mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-25 15:55:40 +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>
56 lines
1.1 KiB
C
56 lines
1.1 KiB
C
#ifndef __NETLINK_DIAG_H__
|
|
#define __NETLINK_DIAG_H__
|
|
|
|
#include <linux/types.h>
|
|
|
|
struct netlink_diag_req {
|
|
__u8 sdiag_family;
|
|
__u8 sdiag_protocol;
|
|
__u16 pad;
|
|
__u32 ndiag_ino;
|
|
__u32 ndiag_show;
|
|
__u32 ndiag_cookie[2];
|
|
};
|
|
|
|
struct netlink_diag_msg {
|
|
__u8 ndiag_family;
|
|
__u8 ndiag_type;
|
|
__u8 ndiag_protocol;
|
|
__u8 ndiag_state;
|
|
|
|
__u32 ndiag_portid;
|
|
__u32 ndiag_dst_portid;
|
|
__u32 ndiag_dst_group;
|
|
__u32 ndiag_ino;
|
|
__u32 ndiag_cookie[2];
|
|
};
|
|
|
|
struct netlink_diag_ring {
|
|
__u32 ndr_block_size;
|
|
__u32 ndr_block_nr;
|
|
__u32 ndr_frame_size;
|
|
__u32 ndr_frame_nr;
|
|
};
|
|
|
|
enum {
|
|
/* NETLINK_DIAG_NONE, standard nl API requires this attribute! */
|
|
NETLINK_DIAG_MEMINFO,
|
|
NETLINK_DIAG_GROUPS,
|
|
NETLINK_DIAG_RX_RING,
|
|
NETLINK_DIAG_TX_RING,
|
|
|
|
__NETLINK_DIAG_MAX,
|
|
};
|
|
|
|
#define NETLINK_DIAG_MAX (__NETLINK_DIAG_MAX - 1)
|
|
|
|
#define NDIAG_PROTO_ALL ((__u8) ~0)
|
|
|
|
#define NDIAG_SHOW_MEMINFO 0x00000001 /* show memory info of a socket */
|
|
#define NDIAG_SHOW_GROUPS 0x00000002 /* show groups of a netlink socket */
|
|
#ifndef __KERNEL__
|
|
#define NDIAG_SHOW_RING_CFG 0x00000004 /* show ring configuration */
|
|
#endif
|
|
|
|
#endif
|