mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-24 22:16:43 +07:00
d1b4c689d4
mmapped netlink has a number of unresolved issues: - TX zerocopy support had to be disabled more than a year ago via commit4682a03586
("netlink: Always copy on mmap TX.") because the content of the mmapped area can change after netlink attribute validation but before message processing. - RX support was implemented mainly to speed up nfqueue dumping packet payload to userspace. However, since commitae08ce0021
("netfilter: nfnetlink_queue: zero copy support") we avoid one copy with the socket-based interface too (via the skb_zerocopy helper). The other problem is that skbs attached to mmaped netlink socket behave different from normal skbs: - they don't have a shinfo area, so all functions that use skb_shinfo() (e.g. skb_clone) cannot be used. - reserving headroom prevents userspace from seeing the content as it expects message to start at skb->head. See for instance commitaa3a022094
("netlink: not trim skb for mmaped socket when dump"). - skbs handed e.g. to netlink_ack must have non-NULL skb->sk, else we crash because it needs the sk to check if a tx ring is attached. Also not obvious, leads to non-intuitive bug fixes such as7c7bdf359
("netfilter: nfnetlink: use original skbuff when acking batches"). mmaped netlink also didn't play nicely with the skb_zerocopy helper used by nfqueue and openvswitch. Daniel Borkmann fixed this via commit6bb0fef489
("netlink, mmap: fix edge-case leakages in nf queue zero-copy")' but at the cost of also needing to provide remaining length to the allocation function. nfqueue also has problems when used with mmaped rx netlink: - mmaped netlink doesn't allow use of nfqueue batch verdict messages. Problem is that in the mmap case, the allocation time also determines the ordering in which the frame will be seen by userspace (A allocating before B means that A is located in earlier ring slot, but this also means that B might get a lower sequence number then A since seqno is decided later. To fix this we would need to extend the spinlocked region to also cover the allocation and message setup which isn't desirable. - nfqueue can now be configured to queue large (GSO) skbs to userspace. Queing GSO packets is faster than having to force a software segmentation in the kernel, so this is a desirable option. However, with a mmap based ring one has to use 64kb per ring slot element, else mmap has to fall back to the socket path (NL_MMAP_STATUS_COPY) for all large packets. To use the mmap interface, userspace not only has to probe for mmap netlink support, it also has to implement a recv/socket receive path in order to handle messages that exceed the size of an rx ring element. Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Ken-ichirou MATSUZAWA <chamaken@gmail.com> Cc: Pablo Neira Ayuso <pablo@netfilter.org> Cc: Patrick McHardy <kaber@trash.net> Cc: Thomas Graf <tgraf@suug.ch> Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: David S. Miller <davem@davemloft.net>
194 lines
5.9 KiB
C
194 lines
5.9 KiB
C
#ifndef _UAPI__LINUX_NETLINK_H
|
|
#define _UAPI__LINUX_NETLINK_H
|
|
|
|
#include <linux/kernel.h>
|
|
#include <linux/socket.h> /* for __kernel_sa_family_t */
|
|
#include <linux/types.h>
|
|
|
|
#define NETLINK_ROUTE 0 /* Routing/device hook */
|
|
#define NETLINK_UNUSED 1 /* Unused number */
|
|
#define NETLINK_USERSOCK 2 /* Reserved for user mode socket protocols */
|
|
#define NETLINK_FIREWALL 3 /* Unused number, formerly ip_queue */
|
|
#define NETLINK_SOCK_DIAG 4 /* socket monitoring */
|
|
#define NETLINK_NFLOG 5 /* netfilter/iptables ULOG */
|
|
#define NETLINK_XFRM 6 /* ipsec */
|
|
#define NETLINK_SELINUX 7 /* SELinux event notifications */
|
|
#define NETLINK_ISCSI 8 /* Open-iSCSI */
|
|
#define NETLINK_AUDIT 9 /* auditing */
|
|
#define NETLINK_FIB_LOOKUP 10
|
|
#define NETLINK_CONNECTOR 11
|
|
#define NETLINK_NETFILTER 12 /* netfilter subsystem */
|
|
#define NETLINK_IP6_FW 13
|
|
#define NETLINK_DNRTMSG 14 /* DECnet routing messages */
|
|
#define NETLINK_KOBJECT_UEVENT 15 /* Kernel messages to userspace */
|
|
#define NETLINK_GENERIC 16
|
|
/* leave room for NETLINK_DM (DM Events) */
|
|
#define NETLINK_SCSITRANSPORT 18 /* SCSI Transports */
|
|
#define NETLINK_ECRYPTFS 19
|
|
#define NETLINK_RDMA 20
|
|
#define NETLINK_CRYPTO 21 /* Crypto layer */
|
|
|
|
#define NETLINK_INET_DIAG NETLINK_SOCK_DIAG
|
|
|
|
#define MAX_LINKS 32
|
|
|
|
struct sockaddr_nl {
|
|
__kernel_sa_family_t nl_family; /* AF_NETLINK */
|
|
unsigned short nl_pad; /* zero */
|
|
__u32 nl_pid; /* port ID */
|
|
__u32 nl_groups; /* multicast groups mask */
|
|
};
|
|
|
|
struct nlmsghdr {
|
|
__u32 nlmsg_len; /* Length of message including header */
|
|
__u16 nlmsg_type; /* Message content */
|
|
__u16 nlmsg_flags; /* Additional flags */
|
|
__u32 nlmsg_seq; /* Sequence number */
|
|
__u32 nlmsg_pid; /* Sending process port ID */
|
|
};
|
|
|
|
/* Flags values */
|
|
|
|
#define NLM_F_REQUEST 1 /* It is request message. */
|
|
#define NLM_F_MULTI 2 /* Multipart message, terminated by NLMSG_DONE */
|
|
#define NLM_F_ACK 4 /* Reply with ack, with zero or error code */
|
|
#define NLM_F_ECHO 8 /* Echo this request */
|
|
#define NLM_F_DUMP_INTR 16 /* Dump was inconsistent due to sequence change */
|
|
#define NLM_F_DUMP_FILTERED 32 /* Dump was filtered as requested */
|
|
|
|
/* Modifiers to GET request */
|
|
#define NLM_F_ROOT 0x100 /* specify tree root */
|
|
#define NLM_F_MATCH 0x200 /* return all matching */
|
|
#define NLM_F_ATOMIC 0x400 /* atomic GET */
|
|
#define NLM_F_DUMP (NLM_F_ROOT|NLM_F_MATCH)
|
|
|
|
/* Modifiers to NEW request */
|
|
#define NLM_F_REPLACE 0x100 /* Override existing */
|
|
#define NLM_F_EXCL 0x200 /* Do not touch, if it exists */
|
|
#define NLM_F_CREATE 0x400 /* Create, if it does not exist */
|
|
#define NLM_F_APPEND 0x800 /* Add to end of list */
|
|
|
|
/*
|
|
4.4BSD ADD NLM_F_CREATE|NLM_F_EXCL
|
|
4.4BSD CHANGE NLM_F_REPLACE
|
|
|
|
True CHANGE NLM_F_CREATE|NLM_F_REPLACE
|
|
Append NLM_F_CREATE
|
|
Check NLM_F_EXCL
|
|
*/
|
|
|
|
#define NLMSG_ALIGNTO 4U
|
|
#define NLMSG_ALIGN(len) ( ((len)+NLMSG_ALIGNTO-1) & ~(NLMSG_ALIGNTO-1) )
|
|
#define NLMSG_HDRLEN ((int) NLMSG_ALIGN(sizeof(struct nlmsghdr)))
|
|
#define NLMSG_LENGTH(len) ((len) + NLMSG_HDRLEN)
|
|
#define NLMSG_SPACE(len) NLMSG_ALIGN(NLMSG_LENGTH(len))
|
|
#define NLMSG_DATA(nlh) ((void*)(((char*)nlh) + NLMSG_LENGTH(0)))
|
|
#define NLMSG_NEXT(nlh,len) ((len) -= NLMSG_ALIGN((nlh)->nlmsg_len), \
|
|
(struct nlmsghdr*)(((char*)(nlh)) + NLMSG_ALIGN((nlh)->nlmsg_len)))
|
|
#define NLMSG_OK(nlh,len) ((len) >= (int)sizeof(struct nlmsghdr) && \
|
|
(nlh)->nlmsg_len >= sizeof(struct nlmsghdr) && \
|
|
(nlh)->nlmsg_len <= (len))
|
|
#define NLMSG_PAYLOAD(nlh,len) ((nlh)->nlmsg_len - NLMSG_SPACE((len)))
|
|
|
|
#define NLMSG_NOOP 0x1 /* Nothing. */
|
|
#define NLMSG_ERROR 0x2 /* Error */
|
|
#define NLMSG_DONE 0x3 /* End of a dump */
|
|
#define NLMSG_OVERRUN 0x4 /* Data lost */
|
|
|
|
#define NLMSG_MIN_TYPE 0x10 /* < 0x10: reserved control messages */
|
|
|
|
struct nlmsgerr {
|
|
int error;
|
|
struct nlmsghdr msg;
|
|
};
|
|
|
|
#define NETLINK_ADD_MEMBERSHIP 1
|
|
#define NETLINK_DROP_MEMBERSHIP 2
|
|
#define NETLINK_PKTINFO 3
|
|
#define NETLINK_BROADCAST_ERROR 4
|
|
#define NETLINK_NO_ENOBUFS 5
|
|
#ifndef __KERNEL__
|
|
#define NETLINK_RX_RING 6
|
|
#define NETLINK_TX_RING 7
|
|
#endif
|
|
#define NETLINK_LISTEN_ALL_NSID 8
|
|
#define NETLINK_LIST_MEMBERSHIPS 9
|
|
#define NETLINK_CAP_ACK 10
|
|
|
|
struct nl_pktinfo {
|
|
__u32 group;
|
|
};
|
|
|
|
struct nl_mmap_req {
|
|
unsigned int nm_block_size;
|
|
unsigned int nm_block_nr;
|
|
unsigned int nm_frame_size;
|
|
unsigned int nm_frame_nr;
|
|
};
|
|
|
|
struct nl_mmap_hdr {
|
|
unsigned int nm_status;
|
|
unsigned int nm_len;
|
|
__u32 nm_group;
|
|
/* credentials */
|
|
__u32 nm_pid;
|
|
__u32 nm_uid;
|
|
__u32 nm_gid;
|
|
};
|
|
|
|
#ifndef __KERNEL__
|
|
enum nl_mmap_status {
|
|
NL_MMAP_STATUS_UNUSED,
|
|
NL_MMAP_STATUS_RESERVED,
|
|
NL_MMAP_STATUS_VALID,
|
|
NL_MMAP_STATUS_COPY,
|
|
NL_MMAP_STATUS_SKIP,
|
|
};
|
|
|
|
#define NL_MMAP_MSG_ALIGNMENT NLMSG_ALIGNTO
|
|
#define NL_MMAP_MSG_ALIGN(sz) __ALIGN_KERNEL(sz, NL_MMAP_MSG_ALIGNMENT)
|
|
#define NL_MMAP_HDRLEN NL_MMAP_MSG_ALIGN(sizeof(struct nl_mmap_hdr))
|
|
#endif
|
|
|
|
#define NET_MAJOR 36 /* Major 36 is reserved for networking */
|
|
|
|
enum {
|
|
NETLINK_UNCONNECTED = 0,
|
|
NETLINK_CONNECTED,
|
|
};
|
|
|
|
/*
|
|
* <------- NLA_HDRLEN ------> <-- NLA_ALIGN(payload)-->
|
|
* +---------------------+- - -+- - - - - - - - - -+- - -+
|
|
* | Header | Pad | Payload | Pad |
|
|
* | (struct nlattr) | ing | | ing |
|
|
* +---------------------+- - -+- - - - - - - - - -+- - -+
|
|
* <-------------- nlattr->nla_len -------------->
|
|
*/
|
|
|
|
struct nlattr {
|
|
__u16 nla_len;
|
|
__u16 nla_type;
|
|
};
|
|
|
|
/*
|
|
* nla_type (16 bits)
|
|
* +---+---+-------------------------------+
|
|
* | N | O | Attribute Type |
|
|
* +---+---+-------------------------------+
|
|
* N := Carries nested attributes
|
|
* O := Payload stored in network byte order
|
|
*
|
|
* Note: The N and O flag are mutually exclusive.
|
|
*/
|
|
#define NLA_F_NESTED (1 << 15)
|
|
#define NLA_F_NET_BYTEORDER (1 << 14)
|
|
#define NLA_TYPE_MASK ~(NLA_F_NESTED | NLA_F_NET_BYTEORDER)
|
|
|
|
#define NLA_ALIGNTO 4
|
|
#define NLA_ALIGN(len) (((len) + NLA_ALIGNTO - 1) & ~(NLA_ALIGNTO - 1))
|
|
#define NLA_HDRLEN ((int) NLA_ALIGN(sizeof(struct nlattr)))
|
|
|
|
|
|
#endif /* _UAPI__LINUX_NETLINK_H */
|