android_kernel_msm-6.1_noth.../include/net/ip.h
Greg Kroah-Hartman 8976ff249f Merge 6.1.42 into android14-6.1-lts
Changes in 6.1.42
	io_uring: treat -EAGAIN for REQ_F_NOWAIT as final for io-wq
	ALSA: hda/realtek - remove 3k pull low procedure
	ALSA: hda/realtek: Add quirk for Clevo NS70AU
	ALSA: hda/realtek: Enable Mute LED on HP Laptop 15s-eq2xxx
	maple_tree: set the node limit when creating a new root node
	maple_tree: fix node allocation testing on 32 bit
	keys: Fix linking a duplicate key to a keyring's assoc_array
	perf probe: Add test for regression introduced by switch to die_get_decl_file()
	btrfs: fix warning when putting transaction with qgroups enabled after abort
	fuse: revalidate: don't invalidate if interrupted
	fuse: Apply flags2 only when userspace set the FUSE_INIT_EXT
	btrfs: set_page_extent_mapped after read_folio in btrfs_cont_expand
	btrfs: zoned: fix memory leak after finding block group with super blocks
	fuse: ioctl: translate ENOSYS in outarg
	btrfs: fix race between balance and cancel/pause
	selftests: tc: set timeout to 15 minutes
	selftests: tc: add 'ct' action kconfig dep
	regmap: Drop initial version of maximum transfer length fixes
	of: Preserve "of-display" device name for compatibility
	regmap: Account for register length in SMBus I/O limits
	arm64/fpsimd: Ensure SME storage is allocated after SVE VL changes
	can: mcp251xfd: __mcp251xfd_chip_set_mode(): increase poll timeout
	can: bcm: Fix UAF in bcm_proc_show()
	can: gs_usb: gs_can_open(): improve error handling
	selftests: tc: add ConnTrack procfs kconfig
	dma-buf/dma-resv: Stop leaking on krealloc() failure
	drm/amdgpu/vkms: relax timer deactivation by hrtimer_try_to_cancel
	drm/amdgpu/pm: make gfxclock consistent for sienna cichlid
	drm/amdgpu/pm: make mclk consistent for smu 13.0.7
	drm/client: Fix memory leak in drm_client_target_cloned
	drm/client: Fix memory leak in drm_client_modeset_probe
	drm/amd/display: only accept async flips for fast updates
	drm/amd/display: Disable MPC split by default on special asic
	drm/amd/display: check TG is non-null before checking if enabled
	drm/amd/display: Keep PHY active for DP displays on DCN31
	ASoC: fsl_sai: Disable bit clock with transmitter
	ASoC: fsl_sai: Revert "ASoC: fsl_sai: Enable MCTL_MCLK_EN bit for master mode"
	ASoC: tegra: Fix ADX byte map
	ASoC: rt5640: Fix sleep in atomic context
	ASoC: cs42l51: fix driver to properly autoload with automatic module loading
	ASoC: codecs: wcd938x: fix missing clsh ctrl error handling
	ASoC: codecs: wcd-mbhc-v2: fix resource leaks on component remove
	ASoC: qdsp6: audioreach: fix topology probe deferral
	ASoC: tegra: Fix AMX byte map
	ASoC: codecs: wcd938x: fix resource leaks on component remove
	ASoC: codecs: wcd938x: fix missing mbhc init error handling
	ASoC: codecs: wcd934x: fix resource leaks on component remove
	ASoC: codecs: wcd938x: fix codec initialisation race
	ASoC: codecs: wcd938x: fix soundwire initialisation race
	ext4: correct inline offset when handling xattrs in inode body
	drm/radeon: Fix integer overflow in radeon_cs_parser_init
	ALSA: emu10k1: roll up loops in DSP setup code for Audigy
	quota: Properly disable quotas when add_dquot_ref() fails
	quota: fix warning in dqgrab()
	HID: add quirk for 03f0:464a HP Elite Presenter Mouse
	ovl: check type and offset of struct vfsmount in ovl_entry
	udf: Fix uninitialized array access for some pathnames
	fs: jfs: Fix UBSAN: array-index-out-of-bounds in dbAllocDmapLev
	MIPS: dec: prom: Address -Warray-bounds warning
	FS: JFS: Fix null-ptr-deref Read in txBegin
	FS: JFS: Check for read-only mounted filesystem in txBegin
	ACPI: video: Add backlight=native DMI quirk for Dell Studio 1569
	rcu-tasks: Avoid pr_info() with spin lock in cblist_init_generic()
	rcu: Mark additional concurrent load from ->cpu_no_qs.b.exp
	sched/fair: Don't balance task to its current running CPU
	wifi: ath11k: fix registration of 6Ghz-only phy without the full channel range
	bpf: Print a warning only if writing to unprivileged_bpf_disabled.
	bpf: Address KCSAN report on bpf_lru_list
	bpf: tcp: Avoid taking fast sock lock in iterator
	wifi: ath11k: add support default regdb while searching board-2.bin for WCN6855
	wifi: mac80211_hwsim: Fix possible NULL dereference
	spi: dw: Add compatible for Intel Mount Evans SoC
	wifi: ath11k: fix memory leak in WMI firmware stats
	net: ethernet: litex: add support for 64 bit stats
	devlink: report devlink_port_type_warn source device
	wifi: wext-core: Fix -Wstringop-overflow warning in ioctl_standard_iw_point()
	wifi: iwlwifi: Add support for new PCI Id
	wifi: iwlwifi: mvm: avoid baid size integer overflow
	wifi: iwlwifi: pcie: add device id 51F1 for killer 1675
	igb: Fix igb_down hung on surprise removal
	net: hns3: fix strncpy() not using dest-buf length as length issue
	ASoC: amd: acp: fix for invalid dai id handling in acp_get_byte_count()
	ASoC: codecs: wcd938x: fix mbhc impedance loglevel
	ASoC: codecs: wcd938x: fix dB range for HPHL and HPHR
	ASoC: qcom: q6apm: do not close GPR port before closing graph
	sched/fair: Use recent_used_cpu to test p->cpus_ptr
	sched/psi: Fix avgs_work re-arm in psi_avgs_work()
	sched/psi: Rearrange polling code in preparation
	sched/psi: Rename existing poll members in preparation
	sched/psi: Extract update_triggers side effect
	sched/psi: Allow unprivileged polling of N*2s period
	sched/psi: use kernfs polling functions for PSI trigger polling
	pinctrl: renesas: rzv2m: Handle non-unique subnode names
	pinctrl: renesas: rzg2l: Handle non-unique subnode names
	spi: bcm63xx: fix max prepend length
	fbdev: imxfb: warn about invalid left/right margin
	fbdev: imxfb: Removed unneeded release_mem_region
	perf build: Fix library not found error when using CSLIBS
	btrfs: be a bit more careful when setting mirror_num_ret in btrfs_map_block
	spi: s3c64xx: clear loopback bit after loopback test
	kallsyms: Improve the performance of kallsyms_lookup_name()
	kallsyms: Correctly sequence symbols when CONFIG_LTO_CLANG=y
	kallsyms: strip LTO-only suffixes from promoted global functions
	dsa: mv88e6xxx: Do a final check before timing out
	net: ethernet: ti: cpsw_ale: Fix cpsw_ale_get_field()/cpsw_ale_set_field()
	bridge: Add extack warning when enabling STP in netns.
	net: ethernet: mtk_eth_soc: handle probe deferral
	cifs: fix mid leak during reconnection after timeout threshold
	ASoC: SOF: ipc3-dtrace: uninitialized data in dfsentry_trace_filter_write()
	net: sched: cls_matchall: Undo tcf_bind_filter in case of failure after mall_set_parms
	net: sched: cls_u32: Undo tcf_bind_filter if u32_replace_hw_knode
	net: sched: cls_u32: Undo refcount decrement in case update failed
	net: sched: cls_bpf: Undo tcf_bind_filter in case of an error
	net: dsa: microchip: ksz8: Separate static MAC table operations for code reuse
	net: dsa: microchip: ksz8: Make ksz8_r_sta_mac_table() static
	net: dsa: microchip: ksz8_r_sta_mac_table(): Avoid using error code for empty entries
	net: dsa: microchip: correct KSZ8795 static MAC table access
	iavf: Fix use-after-free in free_netdev
	iavf: Fix out-of-bounds when setting channels on remove
	iavf: use internal state to free traffic IRQs
	iavf: Move netdev_update_features() into watchdog task
	iavf: send VLAN offloading caps once after VFR
	iavf: make functions static where possible
	iavf: Wait for reset in callbacks which trigger it
	iavf: fix a deadlock caused by rtnl and driver's lock circular dependencies
	iavf: fix reset task race with iavf_remove()
	security: keys: Modify mismatched function name
	octeontx2-pf: Dont allocate BPIDs for LBK interfaces
	bpf: Fix subprog idx logic in check_max_stack_depth
	bpf: Repeat check_max_stack_depth for async callbacks
	bpf, arm64: Fix BTI type used for freplace attached functions
	igc: Avoid transmit queue timeout for XDP
	igc: Prevent garbled TX queue with XDP ZEROCOPY
	net: ipv4: use consistent txhash in TIME_WAIT and SYN_RECV
	tcp: annotate data-races around tcp_rsk(req)->txhash
	tcp: annotate data-races around tcp_rsk(req)->ts_recent
	net: ipv4: Use kfree_sensitive instead of kfree
	net:ipv6: check return value of pskb_trim()
	Revert "tcp: avoid the lookup process failing to get sk in ehash table"
	fbdev: au1200fb: Fix missing IRQ check in au1200fb_drv_probe
	llc: Don't drop packet from non-root netns.
	ALSA: hda/realtek: Fix generic fixup definition for cs35l41 amp
	netfilter: nf_tables: fix spurious set element insertion failure
	netfilter: nf_tables: can't schedule in nft_chain_validate
	netfilter: nft_set_pipapo: fix improper element removal
	netfilter: nf_tables: skip bound chain in netns release path
	netfilter: nf_tables: skip bound chain on rule flush
	Bluetooth: use RCU for hci_conn_params and iterate safely in hci_sync
	Bluetooth: hci_event: call disconnect callback before deleting conn
	Bluetooth: ISO: fix iso_conn related locking and validity issues
	Bluetooth: hci_sync: Avoid use-after-free in dbg for hci_remove_adv_monitor()
	tcp: annotate data-races around tp->tcp_tx_delay
	tcp: annotate data-races around tp->tsoffset
	tcp: annotate data-races around tp->keepalive_time
	tcp: annotate data-races around tp->keepalive_intvl
	tcp: annotate data-races around tp->keepalive_probes
	tcp: annotate data-races around icsk->icsk_syn_retries
	tcp: annotate data-races around tp->linger2
	tcp: annotate data-races around rskq_defer_accept
	tcp: annotate data-races around tp->notsent_lowat
	tcp: annotate data-races around icsk->icsk_user_timeout
	tcp: annotate data-races around fastopenq.max_qlen
	net: phy: prevent stale pointer dereference in phy_init()
	jbd2: recheck chechpointing non-dirty buffer
	tracing/histograms: Return an error if we fail to add histogram to hist_vars list
	drm/ttm: fix bulk_move corruption when adding a entry
	spi: dw: Remove misleading comment for Mount Evans SoC
	kallsyms: add kallsyms_seqs_of_names to list of special symbols
	scripts/kallsyms.c Make the comment up-to-date with current implementation
	scripts/kallsyms: update the usage in the comment block
	bpf: allow precision tracking for programs with subprogs
	bpf: stop setting precise in current state
	bpf: aggressively forget precise markings during state checkpointing
	selftests/bpf: make test_align selftest more robust
	selftests/bpf: Workaround verification failure for fexit_bpf2bpf/func_replace_return_code
	selftests/bpf: Fix sk_assign on s390x
	drm/amd/display: use max_dsc_bpp in amdgpu_dm
	drm/amd/display: fix some coding style issues
	drm/dp_mst: Clear MSG_RDY flag before sending new message
	drm/amd/display: force connector state when bpc changes during compliance
	drm/amd/display: Clean up errors & warnings in amdgpu_dm.c
	drm/amd/display: fix linux dp link lost handled only one time
	drm/amd/display: Add polling method to handle MST reply packet
	Revert "drm/amd/display: edp do not add non-edid timings"
	Linux 6.1.42

Change-Id: I6b7257a16f9a025d0c23dfd3eb43317c1c164a93
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
2023-09-06 10:23:12 +00:00

796 lines
22 KiB
C

/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* Definitions for the IP module.
*
* Version: @(#)ip.h 1.0.2 05/07/93
*
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Alan Cox, <gw4pts@gw4pts.ampr.org>
*
* Changes:
* Mike McLagan : Routing by source
*/
#ifndef _IP_H
#define _IP_H
#include <linux/types.h>
#include <linux/ip.h>
#include <linux/in.h>
#include <linux/skbuff.h>
#include <linux/jhash.h>
#include <linux/sockptr.h>
#include <linux/static_key.h>
#include <linux/android_kabi.h>
#include <net/inet_sock.h>
#include <net/route.h>
#include <net/snmp.h>
#include <net/flow.h>
#include <net/flow_dissector.h>
#include <net/netns/hash.h>
#include <net/lwtunnel.h>
#define IPV4_MAX_PMTU 65535U /* RFC 2675, Section 5.1 */
#define IPV4_MIN_MTU 68 /* RFC 791 */
extern unsigned int sysctl_fib_sync_mem;
extern unsigned int sysctl_fib_sync_mem_min;
extern unsigned int sysctl_fib_sync_mem_max;
struct sock;
struct inet_skb_parm {
int iif;
struct ip_options opt; /* Compiled IP options */
u16 flags;
#define IPSKB_FORWARDED BIT(0)
#define IPSKB_XFRM_TUNNEL_SIZE BIT(1)
#define IPSKB_XFRM_TRANSFORMED BIT(2)
#define IPSKB_FRAG_COMPLETE BIT(3)
#define IPSKB_REROUTED BIT(4)
#define IPSKB_DOREDIRECT BIT(5)
#define IPSKB_FRAG_PMTU BIT(6)
#define IPSKB_L3SLAVE BIT(7)
#define IPSKB_NOPOLICY BIT(8)
u16 frag_max_size;
};
static inline bool ipv4_l3mdev_skb(u16 flags)
{
return !!(flags & IPSKB_L3SLAVE);
}
static inline unsigned int ip_hdrlen(const struct sk_buff *skb)
{
return ip_hdr(skb)->ihl * 4;
}
struct ipcm_cookie {
struct sockcm_cookie sockc;
__be32 addr;
int oif;
struct ip_options_rcu *opt;
__u8 protocol;
__u8 ttl;
__s16 tos;
char priority;
__u16 gso_size;
ANDROID_KABI_RESERVE(1);
};
static inline void ipcm_init(struct ipcm_cookie *ipcm)
{
*ipcm = (struct ipcm_cookie) { .tos = -1 };
}
static inline void ipcm_init_sk(struct ipcm_cookie *ipcm,
const struct inet_sock *inet)
{
ipcm_init(ipcm);
ipcm->sockc.mark = inet->sk.sk_mark;
ipcm->sockc.tsflags = inet->sk.sk_tsflags;
ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if);
ipcm->addr = inet->inet_saddr;
ipcm->protocol = inet->inet_num;
}
#define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb))
#define PKTINFO_SKB_CB(skb) ((struct in_pktinfo *)((skb)->cb))
/* return enslaved device index if relevant */
static inline int inet_sdif(const struct sk_buff *skb)
{
#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
if (skb && ipv4_l3mdev_skb(IPCB(skb)->flags))
return IPCB(skb)->iif;
#endif
return 0;
}
/* Special input handler for packets caught by router alert option.
They are selected only by protocol field, and then processed likely
local ones; but only if someone wants them! Otherwise, router
not running rsvpd will kill RSVP.
It is user level problem, what it will make with them.
I have no idea, how it will masquearde or NAT them (it is joke, joke :-)),
but receiver should be enough clever f.e. to forward mtrace requests,
sent to multicast group to reach destination designated router.
*/
struct ip_ra_chain {
struct ip_ra_chain __rcu *next;
struct sock *sk;
union {
void (*destructor)(struct sock *);
struct sock *saved_sk;
};
struct rcu_head rcu;
};
/* IP flags. */
#define IP_CE 0x8000 /* Flag: "Congestion" */
#define IP_DF 0x4000 /* Flag: "Don't Fragment" */
#define IP_MF 0x2000 /* Flag: "More Fragments" */
#define IP_OFFSET 0x1FFF /* "Fragment Offset" part */
#define IP_FRAG_TIME (30 * HZ) /* fragment lifetime */
struct msghdr;
struct net_device;
struct packet_type;
struct rtable;
struct sockaddr;
int igmp_mc_init(void);
/*
* Functions provided by ip.c
*/
int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk,
__be32 saddr, __be32 daddr,
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,
struct net_device *orig_dev);
int ip_local_deliver(struct sk_buff *skb);
void ip_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int proto);
int ip_mr_input(struct sk_buff *skb);
int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb);
int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb);
int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
int (*output)(struct net *, struct sock *, struct sk_buff *));
struct ip_fraglist_iter {
struct sk_buff *frag;
struct iphdr *iph;
int offset;
unsigned int hlen;
};
void ip_fraglist_init(struct sk_buff *skb, struct iphdr *iph,
unsigned int hlen, struct ip_fraglist_iter *iter);
void ip_fraglist_prepare(struct sk_buff *skb, struct ip_fraglist_iter *iter);
static inline struct sk_buff *ip_fraglist_next(struct ip_fraglist_iter *iter)
{
struct sk_buff *skb = iter->frag;
iter->frag = skb->next;
skb_mark_not_on_list(skb);
return skb;
}
struct ip_frag_state {
bool DF;
unsigned int hlen;
unsigned int ll_rs;
unsigned int mtu;
unsigned int left;
int offset;
int ptr;
__be16 not_last_frag;
};
void ip_frag_init(struct sk_buff *skb, unsigned int hlen, unsigned int ll_rs,
unsigned int mtu, bool DF, struct ip_frag_state *state);
struct sk_buff *ip_frag_next(struct sk_buff *skb,
struct ip_frag_state *state);
void ip_send_check(struct iphdr *ip);
int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb);
int ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb);
int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
__u8 tos);
void ip_init(void);
int ip_append_data(struct sock *sk, struct flowi4 *fl4,
int getfrag(void *from, char *to, int offset, int len,
int odd, struct sk_buff *skb),
void *from, int len, int protolen,
struct ipcm_cookie *ipc,
struct rtable **rt,
unsigned int flags);
int ip_generic_getfrag(void *from, char *to, int offset, int len, int odd,
struct sk_buff *skb);
ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
int offset, size_t size, int flags);
struct sk_buff *__ip_make_skb(struct sock *sk, struct flowi4 *fl4,
struct sk_buff_head *queue,
struct inet_cork *cork);
int ip_send_skb(struct net *net, struct sk_buff *skb);
int ip_push_pending_frames(struct sock *sk, struct flowi4 *fl4);
void ip_flush_pending_frames(struct sock *sk);
struct sk_buff *ip_make_skb(struct sock *sk, struct flowi4 *fl4,
int getfrag(void *from, char *to, int offset,
int len, int odd, struct sk_buff *skb),
void *from, int length, int transhdrlen,
struct ipcm_cookie *ipc, struct rtable **rtp,
struct inet_cork *cork, unsigned int flags);
int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl);
static inline struct sk_buff *ip_finish_skb(struct sock *sk, struct flowi4 *fl4)
{
return __ip_make_skb(sk, fl4, &sk->sk_write_queue, &inet_sk(sk)->cork.base);
}
static inline __u8 get_rttos(struct ipcm_cookie* ipc, struct inet_sock *inet)
{
return (ipc->tos != -1) ? RT_TOS(ipc->tos) : RT_TOS(inet->tos);
}
static inline __u8 get_rtconn_flags(struct ipcm_cookie* ipc, struct sock* sk)
{
return (ipc->tos != -1) ? RT_CONN_FLAGS_TOS(sk, ipc->tos) : RT_CONN_FLAGS(sk);
}
/* datagram.c */
int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
void ip4_datagram_release_cb(struct sock *sk);
struct ip_reply_arg {
struct kvec iov[1];
int flags;
__wsum csum;
int csumoffset; /* u16 offset of csum in iov[0].iov_base */
/* -1 if not needed */
int bound_dev_if;
u8 tos;
kuid_t uid;
};
#define IP_REPLY_ARG_NOSRCCHECK 1
static inline __u8 ip_reply_arg_flowi_flags(const struct ip_reply_arg *arg)
{
return (arg->flags & IP_REPLY_ARG_NOSRCCHECK) ? FLOWI_FLAG_ANYSRC : 0;
}
void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
const struct ip_options *sopt,
__be32 daddr, __be32 saddr,
const struct ip_reply_arg *arg,
unsigned int len, u64 transmit_time, u32 txhash);
#define IP_INC_STATS(net, field) SNMP_INC_STATS64((net)->mib.ip_statistics, field)
#define __IP_INC_STATS(net, field) __SNMP_INC_STATS64((net)->mib.ip_statistics, field)
#define IP_ADD_STATS(net, field, val) SNMP_ADD_STATS64((net)->mib.ip_statistics, field, val)
#define __IP_ADD_STATS(net, field, val) __SNMP_ADD_STATS64((net)->mib.ip_statistics, field, val)
#define IP_UPD_PO_STATS(net, field, val) SNMP_UPD_PO_STATS64((net)->mib.ip_statistics, field, val)
#define __IP_UPD_PO_STATS(net, field, val) __SNMP_UPD_PO_STATS64((net)->mib.ip_statistics, field, val)
#define NET_INC_STATS(net, field) SNMP_INC_STATS((net)->mib.net_statistics, field)
#define __NET_INC_STATS(net, field) __SNMP_INC_STATS((net)->mib.net_statistics, field)
#define NET_ADD_STATS(net, field, adnd) SNMP_ADD_STATS((net)->mib.net_statistics, field, adnd)
#define __NET_ADD_STATS(net, field, adnd) __SNMP_ADD_STATS((net)->mib.net_statistics, field, adnd)
static inline u64 snmp_get_cpu_field(void __percpu *mib, int cpu, int offt)
{
return *(((unsigned long *)per_cpu_ptr(mib, cpu)) + offt);
}
unsigned long snmp_fold_field(void __percpu *mib, int offt);
#if BITS_PER_LONG==32
u64 snmp_get_cpu_field64(void __percpu *mib, int cpu, int offct,
size_t syncp_offset);
u64 snmp_fold_field64(void __percpu *mib, int offt, size_t sync_off);
#else
static inline u64 snmp_get_cpu_field64(void __percpu *mib, int cpu, int offct,
size_t syncp_offset)
{
return snmp_get_cpu_field(mib, cpu, offct);
}
static inline u64 snmp_fold_field64(void __percpu *mib, int offt, size_t syncp_off)
{
return snmp_fold_field(mib, offt);
}
#endif
#define snmp_get_cpu_field64_batch(buff64, stats_list, mib_statistic, offset) \
{ \
int i, c; \
for_each_possible_cpu(c) { \
for (i = 0; stats_list[i].name; i++) \
buff64[i] += snmp_get_cpu_field64( \
mib_statistic, \
c, stats_list[i].entry, \
offset); \
} \
}
#define snmp_get_cpu_field_batch(buff, stats_list, mib_statistic) \
{ \
int i, c; \
for_each_possible_cpu(c) { \
for (i = 0; stats_list[i].name; i++) \
buff[i] += snmp_get_cpu_field( \
mib_statistic, \
c, stats_list[i].entry); \
} \
}
void inet_get_local_port_range(const struct net *net, int *low, int *high);
void inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high);
#ifdef CONFIG_SYSCTL
static inline bool inet_is_local_reserved_port(struct net *net, unsigned short port)
{
if (!net->ipv4.sysctl_local_reserved_ports)
return false;
return test_bit(port, net->ipv4.sysctl_local_reserved_ports);
}
static inline bool sysctl_dev_name_is_allowed(const char *name)
{
return strcmp(name, "default") != 0 && strcmp(name, "all") != 0;
}
static inline bool inet_port_requires_bind_service(struct net *net, unsigned short port)
{
return port < READ_ONCE(net->ipv4.sysctl_ip_prot_sock);
}
#else
static inline bool inet_is_local_reserved_port(struct net *net, unsigned short port)
{
return false;
}
static inline bool inet_port_requires_bind_service(struct net *net, unsigned short port)
{
return port < PROT_SOCK;
}
#endif
__be32 inet_current_timestamp(void);
/* From inetpeer.c */
extern int inet_peer_threshold;
extern int inet_peer_minttl;
extern int inet_peer_maxttl;
void ipfrag_init(void);
void ip_static_sysctl_init(void);
#define IP4_REPLY_MARK(net, mark) \
(READ_ONCE((net)->ipv4.sysctl_fwmark_reflect) ? (mark) : 0)
static inline bool ip_is_fragment(const struct iphdr *iph)
{
return (iph->frag_off & htons(IP_MF | IP_OFFSET)) != 0;
}
#ifdef CONFIG_INET
#include <net/dst.h>
/* The function in 2.2 was invalid, producing wrong result for
* check=0xFEFF. It was noticed by Arthur Skawina _year_ ago. --ANK(000625) */
static inline
int ip_decrease_ttl(struct iphdr *iph)
{
u32 check = (__force u32)iph->check;
check += (__force u32)htons(0x0100);
iph->check = (__force __sum16)(check + (check>=0xFFFF));
return --iph->ttl;
}
static inline int ip_mtu_locked(const struct dst_entry *dst)
{
const struct rtable *rt = (const struct rtable *)dst;
return rt->rt_mtu_locked || dst_metric_locked(dst, RTAX_MTU);
}
static inline
int ip_dont_fragment(const struct sock *sk, const struct dst_entry *dst)
{
u8 pmtudisc = READ_ONCE(inet_sk(sk)->pmtudisc);
return pmtudisc == IP_PMTUDISC_DO ||
(pmtudisc == IP_PMTUDISC_WANT &&
!ip_mtu_locked(dst));
}
static inline bool ip_sk_accept_pmtu(const struct sock *sk)
{
return inet_sk(sk)->pmtudisc != IP_PMTUDISC_INTERFACE &&
inet_sk(sk)->pmtudisc != IP_PMTUDISC_OMIT;
}
static inline bool ip_sk_use_pmtu(const struct sock *sk)
{
return inet_sk(sk)->pmtudisc < IP_PMTUDISC_PROBE;
}
static inline bool ip_sk_ignore_df(const struct sock *sk)
{
return inet_sk(sk)->pmtudisc < IP_PMTUDISC_DO ||
inet_sk(sk)->pmtudisc == IP_PMTUDISC_OMIT;
}
static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst,
bool forwarding)
{
const struct rtable *rt = container_of(dst, struct rtable, dst);
struct net *net = dev_net(dst->dev);
unsigned int mtu;
if (READ_ONCE(net->ipv4.sysctl_ip_fwd_use_pmtu) ||
ip_mtu_locked(dst) ||
!forwarding) {
mtu = rt->rt_pmtu;
if (mtu && time_before(jiffies, rt->dst.expires))
goto out;
}
/* 'forwarding = true' case should always honour route mtu */
mtu = dst_metric_raw(dst, RTAX_MTU);
if (mtu)
goto out;
mtu = READ_ONCE(dst->dev->mtu);
if (unlikely(ip_mtu_locked(dst))) {
if (rt->rt_uses_gateway && mtu > 576)
mtu = 576;
}
out:
mtu = min_t(unsigned int, mtu, IP_MAX_MTU);
return mtu - lwtunnel_headroom(dst->lwtstate, mtu);
}
static inline unsigned int ip_skb_dst_mtu(struct sock *sk,
const struct sk_buff *skb)
{
unsigned int mtu;
if (!sk || !sk_fullsock(sk) || ip_sk_use_pmtu(sk)) {
bool forwarding = IPCB(skb)->flags & IPSKB_FORWARDED;
return ip_dst_mtu_maybe_forward(skb_dst(skb), forwarding);
}
mtu = min(READ_ONCE(skb_dst(skb)->dev->mtu), IP_MAX_MTU);
return mtu - lwtunnel_headroom(skb_dst(skb)->lwtstate, mtu);
}
struct dst_metrics *ip_fib_metrics_init(struct net *net, struct nlattr *fc_mx,
int fc_mx_len,
struct netlink_ext_ack *extack);
static inline void ip_fib_metrics_put(struct dst_metrics *fib_metrics)
{
if (fib_metrics != &dst_default_metrics &&
refcount_dec_and_test(&fib_metrics->refcnt))
kfree(fib_metrics);
}
/* ipv4 and ipv6 both use refcounted metrics if it is not the default */
static inline
void ip_dst_init_metrics(struct dst_entry *dst, struct dst_metrics *fib_metrics)
{
dst_init_metrics(dst, fib_metrics->metrics, true);
if (fib_metrics != &dst_default_metrics) {
dst->_metrics |= DST_METRICS_REFCOUNTED;
refcount_inc(&fib_metrics->refcnt);
}
}
static inline
void ip_dst_metrics_put(struct dst_entry *dst)
{
struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst);
if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt))
kfree(p);
}
void __ip_select_ident(struct net *net, struct iphdr *iph, int segs);
static inline void ip_select_ident_segs(struct net *net, struct sk_buff *skb,
struct sock *sk, int segs)
{
struct iphdr *iph = ip_hdr(skb);
/* We had many attacks based on IPID, use the private
* generator as much as we can.
*/
if (sk && inet_sk(sk)->inet_daddr) {
iph->id = htons(inet_sk(sk)->inet_id);
inet_sk(sk)->inet_id += segs;
return;
}
if ((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) {
iph->id = 0;
} else {
/* Unfortunately we need the big hammer to get a suitable IPID */
__ip_select_ident(net, iph, segs);
}
}
static inline void ip_select_ident(struct net *net, struct sk_buff *skb,
struct sock *sk)
{
ip_select_ident_segs(net, skb, sk, 1);
}
static inline __wsum inet_compute_pseudo(struct sk_buff *skb, int proto)
{
return csum_tcpudp_nofold(ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
skb->len, proto, 0);
}
/* copy IPv4 saddr & daddr to flow_keys, possibly using 64bit load/store
* Equivalent to : flow->v4addrs.src = iph->saddr;
* flow->v4addrs.dst = iph->daddr;
*/
static inline void iph_to_flow_copy_v4addrs(struct flow_keys *flow,
const struct iphdr *iph)
{
BUILD_BUG_ON(offsetof(typeof(flow->addrs), v4addrs.dst) !=
offsetof(typeof(flow->addrs), v4addrs.src) +
sizeof(flow->addrs.v4addrs.src));
memcpy(&flow->addrs.v4addrs, &iph->addrs, sizeof(flow->addrs.v4addrs));
flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
}
/*
* Map a multicast IP onto multicast MAC for type ethernet.
*/
static inline void ip_eth_mc_map(__be32 naddr, char *buf)
{
__u32 addr=ntohl(naddr);
buf[0]=0x01;
buf[1]=0x00;
buf[2]=0x5e;
buf[5]=addr&0xFF;
addr>>=8;
buf[4]=addr&0xFF;
addr>>=8;
buf[3]=addr&0x7F;
}
/*
* Map a multicast IP onto multicast MAC for type IP-over-InfiniBand.
* Leave P_Key as 0 to be filled in by driver.
*/
static inline void ip_ib_mc_map(__be32 naddr, const unsigned char *broadcast, char *buf)
{
__u32 addr;
unsigned char scope = broadcast[5] & 0xF;
buf[0] = 0; /* Reserved */
buf[1] = 0xff; /* Multicast QPN */
buf[2] = 0xff;
buf[3] = 0xff;
addr = ntohl(naddr);
buf[4] = 0xff;
buf[5] = 0x10 | scope; /* scope from broadcast address */
buf[6] = 0x40; /* IPv4 signature */
buf[7] = 0x1b;
buf[8] = broadcast[8]; /* P_Key */
buf[9] = broadcast[9];
buf[10] = 0;
buf[11] = 0;
buf[12] = 0;
buf[13] = 0;
buf[14] = 0;
buf[15] = 0;
buf[19] = addr & 0xff;
addr >>= 8;
buf[18] = addr & 0xff;
addr >>= 8;
buf[17] = addr & 0xff;
addr >>= 8;
buf[16] = addr & 0x0f;
}
static inline void ip_ipgre_mc_map(__be32 naddr, const unsigned char *broadcast, char *buf)
{
if ((broadcast[0] | broadcast[1] | broadcast[2] | broadcast[3]) != 0)
memcpy(buf, broadcast, 4);
else
memcpy(buf, &naddr, sizeof(naddr));
}
#if IS_ENABLED(CONFIG_IPV6)
#include <linux/ipv6.h>
#endif
static __inline__ void inet_reset_saddr(struct sock *sk)
{
inet_sk(sk)->inet_rcv_saddr = inet_sk(sk)->inet_saddr = 0;
#if IS_ENABLED(CONFIG_IPV6)
if (sk->sk_family == PF_INET6) {
struct ipv6_pinfo *np = inet6_sk(sk);
memset(&np->saddr, 0, sizeof(np->saddr));
memset(&sk->sk_v6_rcv_saddr, 0, sizeof(sk->sk_v6_rcv_saddr));
}
#endif
}
#endif
static inline unsigned int ipv4_addr_hash(__be32 ip)
{
return (__force unsigned int) ip;
}
static inline u32 ipv4_portaddr_hash(const struct net *net,
__be32 saddr,
unsigned int port)
{
return jhash_1word((__force u32)saddr, net_hash_mix(net)) ^ port;
}
bool ip_call_ra_chain(struct sk_buff *skb);
/*
* Functions provided by ip_fragment.c
*/
enum ip_defrag_users {
IP_DEFRAG_LOCAL_DELIVER,
IP_DEFRAG_CALL_RA_CHAIN,
IP_DEFRAG_CONNTRACK_IN,
__IP_DEFRAG_CONNTRACK_IN_END = IP_DEFRAG_CONNTRACK_IN + USHRT_MAX,
IP_DEFRAG_CONNTRACK_OUT,
__IP_DEFRAG_CONNTRACK_OUT_END = IP_DEFRAG_CONNTRACK_OUT + USHRT_MAX,
IP_DEFRAG_CONNTRACK_BRIDGE_IN,
__IP_DEFRAG_CONNTRACK_BRIDGE_IN = IP_DEFRAG_CONNTRACK_BRIDGE_IN + USHRT_MAX,
IP_DEFRAG_VS_IN,
IP_DEFRAG_VS_OUT,
IP_DEFRAG_VS_FWD,
IP_DEFRAG_AF_PACKET,
IP_DEFRAG_MACVLAN,
};
/* Return true if the value of 'user' is between 'lower_bond'
* and 'upper_bond' inclusively.
*/
static inline bool ip_defrag_user_in_between(u32 user,
enum ip_defrag_users lower_bond,
enum ip_defrag_users upper_bond)
{
return user >= lower_bond && user <= upper_bond;
}
int ip_defrag(struct net *net, struct sk_buff *skb, u32 user);
#ifdef CONFIG_INET
struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user);
#else
static inline struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user)
{
return skb;
}
#endif
/*
* Functions provided by ip_forward.c
*/
int ip_forward(struct sk_buff *skb);
/*
* Functions provided by ip_options.c
*/
void ip_options_build(struct sk_buff *skb, struct ip_options *opt,
__be32 daddr, struct rtable *rt);
int __ip_options_echo(struct net *net, struct ip_options *dopt,
struct sk_buff *skb, const struct ip_options *sopt);
static inline int ip_options_echo(struct net *net, struct ip_options *dopt,
struct sk_buff *skb)
{
return __ip_options_echo(net, dopt, skb, &IPCB(skb)->opt);
}
void ip_options_fragment(struct sk_buff *skb);
int __ip_options_compile(struct net *net, struct ip_options *opt,
struct sk_buff *skb, __be32 *info);
int ip_options_compile(struct net *net, struct ip_options *opt,
struct sk_buff *skb);
int ip_options_get(struct net *net, struct ip_options_rcu **optp,
sockptr_t data, int optlen);
void ip_options_undo(struct ip_options *opt);
void ip_forward_options(struct sk_buff *skb);
int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev);
/*
* Functions provided by ip_sockglue.c
*/
void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb);
void ip_cmsg_recv_offset(struct msghdr *msg, struct sock *sk,
struct sk_buff *skb, int tlen, int offset);
int ip_cmsg_send(struct sock *sk, struct msghdr *msg,
struct ipcm_cookie *ipc, bool allow_ipv6);
DECLARE_STATIC_KEY_FALSE(ip4_min_ttl);
int do_ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
unsigned int optlen);
int ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
unsigned int optlen);
int do_ip_getsockopt(struct sock *sk, int level, int optname,
sockptr_t optval, sockptr_t optlen);
int ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval,
int __user *optlen);
int ip_ra_control(struct sock *sk, unsigned char on,
void (*destructor)(struct sock *));
int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len);
void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port,
u32 info, u8 *payload);
void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 dport,
u32 info);
static inline void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb)
{
ip_cmsg_recv_offset(msg, skb->sk, skb, 0, 0);
}
bool icmp_global_allow(void);
extern int sysctl_icmp_msgs_per_sec;
extern int sysctl_icmp_msgs_burst;
#ifdef CONFIG_PROC_FS
int ip_misc_proc_init(void);
#endif
int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto, u8 family,
struct netlink_ext_ack *extack);
static inline bool inetdev_valid_mtu(unsigned int mtu)
{
return likely(mtu >= IPV4_MIN_MTU);
}
void ip_sock_set_freebind(struct sock *sk);
int ip_sock_set_mtu_discover(struct sock *sk, int val);
void ip_sock_set_pktinfo(struct sock *sk);
void ip_sock_set_recverr(struct sock *sk);
void ip_sock_set_tos(struct sock *sk, int val);
void __ip_sock_set_tos(struct sock *sk, int val);
#endif /* _IP_H */