Re: [PATCH net-next v5] ipmr: ip6mr: Create new sockopt to clear mfc cache or vifs

From: Nikolay Aleksandrov
Date: Fri Feb 15 2019 - 19:22:01 EST

Next message: Linus Torvalds: "Re: [PATCH] sched/x86: Save [ER]FLAGS on context switch"
Previous message: Steven Rostedt: "Re: [PATCH 1/2 v2] kprobe: Do not use uaccess functions to access kernel memory that can fault"
In reply to: Nicolas Dichtel: "Re: [PATCH net-next v5] ipmr: ip6mr: Create new sockopt to clear mfc cache or vifs"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

On 14/02/2019 04:44, Callum Sinclair wrote:
> Currently the only way to clear the forwarding cache was to delete the
> entries one by one using the MRT_DEL_MFC socket option or to destroy and
> recreate the socket.
>
> Create a new socket option which with the use of optional flags can
> clear any combination of multicast entries (static or not static) and
> multicast vifs (static or not static).
>
> Calling the new socket option MRT_FLUSH with the flags MRT_FLUSH_MFC and
> MRT_FLUSH_VIFS will clear all entries and vifs on the socket except for
> static entries.
>
> Signed-off-by: Callum Sinclair <callum.sinclair@xxxxxxxxxxxxxxxxxxx>
> ---
> v1 -> v2:
> Implemented additional flags for static entries
> v2 -> v3:
> Cleaned up flag logic so any combination of routes can be cleared.
> Fixed style errors
> Fixed incorrect flag values
> v3 -> v4:
> Fixed style errors
> Fixed incorrect flag (MRT_FLUSH was used instead of MRT_FLUSH_VIFS)
> v4 -> v5:
> Only clear the unresolved queue when MRT_FLUSH_MFC flag is set.
>
> include/uapi/linux/mroute.h | 9 ++++-
> include/uapi/linux/mroute6.h | 9 ++++-
> net/ipv4/ipmr.c | 75 +++++++++++++++++++++-------------
> net/ipv6/ip6mr.c | 78 +++++++++++++++++++++++-------------
> 4 files changed, 115 insertions(+), 56 deletions(-)
>

+1 about Nicolas' comments, other than that looks good:
Signed-off-by: Nikolay Aleksandrov <nikolay@xxxxxxxxxxxxxxxxxxx>

> diff --git a/include/uapi/linux/mroute.h b/include/uapi/linux/mroute.h
> index 5d37a9ccce63..11c8c1fc1124 100644
> --- a/include/uapi/linux/mroute.h
> +++ b/include/uapi/linux/mroute.h
> @@ -28,12 +28,19 @@
> #define MRT_TABLE (MRT_BASE+9) /* Specify mroute table ID */
> #define MRT_ADD_MFC_PROXY (MRT_BASE+10) /* Add a (*,*|G) mfc entry */
> #define MRT_DEL_MFC_PROXY (MRT_BASE+11) /* Del a (*,*|G) mfc entry */
> -#define MRT_MAX (MRT_BASE+11)
> +#define MRT_FLUSH (MRT_BASE+12) /* Flush all mfc entries and/or vifs */
> +#define MRT_MAX (MRT_BASE+12)
>
> #define SIOCGETVIFCNT SIOCPROTOPRIVATE /* IP protocol privates */
> #define SIOCGETSGCNT (SIOCPROTOPRIVATE+1)
> #define SIOCGETRPF (SIOCPROTOPRIVATE+2)
>
> +/* MRT_FLUSH optional flags */
> +#define MRT_FLUSH_MFC 1 /* Flush multicast entries */
> +#define MRT_FLUSH_MFC_STATIC 2 /* Flush static multicast entries */
> +#define MRT_FLUSH_VIFS 4 /* Flush multicast vifs */
> +#define MRT_FLUSH_VIFS_STATIC 8 /* Flush static multicast vifs */
> +
> #define MAXVIFS 32
> typedef unsigned long vifbitmap_t; /* User mode code depends on this lot */
> typedef unsigned short vifi_t;
> diff --git a/include/uapi/linux/mroute6.h b/include/uapi/linux/mroute6.h
> index 9999cc006390..ac84ef11b29c 100644
> --- a/include/uapi/linux/mroute6.h
> +++ b/include/uapi/linux/mroute6.h
> @@ -31,12 +31,19 @@
> #define MRT6_TABLE (MRT6_BASE+9) /* Specify mroute table ID */
> #define MRT6_ADD_MFC_PROXY (MRT6_BASE+10) /* Add a (*,*|G) mfc entry */
> #define MRT6_DEL_MFC_PROXY (MRT6_BASE+11) /* Del a (*,*|G) mfc entry */
> -#define MRT6_MAX (MRT6_BASE+11)
> +#define MRT6_FLUSH (MRT6_BASE+12) /* Flush all mfc entries and/or vifs */
> +#define MRT6_MAX (MRT6_BASE+12)
>
> #define SIOCGETMIFCNT_IN6 SIOCPROTOPRIVATE /* IP protocol privates */
> #define SIOCGETSGCNT_IN6 (SIOCPROTOPRIVATE+1)
> #define SIOCGETRPF (SIOCPROTOPRIVATE+2)
>
> +/* MRT6_FLUSH optional flags */
> +#define MRT6_FLUSH_MFC 1 /* Flush multicast entries */
> +#define MRT6_FLUSH_MFC_STATIC 2 /* Flush static multicast entries */
> +#define MRT6_FLUSH_VIFS 4 /* Flushing multicast vifs */
> +#define MRT6_FLUSH_VIFS_STATIC 8 /* Flush static multicast vifs */
> +
> #define MAXMIFS 32
> typedef unsigned long mifbitmap_t; /* User mode code depends on this lot */
> typedef unsigned short mifi_t;
> diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
> index e536970557dd..53869779af74 100644
> --- a/net/ipv4/ipmr.c
> +++ b/net/ipv4/ipmr.c
> @@ -110,7 +110,7 @@ static int ipmr_cache_report(struct mr_table *mrt,
> static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc,
> int cmd);
> static void igmpmsg_netlink_event(struct mr_table *mrt, struct sk_buff *pkt);
> -static void mroute_clean_tables(struct mr_table *mrt, bool all);
> +static void mroute_clean_tables(struct mr_table *mrt, int flags);
> static void ipmr_expire_process(struct timer_list *t);
>
> #ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES
> @@ -415,7 +415,8 @@ static struct mr_table *ipmr_new_table(struct net *net, u32 id)
> static void ipmr_free_table(struct mr_table *mrt)
> {
> del_timer_sync(&mrt->ipmr_expire_timer);
> - mroute_clean_tables(mrt, true);
> + mroute_clean_tables(mrt, MRT_FLUSH_VIFS | MRT_FLUSH_VIFS_STATIC |
> + MRT_FLUSH_MFC | MRT_FLUSH_MFC_STATIC);
> rhltable_destroy(&mrt->mfc_hash);
> kfree(mrt);
> }
> @@ -1296,7 +1297,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
> }
>
> /* Close the multicast socket, and clear the vif tables etc */
> -static void mroute_clean_tables(struct mr_table *mrt, bool all)
> +static void mroute_clean_tables(struct mr_table *mrt, int flags)
> {
> struct net *net = read_pnet(&mrt->net);
> struct mr_mfc *c, *tmp;
> @@ -1305,35 +1306,44 @@ static void mroute_clean_tables(struct mr_table *mrt, bool all)
> int i;
>
> /* Shut down all active vif entries */
> - for (i = 0; i < mrt->maxvif; i++) {
> - if (!all && (mrt->vif_table[i].flags & VIFF_STATIC))
> - continue;
> - vif_delete(mrt, i, 0, &list);
> + if (flags & (MRT_FLUSH_VIFS | MRT_FLUSH_VIFS_STATIC)) {
> + for (i = 0; i < mrt->maxvif; i++) {
> + if (((mrt->vif_table[i].flags & VIFF_STATIC) &&
> + !(flags & MRT_FLUSH_VIFS_STATIC)) ||
> + (!(mrt->vif_table[i].flags & VIFF_STATIC) && !(flags & MRT_FLUSH_VIFS)))
> + continue;
> + vif_delete(mrt, i, 0, &list);
> + }
> + unregister_netdevice_many(&list);
> }
> - unregister_netdevice_many(&list);
>
> /* Wipe the cache */
> - list_for_each_entry_safe(c, tmp, &mrt->mfc_cache_list, list) {
> - if (!all && (c->mfc_flags & MFC_STATIC))
> - continue;
> - rhltable_remove(&mrt->mfc_hash, &c->mnode, ipmr_rht_params);
> - list_del_rcu(&c->list);
> - cache = (struct mfc_cache *)c;
> - call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, cache,
> - mrt->id);
> - mroute_netlink_event(mrt, cache, RTM_DELROUTE);
> - mr_cache_put(c);
> - }
> -
> - if (atomic_read(&mrt->cache_resolve_queue_len) != 0) {
> - spin_lock_bh(&mfc_unres_lock);
> - list_for_each_entry_safe(c, tmp, &mrt->mfc_unres_queue, list) {
> - list_del(&c->list);
> + if (flags & (MRT_FLUSH_MFC | MRT_FLUSH_MFC_STATIC)) {
> + list_for_each_entry_safe(c, tmp, &mrt->mfc_cache_list, list) {
> + if (((c->mfc_flags & MFC_STATIC) && !(flags & MRT_FLUSH_MFC_STATIC)) ||
> + (!(c->mfc_flags & MFC_STATIC) && !(flags & MRT_FLUSH_MFC)))
> + continue;
> + rhltable_remove(&mrt->mfc_hash, &c->mnode, ipmr_rht_params);
> + list_del_rcu(&c->list);
> cache = (struct mfc_cache *)c;
> + call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, cache,
> + mrt->id);
> mroute_netlink_event(mrt, cache, RTM_DELROUTE);
> - ipmr_destroy_unres(mrt, cache);
> + mr_cache_put(c);
> + }
> + }
> +
> + if (flags & MRT_FLUSH_MFC) {
> + if (atomic_read(&mrt->cache_resolve_queue_len) != 0) {
> + spin_lock_bh(&mfc_unres_lock);
> + list_for_each_entry_safe(c, tmp, &mrt->mfc_unres_queue, list) {
> + list_del(&c->list);
> + cache = (struct mfc_cache *)c;
> + mroute_netlink_event(mrt, cache, RTM_DELROUTE);
> + ipmr_destroy_unres(mrt, cache);
> + }
> + spin_unlock_bh(&mfc_unres_lock);
> }
> - spin_unlock_bh(&mfc_unres_lock);
> }
> }
>
> @@ -1354,7 +1364,7 @@ static void mrtsock_destruct(struct sock *sk)
> NETCONFA_IFINDEX_ALL,
> net->ipv4.devconf_all);
> RCU_INIT_POINTER(mrt->mroute_sk, NULL);
> - mroute_clean_tables(mrt, false);
> + mroute_clean_tables(mrt, MRT_FLUSH_VIFS | MRT_FLUSH_MFC);
> }
> }
> rtnl_unlock();
> @@ -1479,6 +1489,17 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval,
> sk == rtnl_dereference(mrt->mroute_sk),
> parent);
> break;
> + case MRT_FLUSH:
> + if (optlen != sizeof(val)) {
> + ret = -EINVAL;
> + break;
> + }
> + if (get_user(val, (int __user *)optval)) {
> + ret = -EFAULT;
> + break;
> + }
> + mroute_clean_tables(mrt, val);
> + break;
> /* Control PIM assert. */
> case MRT_ASSERT:
> if (optlen != sizeof(val)) {
> diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
> index cc01aa3f2b5e..b67a7c1e3615 100644
> --- a/net/ipv6/ip6mr.c
> +++ b/net/ipv6/ip6mr.c
> @@ -97,7 +97,7 @@ static void mr6_netlink_event(struct mr_table *mrt, struct mfc6_cache *mfc,
> static void mrt6msg_netlink_event(struct mr_table *mrt, struct sk_buff *pkt);
> static int ip6mr_rtm_dumproute(struct sk_buff *skb,
> struct netlink_callback *cb);
> -static void mroute_clean_tables(struct mr_table *mrt, bool all);
> +static void mroute_clean_tables(struct mr_table *mrt, int flags);
> static void ipmr_expire_process(struct timer_list *t);
>
> #ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES
> @@ -393,7 +393,8 @@ static struct mr_table *ip6mr_new_table(struct net *net, u32 id)
> static void ip6mr_free_table(struct mr_table *mrt)
> {
> del_timer_sync(&mrt->ipmr_expire_timer);
> - mroute_clean_tables(mrt, true);
> + mroute_clean_tables(mrt, MRT6_FLUSH_VIFS | MRT6_FLUSH_VIFS_STATIC |
> + MRT6_FLUSH_MFC | MRT6_FLUSH_MFC_STATIC);
> rhltable_destroy(&mrt->mfc_hash);
> kfree(mrt);
> }
> @@ -1496,42 +1497,51 @@ static int ip6mr_mfc_add(struct net *net, struct mr_table *mrt,
> * Close the multicast socket, and clear the vif tables etc
> */
>
> -static void mroute_clean_tables(struct mr_table *mrt, bool all)
> +static void mroute_clean_tables(struct mr_table *mrt, int flags)
> {
> struct mr_mfc *c, *tmp;
> LIST_HEAD(list);
> int i;
>
> /* Shut down all active vif entries */
> - for (i = 0; i < mrt->maxvif; i++) {
> - if (!all && (mrt->vif_table[i].flags & VIFF_STATIC))
> - continue;
> - mif6_delete(mrt, i, 0, &list);
> + if (flags & (MRT6_FLUSH_VIFS | MRT6_FLUSH_VIFS_STATIC)) {
> + for (i = 0; i < mrt->maxvif; i++) {
> + if (((mrt->vif_table[i].flags & VIFF_STATIC) &&
> + !(flags & MRT6_FLUSH_VIFS_STATIC)) ||
> + (!(mrt->vif_table[i].flags & VIFF_STATIC) && !(flags & MRT6_FLUSH_VIFS)))
> + continue;
> + mif6_delete(mrt, i, 0, &list);
> + }
> + unregister_netdevice_many(&list);
> }
> - unregister_netdevice_many(&list);
>
> /* Wipe the cache */
> - list_for_each_entry_safe(c, tmp, &mrt->mfc_cache_list, list) {
> - if (!all && (c->mfc_flags & MFC_STATIC))
> - continue;
> - rhltable_remove(&mrt->mfc_hash, &c->mnode, ip6mr_rht_params);
> - list_del_rcu(&c->list);
> - call_ip6mr_mfc_entry_notifiers(read_pnet(&mrt->net),
> - FIB_EVENT_ENTRY_DEL,
> - (struct mfc6_cache *)c, mrt->id);
> - mr6_netlink_event(mrt, (struct mfc6_cache *)c, RTM_DELROUTE);
> - mr_cache_put(c);
> + if (flags & (MRT6_FLUSH_MFC | MRT6_FLUSH_MFC_STATIC)) {
> + list_for_each_entry_safe(c, tmp, &mrt->mfc_cache_list, list) {
> + if (((c->mfc_flags & MFC_STATIC) && !(flags & MRT6_FLUSH_MFC_STATIC)) ||
> + (!(c->mfc_flags & MFC_STATIC) && !(flags & MRT6_FLUSH_MFC)))
> + continue;
> + rhltable_remove(&mrt->mfc_hash, &c->mnode, ip6mr_rht_params);
> + list_del_rcu(&c->list);
> + call_ip6mr_mfc_entry_notifiers(read_pnet(&mrt->net),
> + FIB_EVENT_ENTRY_DEL,
> + (struct mfc6_cache *)c, mrt->id);
> + mr6_netlink_event(mrt, (struct mfc6_cache *)c, RTM_DELROUTE);
> + mr_cache_put(c);
> + }
> }
>
> - if (atomic_read(&mrt->cache_resolve_queue_len) != 0) {
> - spin_lock_bh(&mfc_unres_lock);
> - list_for_each_entry_safe(c, tmp, &mrt->mfc_unres_queue, list) {
> - list_del(&c->list);
> - mr6_netlink_event(mrt, (struct mfc6_cache *)c,
> - RTM_DELROUTE);
> - ip6mr_destroy_unres(mrt, (struct mfc6_cache *)c);
> + if (flags & MRT6_FLUSH_MFC) {
> + if (atomic_read(&mrt->cache_resolve_queue_len) != 0) {
> + spin_lock_bh(&mfc_unres_lock);
> + list_for_each_entry_safe(c, tmp, &mrt->mfc_unres_queue, list) {
> + list_del(&c->list);
> + mr6_netlink_event(mrt, (struct mfc6_cache *)c,
> + RTM_DELROUTE);
> + ip6mr_destroy_unres(mrt, (struct mfc6_cache *)c);
> + }
> + spin_unlock_bh(&mfc_unres_lock);
> }
> - spin_unlock_bh(&mfc_unres_lock);
> }
> }
>
> @@ -1587,7 +1597,7 @@ int ip6mr_sk_done(struct sock *sk)
> NETCONFA_IFINDEX_ALL,
> net->ipv6.devconf_all);
>
> - mroute_clean_tables(mrt, false);
> + mroute_clean_tables(mrt, MRT6_FLUSH_VIFS | MRT6_FLUSH_MFC);
> err = 0;
> break;
> }
> @@ -1703,6 +1713,20 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
> rtnl_unlock();
> return ret;
>
> + case MRT6_FLUSH:
> + {
> + int flags;
> +
> + if (optlen != sizeof(flags))
> + return -EINVAL;
> + if (get_user(flags, (int __user *)optval))
> + return -EFAULT;
> + rtnl_lock();
> + mroute_clean_tables(mrt, flags);
> + rtnl_unlock();
> + return 0;
> + }
> +
> /*
> * Control PIM assert (to activate pim will activate assert)
> */
>

Next message: Linus Torvalds: "Re: [PATCH] sched/x86: Save [ER]FLAGS on context switch"
Previous message: Steven Rostedt: "Re: [PATCH 1/2 v2] kprobe: Do not use uaccess functions to access kernel memory that can fault"
In reply to: Nicolas Dichtel: "Re: [PATCH net-next v5] ipmr: ip6mr: Create new sockopt to clear mfc cache or vifs"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]