26d2177e97
- Create drivers/staging/rdma - Move amso1100 driver to staging/rdma and schedule for deletion - Move ipath driver to staging/rdma and schedule for deletion - Add hfi1 driver to staging/rdma and set TODO for move to regular tree - Initial support for namespaces to be used on RDMA devices - Add RoCE GID table handling to the RDMA core caching code - Infrastructure to support handling of devices with differing read and write scatter gather capabilities - Various iSER updates - Kill off unsafe usage of global mr registrations - Update SRP driver - Misc. mlx4 driver updates - Support for the mr_alloc verb - Support for a netlink interface between kernel and user space cache daemon to speed path record queries and route resolution - Ininitial support for safe hot removal of verbs devices -----BEGIN PGP SIGNATURE----- Version: GnuPG v1 iQIcBAABAgAGBQJV7v8wAAoJELgmozMOVy/d2dcP/3PXnGFPgFGJODKE6VCZtTvj nooNXRKXjxv470UT5DiAX7SNcBxzzS7Zl/Lj+831H9iNXUyzuH31KtBOAZ3W03vZ yXwCB2caOStSldTRSUUvPe2aIFPnyNmSpC4i6XcJLJMCFijKmxin5pAo8qE44BQU yjhT+wC9P6LL5wZXsn/nFIMLjOFfu0WBFHNp3gs5j59paxlx5VeIAZk16aQZH135 m7YCyicwrS8iyWQl2bEXRMon2vlCHlX2RHmOJ4f/P5I0quNcGF2+d8Yxa+K1VyC5 zcb3OBezz+wZtvh16yhsDfSPqHWirljwID2VzOgRSzTJWvQjju8VkwHtkq6bYoBW egIxGCHcGWsD0R5iBXLYr/tB+BmjbDObSm0AsR4+JvSShkeVA1IpeoO+19162ixE n6CQnk2jCee8KXeIN4PoIKsjRSbIECM0JliWPLoIpuTuEhhpajftlSLgL5hf1dzp HrSy6fXmmoRj7wlTa7DnYIC3X+ffwckB8/t1zMAm2sKnIFUTjtQXF7upNiiyWk4L /T1QEzJ2bLQckQ9yY4v528SvBQwA4Dy1amIQB7SU8+2S//bYdUvhysWPkdKC4oOT WlqS5PFDCI31MvNbbM3rUbMAD8eBAR8ACw9ZpGI/Rffm5FEX5W3LoxA8gfEBRuqt 30ZYFuW8evTL+YQcaV65 =EHLg -----END PGP SIGNATURE----- Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma Pull inifiniband/rdma updates from Doug Ledford: "This is a fairly sizeable set of changes. I've put them through a decent amount of testing prior to sending the pull request due to that. There are still a few fixups that I know are coming, but I wanted to go ahead and get the big, sizable chunk into your hands sooner rather than waiting for those last few fixups. Of note is the fact that this creates what is intended to be a temporary area in the drivers/staging tree specifically for some cleanups and additions that are coming for the RDMA stack. We deprecated two drivers (ipath and amso1100) and are waiting to hear back if we can deprecate another one (ehca). We also put Intel's new hfi1 driver into this area because it needs to be refactored and a transfer library created out of the factored out code, and then it and the qib driver and the soft-roce driver should all be modified to use that library. I expect drivers/staging/rdma to be around for three or four kernel releases and then to go away as all of the work is completed and final deletions of deprecated drivers are done. Summary of changes for 4.3: - Create drivers/staging/rdma - Move amso1100 driver to staging/rdma and schedule for deletion - Move ipath driver to staging/rdma and schedule for deletion - Add hfi1 driver to staging/rdma and set TODO for move to regular tree - Initial support for namespaces to be used on RDMA devices - Add RoCE GID table handling to the RDMA core caching code - Infrastructure to support handling of devices with differing read and write scatter gather capabilities - Various iSER updates - Kill off unsafe usage of global mr registrations - Update SRP driver - Misc mlx4 driver updates - Support for the mr_alloc verb - Support for a netlink interface between kernel and user space cache daemon to speed path record queries and route resolution - Ininitial support for safe hot removal of verbs devices" * tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (136 commits) IB/ipoib: Suppress warning for send only join failures IB/ipoib: Clean up send-only multicast joins IB/srp: Fix possible protection fault IB/core: Move SM class defines from ib_mad.h to ib_smi.h IB/core: Remove unnecessary defines from ib_mad.h IB/hfi1: Add PSM2 user space header to header_install IB/hfi1: Add CSRs for CONFIG_SDMA_VERBOSITY mlx5: Fix incorrect wc pkey_index assignment for GSI messages IB/mlx5: avoid destroying a NULL mr in reg_user_mr error flow IB/uverbs: reject invalid or unknown opcodes IB/cxgb4: Fix if statement in pick_local_ip6adddrs IB/sa: Fix rdma netlink message flags IB/ucma: HW Device hot-removal support IB/mlx4_ib: Disassociate support IB/uverbs: Enable device removal when there are active user space applications IB/uverbs: Explicitly pass ib_dev to uverbs commands IB/uverbs: Fix race between ib_uverbs_open and remove_one IB/uverbs: Fix reference counting usage of event files IB/core: Make ib_dealloc_pd return void IB/srp: Create an insecure all physical rkey only if needed ...
395 lines
11 KiB
C
395 lines
11 KiB
C
#ifndef _ADDRCONF_H
|
|
#define _ADDRCONF_H
|
|
|
|
#define MAX_RTR_SOLICITATIONS 3
|
|
#define RTR_SOLICITATION_INTERVAL (4*HZ)
|
|
|
|
#define MIN_VALID_LIFETIME (2*3600) /* 2 hours */
|
|
|
|
#define TEMP_VALID_LIFETIME (7*86400)
|
|
#define TEMP_PREFERRED_LIFETIME (86400)
|
|
#define REGEN_MAX_RETRY (3)
|
|
#define MAX_DESYNC_FACTOR (600)
|
|
|
|
#define ADDR_CHECK_FREQUENCY (120*HZ)
|
|
|
|
#define IPV6_MAX_ADDRESSES 16
|
|
|
|
#define ADDRCONF_TIMER_FUZZ_MINUS (HZ > 50 ? HZ / 50 : 1)
|
|
#define ADDRCONF_TIMER_FUZZ (HZ / 4)
|
|
#define ADDRCONF_TIMER_FUZZ_MAX (HZ)
|
|
|
|
#include <linux/in.h>
|
|
#include <linux/in6.h>
|
|
|
|
struct prefix_info {
|
|
__u8 type;
|
|
__u8 length;
|
|
__u8 prefix_len;
|
|
|
|
#if defined(__BIG_ENDIAN_BITFIELD)
|
|
__u8 onlink : 1,
|
|
autoconf : 1,
|
|
reserved : 6;
|
|
#elif defined(__LITTLE_ENDIAN_BITFIELD)
|
|
__u8 reserved : 6,
|
|
autoconf : 1,
|
|
onlink : 1;
|
|
#else
|
|
#error "Please fix <asm/byteorder.h>"
|
|
#endif
|
|
__be32 valid;
|
|
__be32 prefered;
|
|
__be32 reserved2;
|
|
|
|
struct in6_addr prefix;
|
|
};
|
|
|
|
|
|
#include <linux/netdevice.h>
|
|
#include <net/if_inet6.h>
|
|
#include <net/ipv6.h>
|
|
|
|
#define IN6_ADDR_HSIZE_SHIFT 4
|
|
#define IN6_ADDR_HSIZE (1 << IN6_ADDR_HSIZE_SHIFT)
|
|
|
|
int addrconf_init(void);
|
|
void addrconf_cleanup(void);
|
|
|
|
int addrconf_add_ifaddr(struct net *net, void __user *arg);
|
|
int addrconf_del_ifaddr(struct net *net, void __user *arg);
|
|
int addrconf_set_dstaddr(struct net *net, void __user *arg);
|
|
|
|
int ipv6_chk_addr(struct net *net, const struct in6_addr *addr,
|
|
const struct net_device *dev, int strict);
|
|
int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr,
|
|
const struct net_device *dev, int strict,
|
|
u32 banned_flags);
|
|
|
|
#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
|
|
int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr);
|
|
#endif
|
|
|
|
bool ipv6_chk_custom_prefix(const struct in6_addr *addr,
|
|
const unsigned int prefix_len,
|
|
struct net_device *dev);
|
|
|
|
int ipv6_chk_prefix(const struct in6_addr *addr, struct net_device *dev);
|
|
|
|
struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net,
|
|
const struct in6_addr *addr,
|
|
struct net_device *dev, int strict);
|
|
|
|
int ipv6_dev_get_saddr(struct net *net, const struct net_device *dev,
|
|
const struct in6_addr *daddr, unsigned int srcprefs,
|
|
struct in6_addr *saddr);
|
|
int __ipv6_get_lladdr(struct inet6_dev *idev, struct in6_addr *addr,
|
|
u32 banned_flags);
|
|
int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr,
|
|
u32 banned_flags);
|
|
int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2);
|
|
void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr);
|
|
void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr);
|
|
|
|
static inline int addrconf_ifid_eui48(u8 *eui, struct net_device *dev)
|
|
{
|
|
if (dev->addr_len != ETH_ALEN)
|
|
return -1;
|
|
memcpy(eui, dev->dev_addr, 3);
|
|
memcpy(eui + 5, dev->dev_addr + 3, 3);
|
|
|
|
/*
|
|
* The zSeries OSA network cards can be shared among various
|
|
* OS instances, but the OSA cards have only one MAC address.
|
|
* This leads to duplicate address conflicts in conjunction
|
|
* with IPv6 if more than one instance uses the same card.
|
|
*
|
|
* The driver for these cards can deliver a unique 16-bit
|
|
* identifier for each instance sharing the same card. It is
|
|
* placed instead of 0xFFFE in the interface identifier. The
|
|
* "u" bit of the interface identifier is not inverted in this
|
|
* case. Hence the resulting interface identifier has local
|
|
* scope according to RFC2373.
|
|
*/
|
|
if (dev->dev_id) {
|
|
eui[3] = (dev->dev_id >> 8) & 0xFF;
|
|
eui[4] = dev->dev_id & 0xFF;
|
|
} else {
|
|
eui[3] = 0xFF;
|
|
eui[4] = 0xFE;
|
|
eui[0] ^= 2;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
static inline unsigned long addrconf_timeout_fixup(u32 timeout,
|
|
unsigned int unit)
|
|
{
|
|
if (timeout == 0xffffffff)
|
|
return ~0UL;
|
|
|
|
/*
|
|
* Avoid arithmetic overflow.
|
|
* Assuming unit is constant and non-zero, this "if" statement
|
|
* will go away on 64bit archs.
|
|
*/
|
|
if (0xfffffffe > LONG_MAX / unit && timeout > LONG_MAX / unit)
|
|
return LONG_MAX / unit;
|
|
|
|
return timeout;
|
|
}
|
|
|
|
static inline int addrconf_finite_timeout(unsigned long timeout)
|
|
{
|
|
return ~timeout;
|
|
}
|
|
|
|
/*
|
|
* IPv6 Address Label subsystem (addrlabel.c)
|
|
*/
|
|
int ipv6_addr_label_init(void);
|
|
void ipv6_addr_label_cleanup(void);
|
|
void ipv6_addr_label_rtnl_register(void);
|
|
u32 ipv6_addr_label(struct net *net, const struct in6_addr *addr,
|
|
int type, int ifindex);
|
|
|
|
/*
|
|
* multicast prototypes (mcast.c)
|
|
*/
|
|
int ipv6_sock_mc_join(struct sock *sk, int ifindex,
|
|
const struct in6_addr *addr);
|
|
int ipv6_sock_mc_drop(struct sock *sk, int ifindex,
|
|
const struct in6_addr *addr);
|
|
void ipv6_sock_mc_close(struct sock *sk);
|
|
bool inet6_mc_check(struct sock *sk, const struct in6_addr *mc_addr,
|
|
const struct in6_addr *src_addr);
|
|
|
|
int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr);
|
|
int __ipv6_dev_mc_dec(struct inet6_dev *idev, const struct in6_addr *addr);
|
|
int ipv6_dev_mc_dec(struct net_device *dev, const struct in6_addr *addr);
|
|
void ipv6_mc_up(struct inet6_dev *idev);
|
|
void ipv6_mc_down(struct inet6_dev *idev);
|
|
void ipv6_mc_unmap(struct inet6_dev *idev);
|
|
void ipv6_mc_remap(struct inet6_dev *idev);
|
|
void ipv6_mc_init_dev(struct inet6_dev *idev);
|
|
void ipv6_mc_destroy_dev(struct inet6_dev *idev);
|
|
int ipv6_mc_check_mld(struct sk_buff *skb, struct sk_buff **skb_trimmed);
|
|
void addrconf_dad_failure(struct inet6_ifaddr *ifp);
|
|
|
|
bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group,
|
|
const struct in6_addr *src_addr);
|
|
|
|
void ipv6_mc_dad_complete(struct inet6_dev *idev);
|
|
|
|
/* A stub used by vxlan module. This is ugly, ideally these
|
|
* symbols should be built into the core kernel.
|
|
*/
|
|
struct ipv6_stub {
|
|
int (*ipv6_sock_mc_join)(struct sock *sk, int ifindex,
|
|
const struct in6_addr *addr);
|
|
int (*ipv6_sock_mc_drop)(struct sock *sk, int ifindex,
|
|
const struct in6_addr *addr);
|
|
int (*ipv6_dst_lookup)(struct net *net, struct sock *sk,
|
|
struct dst_entry **dst, struct flowi6 *fl6);
|
|
void (*udpv6_encap_enable)(void);
|
|
void (*ndisc_send_na)(struct net_device *dev, struct neighbour *neigh,
|
|
const struct in6_addr *daddr,
|
|
const struct in6_addr *solicited_addr,
|
|
bool router, bool solicited, bool override, bool inc_opt);
|
|
struct neigh_table *nd_tbl;
|
|
};
|
|
extern const struct ipv6_stub *ipv6_stub __read_mostly;
|
|
|
|
/*
|
|
* identify MLD packets for MLD filter exceptions
|
|
*/
|
|
static inline bool ipv6_is_mld(struct sk_buff *skb, int nexthdr, int offset)
|
|
{
|
|
struct icmp6hdr *hdr;
|
|
|
|
if (nexthdr != IPPROTO_ICMPV6 ||
|
|
!pskb_network_may_pull(skb, offset + sizeof(struct icmp6hdr)))
|
|
return false;
|
|
|
|
hdr = (struct icmp6hdr *)(skb_network_header(skb) + offset);
|
|
|
|
switch (hdr->icmp6_type) {
|
|
case ICMPV6_MGM_QUERY:
|
|
case ICMPV6_MGM_REPORT:
|
|
case ICMPV6_MGM_REDUCTION:
|
|
case ICMPV6_MLD2_REPORT:
|
|
return true;
|
|
default:
|
|
break;
|
|
}
|
|
return false;
|
|
}
|
|
|
|
void addrconf_prefix_rcv(struct net_device *dev,
|
|
u8 *opt, int len, bool sllao);
|
|
|
|
/*
|
|
* anycast prototypes (anycast.c)
|
|
*/
|
|
int ipv6_sock_ac_join(struct sock *sk, int ifindex,
|
|
const struct in6_addr *addr);
|
|
int ipv6_sock_ac_drop(struct sock *sk, int ifindex,
|
|
const struct in6_addr *addr);
|
|
void ipv6_sock_ac_close(struct sock *sk);
|
|
|
|
int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr);
|
|
int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr);
|
|
void ipv6_ac_destroy_dev(struct inet6_dev *idev);
|
|
bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev,
|
|
const struct in6_addr *addr);
|
|
bool ipv6_chk_acast_addr_src(struct net *net, struct net_device *dev,
|
|
const struct in6_addr *addr);
|
|
|
|
/* Device notifier */
|
|
int register_inet6addr_notifier(struct notifier_block *nb);
|
|
int unregister_inet6addr_notifier(struct notifier_block *nb);
|
|
int inet6addr_notifier_call_chain(unsigned long val, void *v);
|
|
|
|
void inet6_netconf_notify_devconf(struct net *net, int type, int ifindex,
|
|
struct ipv6_devconf *devconf);
|
|
|
|
/**
|
|
* __in6_dev_get - get inet6_dev pointer from netdevice
|
|
* @dev: network device
|
|
*
|
|
* Caller must hold rcu_read_lock or RTNL, because this function
|
|
* does not take a reference on the inet6_dev.
|
|
*/
|
|
static inline struct inet6_dev *__in6_dev_get(const struct net_device *dev)
|
|
{
|
|
return rcu_dereference_rtnl(dev->ip6_ptr);
|
|
}
|
|
|
|
/**
|
|
* in6_dev_get - get inet6_dev pointer from netdevice
|
|
* @dev: network device
|
|
*
|
|
* This version can be used in any context, and takes a reference
|
|
* on the inet6_dev. Callers must use in6_dev_put() later to
|
|
* release this reference.
|
|
*/
|
|
static inline struct inet6_dev *in6_dev_get(const struct net_device *dev)
|
|
{
|
|
struct inet6_dev *idev;
|
|
|
|
rcu_read_lock();
|
|
idev = rcu_dereference(dev->ip6_ptr);
|
|
if (idev)
|
|
atomic_inc(&idev->refcnt);
|
|
rcu_read_unlock();
|
|
return idev;
|
|
}
|
|
|
|
static inline struct neigh_parms *__in6_dev_nd_parms_get_rcu(const struct net_device *dev)
|
|
{
|
|
struct inet6_dev *idev = __in6_dev_get(dev);
|
|
|
|
return idev ? idev->nd_parms : NULL;
|
|
}
|
|
|
|
void in6_dev_finish_destroy(struct inet6_dev *idev);
|
|
|
|
static inline void in6_dev_put(struct inet6_dev *idev)
|
|
{
|
|
if (atomic_dec_and_test(&idev->refcnt))
|
|
in6_dev_finish_destroy(idev);
|
|
}
|
|
|
|
static inline void __in6_dev_put(struct inet6_dev *idev)
|
|
{
|
|
atomic_dec(&idev->refcnt);
|
|
}
|
|
|
|
static inline void in6_dev_hold(struct inet6_dev *idev)
|
|
{
|
|
atomic_inc(&idev->refcnt);
|
|
}
|
|
|
|
void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp);
|
|
|
|
static inline void in6_ifa_put(struct inet6_ifaddr *ifp)
|
|
{
|
|
if (atomic_dec_and_test(&ifp->refcnt))
|
|
inet6_ifa_finish_destroy(ifp);
|
|
}
|
|
|
|
static inline void __in6_ifa_put(struct inet6_ifaddr *ifp)
|
|
{
|
|
atomic_dec(&ifp->refcnt);
|
|
}
|
|
|
|
static inline void in6_ifa_hold(struct inet6_ifaddr *ifp)
|
|
{
|
|
atomic_inc(&ifp->refcnt);
|
|
}
|
|
|
|
|
|
/*
|
|
* compute link-local solicited-node multicast address
|
|
*/
|
|
|
|
static inline void addrconf_addr_solict_mult(const struct in6_addr *addr,
|
|
struct in6_addr *solicited)
|
|
{
|
|
ipv6_addr_set(solicited,
|
|
htonl(0xFF020000), 0,
|
|
htonl(0x1),
|
|
htonl(0xFF000000) | addr->s6_addr32[3]);
|
|
}
|
|
|
|
static inline bool ipv6_addr_is_ll_all_nodes(const struct in6_addr *addr)
|
|
{
|
|
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
|
|
__be64 *p = (__be64 *)addr;
|
|
return ((p[0] ^ cpu_to_be64(0xff02000000000000UL)) | (p[1] ^ cpu_to_be64(1))) == 0UL;
|
|
#else
|
|
return ((addr->s6_addr32[0] ^ htonl(0xff020000)) |
|
|
addr->s6_addr32[1] | addr->s6_addr32[2] |
|
|
(addr->s6_addr32[3] ^ htonl(0x00000001))) == 0;
|
|
#endif
|
|
}
|
|
|
|
static inline bool ipv6_addr_is_ll_all_routers(const struct in6_addr *addr)
|
|
{
|
|
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
|
|
__be64 *p = (__be64 *)addr;
|
|
return ((p[0] ^ cpu_to_be64(0xff02000000000000UL)) | (p[1] ^ cpu_to_be64(2))) == 0UL;
|
|
#else
|
|
return ((addr->s6_addr32[0] ^ htonl(0xff020000)) |
|
|
addr->s6_addr32[1] | addr->s6_addr32[2] |
|
|
(addr->s6_addr32[3] ^ htonl(0x00000002))) == 0;
|
|
#endif
|
|
}
|
|
|
|
static inline bool ipv6_addr_is_isatap(const struct in6_addr *addr)
|
|
{
|
|
return (addr->s6_addr32[2] | htonl(0x02000000)) == htonl(0x02005EFE);
|
|
}
|
|
|
|
static inline bool ipv6_addr_is_solict_mult(const struct in6_addr *addr)
|
|
{
|
|
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
|
|
__be64 *p = (__be64 *)addr;
|
|
return ((p[0] ^ cpu_to_be64(0xff02000000000000UL)) |
|
|
((p[1] ^ cpu_to_be64(0x00000001ff000000UL)) &
|
|
cpu_to_be64(0xffffffffff000000UL))) == 0UL;
|
|
#else
|
|
return ((addr->s6_addr32[0] ^ htonl(0xff020000)) |
|
|
addr->s6_addr32[1] |
|
|
(addr->s6_addr32[2] ^ htonl(0x00000001)) |
|
|
(addr->s6_addr[12] ^ 0xff)) == 0;
|
|
#endif
|
|
}
|
|
|
|
#ifdef CONFIG_PROC_FS
|
|
int if6_proc_init(void);
|
|
void if6_proc_exit(void);
|
|
#endif
|
|
|
|
#endif
|