mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-14 22:56:41 +07:00
3a36515f72
Since (c05cdb1 netlink: allow large data transfers from user-space),
netlink splats if it invokes skb_clone on large netlink skbs since:
* skb_shared_info was not correctly initialized.
* skb->destructor is not set in the cloned skb.
This was spotted by trinity:
[ 894.990671] BUG: unable to handle kernel paging request at ffffc9000047b001
[ 894.991034] IP: [<ffffffff81a212c4>] skb_clone+0x24/0xc0
[...]
[ 894.991034] Call Trace:
[ 894.991034] [<ffffffff81ad299a>] nl_fib_input+0x6a/0x240
[ 894.991034] [<ffffffff81c3b7e6>] ? _raw_read_unlock+0x26/0x40
[ 894.991034] [<ffffffff81a5f189>] netlink_unicast+0x169/0x1e0
[ 894.991034] [<ffffffff81a601e1>] netlink_sendmsg+0x251/0x3d0
Fix it by:
1) introducing a new netlink_skb_clone function that is used in nl_fib_input,
that sets our special skb->destructor in the cloned skb. Moreover, handle
the release of the large cloned skb head area in the destructor path.
2) not allowing large skbuffs in the netlink broadcast path. I cannot find
any reasonable use of the large data transfer using netlink in that path,
moreover this helps to skip extra skb_clone handling.
I found two more netlink clients that are cloning the skbs, but they are
not in the sendmsg path. Therefore, the sole client cloning that I found
seems to be the fib frontend.
Thanks to Eric Dumazet for helping to address this issue.
Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
175 lines
5.2 KiB
C
175 lines
5.2 KiB
C
#ifndef __LINUX_NETLINK_H
|
|
#define __LINUX_NETLINK_H
|
|
|
|
|
|
#include <linux/capability.h>
|
|
#include <linux/skbuff.h>
|
|
#include <linux/export.h>
|
|
#include <net/scm.h>
|
|
#include <uapi/linux/netlink.h>
|
|
|
|
struct net;
|
|
|
|
static inline struct nlmsghdr *nlmsg_hdr(const struct sk_buff *skb)
|
|
{
|
|
return (struct nlmsghdr *)skb->data;
|
|
}
|
|
|
|
enum netlink_skb_flags {
|
|
NETLINK_SKB_MMAPED = 0x1, /* Packet data is mmaped */
|
|
NETLINK_SKB_TX = 0x2, /* Packet was sent by userspace */
|
|
NETLINK_SKB_DELIVERED = 0x4, /* Packet was delivered */
|
|
};
|
|
|
|
struct netlink_skb_parms {
|
|
struct scm_creds creds; /* Skb credentials */
|
|
__u32 portid;
|
|
__u32 dst_group;
|
|
__u32 flags;
|
|
struct sock *sk;
|
|
};
|
|
|
|
#define NETLINK_CB(skb) (*(struct netlink_skb_parms*)&((skb)->cb))
|
|
#define NETLINK_CREDS(skb) (&NETLINK_CB((skb)).creds)
|
|
|
|
|
|
extern void netlink_table_grab(void);
|
|
extern void netlink_table_ungrab(void);
|
|
|
|
#define NL_CFG_F_NONROOT_RECV (1 << 0)
|
|
#define NL_CFG_F_NONROOT_SEND (1 << 1)
|
|
|
|
/* optional Netlink kernel configuration parameters */
|
|
struct netlink_kernel_cfg {
|
|
unsigned int groups;
|
|
unsigned int flags;
|
|
void (*input)(struct sk_buff *skb);
|
|
struct mutex *cb_mutex;
|
|
void (*bind)(int group);
|
|
bool (*compare)(struct net *net, struct sock *sk);
|
|
};
|
|
|
|
extern struct sock *__netlink_kernel_create(struct net *net, int unit,
|
|
struct module *module,
|
|
struct netlink_kernel_cfg *cfg);
|
|
static inline struct sock *
|
|
netlink_kernel_create(struct net *net, int unit, struct netlink_kernel_cfg *cfg)
|
|
{
|
|
return __netlink_kernel_create(net, unit, THIS_MODULE, cfg);
|
|
}
|
|
|
|
extern void netlink_kernel_release(struct sock *sk);
|
|
extern int __netlink_change_ngroups(struct sock *sk, unsigned int groups);
|
|
extern int netlink_change_ngroups(struct sock *sk, unsigned int groups);
|
|
extern void __netlink_clear_multicast_users(struct sock *sk, unsigned int group);
|
|
extern void netlink_clear_multicast_users(struct sock *sk, unsigned int group);
|
|
extern void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err);
|
|
extern int netlink_has_listeners(struct sock *sk, unsigned int group);
|
|
extern struct sk_buff *netlink_alloc_skb(struct sock *ssk, unsigned int size,
|
|
u32 dst_portid, gfp_t gfp_mask);
|
|
extern int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 portid, int nonblock);
|
|
extern int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 portid,
|
|
__u32 group, gfp_t allocation);
|
|
extern int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb,
|
|
__u32 portid, __u32 group, gfp_t allocation,
|
|
int (*filter)(struct sock *dsk, struct sk_buff *skb, void *data),
|
|
void *filter_data);
|
|
extern int netlink_set_err(struct sock *ssk, __u32 portid, __u32 group, int code);
|
|
extern int netlink_register_notifier(struct notifier_block *nb);
|
|
extern int netlink_unregister_notifier(struct notifier_block *nb);
|
|
|
|
/* finegrained unicast helpers: */
|
|
struct sock *netlink_getsockbyfilp(struct file *filp);
|
|
int netlink_attachskb(struct sock *sk, struct sk_buff *skb,
|
|
long *timeo, struct sock *ssk);
|
|
void netlink_detachskb(struct sock *sk, struct sk_buff *skb);
|
|
int netlink_sendskb(struct sock *sk, struct sk_buff *skb);
|
|
|
|
static inline struct sk_buff *
|
|
netlink_skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
|
|
{
|
|
struct sk_buff *nskb;
|
|
|
|
nskb = skb_clone(skb, gfp_mask);
|
|
if (!nskb)
|
|
return NULL;
|
|
|
|
/* This is a large skb, set destructor callback to release head */
|
|
if (is_vmalloc_addr(skb->head))
|
|
nskb->destructor = skb->destructor;
|
|
|
|
return nskb;
|
|
}
|
|
|
|
/*
|
|
* skb should fit one page. This choice is good for headerless malloc.
|
|
* But we should limit to 8K so that userspace does not have to
|
|
* use enormous buffer sizes on recvmsg() calls just to avoid
|
|
* MSG_TRUNC when PAGE_SIZE is very large.
|
|
*/
|
|
#if PAGE_SIZE < 8192UL
|
|
#define NLMSG_GOODSIZE SKB_WITH_OVERHEAD(PAGE_SIZE)
|
|
#else
|
|
#define NLMSG_GOODSIZE SKB_WITH_OVERHEAD(8192UL)
|
|
#endif
|
|
|
|
#define NLMSG_DEFAULT_SIZE (NLMSG_GOODSIZE - NLMSG_HDRLEN)
|
|
|
|
|
|
struct netlink_callback {
|
|
struct sk_buff *skb;
|
|
const struct nlmsghdr *nlh;
|
|
int (*dump)(struct sk_buff * skb,
|
|
struct netlink_callback *cb);
|
|
int (*done)(struct netlink_callback *cb);
|
|
void *data;
|
|
/* the module that dump function belong to */
|
|
struct module *module;
|
|
u16 family;
|
|
u16 min_dump_alloc;
|
|
unsigned int prev_seq, seq;
|
|
long args[6];
|
|
};
|
|
|
|
struct netlink_notify {
|
|
struct net *net;
|
|
int portid;
|
|
int protocol;
|
|
};
|
|
|
|
struct nlmsghdr *
|
|
__nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, int type, int len, int flags);
|
|
|
|
struct netlink_dump_control {
|
|
int (*dump)(struct sk_buff *skb, struct netlink_callback *);
|
|
int (*done)(struct netlink_callback *);
|
|
void *data;
|
|
struct module *module;
|
|
u16 min_dump_alloc;
|
|
};
|
|
|
|
extern int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
|
|
const struct nlmsghdr *nlh,
|
|
struct netlink_dump_control *control);
|
|
static inline int netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
|
|
const struct nlmsghdr *nlh,
|
|
struct netlink_dump_control *control)
|
|
{
|
|
if (!control->module)
|
|
control->module = THIS_MODULE;
|
|
|
|
return __netlink_dump_start(ssk, skb, nlh, control);
|
|
}
|
|
|
|
struct netlink_tap {
|
|
struct net_device *dev;
|
|
struct module *module;
|
|
struct list_head list;
|
|
};
|
|
|
|
extern int netlink_add_tap(struct netlink_tap *nt);
|
|
extern int __netlink_remove_tap(struct netlink_tap *nt);
|
|
extern int netlink_remove_tap(struct netlink_tap *nt);
|
|
|
|
#endif /* __LINUX_NETLINK_H */
|