mirror of
https://github.com/torvalds/linux.git
synced 2024-11-14 16:12:02 +00:00
dfc39d4026
Packet sockets, like tap, can be used as the backend for kernel vhost. In packet sockets, virtio net header size is currently hardcoded to be the size of struct virtio_net_hdr, which is 10 bytes; however, it is not always the case: some virtio features, such as mrg_rxbuf, need virtio net header to be 12-byte long. Mergeable buffers, as a virtio feature, is worthy of supporting: packets that are larger than one-mbuf size will be dropped in vhost worker's handle_rx if mrg_rxbuf feature is not used, but large packets cannot be avoided and increasing mbuf's size is not economical. With this virtio feature enabled by virtio-user, packet sockets with hardcoded 10-byte virtio net header will parse mac head incorrectly in packet_snd by taking the last two bytes of virtio net header as part of mac header. This incorrect mac header parsing will cause packet to be dropped due to invalid ether head checking in later under-layer device packet receiving. By adding extra field vnet_hdr_sz with utilizing holes in struct packet_sock to record currently used virtio net header size and supporting extra sockopt PACKET_VNET_HDR_SZ to set specified vnet_hdr_sz, packet sockets can know the exact length of virtio net header that virtio user gives. In packet_snd, tpacket_snd and packet_recvmsg, instead of using hardcoded virtio net header size, it can get the exact vnet_hdr_sz from corresponding packet_sock, and parse mac header correctly based on this information to avoid the packets being mistakenly dropped. Signed-off-by: Jianfeng Tan <henry.tjf@antgroup.com> Co-developed-by: Anqi Shen <amy.saq@antgroup.com> Signed-off-by: Anqi Shen <amy.saq@antgroup.com> Reviewed-by: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
165 lines
3.6 KiB
C
165 lines
3.6 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef __PACKET_INTERNAL_H__
|
|
#define __PACKET_INTERNAL_H__
|
|
|
|
#include <linux/refcount.h>
|
|
|
|
struct packet_mclist {
|
|
struct packet_mclist *next;
|
|
int ifindex;
|
|
int count;
|
|
unsigned short type;
|
|
unsigned short alen;
|
|
unsigned char addr[MAX_ADDR_LEN];
|
|
};
|
|
|
|
/* kbdq - kernel block descriptor queue */
|
|
struct tpacket_kbdq_core {
|
|
struct pgv *pkbdq;
|
|
unsigned int feature_req_word;
|
|
unsigned int hdrlen;
|
|
unsigned char reset_pending_on_curr_blk;
|
|
unsigned char delete_blk_timer;
|
|
unsigned short kactive_blk_num;
|
|
unsigned short blk_sizeof_priv;
|
|
|
|
/* last_kactive_blk_num:
|
|
* trick to see if user-space has caught up
|
|
* in order to avoid refreshing timer when every single pkt arrives.
|
|
*/
|
|
unsigned short last_kactive_blk_num;
|
|
|
|
char *pkblk_start;
|
|
char *pkblk_end;
|
|
int kblk_size;
|
|
unsigned int max_frame_len;
|
|
unsigned int knum_blocks;
|
|
uint64_t knxt_seq_num;
|
|
char *prev;
|
|
char *nxt_offset;
|
|
struct sk_buff *skb;
|
|
|
|
rwlock_t blk_fill_in_prog_lock;
|
|
|
|
/* Default is set to 8ms */
|
|
#define DEFAULT_PRB_RETIRE_TOV (8)
|
|
|
|
unsigned short retire_blk_tov;
|
|
unsigned short version;
|
|
unsigned long tov_in_jiffies;
|
|
|
|
/* timer to retire an outstanding block */
|
|
struct timer_list retire_blk_timer;
|
|
};
|
|
|
|
struct pgv {
|
|
char *buffer;
|
|
};
|
|
|
|
struct packet_ring_buffer {
|
|
struct pgv *pg_vec;
|
|
|
|
unsigned int head;
|
|
unsigned int frames_per_block;
|
|
unsigned int frame_size;
|
|
unsigned int frame_max;
|
|
|
|
unsigned int pg_vec_order;
|
|
unsigned int pg_vec_pages;
|
|
unsigned int pg_vec_len;
|
|
|
|
unsigned int __percpu *pending_refcnt;
|
|
|
|
union {
|
|
unsigned long *rx_owner_map;
|
|
struct tpacket_kbdq_core prb_bdqc;
|
|
};
|
|
};
|
|
|
|
extern struct mutex fanout_mutex;
|
|
#define PACKET_FANOUT_MAX (1 << 16)
|
|
|
|
struct packet_fanout {
|
|
possible_net_t net;
|
|
unsigned int num_members;
|
|
u32 max_num_members;
|
|
u16 id;
|
|
u8 type;
|
|
u8 flags;
|
|
union {
|
|
atomic_t rr_cur;
|
|
struct bpf_prog __rcu *bpf_prog;
|
|
};
|
|
struct list_head list;
|
|
spinlock_t lock;
|
|
refcount_t sk_ref;
|
|
struct packet_type prot_hook ____cacheline_aligned_in_smp;
|
|
struct sock __rcu *arr[];
|
|
};
|
|
|
|
struct packet_rollover {
|
|
int sock;
|
|
atomic_long_t num;
|
|
atomic_long_t num_huge;
|
|
atomic_long_t num_failed;
|
|
#define ROLLOVER_HLEN (L1_CACHE_BYTES / sizeof(u32))
|
|
u32 history[ROLLOVER_HLEN] ____cacheline_aligned;
|
|
} ____cacheline_aligned_in_smp;
|
|
|
|
struct packet_sock {
|
|
/* struct sock has to be the first member of packet_sock */
|
|
struct sock sk;
|
|
struct packet_fanout *fanout;
|
|
union tpacket_stats_u stats;
|
|
struct packet_ring_buffer rx_ring;
|
|
struct packet_ring_buffer tx_ring;
|
|
int copy_thresh;
|
|
spinlock_t bind_lock;
|
|
struct mutex pg_vec_lock;
|
|
unsigned long flags;
|
|
int ifindex; /* bound device */
|
|
u8 vnet_hdr_sz;
|
|
__be16 num;
|
|
struct packet_rollover *rollover;
|
|
struct packet_mclist *mclist;
|
|
atomic_t mapped;
|
|
enum tpacket_versions tp_version;
|
|
unsigned int tp_hdrlen;
|
|
unsigned int tp_reserve;
|
|
unsigned int tp_tstamp;
|
|
struct completion skb_completion;
|
|
struct net_device __rcu *cached_dev;
|
|
struct packet_type prot_hook ____cacheline_aligned_in_smp;
|
|
atomic_t tp_drops ____cacheline_aligned_in_smp;
|
|
};
|
|
|
|
#define pkt_sk(ptr) container_of_const(ptr, struct packet_sock, sk)
|
|
|
|
enum packet_sock_flags {
|
|
PACKET_SOCK_ORIGDEV,
|
|
PACKET_SOCK_AUXDATA,
|
|
PACKET_SOCK_TX_HAS_OFF,
|
|
PACKET_SOCK_TP_LOSS,
|
|
PACKET_SOCK_RUNNING,
|
|
PACKET_SOCK_PRESSURE,
|
|
PACKET_SOCK_QDISC_BYPASS,
|
|
};
|
|
|
|
static inline void packet_sock_flag_set(struct packet_sock *po,
|
|
enum packet_sock_flags flag,
|
|
bool val)
|
|
{
|
|
if (val)
|
|
set_bit(flag, &po->flags);
|
|
else
|
|
clear_bit(flag, &po->flags);
|
|
}
|
|
|
|
static inline bool packet_sock_flag(const struct packet_sock *po,
|
|
enum packet_sock_flags flag)
|
|
{
|
|
return test_bit(flag, &po->flags);
|
|
}
|
|
|
|
#endif
|