk, long timeout); void tcp_init_sock(struct sock *sk); -void tcp_init_transfer(struct sock *sk, int bpf_op); +void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb); __poll_t tcp_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); int tcp_getsockopt(struct sock *sk, int level, int optname, @@ -455,7 +455,8 @@ enum tcp_synack_type { struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, struct request_sock *req, struct tcp_fastopen_cookie *foc, - enum tcp_synack_type synack_type); + enum tcp_synack_type synack_type, + struct sk_buff *syn_skb); int tcp_disconnect(struct sock *sk, int flags); void tcp_finish_connect(struct sock *sk, struct sk_buff *skb); @@ -699,7 +700,7 @@ static inline void tcp_fast_path_check(struct sock *sk) static inline u32 tcp_rto_min(struct sock *sk) { const struct dst_entry *dst = __sk_dst_get(sk); - u32 rto_min = TCP_RTO_MIN; + u32 rto_min = inet_csk(sk)->icsk_rto_min; if (dst && dst_metric_locked(dst, RTAX_RTO_MIN)) rto_min = dst_metric_rtt(dst, RTAX_RTO_MIN); @@ -941,16 +942,6 @@ INDIRECT_CALLABLE_DECLARE(void tcp_v6_early_demux(struct sk_buff *skb)); #endif -static inline bool inet_exact_dif_match(struct net *net, struct sk_buff *skb) -{ -#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) - if (!net->ipv4.sysctl_tcp_l3mdev_accept && - skb && ipv4_l3mdev_skb(IPCB(skb)->flags)) - return true; -#endif - return false; -} - /* TCP_SKB_CB reference means this can not be used from early demux */ static inline int tcp_v4_sdif(struct sk_buff *skb) { @@ -1113,7 +1104,7 @@ void tcp_get_available_congestion_control(char *buf, size_t len); void tcp_get_allowed_congestion_control(char *buf, size_t len); int tcp_set_allowed_congestion_control(char *allowed); int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, - bool reinit, bool cap_net_admin); + bool cap_net_admin); u32 tcp_slow_start(struct tcp_sock *tp, u32 acked); void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked); @@ -1423,6 +1414,8 @@ static inline int tcp_full_space(const struct sock *sk) return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf)); } +void tcp_cleanup_rbuf(struct sock *sk, int copied); + /* We provision sk_rcvbuf around 200% of sk_rcvlowat. * If 87.5 % (7/8) of the space has been consumed, we want to override * SO_RCVLOWAT constraint, since we are receiving skbs with too small @@ -2035,7 +2028,8 @@ 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, - enum tcp_synack_type synack_type); + enum tcp_synack_type synack_type, + struct sk_buff *syn_skb); }; extern const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops; @@ -2233,6 +2227,22 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, int len, int flags); #endif /* CONFIG_NET_SOCK_MSG */ +#ifdef CONFIG_CGROUP_BPF +static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops, + struct sk_buff *skb, + unsigned int end_offset) +{ + skops->skb = skb; + skops->skb_data_end = skb->data + end_offset; +} +#else +static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops, + struct sk_buff *skb, + unsigned int end_offset) +{ +} +#endif + /* Call BPF_SOCK_OPS program that returns an int. If the return value * is < 0, then the BPF op failed (for example if the loaded BPF * program does not support the chosen operation or there is no BPF diff --git a/include/net/tls.h b/include/net/tls.h index e5dac7e74e79..baf1e99d8193 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -679,10 +679,6 @@ int decrypt_skb(struct sock *sk, struct sk_buff *skb, struct scatterlist *sgout); struct sk_buff *tls_encrypt_skb(struct sk_buff *skb); -struct sk_buff *tls_validate_xmit_skb(struct sock *sk, - struct net_device *dev, - struct sk_buff *skb); - int tls_sw_fallback_init(struct sock *sk, struct tls_offload_context_tx *offload_ctx, struct tls_crypto_info *crypto_info); diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index 94bb7a882250..2ea453dac876 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -200,11 +200,27 @@ enum udp_tunnel_nic_info_flags { UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN = BIT(3), }; +struct udp_tunnel_nic; + +#define UDP_TUNNEL_NIC_MAX_SHARING_DEVICES (U16_MAX / 2) + +struct udp_tunnel_nic_shared { + struct udp_tunnel_nic *udp_tunnel_nic_info; + + struct list_head devices; +}; + +struct udp_tunnel_nic_shared_node { + struct net_device *dev; + struct list_head list; +}; + /** * struct udp_tunnel_nic_info - driver UDP tunnel offload information * @set_port: callback for adding a new port * @unset_port: callback for removing a port * @sync_table: callback for syncing the entire port table at once + * @shared: reference to device global state (optional) * @flags: device flags from enum udp_tunnel_nic_info_flags * @tables: UDP port tables this device has * @tables.n_entries: number of entries in this table @@ -213,6 +229,12 @@ enum udp_tunnel_nic_info_flags { * Drivers are expected to provide either @set_port and @unset_port callbacks * or the @sync_table callback. Callbacks are invoked with rtnl lock held. * + * Devices which (misguidedly) share the UDP tunnel port table across multiple + * netdevs should allocate an instance of struct udp_tunnel_nic_shared and + * point @shared at it. + * There must never be more than %UDP_TUNNEL_NIC_MAX_SHARING_DEVICES devices + * sharing a table. + * * Known limitations: * - UDP tunnel port notifications are fundamentally best-effort - * it is likely the driver will both see skbs which use a UDP tunnel port, @@ -234,6 +256,8 @@ struct udp_tunnel_nic_info { /* all at once */ int (*sync_table)(struct net_device *dev, unsigned int table); + struct udp_tunnel_nic_shared *shared; + unsigned int flags; struct udp_tunnel_nic_table_info { diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 3a41627cbdfe..08537aa14f7c 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -121,6 +121,9 @@ struct vxlanhdr_gbp { #define VXLAN_GBP_POLICY_APPLIED (BIT(3) << 16) #define VXLAN_GBP_ID_MASK (0xFFFF) +#define VXLAN_GBP_MASK (VXLAN_GBP_DONT_LEARN | VXLAN_GBP_POLICY_APPLIED | \ + VXLAN_GBP_ID_MASK) + /* * VXLAN Generic Protocol Extension (VXLAN_F_GPE): * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index c9d87cc40c11..1a9559c0cbdd 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -18,25 +18,19 @@ struct xsk_queue; struct xdp_buff; struct xdp_umem { - struct xsk_queue *fq; - struct xsk_queue *cq; - struct xsk_buff_pool *pool; + void *addrs; u64 size; u32 headroom; u32 chunk_size; + u32 chunks; + u32 npgs; struct user_struct *user; refcount_t users; - struct work_struct work; - struct page **pgs; - u32 npgs; - u16 queue_id; - u8 need_wakeup; u8 flags; - int id; - struct net_device *dev; bool zc; - spinlock_t xsk_tx_list_lock; - struct list_head xsk_tx_list; + struct page **pgs; + int id; + struct list_head xsk_dma_list; }; struct xsk_map { @@ -48,10 +42,11 @@ struct xsk_map { struct xdp_sock { /* struct sock must be the first member of struct xdp_sock */ struct sock sk; - struct xsk_queue *rx; + struct xsk_queue *rx ____cacheline_aligned_in_smp; struct net_device *dev; struct xdp_umem *umem; struct list_head flush_node; + struct xsk_buff_pool *pool; u16 queue_id; bool zc; enum { @@ -59,10 +54,9 @@ struct xdp_sock { XSK_BOUND, XSK_UNBOUND, } state; - /* Protects multiple processes in the control path */ - struct mutex mutex; + struct xsk_queue *tx ____cacheline_aligned_in_smp; - struct list_head list; + struct list_head tx_list; /* Mutual exclusion of NAPI TX thread and sendmsg error paths * in the SKB destructor callback. */ @@ -77,6 +71,10 @@ struct xdp_sock { struct list_head map_list; /* Protects map_list */ spinlock_t map_list_lock; + /* Protects multiple processes in the control path */ + struct mutex mutex; + struct xsk_queue *fq_tmp; /* Only as tmp storage before bind */ + struct xsk_queue *cq_tmp; /* Only as tmp storage before bind */ }; #ifdef CONFIG_XDP_SOCKETS diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index ccf848f7efa4..5b1ee8a9976d 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -11,47 +11,50 @@ #ifdef CONFIG_XDP_SOCKETS -void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries); -bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc); -void xsk_umem_consume_tx_done(struct xdp_umem *umem); -struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev, u16 queue_id); -void xsk_set_rx_need_wakeup(struct xdp_umem *umem); -void xsk_set_tx_need_wakeup(struct xdp_umem *umem); -void xsk_clear_rx_need_wakeup(struct xdp_umem *umem); -void xsk_clear_tx_need_wakeup(struct xdp_umem *umem); -bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem); +void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries); +bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc); +void xsk_tx_release(struct xsk_buff_pool *pool); +struct xsk_buff_pool *xsk_get_pool_from_qid(struct net_device *dev, + u16 queue_id); +void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool); +void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool); +void xsk_clear_rx_need_wakeup(struct xsk_buff_pool *pool); +void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool); +bool xsk_uses_need_wakeup(struct xsk_buff_pool *pool); -static inline u32 xsk_umem_get_headroom(struct xdp_umem *umem) +static inline u32 xsk_pool_get_headroom(struct xsk_buff_pool *pool) { - return XDP_PACKET_HEADROOM + umem->headroom; + return XDP_PACKET_HEADROOM + pool->headroom; } -static inline u32 xsk_umem_get_chunk_size(struct xdp_umem *umem) +static inline u32 xsk_pool_get_chunk_size(struct xsk_buff_pool *pool) { - return umem->chunk_size; + return pool->chunk_size; } -static inline u32 xsk_umem_get_rx_frame_size(struct xdp_umem *umem) +static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool) { - return xsk_umem_get_chunk_size(umem) - xsk_umem_get_headroom(umem); + return xsk_pool_get_chunk_size(pool) - xsk_pool_get_headroom(pool); } -static inline void xsk_buff_set_rxq_info(struct xdp_umem *umem, +static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq) { - xp_set_rxq_info(umem->pool, rxq); + xp_set_rxq_info(pool, rxq); } -static inline void xsk_buff_dma_unmap(struct xdp_umem *umem, +static inline void xsk_pool_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs) { - xp_dma_unmap(umem->pool, attrs); + xp_dma_unmap(pool, attrs); } -static inline int xsk_buff_dma_map(struct xdp_umem *umem, struct device *dev, - unsigned long attrs) +static inline int xsk_pool_dma_map(struct xsk_buff_pool *pool, + struct device *dev, unsigned long attrs) { - return xp_dma_map(umem->pool, dev, attrs, umem->pgs, umem->npgs); + struct xdp_umem *umem = pool->umem; + + return xp_dma_map(pool, dev, attrs, umem->pgs, umem->npgs); } static inline dma_addr_t xsk_buff_xdp_get_dma(struct xdp_buff *xdp) @@ -68,14 +71,14 @@ static inline dma_addr_t xsk_buff_xdp_get_frame_dma(struct xdp_buff *xdp) return xp_get_frame_dma(xskb); } -static inline struct xdp_buff *xsk_buff_alloc(struct xdp_umem *umem) +static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool) { - return xp_alloc(umem->pool); + return xp_alloc(pool); } -static inline bool xsk_buff_can_alloc(struct xdp_umem *umem, u32 count) +static inline bool xsk_buff_can_alloc(struct xsk_buff_pool *pool, u32 count) { - return xp_can_alloc(umem->pool, count); + return xp_can_alloc(pool, count); } static inline void xsk_buff_free(struct xdp_buff *xdp) @@ -85,100 +88,104 @@ static inline void xsk_buff_free(struct xdp_buff *xdp) xp_free(xskb); } -static inline dma_addr_t xsk_buff_raw_get_dma(struct xdp_umem *umem, u64 addr) +static inline dma_addr_t xsk_buff_raw_get_dma(struct xsk_buff_pool *pool, + u64 addr) { - return xp_raw_get_dma(umem->pool, addr); + return xp_raw_get_dma(pool, addr); } -static inline void *xsk_buff_raw_get_data(struct xdp_umem *umem, u64 addr) +static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr) { - return xp_raw_get_data(umem->pool, addr); + return xp_raw_get_data(pool, addr); } -static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp) +static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool) { struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp); + if (!pool->dma_need_sync) + return; + xp_dma_sync_for_cpu(xskb); } -static inline void xsk_buff_raw_dma_sync_for_device(struct xdp_umem *umem, +static inline void xsk_buff_raw_dma_sync_for_device(struct xsk_buff_pool *pool, dma_addr_t dma, size_t size) { - xp_dma_sync_for_device(umem->pool, dma, size); + xp_dma_sync_for_device(pool, dma, size); } #else -static inline void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries) +static inline void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries) { } -static inline bool xsk_umem_consume_tx(struct xdp_umem *umem, - struct xdp_desc *desc) +static inline bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, + struct xdp_desc *desc) { return false; } -static inline void xsk_umem_consume_tx_done(struct xdp_umem *umem) +static inline void xsk_tx_release(struct xsk_buff_pool *pool) { } -static inline struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev, - u16 queue_id) +static inline struct xsk_buff_pool * +xsk_get_pool_from_qid(struct net_device *dev, u16 queue_id) { return NULL; } -static inline void xsk_set_rx_need_wakeup(struct xdp_umem *umem) +static inline void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool) { } -static inline void xsk_set_tx_need_wakeup(struct xdp_umem *umem) +static inline void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool) { } -static inline void xsk_clear_rx_need_wakeup(struct xdp_umem *umem) +static inline void xsk_clear_rx_need_wakeup(struct xsk_buff_pool *pool) { } -static inline void xsk_clear_tx_need_wakeup(struct xdp_umem *umem) +static inline void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool) { } -static inline bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem) +static inline bool xsk_uses_need_wakeup(struct xsk_buff_pool *pool) { return false; } -static inline u32 xsk_umem_get_headroom(struct xdp_umem *umem) +static inline u32 xsk_pool_get_headroom(struct xsk_buff_pool *pool) { return 0; } -static inline u32 xsk_umem_get_chunk_size(struct xdp_umem *umem) +static inline u32 xsk_pool_get_chunk_size(struct xsk_buff_pool *pool) { return 0; } -static inline u32 xsk_umem_get_rx_frame_size(struct xdp_umem *umem) +static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool) { return 0; } -static inline void xsk_buff_set_rxq_info(struct xdp_umem *umem, +static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq) { } -static inline void xsk_buff_dma_unmap(struct xdp_umem *umem, +static inline void xsk_pool_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs) { } -static inline int xsk_buff_dma_map(struct xdp_umem *umem, struct device *dev, - unsigned long attrs) +static inline int xsk_pool_dma_map(struct xsk_buff_pool *pool, + struct device *dev, unsigned long attrs) { return 0; } @@ -193,12 +200,12 @@ static inline dma_addr_t xsk_buff_xdp_get_frame_dma(struct xdp_buff *xdp) return 0; } -static inline struct xdp_buff *xsk_buff_alloc(struct xdp_umem *umem) +static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool) { return NULL; } -static inline bool xsk_buff_can_alloc(struct xdp_umem *umem, u32 count) +static inline bool xsk_buff_can_alloc(struct xsk_buff_pool *pool, u32 count) { return false; } @@ -207,21 +214,22 @@ static inline void xsk_buff_free(struct xdp_buff *xdp) { } -static inline dma_addr_t xsk_buff_raw_get_dma(struct xdp_umem *umem, u64 addr) +static inline dma_addr_t xsk_buff_raw_get_dma(struct xsk_buff_pool *pool, + u64 addr) { return 0; } -static inline void *xsk_buff_raw_get_data(struct xdp_umem *umem, u64 addr) +static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr) { return NULL; } -static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp) +static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool) { } -static inline void xsk_buff_raw_dma_sync_for_device(struct xdp_umem *umem, +static inline void xsk_buff_raw_dma_sync_for_device(struct xsk_buff_pool *pool, dma_addr_t dma, size_t size) { diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 2737d24ec244..b2a06f10b62c 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1773,21 +1773,17 @@ static inline unsigned int xfrm_replay_state_esn_len(struct xfrm_replay_state_es static inline int xfrm_replay_clone(struct xfrm_state *x, struct xfrm_state *orig) { - x->replay_esn = kzalloc(xfrm_replay_state_esn_len(orig->replay_esn), + + x->replay_esn = kmemdup(orig->replay_esn, + xfrm_replay_state_esn_len(orig->replay_esn), GFP_KERNEL); if (!x->replay_esn) return -ENOMEM; - - x->replay_esn->bmp_len = orig->replay_esn->bmp_len; - x->replay_esn->replay_window = orig->replay_esn->replay_window; - - x->preplay_esn = kmemdup(x->replay_esn, - xfrm_replay_state_esn_len(x->replay_esn), + x->preplay_esn = kmemdup(orig->preplay_esn, + xfrm_replay_state_esn_len(orig->preplay_esn), GFP_KERNEL); - if (!x->preplay_esn) { - kfree(x->replay_esn); + if (!x->preplay_esn) return -ENOMEM; - } return 0; } @@ -2000,6 +1996,39 @@ static inline int xfrm_tunnel_check(struct sk_buff *skb, struct xfrm_state *x, return 0; } +extern const int xfrm_msg_min[XFRM_NR_MSGTYPES]; +extern const struct nla_policy xfrma_policy[XFRMA_MAX+1]; + +struct xfrm_translator { + /* Allocate frag_list and put compat translation there */ + int (*alloc_compat)(struct sk_buff *skb, const struct nlmsghdr *src); + + /* Allocate nlmsg with 64-bit translaton of received 32-bit message */ + struct nlmsghdr *(*rcv_msg_compat)(const struct nlmsghdr *nlh, + int maxtype, const struct nla_policy *policy, + struct netlink_ext_ack *extack); + + /* Translate 32-bit user_policy from sockptr */ + int (*xlate_user_policy_sockptr)(u8 **pdata32, int optlen); + + struct module *owner; +}; + +#if IS_ENABLED(CONFIG_XFRM_USER_COMPAT) +extern int xfrm_register_translator(struct xfrm_translator *xtr); +extern int xfrm_unregister_translator(struct xfrm_translator *xtr); +extern struct xfrm_translator *xfrm_get_translator(void); +extern void xfrm_put_translator(struct xfrm_translator *xtr); +#else +static inline struct xfrm_translator *xfrm_get_translator(void) +{ + return NULL; +} +static inline void xfrm_put_translator(struct xfrm_translator *xtr) +{ +} +#endif + #if IS_ENABLED(CONFIG_IPV6) static inline bool xfrm6_local_dontfrag(const struct sock *sk) { diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 6842990e2712..0140d086dc84 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -13,6 +13,8 @@ struct xsk_buff_pool; struct xdp_rxq_info; struct xsk_queue; struct xdp_desc; +struct xdp_umem; +struct xdp_sock; struct device; struct page; @@ -26,34 +28,68 @@ struct xdp_buff_xsk { struct list_head free_list_node; }; +struct xsk_dma_map { + dma_addr_t *dma_pages; + struct device *dev; + struct net_device *netdev; + refcount_t users; + struct list_head list; /* Protected by the RTNL_LOCK */ + u32 dma_pages_cnt; + bool dma_need_sync; +}; + struct xsk_buff_pool { - struct xsk_queue *fq; + /* Members only used in the control path first. */ + struct device *dev; + struct net_device *netdev; + struct list_head xsk_tx_list; + /* Protects modifications to the xsk_tx_list */ + spinlock_t xsk_tx_list_lock; + refcount_t users; + struct xdp_umem *umem; + struct work_struct work; struct list_head free_list; + u32 heads_cnt; + u16 queue_id; + + /* Data path members as close to free_heads at the end as possible. */ + struct xsk_queue *fq ____cacheline_aligned_in_smp; + struct xsk_queue *cq; + /* For performance reasons, each buff pool has its own array of dma_pages + * even when they are identical. + */ dma_addr_t *dma_pages; struct xdp_buff_xsk *heads; u64 chunk_mask; u64 addrs_cnt; u32 free_list_cnt; u32 dma_pages_cnt; - u32 heads_cnt; u32 free_heads_cnt; u32 headroom; u32 chunk_size; u32 frame_len; + u8 cached_need_wakeup; + bool uses_need_wakeup; bool dma_need_sync; bool unaligned; void *addrs; - struct device *dev; struct xdp_buff_xsk *free_heads[]; }; /* AF_XDP core. */ -struct xsk_buff_pool *xp_create(struct page **pages, u32 nr_pages, u32 chunks, - u32 chunk_size, u32 headroom, u64 size, - bool unaligned); -void xp_set_fq(struct xsk_buff_pool *pool, struct xsk_queue *fq); +struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, + struct xdp_umem *umem); +int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev, + u16 queue_id, u16 flags); +int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_umem *umem, + struct net_device *dev, u16 queue_id); void xp_destroy(struct xsk_buff_pool *pool); void xp_release(struct xdp_buff_xsk *xskb); +void xp_get_pool(struct xsk_buff_pool *pool); +void xp_put_pool(struct xsk_buff_pool *pool); +void xp_clear_dev(struct xsk_buff_pool *pool); +void xp_add_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs); +void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs); /* AF_XDP, and XDP core. */ void xp_free(struct xdp_buff_xsk *xskb); @@ -80,9 +116,6 @@ static inline dma_addr_t xp_get_frame_dma(struct xdp_buff_xsk *xskb) void xp_dma_sync_for_cpu_slow(struct xdp_buff_xsk *xskb); static inline void xp_dma_sync_for_cpu(struct xdp_buff_xsk *xskb) { - if (!xskb->pool->dma_need_sync) - return; - xp_dma_sync_for_cpu_slow(xskb); } |