* [PATCH net-next] net/ipv6: Add knob to skip DELROUTE message on device down
From: David Ahern @ 2018-10-09 21:27 UTC (permalink / raw)
To: netdev, davem; +Cc: roopa, David Ahern
From: David Ahern <dsahern@gmail.com>
Another difference between IPv4 and IPv6 is the generation of RTM_DELROUTE
notifications when a device is taken down (admin down) or deleted. IPv4
does not generate a message for routes evicted by the down or delete;
IPv6 does. A NOS at scale really needs to avoid these messages and have
IPv4 and IPv6 behave similarly, relying on userspace to handle link
notifications and evict the routes.
At this point existing user behavior needs to be preserved. Since
notifications are a global action (not per app) the only way to preserve
existing behavior and allow the messages to be skipped is to add a new
sysctl (net/ipv6/route/skip_notify_on_dev_down) which can be set to
disable the notificatioons.
IPv6 route code already supports the option to skip the message (it is
used for multipath routes for example). Besides the new sysctl we need
to pass the skip_notify setting through the generic fib6_clean and
fib6_walk functions to fib6_clean_node and to set skip_notify on calls
to __ip_del_rt for the addrconf_ifdown path.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
Documentation/networking/ip-sysctl.txt | 8 +++++++
include/net/addrconf.h | 3 ++-
include/net/ip6_fib.h | 3 +++
include/net/ip6_route.h | 1 +
include/net/netns/ipv6.h | 1 +
net/ipv6/addrconf.c | 44 ++++++++++++++++++++++------------
net/ipv6/anycast.c | 10 +++++---
net/ipv6/ip6_fib.c | 20 ++++++++++++----
net/ipv6/route.c | 30 ++++++++++++++++++++++-
9 files changed, 95 insertions(+), 25 deletions(-)
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 960de8fe3f40..163b5ff1073c 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -1442,6 +1442,14 @@ max_hbh_length - INTEGER
header.
Default: INT_MAX (unlimited)
+skip_notify_on_dev_down - BOOLEAN
+ Controls whether an RTM_DELROUTE message is generated for routes
+ removed when a device is taken down or deleted. IPv4 does not
+ generate this message; IPv6 does by default. Setting this sysctl
+ to true skips the message, making IPv4 and IPv6 on par in relying
+ on userspace caches to track link events and evict routes.
+ Default: false (generate message)
+
IPv6 Fragmentation:
ip6frag_high_thresh - INTEGER
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 6def0351bcc3..ee6292f64c86 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -306,7 +306,8 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex,
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);
+int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr,
+ bool skip_notify);
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);
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index f06e968f1992..caabfd84a098 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -407,6 +407,9 @@ struct fib6_node *fib6_locate(struct fib6_node *root,
void fib6_clean_all(struct net *net, int (*func)(struct fib6_info *, void *arg),
void *arg);
+void fib6_clean_all_skip_notify(struct net *net,
+ int (*func)(struct fib6_info *, void *arg),
+ void *arg);
int fib6_add(struct fib6_node *root, struct fib6_info *rt,
struct nl_info *info, struct netlink_ext_ack *extack);
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index cef186dbd2ce..7c140cb2eeb0 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -104,6 +104,7 @@ int ip6_route_add(struct fib6_config *cfg, gfp_t gfp_flags,
struct netlink_ext_ack *extack);
int ip6_ins_rt(struct net *net, struct fib6_info *f6i);
int ip6_del_rt(struct net *net, struct fib6_info *f6i);
+int ip6_del_rt_skip_notify(struct net *net, struct fib6_info *f6i);
void rt6_flush_exceptions(struct fib6_info *f6i);
void rt6_age_exceptions(struct fib6_info *f6i, struct fib6_gc_args *gc_args,
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index f0e396ab9bec..ef1ed529f33c 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -45,6 +45,7 @@ struct netns_sysctl_ipv6 {
int max_dst_opts_len;
int max_hbh_opts_len;
int seg6_flowlabel;
+ bool skip_notify_on_dev_down;
};
struct netns_ipv6 {
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 2496b12bf721..cf591cf66884 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -164,7 +164,7 @@ static struct workqueue_struct *addrconf_wq;
static DECLARE_DELAYED_WORK(addr_chk_work, addrconf_verify_work);
static void addrconf_join_anycast(struct inet6_ifaddr *ifp);
-static void addrconf_leave_anycast(struct inet6_ifaddr *ifp);
+static void addrconf_leave_anycast(struct inet6_ifaddr *ifp, bool skip_notify);
static void addrconf_type_change(struct net_device *dev,
unsigned long event);
@@ -181,7 +181,8 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id,
bool send_na);
static void addrconf_dad_run(struct inet6_dev *idev);
static void addrconf_rs_timer(struct timer_list *t);
-static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa);
+static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa,
+ bool skip_notify);
static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa);
static void inet6_prefix_notify(int event, struct inet6_dev *idev,
@@ -779,7 +780,7 @@ static void dev_forward_change(struct inet6_dev *idev)
if (idev->cnf.forwarding)
addrconf_join_anycast(ifa);
else
- addrconf_leave_anycast(ifa);
+ addrconf_leave_anycast(ifa, false);
}
inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF,
NETCONFA_FORWARDING,
@@ -2141,7 +2142,7 @@ static void addrconf_join_anycast(struct inet6_ifaddr *ifp)
}
/* caller must hold RTNL */
-static void addrconf_leave_anycast(struct inet6_ifaddr *ifp)
+static void addrconf_leave_anycast(struct inet6_ifaddr *ifp, bool skip_notify)
{
struct in6_addr addr;
@@ -2150,7 +2151,7 @@ static void addrconf_leave_anycast(struct inet6_ifaddr *ifp)
ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len);
if (ipv6_addr_any(&addr))
return;
- __ipv6_dev_ac_dec(ifp->idev, &addr);
+ __ipv6_dev_ac_dec(ifp->idev, &addr, skip_notify);
}
static int addrconf_ifid_6lowpan(u8 *eui, struct net_device *dev)
@@ -3655,6 +3656,7 @@ static int addrconf_ifdown(struct net_device *dev, int how)
{
unsigned long event = how ? NETDEV_UNREGISTER : NETDEV_DOWN;
struct net *net = dev_net(dev);
+ bool skip_notify = net->ipv6.sysctl.skip_notify_on_dev_down;
struct inet6_dev *idev;
struct inet6_ifaddr *ifa, *tmp;
bool keep_addr = false;
@@ -3772,15 +3774,19 @@ static int addrconf_ifdown(struct net_device *dev, int how)
spin_unlock_bh(&ifa->lock);
- if (rt)
- ip6_del_rt(net, rt);
+ if (rt) {
+ if (skip_notify)
+ ip6_del_rt_skip_notify(net, rt);
+ else
+ ip6_del_rt(net, rt);
+ }
if (state != INET6_IFADDR_STATE_DEAD) {
- __ipv6_ifa_notify(RTM_DELADDR, ifa);
+ __ipv6_ifa_notify(RTM_DELADDR, ifa, skip_notify);
inet6addr_notifier_call_chain(NETDEV_DOWN, ifa);
} else {
if (idev->cnf.forwarding)
- addrconf_leave_anycast(ifa);
+ addrconf_leave_anycast(ifa, skip_notify);
addrconf_leave_solict(ifa->idev, &ifa->addr);
}
@@ -5830,7 +5836,8 @@ static void inet6_prefix_notify(int event, struct inet6_dev *idev,
rtnl_set_sk_err(net, RTNLGRP_IPV6_PREFIX, err);
}
-static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
+static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp,
+ bool skip_notify)
{
struct net *net = dev_net(ifp->idev->dev);
@@ -5858,18 +5865,25 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
break;
case RTM_DELADDR:
if (ifp->idev->cnf.forwarding)
- addrconf_leave_anycast(ifp);
+ addrconf_leave_anycast(ifp, skip_notify);
addrconf_leave_solict(ifp->idev, &ifp->addr);
if (!ipv6_addr_any(&ifp->peer_addr)) {
struct fib6_info *rt;
rt = addrconf_get_prefix_route(&ifp->peer_addr, 128,
ifp->idev->dev, 0, 0);
- if (rt)
- ip6_del_rt(net, rt);
+ if (rt) {
+ if (skip_notify)
+ ip6_del_rt_skip_notify(net, rt);
+ else
+ ip6_del_rt(net, rt);
+ }
}
if (ifp->rt) {
- ip6_del_rt(net, ifp->rt);
+ if (skip_notify)
+ ip6_del_rt_skip_notify(net, ifp->rt);
+ else
+ ip6_del_rt(net, ifp->rt);
ifp->rt = NULL;
}
rt_genid_bump_ipv6(net);
@@ -5882,7 +5896,7 @@ static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
{
rcu_read_lock_bh();
if (likely(ifp->idev->dead == 0))
- __ipv6_ifa_notify(event, ifp);
+ __ipv6_ifa_notify(event, ifp, false);
rcu_read_unlock_bh();
}
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index 4e0ff7031edd..762fb1de58a8 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -299,7 +299,8 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr)
/*
* device anycast group decrement
*/
-int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr)
+int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr,
+ bool skip_notify)
{
struct ifacaddr6 *aca, *prev_aca;
@@ -327,7 +328,10 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr)
write_unlock_bh(&idev->lock);
addrconf_leave_solict(idev, &aca->aca_addr);
- ip6_del_rt(dev_net(idev->dev), aca->aca_rt);
+ if (skip_notify)
+ ip6_del_rt_skip_notify(dev_net(idev->dev), aca->aca_rt);
+ else
+ ip6_del_rt(dev_net(idev->dev), aca->aca_rt);
aca_put(aca);
return 0;
@@ -340,7 +344,7 @@ static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr)
if (!idev)
return -ENODEV;
- return __ipv6_dev_ac_dec(idev, addr);
+ return __ipv6_dev_ac_dec(idev, addr, false);
}
void ipv6_ac_destroy_dev(struct inet6_dev *idev)
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index e14d244c551f..9ba72d94d60f 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -47,6 +47,7 @@ struct fib6_cleaner {
int (*func)(struct fib6_info *, void *arg);
int sernum;
void *arg;
+ bool skip_notify;
};
#ifdef CONFIG_IPV6_SUBTREES
@@ -1956,6 +1957,7 @@ static int fib6_clean_node(struct fib6_walker *w)
struct fib6_cleaner *c = container_of(w, struct fib6_cleaner, w);
struct nl_info info = {
.nl_net = c->net,
+ .skip_notify = c->skip_notify,
};
if (c->sernum != FIB6_NO_SERNUM_CHANGE &&
@@ -2007,7 +2009,7 @@ static int fib6_clean_node(struct fib6_walker *w)
static void fib6_clean_tree(struct net *net, struct fib6_node *root,
int (*func)(struct fib6_info *, void *arg),
- int sernum, void *arg)
+ int sernum, void *arg, bool skip_notify)
{
struct fib6_cleaner c;
@@ -2019,13 +2021,14 @@ static void fib6_clean_tree(struct net *net, struct fib6_node *root,
c.sernum = sernum;
c.arg = arg;
c.net = net;
+ c.skip_notify = skip_notify;
fib6_walk(net, &c.w);
}
static void __fib6_clean_all(struct net *net,
int (*func)(struct fib6_info *, void *),
- int sernum, void *arg)
+ int sernum, void *arg, bool skip_notify)
{
struct fib6_table *table;
struct hlist_head *head;
@@ -2037,7 +2040,7 @@ static void __fib6_clean_all(struct net *net,
hlist_for_each_entry_rcu(table, head, tb6_hlist) {
spin_lock_bh(&table->tb6_lock);
fib6_clean_tree(net, &table->tb6_root,
- func, sernum, arg);
+ func, sernum, arg, skip_notify);
spin_unlock_bh(&table->tb6_lock);
}
}
@@ -2047,14 +2050,21 @@ static void __fib6_clean_all(struct net *net,
void fib6_clean_all(struct net *net, int (*func)(struct fib6_info *, void *),
void *arg)
{
- __fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg);
+ __fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg, false);
+}
+
+void fib6_clean_all_skip_notify(struct net *net,
+ int (*func)(struct fib6_info *, void *),
+ void *arg)
+{
+ __fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg, true);
}
static void fib6_flush_trees(struct net *net)
{
int new_sernum = fib6_new_sernum(net);
- __fib6_clean_all(net, NULL, new_sernum, NULL);
+ __fib6_clean_all(net, NULL, new_sernum, NULL, false);
}
/*
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 7c38e0e058ae..de161808c540 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3143,6 +3143,16 @@ static int __ip6_del_rt(struct fib6_info *rt, struct nl_info *info)
return err;
}
+int ip6_del_rt_skip_notify(struct net *net, struct fib6_info *rt)
+{
+ struct nl_info info = {
+ .nl_net = net,
+ .skip_notify = true,
+ };
+
+ return __ip6_del_rt(rt, &info);
+}
+
int ip6_del_rt(struct net *net, struct fib6_info *rt)
{
struct nl_info info = { .nl_net = net };
@@ -4026,8 +4036,12 @@ void rt6_sync_down_dev(struct net_device *dev, unsigned long event)
.event = event,
},
};
+ struct net *net = dev_net(dev);
- fib6_clean_all(dev_net(dev), fib6_ifdown, &arg);
+ if (net->ipv6.sysctl.skip_notify_on_dev_down)
+ fib6_clean_all_skip_notify(net, fib6_ifdown, &arg);
+ else
+ fib6_clean_all(net, fib6_ifdown, &arg);
}
void rt6_disable_ip(struct net_device *dev, unsigned long event)
@@ -5031,6 +5045,9 @@ int ipv6_sysctl_rtcache_flush(struct ctl_table *ctl, int write,
return 0;
}
+static int zero;
+static int one = 1;
+
struct ctl_table ipv6_route_table_template[] = {
{
.procname = "flush",
@@ -5102,6 +5119,15 @@ struct ctl_table ipv6_route_table_template[] = {
.mode = 0644,
.proc_handler = proc_dointvec_ms_jiffies,
},
+ {
+ .procname = "skip_notify_on_dev_down",
+ .data = &init_net.ipv6.sysctl.skip_notify_on_dev_down,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ .extra1 = &zero,
+ .extra2 = &one,
+ },
{ }
};
@@ -5125,6 +5151,7 @@ struct ctl_table * __net_init ipv6_route_sysctl_init(struct net *net)
table[7].data = &net->ipv6.sysctl.ip6_rt_mtu_expires;
table[8].data = &net->ipv6.sysctl.ip6_rt_min_advmss;
table[9].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval;
+ table[10].data = &net->ipv6.sysctl.skip_notify_on_dev_down;
/* Don't export sysctls to unprivileged users */
if (net->user_ns != &init_user_ns)
@@ -5189,6 +5216,7 @@ static int __net_init ip6_route_net_init(struct net *net)
net->ipv6.sysctl.ip6_rt_gc_elasticity = 9;
net->ipv6.sysctl.ip6_rt_mtu_expires = 10*60*HZ;
net->ipv6.sysctl.ip6_rt_min_advmss = IPV6_MIN_MTU - 20 - 40;
+ net->ipv6.sysctl.skip_notify_on_dev_down = 0;
net->ipv6.ip6_rt_gc_expire = 30*HZ;
--
2.11.0
^ permalink raw reply related
* Re: [PATCH] bpf: btf: Fix a missing check bug
From: Alexei Starovoitov @ 2018-10-10 4:47 UTC (permalink / raw)
To: Song Liu
Cc: valdis.kletnieks, wang6495, kjlu, Alexei Starovoitov,
Daniel Borkmann, Networking, open list
In-Reply-To: <CAPhsuW7-Xa=_2BTATEhthWnyfETPv173p_cG2YrcCZ0BOsS9ow@mail.gmail.com>
On Mon, Oct 08, 2018 at 11:55:15PM -0700, Song Liu wrote:
> On Mon, Oct 8, 2018 at 6:07 PM <valdis.kletnieks@vt.edu> wrote:
> >
> > On Mon, 08 Oct 2018 17:44:46 -0700, Song Liu said:
> >
> > > I think I get the security concept here. However, hdr_len here is only used to
> > > copy the whole header into kernel space, and it is not used in other
> > > logic at all.
> > > I cannot image any security flaw with either hdr_len > btf->hdr->hdr_len case or
> > > hdr_len < btf->hdr->hdr_len. Could you please provide more insights on what
> > > would break by malicious user space?
> >
> > Say the biggest allowed value for hdr_len is 128. We check the value, the user has 98.
> > They then stuff 16,383 into there.
> >
> > Now here's the problem - hdr_len is a local variable, and evaporates when the function
> > returns. From here on out, anybody who cares about the header length will use the
> > value in btf->hdr_len....
> >
> > (And yes, somebody *does* care about the length, otherwise we wouldn't need a field
> > saying what the length was....)
> >
> > Now think how many ways that can go pear-shaped. You copied in 98 bytes, but outside
> > the function, they think that header is almost 4 pages long. Does that ever get used as
> > a length for kmemcpy()? Or a limit for a 'for (i=start; i< (start+hdr->hdr_len); i++)' that
> > walks across a variable length header?
> >
> > Can you cook up a way to have a good chance to oops the kernel when it walks off the
> > page you allocated the 98 bytes on? Can you use it to export chunks of memory out to
> > userspace? Lots and lots of ways for this to kersplat a kernel...;
>
> In current code, I don't thing any malicious hdr_len value could pass
> btf_check_sec_info().
> On the other hand, I agree this is a good-to-have check.
>
> Acked-by: Song Liu <songliubraving@fb.com>
I agree with Song's analysis that the current shape of code in
btf_check_sec_info() has us covered, but it's a good coding style
to check for TOCTOU like this, hence applied to bpf-next.
^ permalink raw reply
* Re: [PATCH net v2] net/sched: cls_api: add missing validation of netlink attributes
From: Cong Wang @ 2018-10-09 22:12 UTC (permalink / raw)
To: Davide Caratti
Cc: David Miller, David Ahern, Jamal Hadi Salim,
Linux Kernel Network Developers
In-Reply-To: <25a127708c97408a747c08a328441dee1d652f79.1539120141.git.dcaratti@redhat.com>
On Tue, Oct 9, 2018 at 2:26 PM Davide Caratti <dcaratti@redhat.com> wrote:
> --- a/net/sched/sch_api.c
> +++ b/net/sched/sch_api.c
> @@ -1322,6 +1322,7 @@ const struct nla_policy rtm_tca_policy[TCA_MAX + 1] = {
> [TCA_INGRESS_BLOCK] = { .type = NLA_U32 },
> [TCA_EGRESS_BLOCK] = { .type = NLA_U32 },
> };
> +EXPORT_SYMBOL(rtm_tca_policy);
cls_api.c is not a module, so you don't need to export it.
^ permalink raw reply
* Re: [PATCH bpf-next 0/6] Consistent prefixes for libbpf interfaces
From: Daniel Borkmann @ 2018-10-09 22:17 UTC (permalink / raw)
To: Yonghong Song, Andrey Ignatov, netdev@vger.kernel.org
Cc: ast@kernel.org, Kernel Team
In-Reply-To: <73d17896-e452-de4a-4cf6-d251bb0ef24c@fb.com>
On 10/09/2018 08:43 AM, Yonghong Song wrote:
> On 10/4/18 7:22 AM, Daniel Borkmann wrote:
>> [ +Yonghong ]
>>
>> On 10/04/2018 12:26 AM, Andrey Ignatov wrote:
>>> This patch set renames a few interfaces in libbpf, mostly netlink related,
>>> so that all symbols provided by the library have only three possible
>>> prefixes:
>>>
>>> % nm -D tools/lib/bpf/libbpf.so | \
>>> awk '$2 == "T" {sub(/[_\(].*/, "", $3); if ($3) print $3}' | \
>>> sort | \
>>> uniq -c
>>> 91 bpf
>>> 8 btf
>>> 14 libbpf
>>>
>>> libbpf is used more and more outside kernel tree. That means the library
>>> should follow good practices in library design and implementation to
>>> play well with third party code that uses it.
>>>
>>> One of such practices is to have a common prefix (or a few) for every
>>> interface, function or data structure, library provides. It helps to
>>> avoid name conflicts with other libraries and keeps API/ABI consistent.
>>>
>>> Inconsistent names in libbpf already cause problems in real life. E.g.
>>> an application can't use both libbpf and libnl due to conflicting
>>> symbols (specifically nla_parse, nla_parse_nested and a few others).
>>>
>>> Some of problematic global symbols are not part of ABI and can be
>>> restricted from export with either visibility attribute/pragma or export
>>> map (what is useful by itself and can be done in addition). That won't
>>> solve the problem for those that are part of ABI though. Also export
>>> restrictions would help only in DSO case. If third party application links
>>> libbpf statically it won't help, and people do it (e.g. Facebook links
>>> most of libraries statically, including libbpf).
>>>
>>> libbpf already uses the following prefixes for its interfaces:
>>> * bpf_ for bpf system call wrappers, program/map/elf-object
>>> abstractions and a few other things;
>>> * btf_ for BTF related API;
>>> * libbpf_ for everything else.
>>>
>>> The patch adds libbpf_ prefix to interfaces that use none of mentioned
>>> above prefixes and don't fit well into the first two categories.
>>>
>>> Long term benefits of having common prefix should outweigh possible
>>> inconvenience of changing API for those functions now.
>>>
>>> Patches 2-4 add libbpf_ prefix to libbpf interfaces: separate patch per
>>> header. Other patches are simple improvements in API.
>>>
>>>
>>> Andrey Ignatov (6):
>>> libbpf: Move __dump_nlmsg_t from API to implementation
>>> libbpf: Consistent prefixes for interfaces in libbpf.h.
>>> libbpf: Consistent prefixes for interfaces in nlattr.h.
>>> libbpf: Consistent prefixes for interfaces in str_error.h.
>>> libbpf: Make include guards consistent
>>> libbpf: Use __u32 instead of u32 in bpf_program__load
>>>
>>> tools/bpf/bpftool/net.c | 41 ++++++++++---------
>>> tools/bpf/bpftool/netlink_dumper.c | 32 ++++++++-------
>>> tools/lib/bpf/bpf.h | 6 +--
>>> tools/lib/bpf/btf.h | 6 +--
>>> tools/lib/bpf/libbpf.c | 22 +++++-----
>>> tools/lib/bpf/libbpf.h | 31 +++++++-------
>>> tools/lib/bpf/netlink.c | 48 ++++++++++++----------
>>> tools/lib/bpf/nlattr.c | 64 +++++++++++++++--------------
>>> tools/lib/bpf/nlattr.h | 65 +++++++++++++++---------------
>>> tools/lib/bpf/str_error.c | 2 +-
>>> tools/lib/bpf/str_error.h | 8 ++--
>>> 11 files changed, 171 insertions(+), 154 deletions(-)
>>
>> Overall agree that this is needed, and I've therefore applied the
>> set, thanks for cleaning up, Andrey!
>>
>> But, I would actually like to see this going one step further, in
>> particular, we should keep all the netlink related stuff inside
>> libbpf-/only/. Meaning, the goal of libbpf is not to provide yet
>> another set of netlink primitives but instead e.g. for the bpftool
>> dumper this should be abstracted away such that we pass in a callback
>> from bpftool side and have an iterator object which will then be
>> populated from inside the libbpf logic, meaning, bpftool shouldn't
>> even be aware of anything netlink there.
>
> Agreed. This indeed make sense, the user really only cares a few fields
> like devname/id, attachment_type, prog_id, etc. I will take a look at
> this later if nobody works on it.
Awesome, that would be great, thanks!
^ permalink raw reply
* [PATCH net-next] net: sched: avoid writing on noop_qdisc
From: Eric Dumazet @ 2018-10-09 22:20 UTC (permalink / raw)
To: David S . Miller; +Cc: netdev, John Fastabend, Eric Dumazet, Eric Dumazet
While noop_qdisc.gso_skb and noop_qdisc.skb_bad_txq are not used
in other places, it seems not correct to overwrite their fields
in dev_init_scheduler_queue().
noop_qdisc is essentially a shared and read-only object, even if
it is not marked as const because of some implementation detail.
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
net/sched/sch_generic.c | 14 ++++++++++++--
1 file changed, 12 insertions(+), 2 deletions(-)
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 3023929852e8c4aaa4172861d2d0beff17e25f27..de1663f7d3ad6e2c06cd2e031036cef5979366a5 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -572,6 +572,18 @@ struct Qdisc noop_qdisc = {
.dev_queue = &noop_netdev_queue,
.running = SEQCNT_ZERO(noop_qdisc.running),
.busylock = __SPIN_LOCK_UNLOCKED(noop_qdisc.busylock),
+ .gso_skb = {
+ .next = (struct sk_buff *)&noop_qdisc.gso_skb,
+ .prev = (struct sk_buff *)&noop_qdisc.gso_skb,
+ .qlen = 0,
+ .lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.gso_skb.lock),
+ },
+ .skb_bad_txq = {
+ .next = (struct sk_buff *)&noop_qdisc.skb_bad_txq,
+ .prev = (struct sk_buff *)&noop_qdisc.skb_bad_txq,
+ .qlen = 0,
+ .lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.skb_bad_txq.lock),
+ },
};
EXPORT_SYMBOL(noop_qdisc);
@@ -1273,8 +1285,6 @@ static void dev_init_scheduler_queue(struct net_device *dev,
rcu_assign_pointer(dev_queue->qdisc, qdisc);
dev_queue->qdisc_sleeping = qdisc;
- __skb_queue_head_init(&qdisc->gso_skb);
- __skb_queue_head_init(&qdisc->skb_bad_txq);
}
void dev_init_scheduler(struct net_device *dev)
--
2.19.0.605.g01d371f741-goog
^ permalink raw reply related
* [PATCH net-next 0/3] ip_tunnel: specify tunnel type via template
From: Pablo Neira Ayuso @ 2018-10-09 22:24 UTC (permalink / raw)
To: netfilter-devel
Cc: davem, netdev, roopa, amir, pshelar, u9012063, daniel,
jakub.kicinski
Hi,
The following patchset adds a new field to the tunnel metadata template.
This new field allows us to restrict the configuration to a given tunnel
driver in order to catch incorrect configuration that may result in
packets going to the wrong tunnel driver.
Changes with regards to initial RFC [1] are:
1) Explicit tunnel type initialization to TUNNEL_TYPE_UNSPEC in existing
clients for this code, as requested by Daniel.
2) Add TUNNEL_TYPE_* definition through enum tunnel_type in
uapi/linux/if_tunnel.h, so we don't need to redefine this in every
client of this infrastructure.
3) Add TUNNEL_TYPE_IPIP, TUNNEL_TYPE_IPIP6 and TUNNEL_TYPE_IP6IP6, which
were missing in the original RFC.
Let me know if you any more comments, thanks.
[1] https://marc.info/?l=netfilter-devel&m=153861145204094&w=2
Pablo Neira Ayuso (3):
ip_tunnel: add type field to struct ip_tunnel_info
net: act_tunnel_key: support for tunnel type
netfilter: nft_tunnel: support for tunnel type
drivers/net/geneve.c | 3 ++-
drivers/net/vxlan.c | 13 +++++++------
include/net/dst_metadata.h | 1 +
include/net/ip_tunnels.h | 8 ++++++++
include/uapi/linux/if_tunnel.h | 13 ++++++++++++-
include/uapi/linux/netfilter/nf_tables.h | 1 +
include/uapi/linux/tc_act/tc_tunnel_key.h | 1 +
net/core/filter.c | 1 +
net/ipv4/ip_gre.c | 2 ++
net/ipv4/ip_tunnel.c | 3 ++-
net/ipv6/ip6_gre.c | 2 ++
net/ipv6/ip6_tunnel.c | 6 ++++--
net/netfilter/nft_tunnel.c | 9 ++++++++-
net/openvswitch/flow_netlink.c | 1 +
net/sched/act_tunnel_key.c | 9 +++++++++
15 files changed, 61 insertions(+), 12 deletions(-)
^ permalink raw reply
* [PATCH net-next 1/3] ip_tunnel: add type field to struct ip_tunnel_info
From: Pablo Neira Ayuso @ 2018-10-09 22:24 UTC (permalink / raw)
To: netfilter-devel
Cc: davem, netdev, roopa, amir, pshelar, u9012063, daniel,
jakub.kicinski
In-Reply-To: <20181009222439.29399-1-pablo@netfilter.org>
This new field allows you to restrict the metadata template for a given
tunnel driver. This is convenient in scenarios that combine different
tunneling drivers, eg. vxlan and erspan. This helps you deal with
possible incorrect configurations. Default value is TUNNEL_TYPE_UNSPEC,
to retain the existing behaviour. This also implicitly exposes what
drivers are currently supported in the TUNNEL_INFO_TX mode.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
drivers/net/geneve.c | 3 ++-
drivers/net/vxlan.c | 13 +++++++------
include/net/dst_metadata.h | 1 +
include/net/ip_tunnels.h | 8 ++++++++
include/uapi/linux/if_tunnel.h | 13 ++++++++++++-
net/core/filter.c | 1 +
net/ipv4/ip_gre.c | 2 ++
net/ipv4/ip_tunnel.c | 3 ++-
net/ipv6/ip6_gre.c | 2 ++
net/ipv6/ip6_tunnel.c | 6 ++++--
net/openvswitch/flow_netlink.c | 1 +
11 files changed, 42 insertions(+), 11 deletions(-)
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 82eccc930c5c..e4fd2acb6732 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -920,7 +920,8 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
if (geneve->collect_md) {
info = skb_tunnel_info(skb);
- if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX))) {
+ if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX) ||
+ !ip_tunnel_type(info, TUNNEL_TYPE_GENEVE))) {
err = -EINVAL;
netdev_dbg(dev, "no tunnel metadata\n");
goto tx_error;
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index fb0cdbba8d76..c279c50816cf 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2296,14 +2296,15 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
skb_reset_mac_header(skb);
if (vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) {
- if (info && info->mode & IP_TUNNEL_INFO_BRIDGE &&
- info->mode & IP_TUNNEL_INFO_TX) {
+ if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX) ||
+ !ip_tunnel_type(info, TUNNEL_TYPE_VXLAN))) {
+ kfree_skb(skb);
+ return NETDEV_TX_OK;
+ }
+ if (info->mode & IP_TUNNEL_INFO_BRIDGE) {
vni = tunnel_id_to_key32(info->key.tun_id);
} else {
- if (info && info->mode & IP_TUNNEL_INFO_TX)
- vxlan_xmit_one(skb, dev, vni, NULL, false);
- else
- kfree_skb(skb);
+ vxlan_xmit_one(skb, dev, vni, NULL, false);
return NETDEV_TX_OK;
}
}
diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h
index 56cb3c38569a..fb3865b2f038 100644
--- a/include/net/dst_metadata.h
+++ b/include/net/dst_metadata.h
@@ -100,6 +100,7 @@ static inline struct metadata_dst *tun_rx_dst(int md_size)
if (!tun_dst)
return NULL;
+ tun_dst->u.tun_info.type = TUNNEL_TYPE_UNSPEC;
tun_dst->u.tun_info.options_len = 0;
tun_dst->u.tun_info.mode = 0;
return tun_dst;
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index b0d022ff6ea1..34d748ca8b30 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -67,6 +67,7 @@ struct ip_tunnel_key {
options_len) * BITS_PER_BYTE) - 1, 0)
struct ip_tunnel_info {
+ enum tunnel_type type;
struct ip_tunnel_key key;
#ifdef CONFIG_DST_CACHE
struct dst_cache dst_cache;
@@ -75,6 +76,13 @@ struct ip_tunnel_info {
u8 mode;
};
+static inline bool ip_tunnel_type(const struct ip_tunnel_info *tun_info,
+ enum tunnel_type type)
+{
+ return tun_info->type == TUNNEL_TYPE_UNSPEC ||
+ tun_info->type == type;
+}
+
/* 6rd prefix/relay information */
#ifdef CONFIG_IPV6_SIT_6RD
struct ip_tunnel_6rd_parm {
diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h
index 1b3d148c4560..1659b81fbae6 100644
--- a/include/uapi/linux/if_tunnel.h
+++ b/include/uapi/linux/if_tunnel.h
@@ -158,6 +158,17 @@ enum {
IFLA_VTI_FWMARK,
__IFLA_VTI_MAX,
};
-
#define IFLA_VTI_MAX (__IFLA_VTI_MAX - 1)
+
+enum tunnel_type {
+ TUNNEL_TYPE_UNSPEC = 0,
+ TUNNEL_TYPE_GRE,
+ TUNNEL_TYPE_VXLAN,
+ TUNNEL_TYPE_GENEVE,
+ TUNNEL_TYPE_ERSPAN,
+ TUNNEL_TYPE_IPIP,
+ TUNNEL_TYPE_IPIP6,
+ TUNNEL_TYPE_IP6IP6,
+};
+
#endif /* _UAPI_IF_TUNNEL_H_ */
diff --git a/net/core/filter.c b/net/core/filter.c
index 4bbc6567fcb8..2e75e1b014df 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3654,6 +3654,7 @@ BPF_CALL_4(bpf_skb_set_tunnel_key, struct sk_buff *, skb,
info = &md->u.tun_info;
memset(info, 0, sizeof(*info));
info->mode = IP_TUNNEL_INFO_TX;
+ info->type = TUNNEL_TYPE_UNSPEC;
info->key.tun_flags = TUNNEL_KEY | TUNNEL_CSUM | TUNNEL_NOCACHE;
if (flags & BPF_F_DONT_FRAGMENT)
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 38befe829caf..ab5de3901bc3 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -534,6 +534,7 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev,
tun_info = skb_tunnel_info(skb);
if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
+ !ip_tunnel_type(tun_info, TUNNEL_TYPE_GRE) ||
ip_tunnel_info_af(tun_info) != AF_INET))
goto err_free_skb;
@@ -585,6 +586,7 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev,
tun_info = skb_tunnel_info(skb);
if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
+ !ip_tunnel_type(tun_info, TUNNEL_TYPE_ERSPAN) ||
ip_tunnel_info_af(tun_info) != AF_INET))
goto err_free_skb;
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 284a22154b4e..b62b424183b4 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -562,7 +562,8 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto)
tun_info = skb_tunnel_info(skb);
if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
- ip_tunnel_info_af(tun_info) != AF_INET))
+ ip_tunnel_info_af(tun_info) != AF_INET) ||
+ !ip_tunnel_type(tun_info, TUNNEL_TYPE_IPIP))
goto tx_error;
key = &tun_info->key;
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 515adbdba1d2..7ff469652e6f 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -732,6 +732,7 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb,
tun_info = skb_tunnel_info(skb);
if (unlikely(!tun_info ||
!(tun_info->mode & IP_TUNNEL_INFO_TX) ||
+ !ip_tunnel_type(tun_info, TUNNEL_TYPE_GRE) ||
ip_tunnel_info_af(tun_info) != AF_INET6))
return -EINVAL;
@@ -960,6 +961,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
tun_info = skb_tunnel_info(skb);
if (unlikely(!tun_info ||
!(tun_info->mode & IP_TUNNEL_INFO_TX) ||
+ !ip_tunnel_type(tun_info, TUNNEL_TYPE_ERSPAN) ||
ip_tunnel_info_af(tun_info) != AF_INET6))
return -EINVAL;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index a0b6932c3afd..819abbcd2ebe 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1259,7 +1259,8 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
tun_info = skb_tunnel_info(skb);
if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
- ip_tunnel_info_af(tun_info) != AF_INET6))
+ ip_tunnel_info_af(tun_info) != AF_INET6) ||
+ !ip_tunnel_type(tun_info, TUNNEL_TYPE_IPIP6))
return -1;
key = &tun_info->key;
memset(&fl6, 0, sizeof(fl6));
@@ -1335,7 +1336,8 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
tun_info = skb_tunnel_info(skb);
if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
- ip_tunnel_info_af(tun_info) != AF_INET6))
+ ip_tunnel_info_af(tun_info) != AF_INET6 ||
+ !ip_tunnel_type(tun_info, TUNNEL_TYPE_IP6IP6)))
return -1;
key = &tun_info->key;
memset(&fl6, 0, sizeof(fl6));
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index a70097ecf33c..29623ad54611 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -2602,6 +2602,7 @@ static int validate_and_copy_set_tun(const struct nlattr *attr,
ovs_tun->tun_dst = tun_dst;
tun_info = &tun_dst->u.tun_info;
+ tun_info->type = TUNNEL_TYPE_UNSPEC;
tun_info->mode = IP_TUNNEL_INFO_TX;
if (key.tun_proto == AF_INET6)
tun_info->mode |= IP_TUNNEL_INFO_IPV6;
--
2.11.0
^ permalink raw reply related
* [PATCH net-next 2/3] net: act_tunnel_key: support for tunnel type
From: Pablo Neira Ayuso @ 2018-10-09 22:24 UTC (permalink / raw)
To: netfilter-devel
Cc: davem, netdev, roopa, amir, pshelar, u9012063, daniel,
jakub.kicinski
In-Reply-To: <20181009222439.29399-1-pablo@netfilter.org>
This patch allows you to set an explicit tunnel driver type in the
metadata template. In case of misconfiguration, ie. if the packets ends
up in the wrong tunnel device, the packet is dropped.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/uapi/linux/tc_act/tc_tunnel_key.h | 1 +
net/sched/act_tunnel_key.c | 9 +++++++++
2 files changed, 10 insertions(+)
diff --git a/include/uapi/linux/tc_act/tc_tunnel_key.h b/include/uapi/linux/tc_act/tc_tunnel_key.h
index be384d63e1b5..b9822433e7f1 100644
--- a/include/uapi/linux/tc_act/tc_tunnel_key.h
+++ b/include/uapi/linux/tc_act/tc_tunnel_key.h
@@ -41,6 +41,7 @@ enum {
*/
TCA_TUNNEL_KEY_ENC_TOS, /* u8 */
TCA_TUNNEL_KEY_ENC_TTL, /* u8 */
+ TCA_TUNNEL_KEY_ENC_TYPE, /* u32 */
__TCA_TUNNEL_KEY_MAX,
};
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 4cca8f274662..7852715603e9 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -195,6 +195,7 @@ static const struct nla_policy tunnel_key_policy[TCA_TUNNEL_KEY_MAX + 1] = {
[TCA_TUNNEL_KEY_ENC_OPTS] = { .type = NLA_NESTED },
[TCA_TUNNEL_KEY_ENC_TOS] = { .type = NLA_U8 },
[TCA_TUNNEL_KEY_ENC_TTL] = { .type = NLA_U8 },
+ [TCA_TUNNEL_KEY_ENC_TYPE] = { .type = NLA_U32 },
};
static int tunnel_key_init(struct net *net, struct nlattr *nla,
@@ -215,6 +216,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
__be16 flags;
u8 tos, ttl;
int ret = 0;
+ u32 type;
int err;
if (!nla) {
@@ -278,6 +280,10 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
if (tb[TCA_TUNNEL_KEY_ENC_TTL])
ttl = nla_get_u8(tb[TCA_TUNNEL_KEY_ENC_TTL]);
+ type = TUNNEL_TYPE_UNSPEC;
+ if (tb[TCA_TUNNEL_KEY_ENC_TYPE])
+ type = nla_get_u32(tb[TCA_TUNNEL_KEY_ENC_TYPE]);
+
if (tb[TCA_TUNNEL_KEY_ENC_IPV4_SRC] &&
tb[TCA_TUNNEL_KEY_ENC_IPV4_DST]) {
__be32 saddr;
@@ -320,6 +326,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
goto release_tun_meta;
}
+ metadata->u.tun_info.type = type;
metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX;
break;
default:
@@ -522,6 +529,8 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a,
if (key->ttl && nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_TTL, key->ttl))
goto nla_put_failure;
+ if (nla_put_u32(skb, TCA_TUNNEL_KEY_ENC_TYPE, info->type))
+ goto nla_put_failure;
}
tcf_tm_dump(&tm, &t->tcf_tm);
--
2.11.0
^ permalink raw reply related
* [PATCH net-next 3/3] netfilter: nft_tunnel: support for tunnel type
From: Pablo Neira Ayuso @ 2018-10-09 22:24 UTC (permalink / raw)
To: netfilter-devel
Cc: davem, netdev, roopa, amir, pshelar, u9012063, daniel,
jakub.kicinski
In-Reply-To: <20181009222439.29399-1-pablo@netfilter.org>
This patch allows you to set an explicit tunnel driver type in the
metadata template. In case of misconfiguration, ie. if the packets ends
up in the wrong tunnel device, the packet is dropped.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/uapi/linux/netfilter/nf_tables.h | 1 +
net/netfilter/nft_tunnel.c | 9 ++++++++-
2 files changed, 9 insertions(+), 1 deletion(-)
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 5444e76870bb..f484dace2b4b 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -1703,6 +1703,7 @@ enum nft_tunnel_key_attributes {
NFTA_TUNNEL_KEY_SPORT,
NFTA_TUNNEL_KEY_DPORT,
NFTA_TUNNEL_KEY_OPTS,
+ NFTA_TUNNEL_KEY_TYPE,
__NFTA_TUNNEL_KEY_MAX
};
#define NFTA_TUNNEL_KEY_MAX (__NFTA_TUNNEL_KEY_MAX - 1)
diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c
index 3a15f219e4e7..2513968d8503 100644
--- a/net/netfilter/nft_tunnel.c
+++ b/net/netfilter/nft_tunnel.c
@@ -305,6 +305,7 @@ static const struct nla_policy nft_tunnel_key_policy[NFTA_TUNNEL_KEY_MAX + 1] =
[NFTA_TUNNEL_KEY_TOS] = { .type = NLA_U8, },
[NFTA_TUNNEL_KEY_TTL] = { .type = NLA_U8, },
[NFTA_TUNNEL_KEY_OPTS] = { .type = NLA_NESTED, },
+ [NFTA_TUNNEL_KEY_TYPE] = { .type = NLA_U32, },
};
static int nft_tunnel_obj_init(const struct nft_ctx *ctx,
@@ -312,6 +313,7 @@ static int nft_tunnel_obj_init(const struct nft_ctx *ctx,
struct nft_object *obj)
{
struct nft_tunnel_obj *priv = nft_obj_data(obj);
+ u32 type = TUNNEL_TYPE_UNSPEC;
struct ip_tunnel_info info;
struct metadata_dst *md;
int err;
@@ -319,7 +321,11 @@ static int nft_tunnel_obj_init(const struct nft_ctx *ctx,
if (!tb[NFTA_TUNNEL_KEY_ID])
return -EINVAL;
+ if (tb[NFTA_TUNNEL_KEY_TYPE])
+ type = ntohl(nla_get_be32(tb[NFTA_TUNNEL_KEY_TYPE]));
+
memset(&info, 0, sizeof(info));
+ info.type = type;
info.mode = IP_TUNNEL_INFO_TX;
info.key.tun_id = key32_to_tunnel_id(nla_get_be32(tb[NFTA_TUNNEL_KEY_ID]));
info.key.tun_flags = TUNNEL_KEY | TUNNEL_CSUM | TUNNEL_NOCACHE;
@@ -494,7 +500,8 @@ static int nft_tunnel_obj_dump(struct sk_buff *skb,
struct nft_tunnel_obj *priv = nft_obj_data(obj);
struct ip_tunnel_info *info = &priv->md->u.tun_info;
- if (nla_put_be32(skb, NFTA_TUNNEL_KEY_ID,
+ if (nla_put_be32(skb, NFTA_TUNNEL_KEY_TYPE, htonl(info->type)) ||
+ nla_put_be32(skb, NFTA_TUNNEL_KEY_ID,
tunnel_id_to_key32(info->key.tun_id)) ||
nft_tunnel_ip_dump(skb, info) < 0 ||
nft_tunnel_ports_dump(skb, info) < 0 ||
--
2.11.0
^ permalink raw reply related
* [net-next:master 375/375] drivers/net//ethernet/chelsio/cxgb4/cxgb4_thermal.c:48:11: error: 'struct adapter' has no member named 'ch_thermal'
From: kbuild test robot @ 2018-10-09 22:24 UTC (permalink / raw)
To: Ganesh Goudar; +Cc: kbuild-all, netdev
[-- Attachment #1: Type: text/plain, Size: 4984 bytes --]
tree: https://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next.git master
head: b187191577629b5358acf4e234809ee8d441ceb4
commit: b187191577629b5358acf4e234809ee8d441ceb4 [375/375] cxgb4: Add thermal zone support
config: parisc-allmodconfig (attached as .config)
compiler: hppa-linux-gnu-gcc (Debian 7.2.0-11) 7.2.0
reproduce:
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
git checkout b187191577629b5358acf4e234809ee8d441ceb4
# save the attached .config to linux build tree
GCC_VERSION=7.2.0 make.cross ARCH=parisc
All errors (new ones prefixed by >>):
drivers/net//ethernet/chelsio/cxgb4/cxgb4_thermal.c: In function 'cxgb4_thermal_get_trip_type':
>> drivers/net//ethernet/chelsio/cxgb4/cxgb4_thermal.c:48:11: error: 'struct adapter' has no member named 'ch_thermal'
if (!adap->ch_thermal.trip_temp)
^~
drivers/net//ethernet/chelsio/cxgb4/cxgb4_thermal.c:51:14: error: 'struct adapter' has no member named 'ch_thermal'
*type = adap->ch_thermal.trip_type;
^~
drivers/net//ethernet/chelsio/cxgb4/cxgb4_thermal.c: In function 'cxgb4_thermal_get_trip_temp':
drivers/net//ethernet/chelsio/cxgb4/cxgb4_thermal.c:60:11: error: 'struct adapter' has no member named 'ch_thermal'
if (!adap->ch_thermal.trip_temp)
^~
drivers/net//ethernet/chelsio/cxgb4/cxgb4_thermal.c:63:14: error: 'struct adapter' has no member named 'ch_thermal'
*temp = adap->ch_thermal.trip_temp;
^~
drivers/net//ethernet/chelsio/cxgb4/cxgb4_thermal.c: In function 'cxgb4_thermal_init':
drivers/net//ethernet/chelsio/cxgb4/cxgb4_thermal.c:75:39: error: 'struct adapter' has no member named 'ch_thermal'
struct ch_thermal *ch_thermal = &adap->ch_thermal;
^~
>> drivers/net//ethernet/chelsio/cxgb4/cxgb4_thermal.c:92:13: error: dereferencing pointer to incomplete type 'struct ch_thermal'
ch_thermal->trip_temp = val * 1000;
^~
drivers/net//ethernet/chelsio/cxgb4/cxgb4_thermal.c: In function 'cxgb4_thermal_remove':
drivers/net//ethernet/chelsio/cxgb4/cxgb4_thermal.c:111:10: error: 'struct adapter' has no member named 'ch_thermal'
if (adap->ch_thermal.tzdev)
^~
drivers/net//ethernet/chelsio/cxgb4/cxgb4_thermal.c:112:38: error: 'struct adapter' has no member named 'ch_thermal'
thermal_zone_device_unregister(adap->ch_thermal.tzdev);
^~
vim +48 drivers/net//ethernet/chelsio/cxgb4/cxgb4_thermal.c
42
43 static int cxgb4_thermal_get_trip_type(struct thermal_zone_device *tzdev,
44 int trip, enum thermal_trip_type *type)
45 {
46 struct adapter *adap = tzdev->devdata;
47
> 48 if (!adap->ch_thermal.trip_temp)
49 return -EINVAL;
50
51 *type = adap->ch_thermal.trip_type;
52 return 0;
53 }
54
55 static int cxgb4_thermal_get_trip_temp(struct thermal_zone_device *tzdev,
56 int trip, int *temp)
57 {
58 struct adapter *adap = tzdev->devdata;
59
60 if (!adap->ch_thermal.trip_temp)
61 return -EINVAL;
62
> 63 *temp = adap->ch_thermal.trip_temp;
64 return 0;
65 }
66
67 static struct thermal_zone_device_ops cxgb4_thermal_ops = {
68 .get_temp = cxgb4_thermal_get_temp,
69 .get_trip_type = cxgb4_thermal_get_trip_type,
70 .get_trip_temp = cxgb4_thermal_get_trip_temp,
71 };
72
73 int cxgb4_thermal_init(struct adapter *adap)
74 {
75 struct ch_thermal *ch_thermal = &adap->ch_thermal;
76 int num_trip = CXGB4_NUM_TRIPS;
77 u32 param, val;
78 int ret;
79
80 /* on older firmwares we may not get the trip temperature,
81 * set the num of trips to 0.
82 */
83 param = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
84 FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_DIAG) |
85 FW_PARAMS_PARAM_Y_V(FW_PARAM_DEV_DIAG_MAXTMPTHRESH));
86
87 ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 1,
88 ¶m, &val);
89 if (ret < 0) {
90 num_trip = 0; /* could not get trip temperature */
91 } else {
> 92 ch_thermal->trip_temp = val * 1000;
93 ch_thermal->trip_type = THERMAL_TRIP_CRITICAL;
94 }
95
96 ch_thermal->tzdev = thermal_zone_device_register("cxgb4", num_trip,
97 0, adap,
98 &cxgb4_thermal_ops,
99 NULL, 0, 0);
100 if (IS_ERR(ch_thermal->tzdev)) {
101 ret = PTR_ERR(ch_thermal->tzdev);
102 dev_err(adap->pdev_dev, "Failed to register thermal zone\n");
103 ch_thermal->tzdev = NULL;
104 return ret;
105 }
106 return 0;
107 }
108
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 54415 bytes --]
^ permalink raw reply
* Re: [RFC PATCH 01/11] phy: core add phy_set_netif_mode() api
From: Grygorii Strashko @ 2018-10-09 22:43 UTC (permalink / raw)
To: Kishon Vijay Abraham I, David S. Miller, netdev, Tony Lindgren,
Rob Herring
Cc: Sekhar Nori, linux-kernel, linux-omap, devicetree
In-Reply-To: <54ba13bb-95e1-1519-a30f-8da198447489@ti.com>
On 10/09/2018 12:22 AM, Kishon Vijay Abraham I wrote:
> Hi Grygorii,
>
> On Tuesday 09 October 2018 05:19 AM, Grygorii Strashko wrote:
>> Add new API phy_set_netif_mode(struct phy *phy, phy_interface_t mode) and
>> new PHY operation callback .set_netif_mode() which intended to be implemnte
>> by PHY drivers which supports Network interrfaces mode selection. Both
>> accepts phy_interface_t vlaue as input parameter.
>>
>> Cc: Kishon Vijay Abraham I <kishon@ti.com>
>> Cc: Tony Lindgren <tony@atomide.com>
>> Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
>> ---
>> drivers/phy/phy-core.c | 15 +++++++++++++++
>> include/linux/phy/phy.h | 12 ++++++++++++
>> 2 files changed, 27 insertions(+)
>>
>> diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c
>> index 35fd38c..d9aba1a 100644
>> --- a/drivers/phy/phy-core.c
>> +++ b/drivers/phy/phy-core.c
>> @@ -377,6 +377,21 @@ int phy_set_mode(struct phy *phy, enum phy_mode mode)
>> }
>> EXPORT_SYMBOL_GPL(phy_set_mode);
>>
>> +int phy_set_netif_mode(struct phy *phy, phy_interface_t mode)
>> +{
>> + int ret;
>> +
>> + if (!phy || !phy->ops->set_netif_mode)
>> + return 0;
>> +
>> + mutex_lock(&phy->mutex);
>> + ret = phy->ops->set_netif_mode(phy, mode);
>> + mutex_unlock(&phy->mutex);
>> +
>> + return ret;
>> +}
>> +EXPORT_SYMBOL_GPL(phy_set_netif_mode);
>
> We should try to add only generic PHY APIs and not subsystem specific APIs. In
> this case I think phy_set_mode should suffice.
This is what I've had in mind first, but all my guts argued against it after I've tried:
diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h
index bc73d2b..961b156 100644
--- a/include/linux/phy/phy.h
+++ b/include/linux/phy/phy.h
@@ -41,6 +41,14 @@ enum phy_mode {
PHY_MODE_10GKR,
PHY_MODE_UFS_HS_A,
PHY_MODE_UFS_HS_B,
+ PHY_MODE_MODE_MII,
+ PHY_MODE_MODE_GMII,
+ PHY_MODE_MODE_SGMII,
+ PHY_MODE_MODE_RMII,
+ PHY_MODE_MODE_RGMII,
+ PHY_MODE_MODE_RGMII_ID,
+ PHY_MODE_MODE_RGMII_RXID,
+ PHY_MODE_MODE_RGMII_TXID,
};
above introduces ugly constants duplication and required every network phy driver
to maintain conversation table phy_interface_t -> enum phy_mode.
More over, if above change happens third time (first time PHY_MODE_SGMII/PHY_MODE_10GKR were added,
second - PHY_MODE_2500SGMII) it will never ends (there are ~15 more items only in phy_interface_t).
As result, enum phy_mode might became a un-maintainable monster.
So, as per above, and considering that Network subsystem is based on standards (phy_interface_t lists standard intf)
I've tried to add separate PHY API.
As an idea:
- seems it could be reasonable to introduce PHY_MODE_NETWORK (or PHY_MODE_ETHERNET) and
add generic phy_set_submode(struct phy *phy, long submode).
So, single functional PHY device can just use phy_set_submode() and
multi-functional devices (like serdes which can be muxed between PCIe, USB, NET), can use:
phy_set_mode(PHY_MODE_ETHERNET)
phy_set_submode(X);
Any way, if you still agree to just add new above phy_modes - i'll redo patches.
--
regards,
-grygorii
^ permalink raw reply related
* [PATCH stable 4.9 01/29] inet: frags: change inet_frags_init_net() return value
From: Florian Fainelli @ 2018-10-09 22:48 UTC (permalink / raw)
To: netdev; +Cc: davem, gregkh, stable, edumazet, sthemmin
In-Reply-To: <20181009224924.30151-1-f.fainelli@gmail.com>
From: Eric Dumazet <edumazet@google.com>
We will soon initialize one rhashtable per struct netns_frags
in inet_frags_init_net().
This patch changes the return value to eventually propagate an
error.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
(cherry picked from commit 787bea7748a76130566f881c2342a0be4127d182)
---
include/net/inet_frag.h | 3 ++-
net/ieee802154/6lowpan/reassembly.c | 11 ++++++++---
net/ipv4/ip_fragment.c | 12 +++++++++---
net/ipv6/netfilter/nf_conntrack_reasm.c | 12 +++++++++---
net/ipv6/reassembly.c | 11 +++++++++--
5 files changed, 37 insertions(+), 12 deletions(-)
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 634d19203e7d..3fb9c48dedfe 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -103,9 +103,10 @@ struct inet_frags {
int inet_frags_init(struct inet_frags *);
void inet_frags_fini(struct inet_frags *);
-static inline void inet_frags_init_net(struct netns_frags *nf)
+static inline int inet_frags_init_net(struct netns_frags *nf)
{
atomic_set(&nf->mem, 0);
+ return 0;
}
void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f);
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index f85b08baff16..9757ce6c077a 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -580,14 +580,19 @@ static int __net_init lowpan_frags_init_net(struct net *net)
{
struct netns_ieee802154_lowpan *ieee802154_lowpan =
net_ieee802154_lowpan(net);
+ int res;
ieee802154_lowpan->frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
ieee802154_lowpan->frags.low_thresh = IPV6_FRAG_LOW_THRESH;
ieee802154_lowpan->frags.timeout = IPV6_FRAG_TIMEOUT;
- inet_frags_init_net(&ieee802154_lowpan->frags);
-
- return lowpan_frags_ns_sysctl_register(net);
+ res = inet_frags_init_net(&ieee802154_lowpan->frags);
+ if (res < 0)
+ return res;
+ res = lowpan_frags_ns_sysctl_register(net);
+ if (res < 0)
+ inet_frags_exit_net(&ieee802154_lowpan->frags, &lowpan_frags);
+ return res;
}
static void __net_exit lowpan_frags_exit_net(struct net *net)
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 752711cd4834..803914569858 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -849,6 +849,8 @@ static void __init ip4_frags_ctl_register(void)
static int __net_init ipv4_frags_init_net(struct net *net)
{
+ int res;
+
/* Fragment cache limits.
*
* The fragment memory accounting code, (tries to) account for
@@ -874,9 +876,13 @@ static int __net_init ipv4_frags_init_net(struct net *net)
net->ipv4.frags.max_dist = 64;
- inet_frags_init_net(&net->ipv4.frags);
-
- return ip4_frags_ns_ctl_register(net);
+ res = inet_frags_init_net(&net->ipv4.frags);
+ if (res < 0)
+ return res;
+ res = ip4_frags_ns_ctl_register(net);
+ if (res < 0)
+ inet_frags_exit_net(&net->ipv4.frags, &ip4_frags);
+ return res;
}
static void __net_exit ipv4_frags_exit_net(struct net *net)
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index ee33a6743f3b..afa9ea76155d 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -630,12 +630,18 @@ EXPORT_SYMBOL_GPL(nf_ct_frag6_gather);
static int nf_ct_net_init(struct net *net)
{
+ int res;
+
net->nf_frag.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
net->nf_frag.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
net->nf_frag.frags.timeout = IPV6_FRAG_TIMEOUT;
- inet_frags_init_net(&net->nf_frag.frags);
-
- return nf_ct_frag6_sysctl_register(net);
+ res = inet_frags_init_net(&net->nf_frag.frags);
+ if (res < 0)
+ return res;
+ res = nf_ct_frag6_sysctl_register(net);
+ if (res < 0)
+ inet_frags_exit_net(&net->nf_frag.frags, &nf_frags);
+ return res;
}
static void nf_ct_net_exit(struct net *net)
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index e585c0a2591c..ee8095eaca5d 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -709,13 +709,20 @@ static void ip6_frags_sysctl_unregister(void)
static int __net_init ipv6_frags_init_net(struct net *net)
{
+ int res;
+
net->ipv6.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
net->ipv6.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
net->ipv6.frags.timeout = IPV6_FRAG_TIMEOUT;
- inet_frags_init_net(&net->ipv6.frags);
+ res = inet_frags_init_net(&net->ipv6.frags);
+ if (res < 0)
+ return res;
- return ip6_frags_ns_sysctl_register(net);
+ res = ip6_frags_ns_sysctl_register(net);
+ if (res < 0)
+ inet_frags_exit_net(&net->ipv6.frags, &ip6_frags);
+ return res;
}
static void __net_exit ipv6_frags_exit_net(struct net *net)
--
2.17.1
^ permalink raw reply related
* [PATCH stable 4.9 02/29] inet: frags: add a pointer to struct netns_frags
From: Florian Fainelli @ 2018-10-09 22:48 UTC (permalink / raw)
To: netdev; +Cc: davem, gregkh, stable, edumazet, sthemmin
In-Reply-To: <20181009224924.30151-1-f.fainelli@gmail.com>
From: Eric Dumazet <edumazet@google.com>
In order to simplify the API, add a pointer to struct inet_frags.
This will allow us to make things less complex.
These functions no longer have a struct inet_frags parameter :
inet_frag_destroy(struct inet_frag_queue *q /*, struct inet_frags *f */)
inet_frag_put(struct inet_frag_queue *q /*, struct inet_frags *f */)
inet_frag_kill(struct inet_frag_queue *q /*, struct inet_frags *f */)
inet_frags_exit_net(struct netns_frags *nf /*, struct inet_frags *f */)
ip6_expire_frag_queue(struct net *net, struct frag_queue *fq)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
(cherry picked from commit 093ba72914b696521e4885756a68a3332782c8de)
---
include/net/inet_frag.h | 11 ++++++-----
include/net/ipv6.h | 3 +--
net/ieee802154/6lowpan/reassembly.c | 13 +++++++------
net/ipv4/inet_fragment.c | 17 ++++++++++-------
net/ipv4/ip_fragment.c | 9 +++++----
net/ipv6/netfilter/nf_conntrack_reasm.c | 16 +++++++++-------
net/ipv6/reassembly.c | 20 ++++++++++----------
7 files changed, 48 insertions(+), 41 deletions(-)
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 3fb9c48dedfe..19a2ccda0300 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -9,6 +9,7 @@ struct netns_frags {
int high_thresh;
int low_thresh;
int max_dist;
+ struct inet_frags *f;
};
/**
@@ -108,20 +109,20 @@ static inline int inet_frags_init_net(struct netns_frags *nf)
atomic_set(&nf->mem, 0);
return 0;
}
-void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f);
+void inet_frags_exit_net(struct netns_frags *nf);
-void inet_frag_kill(struct inet_frag_queue *q, struct inet_frags *f);
-void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f);
+void inet_frag_kill(struct inet_frag_queue *q);
+void inet_frag_destroy(struct inet_frag_queue *q);
struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
struct inet_frags *f, void *key, unsigned int hash);
void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
const char *prefix);
-static inline void inet_frag_put(struct inet_frag_queue *q, struct inet_frags *f)
+static inline void inet_frag_put(struct inet_frag_queue *q)
{
if (atomic_dec_and_test(&q->refcnt))
- inet_frag_destroy(q, f);
+ inet_frag_destroy(q);
}
static inline bool inet_frag_evicting(struct inet_frag_queue *q)
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 64b0e9df31c7..903a10a5f259 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -559,8 +559,7 @@ struct frag_queue {
u8 ecn;
};
-void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq,
- struct inet_frags *frags);
+void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq);
static inline bool ipv6_addr_any(const struct in6_addr *a)
{
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index 9757ce6c077a..9ccb8458b5c3 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -93,10 +93,10 @@ static void lowpan_frag_expire(unsigned long data)
if (fq->q.flags & INET_FRAG_COMPLETE)
goto out;
- inet_frag_kill(&fq->q, &lowpan_frags);
+ inet_frag_kill(&fq->q);
out:
spin_unlock(&fq->q.lock);
- inet_frag_put(&fq->q, &lowpan_frags);
+ inet_frag_put(&fq->q);
}
static inline struct lowpan_frag_queue *
@@ -229,7 +229,7 @@ static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *prev,
struct sk_buff *fp, *head = fq->q.fragments;
int sum_truesize;
- inet_frag_kill(&fq->q, &lowpan_frags);
+ inet_frag_kill(&fq->q);
/* Make the one we just received the head. */
if (prev) {
@@ -437,7 +437,7 @@ int lowpan_frag_rcv(struct sk_buff *skb, u8 frag_type)
ret = lowpan_frag_queue(fq, skb, frag_type);
spin_unlock(&fq->q.lock);
- inet_frag_put(&fq->q, &lowpan_frags);
+ inet_frag_put(&fq->q);
return ret;
}
@@ -585,13 +585,14 @@ static int __net_init lowpan_frags_init_net(struct net *net)
ieee802154_lowpan->frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
ieee802154_lowpan->frags.low_thresh = IPV6_FRAG_LOW_THRESH;
ieee802154_lowpan->frags.timeout = IPV6_FRAG_TIMEOUT;
+ ieee802154_lowpan->frags.f = &lowpan_frags;
res = inet_frags_init_net(&ieee802154_lowpan->frags);
if (res < 0)
return res;
res = lowpan_frags_ns_sysctl_register(net);
if (res < 0)
- inet_frags_exit_net(&ieee802154_lowpan->frags, &lowpan_frags);
+ inet_frags_exit_net(&ieee802154_lowpan->frags);
return res;
}
@@ -601,7 +602,7 @@ static void __net_exit lowpan_frags_exit_net(struct net *net)
net_ieee802154_lowpan(net);
lowpan_frags_ns_sysctl_unregister(net);
- inet_frags_exit_net(&ieee802154_lowpan->frags, &lowpan_frags);
+ inet_frags_exit_net(&ieee802154_lowpan->frags);
}
static struct pernet_operations lowpan_frags_ops = {
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index f8b41aaac76f..89cfe0df8e56 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -219,8 +219,9 @@ void inet_frags_fini(struct inet_frags *f)
}
EXPORT_SYMBOL(inet_frags_fini);
-void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f)
+void inet_frags_exit_net(struct netns_frags *nf)
{
+ struct inet_frags *f =nf->f;
unsigned int seq;
int i;
@@ -264,33 +265,34 @@ __acquires(hb->chain_lock)
return hb;
}
-static inline void fq_unlink(struct inet_frag_queue *fq, struct inet_frags *f)
+static inline void fq_unlink(struct inet_frag_queue *fq)
{
struct inet_frag_bucket *hb;
- hb = get_frag_bucket_locked(fq, f);
+ hb = get_frag_bucket_locked(fq, fq->net->f);
hlist_del(&fq->list);
fq->flags |= INET_FRAG_COMPLETE;
spin_unlock(&hb->chain_lock);
}
-void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f)
+void inet_frag_kill(struct inet_frag_queue *fq)
{
if (del_timer(&fq->timer))
atomic_dec(&fq->refcnt);
if (!(fq->flags & INET_FRAG_COMPLETE)) {
- fq_unlink(fq, f);
+ fq_unlink(fq);
atomic_dec(&fq->refcnt);
}
}
EXPORT_SYMBOL(inet_frag_kill);
-void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f)
+void inet_frag_destroy(struct inet_frag_queue *q)
{
struct sk_buff *fp;
struct netns_frags *nf;
unsigned int sum, sum_truesize = 0;
+ struct inet_frags *f;
WARN_ON(!(q->flags & INET_FRAG_COMPLETE));
WARN_ON(del_timer(&q->timer) != 0);
@@ -298,6 +300,7 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f)
/* Release all fragment data. */
fp = q->fragments;
nf = q->net;
+ f = nf->f;
while (fp) {
struct sk_buff *xp = fp->next;
@@ -333,7 +336,7 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf,
atomic_inc(&qp->refcnt);
spin_unlock(&hb->chain_lock);
qp_in->flags |= INET_FRAG_COMPLETE;
- inet_frag_put(qp_in, f);
+ inet_frag_put(qp_in);
return qp;
}
}
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 803914569858..0fd3b475b929 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -167,7 +167,7 @@ static void ip4_frag_free(struct inet_frag_queue *q)
static void ipq_put(struct ipq *ipq)
{
- inet_frag_put(&ipq->q, &ip4_frags);
+ inet_frag_put(&ipq->q);
}
/* Kill ipq entry. It is not destroyed immediately,
@@ -175,7 +175,7 @@ static void ipq_put(struct ipq *ipq)
*/
static void ipq_kill(struct ipq *ipq)
{
- inet_frag_kill(&ipq->q, &ip4_frags);
+ inet_frag_kill(&ipq->q);
}
static bool frag_expire_skip_icmp(u32 user)
@@ -875,20 +875,21 @@ static int __net_init ipv4_frags_init_net(struct net *net)
net->ipv4.frags.timeout = IP_FRAG_TIME;
net->ipv4.frags.max_dist = 64;
+ net->ipv4.frags.f = &ip4_frags;
res = inet_frags_init_net(&net->ipv4.frags);
if (res < 0)
return res;
res = ip4_frags_ns_ctl_register(net);
if (res < 0)
- inet_frags_exit_net(&net->ipv4.frags, &ip4_frags);
+ inet_frags_exit_net(&net->ipv4.frags);
return res;
}
static void __net_exit ipv4_frags_exit_net(struct net *net)
{
ip4_frags_ns_ctl_unregister(net);
- inet_frags_exit_net(&net->ipv4.frags, &ip4_frags);
+ inet_frags_exit_net(&net->ipv4.frags);
}
static struct pernet_operations ip4_frags_ops = {
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index afa9ea76155d..7ea2b4490672 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -177,7 +177,7 @@ static void nf_ct_frag6_expire(unsigned long data)
fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q);
net = container_of(fq->q.net, struct net, nf_frag.frags);
- ip6_expire_frag_queue(net, fq, &nf_frags);
+ ip6_expire_frag_queue(net, fq);
}
/* Creation primitives. */
@@ -263,7 +263,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,
* this case. -DaveM
*/
pr_debug("end of fragment not rounded to 8 bytes.\n");
- inet_frag_kill(&fq->q, &nf_frags);
+ inet_frag_kill(&fq->q);
return -EPROTO;
}
if (end > fq->q.len) {
@@ -356,7 +356,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,
return 0;
discard_fq:
- inet_frag_kill(&fq->q, &nf_frags);
+ inet_frag_kill(&fq->q);
err:
return -EINVAL;
}
@@ -378,7 +378,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_devic
int payload_len;
u8 ecn;
- inet_frag_kill(&fq->q, &nf_frags);
+ inet_frag_kill(&fq->q);
WARN_ON(head == NULL);
WARN_ON(NFCT_FRAG6_CB(head)->offset != 0);
@@ -623,7 +623,7 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
out_unlock:
spin_unlock_bh(&fq->q.lock);
- inet_frag_put(&fq->q, &nf_frags);
+ inet_frag_put(&fq->q);
return ret;
}
EXPORT_SYMBOL_GPL(nf_ct_frag6_gather);
@@ -635,19 +635,21 @@ static int nf_ct_net_init(struct net *net)
net->nf_frag.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
net->nf_frag.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
net->nf_frag.frags.timeout = IPV6_FRAG_TIMEOUT;
+ net->nf_frag.frags.f = &nf_frags;
+
res = inet_frags_init_net(&net->nf_frag.frags);
if (res < 0)
return res;
res = nf_ct_frag6_sysctl_register(net);
if (res < 0)
- inet_frags_exit_net(&net->nf_frag.frags, &nf_frags);
+ inet_frags_exit_net(&net->nf_frag.frags);
return res;
}
static void nf_ct_net_exit(struct net *net)
{
nf_ct_frags6_sysctl_unregister(net);
- inet_frags_exit_net(&net->nf_frag.frags, &nf_frags);
+ inet_frags_exit_net(&net->nf_frag.frags);
}
static struct pernet_operations nf_ct_net_ops = {
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index ee8095eaca5d..436e6d594f25 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -128,8 +128,7 @@ void ip6_frag_init(struct inet_frag_queue *q, const void *a)
}
EXPORT_SYMBOL(ip6_frag_init);
-void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq,
- struct inet_frags *frags)
+void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq)
{
struct net_device *dev = NULL;
@@ -138,7 +137,7 @@ void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq,
if (fq->q.flags & INET_FRAG_COMPLETE)
goto out;
- inet_frag_kill(&fq->q, frags);
+ inet_frag_kill(&fq->q);
rcu_read_lock();
dev = dev_get_by_index_rcu(net, fq->iif);
@@ -166,7 +165,7 @@ void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq,
rcu_read_unlock();
out:
spin_unlock(&fq->q.lock);
- inet_frag_put(&fq->q, frags);
+ inet_frag_put(&fq->q);
}
EXPORT_SYMBOL(ip6_expire_frag_queue);
@@ -178,7 +177,7 @@ static void ip6_frag_expire(unsigned long data)
fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q);
net = container_of(fq->q.net, struct net, ipv6.frags);
- ip6_expire_frag_queue(net, fq, &ip6_frags);
+ ip6_expire_frag_queue(net, fq);
}
static struct frag_queue *
@@ -359,7 +358,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
return -1;
discard_fq:
- inet_frag_kill(&fq->q, &ip6_frags);
+ inet_frag_kill(&fq->q);
err:
__IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_REASMFAILS);
@@ -386,7 +385,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
int sum_truesize;
u8 ecn;
- inet_frag_kill(&fq->q, &ip6_frags);
+ inet_frag_kill(&fq->q);
ecn = ip_frag_ecn_table[fq->ecn];
if (unlikely(ecn == 0xff))
@@ -563,7 +562,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff);
spin_unlock(&fq->q.lock);
- inet_frag_put(&fq->q, &ip6_frags);
+ inet_frag_put(&fq->q);
return ret;
}
@@ -714,6 +713,7 @@ static int __net_init ipv6_frags_init_net(struct net *net)
net->ipv6.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
net->ipv6.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
net->ipv6.frags.timeout = IPV6_FRAG_TIMEOUT;
+ net->ipv6.frags.f = &ip6_frags;
res = inet_frags_init_net(&net->ipv6.frags);
if (res < 0)
@@ -721,14 +721,14 @@ static int __net_init ipv6_frags_init_net(struct net *net)
res = ip6_frags_ns_sysctl_register(net);
if (res < 0)
- inet_frags_exit_net(&net->ipv6.frags, &ip6_frags);
+ inet_frags_exit_net(&net->ipv6.frags);
return res;
}
static void __net_exit ipv6_frags_exit_net(struct net *net)
{
ip6_frags_ns_sysctl_unregister(net);
- inet_frags_exit_net(&net->ipv6.frags, &ip6_frags);
+ inet_frags_exit_net(&net->ipv6.frags);
}
static struct pernet_operations ip6_frags_ops = {
--
2.17.1
^ permalink raw reply related
* [PATCH stable 4.9 03/29] inet: frags: refactor ipfrag_init()
From: Florian Fainelli @ 2018-10-09 22:48 UTC (permalink / raw)
To: netdev; +Cc: davem, gregkh, stable, edumazet, sthemmin
In-Reply-To: <20181009224924.30151-1-f.fainelli@gmail.com>
From: Eric Dumazet <edumazet@google.com>
We need to call inet_frags_init() before register_pernet_subsys(),
as a prereq for following patch ("inet: frags: use rhashtables for reassembly units")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
(cherry picked from commit 483a6e4fa055123142d8956866fe2aa9c98d546d)
---
net/ipv4/ip_fragment.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 0fd3b475b929..b6fe05e8a431 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -899,8 +899,6 @@ static struct pernet_operations ip4_frags_ops = {
void __init ipfrag_init(void)
{
- ip4_frags_ctl_register();
- register_pernet_subsys(&ip4_frags_ops);
ip4_frags.hashfn = ip4_hashfn;
ip4_frags.constructor = ip4_frag_init;
ip4_frags.destructor = ip4_frag_free;
@@ -910,4 +908,6 @@ void __init ipfrag_init(void)
ip4_frags.frags_cache_name = ip_frag_cache_name;
if (inet_frags_init(&ip4_frags))
panic("IP: failed to allocate ip4_frags cache\n");
+ ip4_frags_ctl_register();
+ register_pernet_subsys(&ip4_frags_ops);
}
--
2.17.1
^ permalink raw reply related
* [PATCH stable 4.9 06/29] ipv6: export ip6 fragments sysctl to unprivileged users
From: Florian Fainelli @ 2018-10-09 22:49 UTC (permalink / raw)
To: netdev; +Cc: davem, gregkh, stable, edumazet, sthemmin, Nikolay Borisov
In-Reply-To: <20181009224924.30151-1-f.fainelli@gmail.com>
From: Eric Dumazet <edumazet@google.com>
IPv4 was changed in commit 52a773d645e9 ("net: Export ip fragment
sysctl to unprivileged users")
The only sysctl that is not per-netns is not used :
ip6frag_secret_interval
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Nikolay Borisov <kernel@kyup.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
(cherry picked from commit 18dcbe12fe9fca0ab825f7eff993060525ac2503)
---
net/ipv6/reassembly.c | 4 ----
1 file changed, 4 deletions(-)
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 9440bb9bdab7..9fe99475bddf 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -643,10 +643,6 @@ static int __net_init ip6_frags_ns_sysctl_register(struct net *net)
table[1].data = &net->ipv6.frags.low_thresh;
table[1].extra2 = &net->ipv6.frags.high_thresh;
table[2].data = &net->ipv6.frags.timeout;
-
- /* Don't export sysctls to unprivileged users */
- if (net->user_ns != &init_user_ns)
- table[0].procname = NULL;
}
hdr = register_net_sysctl(net, "net/ipv6", table);
--
2.17.1
^ permalink raw reply related
* [PATCH stable 4.9 07/29] rhashtable: add schedule points
From: Florian Fainelli @ 2018-10-09 22:49 UTC (permalink / raw)
To: netdev; +Cc: davem, gregkh, stable, edumazet, sthemmin
In-Reply-To: <20181009224924.30151-1-f.fainelli@gmail.com>
From: Eric Dumazet <edumazet@google.com>
Rehashing and destroying large hash table takes a lot of time,
and happens in process context. It is safe to add cond_resched()
in rhashtable_rehash_table() and rhashtable_free_and_destroy()
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
(cherry picked from commit ae6da1f503abb5a5081f9f6c4a6881de97830f3e)
---
lib/rhashtable.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 101dac085c62..fdffd6232365 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -251,8 +251,10 @@ static int rhashtable_rehash_table(struct rhashtable *ht)
if (!new_tbl)
return 0;
- for (old_hash = 0; old_hash < old_tbl->size; old_hash++)
+ for (old_hash = 0; old_hash < old_tbl->size; old_hash++) {
rhashtable_rehash_chain(ht, old_hash);
+ cond_resched();
+ }
/* Publish the new table pointer. */
rcu_assign_pointer(ht->tbl, new_tbl);
@@ -993,6 +995,7 @@ void rhashtable_free_and_destroy(struct rhashtable *ht,
for (i = 0; i < tbl->size; i++) {
struct rhash_head *pos, *next;
+ cond_resched();
for (pos = rht_dereference(tbl->buckets[i], ht),
next = !rht_is_a_nulls(pos) ?
rht_dereference(pos->next, ht) : NULL;
--
2.17.1
^ permalink raw reply related
* [PATCH stable 4.9 08/29] inet: frags: use rhashtables for reassembly units
From: Florian Fainelli @ 2018-10-09 22:49 UTC (permalink / raw)
To: netdev
Cc: davem, gregkh, stable, edumazet, sthemmin, Kirill Tkhai,
Herbert Xu, Florian Westphal, Jesper Dangaard Brouer,
Alexander Aring, Stefan Schmidt
In-Reply-To: <20181009224924.30151-1-f.fainelli@gmail.com>
From: Eric Dumazet <edumazet@google.com>
Some applications still rely on IP fragmentation, and to be fair linux
reassembly unit is not working under any serious load.
It uses static hash tables of 1024 buckets, and up to 128 items per bucket (!!!)
A work queue is supposed to garbage collect items when host is under memory
pressure, and doing a hash rebuild, changing seed used in hash computations.
This work queue blocks softirqs for up to 25 ms when doing a hash rebuild,
occurring every 5 seconds if host is under fire.
Then there is the problem of sharing this hash table for all netns.
It is time to switch to rhashtables, and allocate one of them per netns
to speedup netns dismantle, since this is a critical metric these days.
Lookup is now using RCU. A followup patch will even remove
the refcount hold/release left from prior implementation and save
a couple of atomic operations.
Before this patch, 16 cpus (16 RX queue NIC) could not handle more
than 1 Mpps frags DDOS.
After the patch, I reach 9 Mpps without any tuning, and can use up to 2GB
of storage for the fragments (exact number depends on frags being evicted
after timeout)
$ grep FRAG /proc/net/sockstat
FRAG: inuse 1966916 memory 2140004608
A followup patch will change the limits for 64bit arches.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Kirill Tkhai <ktkhai@virtuozzo.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Florian Westphal <fw@strlen.de>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Alexander Aring <alex.aring@gmail.com>
Cc: Stefan Schmidt <stefan@osg.samsung.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
(cherry picked from commit 648700f76b03b7e8149d13cc2bdb3355035258a9)
---
Documentation/networking/ip-sysctl.txt | 7 +-
include/net/inet_frag.h | 81 +++---
include/net/ipv6.h | 16 +-
net/ieee802154/6lowpan/6lowpan_i.h | 26 +-
net/ieee802154/6lowpan/reassembly.c | 91 +++---
net/ipv4/inet_fragment.c | 349 +++++-------------------
net/ipv4/ip_fragment.c | 112 ++++----
net/ipv6/netfilter/nf_conntrack_reasm.c | 51 +---
net/ipv6/reassembly.c | 110 ++++----
9 files changed, 267 insertions(+), 576 deletions(-)
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 3db8c67d2c8d..6cd632578ce8 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -123,13 +123,10 @@ min_adv_mss - INTEGER
IP Fragmentation:
ipfrag_high_thresh - INTEGER
- Maximum memory used to reassemble IP fragments. When
- ipfrag_high_thresh bytes of memory is allocated for this purpose,
- the fragment handler will toss packets until ipfrag_low_thresh
- is reached. This also serves as a maximum limit to namespaces
- different from the initial one.
+ Maximum memory used to reassemble IP fragments.
ipfrag_low_thresh - INTEGER
+ (Obsolete since linux-4.17)
Maximum memory used to reassemble IP fragments before the kernel
begins to remove incomplete fragment queues to free up resources.
The kernel still accepts new fragments for defragmentation.
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 19a2ccda0300..b146f1e456a5 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -1,7 +1,11 @@
#ifndef __NET_FRAG_H__
#define __NET_FRAG_H__
+#include <linux/rhashtable.h>
+
struct netns_frags {
+ struct rhashtable rhashtable ____cacheline_aligned_in_smp;
+
/* Keep atomic mem on separate cachelines in structs that include it */
atomic_t mem ____cacheline_aligned_in_smp;
/* sysctls */
@@ -25,12 +29,30 @@ enum {
INET_FRAG_COMPLETE = BIT(2),
};
+struct frag_v4_compare_key {
+ __be32 saddr;
+ __be32 daddr;
+ u32 user;
+ u32 vif;
+ __be16 id;
+ u16 protocol;
+};
+
+struct frag_v6_compare_key {
+ struct in6_addr saddr;
+ struct in6_addr daddr;
+ u32 user;
+ __be32 id;
+ u32 iif;
+};
+
/**
* struct inet_frag_queue - fragment queue
*
- * @lock: spinlock protecting the queue
+ * @node: rhash node
+ * @key: keys identifying this frag.
* @timer: queue expiration timer
- * @list: hash bucket list
+ * @lock: spinlock protecting this frag
* @refcnt: reference count of the queue
* @fragments: received fragments head
* @fragments_tail: received fragments tail
@@ -40,12 +62,16 @@ enum {
* @flags: fragment queue flags
* @max_size: maximum received fragment size
* @net: namespace that this frag belongs to
- * @list_evictor: list of queues to forcefully evict (e.g. due to low memory)
+ * @rcu: rcu head for freeing deferall
*/
struct inet_frag_queue {
- spinlock_t lock;
+ struct rhash_head node;
+ union {
+ struct frag_v4_compare_key v4;
+ struct frag_v6_compare_key v6;
+ } key;
struct timer_list timer;
- struct hlist_node list;
+ spinlock_t lock;
atomic_t refcnt;
struct sk_buff *fragments;
struct sk_buff *fragments_tail;
@@ -54,51 +80,20 @@ struct inet_frag_queue {
int meat;
__u8 flags;
u16 max_size;
- struct netns_frags *net;
- struct hlist_node list_evictor;
-};
-
-#define INETFRAGS_HASHSZ 1024
-
-/* averaged:
- * max_depth = default ipfrag_high_thresh / INETFRAGS_HASHSZ /
- * rounded up (SKB_TRUELEN(0) + sizeof(struct ipq or
- * struct frag_queue))
- */
-#define INETFRAGS_MAXDEPTH 128
-
-struct inet_frag_bucket {
- struct hlist_head chain;
- spinlock_t chain_lock;
+ struct netns_frags *net;
+ struct rcu_head rcu;
};
struct inet_frags {
- struct inet_frag_bucket hash[INETFRAGS_HASHSZ];
-
- struct work_struct frags_work;
- unsigned int next_bucket;
- unsigned long last_rebuild_jiffies;
- bool rebuild;
-
- /* The first call to hashfn is responsible to initialize
- * rnd. This is best done with net_get_random_once.
- *
- * rnd_seqlock is used to let hash insertion detect
- * when it needs to re-lookup the hash chain to use.
- */
- u32 rnd;
- seqlock_t rnd_seqlock;
int qsize;
- unsigned int (*hashfn)(const struct inet_frag_queue *);
- bool (*match)(const struct inet_frag_queue *q,
- const void *arg);
void (*constructor)(struct inet_frag_queue *q,
const void *arg);
void (*destructor)(struct inet_frag_queue *);
void (*frag_expire)(unsigned long data);
struct kmem_cache *frags_cachep;
const char *frags_cache_name;
+ struct rhashtable_params rhash_params;
};
int inet_frags_init(struct inet_frags *);
@@ -107,15 +102,13 @@ void inet_frags_fini(struct inet_frags *);
static inline int inet_frags_init_net(struct netns_frags *nf)
{
atomic_set(&nf->mem, 0);
- return 0;
+ return rhashtable_init(&nf->rhashtable, &nf->f->rhash_params);
}
void inet_frags_exit_net(struct netns_frags *nf);
void inet_frag_kill(struct inet_frag_queue *q);
void inet_frag_destroy(struct inet_frag_queue *q);
-struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
- struct inet_frags *f, void *key, unsigned int hash);
-
+struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key);
void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
const char *prefix);
@@ -127,7 +120,7 @@ static inline void inet_frag_put(struct inet_frag_queue *q)
static inline bool inet_frag_evicting(struct inet_frag_queue *q)
{
- return !hlist_unhashed(&q->list_evictor);
+ return false;
}
/* Memory Tracking Functions. */
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 903a10a5f259..6b9b551f653b 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -530,17 +530,8 @@ enum ip6_defrag_users {
__IP6_DEFRAG_CONNTRACK_BRIDGE_IN = IP6_DEFRAG_CONNTRACK_BRIDGE_IN + USHRT_MAX,
};
-struct ip6_create_arg {
- __be32 id;
- u32 user;
- const struct in6_addr *src;
- const struct in6_addr *dst;
- int iif;
- u8 ecn;
-};
-
void ip6_frag_init(struct inet_frag_queue *q, const void *a);
-bool ip6_frag_match(const struct inet_frag_queue *q, const void *a);
+extern const struct rhashtable_params ip6_rhash_params;
/*
* Equivalent of ipv4 struct ip
@@ -548,11 +539,6 @@ bool ip6_frag_match(const struct inet_frag_queue *q, const void *a);
struct frag_queue {
struct inet_frag_queue q;
- __be32 id; /* fragment id */
- u32 user;
- struct in6_addr saddr;
- struct in6_addr daddr;
-
int iif;
unsigned int csum;
__u16 nhoffset;
diff --git a/net/ieee802154/6lowpan/6lowpan_i.h b/net/ieee802154/6lowpan/6lowpan_i.h
index 5ac778962e4e..3bfec472734a 100644
--- a/net/ieee802154/6lowpan/6lowpan_i.h
+++ b/net/ieee802154/6lowpan/6lowpan_i.h
@@ -16,37 +16,19 @@ typedef unsigned __bitwise__ lowpan_rx_result;
#define LOWPAN_DISPATCH_FRAG1 0xc0
#define LOWPAN_DISPATCH_FRAGN 0xe0
-struct lowpan_create_arg {
+struct frag_lowpan_compare_key {
u16 tag;
u16 d_size;
- const struct ieee802154_addr *src;
- const struct ieee802154_addr *dst;
+ const struct ieee802154_addr src;
+ const struct ieee802154_addr dst;
};
-/* Equivalent of ipv4 struct ip
+/* Equivalent of ipv4 struct ipq
*/
struct lowpan_frag_queue {
struct inet_frag_queue q;
-
- u16 tag;
- u16 d_size;
- struct ieee802154_addr saddr;
- struct ieee802154_addr daddr;
};
-static inline u32 ieee802154_addr_hash(const struct ieee802154_addr *a)
-{
- switch (a->mode) {
- case IEEE802154_ADDR_LONG:
- return (((__force u64)a->extended_addr) >> 32) ^
- (((__force u64)a->extended_addr) & 0xffffffff);
- case IEEE802154_ADDR_SHORT:
- return (__force u32)(a->short_addr + (a->pan_id << 16));
- default:
- return 0;
- }
-}
-
int lowpan_frag_rcv(struct sk_buff *skb, const u8 frag_type);
void lowpan_net_frag_exit(void);
int lowpan_net_frag_init(void);
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index 977b4ed58112..a63360a05108 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -37,47 +37,15 @@ static struct inet_frags lowpan_frags;
static int lowpan_frag_reasm(struct lowpan_frag_queue *fq,
struct sk_buff *prev, struct net_device *ldev);
-static unsigned int lowpan_hash_frag(u16 tag, u16 d_size,
- const struct ieee802154_addr *saddr,
- const struct ieee802154_addr *daddr)
-{
- net_get_random_once(&lowpan_frags.rnd, sizeof(lowpan_frags.rnd));
- return jhash_3words(ieee802154_addr_hash(saddr),
- ieee802154_addr_hash(daddr),
- (__force u32)(tag + (d_size << 16)),
- lowpan_frags.rnd);
-}
-
-static unsigned int lowpan_hashfn(const struct inet_frag_queue *q)
-{
- const struct lowpan_frag_queue *fq;
-
- fq = container_of(q, struct lowpan_frag_queue, q);
- return lowpan_hash_frag(fq->tag, fq->d_size, &fq->saddr, &fq->daddr);
-}
-
-static bool lowpan_frag_match(const struct inet_frag_queue *q, const void *a)
-{
- const struct lowpan_frag_queue *fq;
- const struct lowpan_create_arg *arg = a;
-
- fq = container_of(q, struct lowpan_frag_queue, q);
- return fq->tag == arg->tag && fq->d_size == arg->d_size &&
- ieee802154_addr_equal(&fq->saddr, arg->src) &&
- ieee802154_addr_equal(&fq->daddr, arg->dst);
-}
-
static void lowpan_frag_init(struct inet_frag_queue *q, const void *a)
{
- const struct lowpan_create_arg *arg = a;
+ const struct frag_lowpan_compare_key *key = a;
struct lowpan_frag_queue *fq;
fq = container_of(q, struct lowpan_frag_queue, q);
- fq->tag = arg->tag;
- fq->d_size = arg->d_size;
- fq->saddr = *arg->src;
- fq->daddr = *arg->dst;
+ BUILD_BUG_ON(sizeof(*key) > sizeof(q->key));
+ memcpy(&q->key, key, sizeof(*key));
}
static void lowpan_frag_expire(unsigned long data)
@@ -104,21 +72,17 @@ fq_find(struct net *net, const struct lowpan_802154_cb *cb,
const struct ieee802154_addr *src,
const struct ieee802154_addr *dst)
{
- struct inet_frag_queue *q;
- struct lowpan_create_arg arg;
- unsigned int hash;
struct netns_ieee802154_lowpan *ieee802154_lowpan =
net_ieee802154_lowpan(net);
+ struct frag_lowpan_compare_key key = {
+ .tag = cb->d_tag,
+ .d_size = cb->d_size,
+ .src = *src,
+ .dst = *dst,
+ };
+ struct inet_frag_queue *q;
- arg.tag = cb->d_tag;
- arg.d_size = cb->d_size;
- arg.src = src;
- arg.dst = dst;
-
- hash = lowpan_hash_frag(cb->d_tag, cb->d_size, src, dst);
-
- q = inet_frag_find(&ieee802154_lowpan->frags,
- &lowpan_frags, &arg, hash);
+ q = inet_frag_find(&ieee802154_lowpan->frags, &key);
if (IS_ERR_OR_NULL(q)) {
inet_frag_maybe_warn_overflow(q, pr_fmt());
return NULL;
@@ -610,17 +574,46 @@ static struct pernet_operations lowpan_frags_ops = {
.exit = lowpan_frags_exit_net,
};
+static u32 lowpan_key_hashfn(const void *data, u32 len, u32 seed)
+{
+ return jhash2(data,
+ sizeof(struct frag_lowpan_compare_key) / sizeof(u32), seed);
+}
+
+static u32 lowpan_obj_hashfn(const void *data, u32 len, u32 seed)
+{
+ const struct inet_frag_queue *fq = data;
+
+ return jhash2((const u32 *)&fq->key,
+ sizeof(struct frag_lowpan_compare_key) / sizeof(u32), seed);
+}
+
+static int lowpan_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr)
+{
+ const struct frag_lowpan_compare_key *key = arg->key;
+ const struct inet_frag_queue *fq = ptr;
+
+ return !!memcmp(&fq->key, key, sizeof(*key));
+}
+
+static const struct rhashtable_params lowpan_rhash_params = {
+ .head_offset = offsetof(struct inet_frag_queue, node),
+ .hashfn = lowpan_key_hashfn,
+ .obj_hashfn = lowpan_obj_hashfn,
+ .obj_cmpfn = lowpan_obj_cmpfn,
+ .automatic_shrinking = true,
+};
+
int __init lowpan_net_frag_init(void)
{
int ret;
- lowpan_frags.hashfn = lowpan_hashfn;
lowpan_frags.constructor = lowpan_frag_init;
lowpan_frags.destructor = NULL;
lowpan_frags.qsize = sizeof(struct frag_queue);
- lowpan_frags.match = lowpan_frag_match;
lowpan_frags.frag_expire = lowpan_frag_expire;
lowpan_frags.frags_cache_name = lowpan_frags_cache_name;
+ lowpan_frags.rhash_params = lowpan_rhash_params;
ret = inet_frags_init(&lowpan_frags);
if (ret)
goto out;
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 89cfe0df8e56..a50ac25878aa 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -25,12 +25,6 @@
#include <net/inet_frag.h>
#include <net/inet_ecn.h>
-#define INETFRAGS_EVICT_BUCKETS 128
-#define INETFRAGS_EVICT_MAX 512
-
-/* don't rebuild inetfrag table with new secret more often than this */
-#define INETFRAGS_MIN_REBUILD_INTERVAL (5 * HZ)
-
/* Given the OR values of all fragments, apply RFC 3168 5.3 requirements
* Value : 0xff if frame should be dropped.
* 0 or INET_ECN_CE value, to be ORed in to final iph->tos field
@@ -52,157 +46,8 @@ const u8 ip_frag_ecn_table[16] = {
};
EXPORT_SYMBOL(ip_frag_ecn_table);
-static unsigned int
-inet_frag_hashfn(const struct inet_frags *f, const struct inet_frag_queue *q)
-{
- return f->hashfn(q) & (INETFRAGS_HASHSZ - 1);
-}
-
-static bool inet_frag_may_rebuild(struct inet_frags *f)
-{
- return time_after(jiffies,
- f->last_rebuild_jiffies + INETFRAGS_MIN_REBUILD_INTERVAL);
-}
-
-static void inet_frag_secret_rebuild(struct inet_frags *f)
-{
- int i;
-
- write_seqlock_bh(&f->rnd_seqlock);
-
- if (!inet_frag_may_rebuild(f))
- goto out;
-
- get_random_bytes(&f->rnd, sizeof(u32));
-
- for (i = 0; i < INETFRAGS_HASHSZ; i++) {
- struct inet_frag_bucket *hb;
- struct inet_frag_queue *q;
- struct hlist_node *n;
-
- hb = &f->hash[i];
- spin_lock(&hb->chain_lock);
-
- hlist_for_each_entry_safe(q, n, &hb->chain, list) {
- unsigned int hval = inet_frag_hashfn(f, q);
-
- if (hval != i) {
- struct inet_frag_bucket *hb_dest;
-
- hlist_del(&q->list);
-
- /* Relink to new hash chain. */
- hb_dest = &f->hash[hval];
-
- /* This is the only place where we take
- * another chain_lock while already holding
- * one. As this will not run concurrently,
- * we cannot deadlock on hb_dest lock below, if its
- * already locked it will be released soon since
- * other caller cannot be waiting for hb lock
- * that we've taken above.
- */
- spin_lock_nested(&hb_dest->chain_lock,
- SINGLE_DEPTH_NESTING);
- hlist_add_head(&q->list, &hb_dest->chain);
- spin_unlock(&hb_dest->chain_lock);
- }
- }
- spin_unlock(&hb->chain_lock);
- }
-
- f->rebuild = false;
- f->last_rebuild_jiffies = jiffies;
-out:
- write_sequnlock_bh(&f->rnd_seqlock);
-}
-
-static bool inet_fragq_should_evict(const struct inet_frag_queue *q)
-{
- if (!hlist_unhashed(&q->list_evictor))
- return false;
-
- return q->net->low_thresh == 0 ||
- frag_mem_limit(q->net) >= q->net->low_thresh;
-}
-
-static unsigned int
-inet_evict_bucket(struct inet_frags *f, struct inet_frag_bucket *hb)
-{
- struct inet_frag_queue *fq;
- struct hlist_node *n;
- unsigned int evicted = 0;
- HLIST_HEAD(expired);
-
- spin_lock(&hb->chain_lock);
-
- hlist_for_each_entry_safe(fq, n, &hb->chain, list) {
- if (!inet_fragq_should_evict(fq))
- continue;
-
- if (!del_timer(&fq->timer))
- continue;
-
- hlist_add_head(&fq->list_evictor, &expired);
- ++evicted;
- }
-
- spin_unlock(&hb->chain_lock);
-
- hlist_for_each_entry_safe(fq, n, &expired, list_evictor)
- f->frag_expire((unsigned long) fq);
-
- return evicted;
-}
-
-static void inet_frag_worker(struct work_struct *work)
-{
- unsigned int budget = INETFRAGS_EVICT_BUCKETS;
- unsigned int i, evicted = 0;
- struct inet_frags *f;
-
- f = container_of(work, struct inet_frags, frags_work);
-
- BUILD_BUG_ON(INETFRAGS_EVICT_BUCKETS >= INETFRAGS_HASHSZ);
-
- local_bh_disable();
-
- for (i = ACCESS_ONCE(f->next_bucket); budget; --budget) {
- evicted += inet_evict_bucket(f, &f->hash[i]);
- i = (i + 1) & (INETFRAGS_HASHSZ - 1);
- if (evicted > INETFRAGS_EVICT_MAX)
- break;
- }
-
- f->next_bucket = i;
-
- local_bh_enable();
-
- if (f->rebuild && inet_frag_may_rebuild(f))
- inet_frag_secret_rebuild(f);
-}
-
-static void inet_frag_schedule_worker(struct inet_frags *f)
-{
- if (unlikely(!work_pending(&f->frags_work)))
- schedule_work(&f->frags_work);
-}
-
int inet_frags_init(struct inet_frags *f)
{
- int i;
-
- INIT_WORK(&f->frags_work, inet_frag_worker);
-
- for (i = 0; i < INETFRAGS_HASHSZ; i++) {
- struct inet_frag_bucket *hb = &f->hash[i];
-
- spin_lock_init(&hb->chain_lock);
- INIT_HLIST_HEAD(&hb->chain);
- }
-
- seqlock_init(&f->rnd_seqlock);
- f->last_rebuild_jiffies = 0;
f->frags_cachep = kmem_cache_create(f->frags_cache_name, f->qsize, 0, 0,
NULL);
if (!f->frags_cachep)
@@ -214,66 +59,42 @@ EXPORT_SYMBOL(inet_frags_init);
void inet_frags_fini(struct inet_frags *f)
{
- cancel_work_sync(&f->frags_work);
+ /* We must wait that all inet_frag_destroy_rcu() have completed. */
+ rcu_barrier();
+
kmem_cache_destroy(f->frags_cachep);
+ f->frags_cachep = NULL;
}
EXPORT_SYMBOL(inet_frags_fini);
-void inet_frags_exit_net(struct netns_frags *nf)
-{
- struct inet_frags *f =nf->f;
- unsigned int seq;
- int i;
-
- nf->low_thresh = 0;
-
-evict_again:
- local_bh_disable();
- seq = read_seqbegin(&f->rnd_seqlock);
-
- for (i = 0; i < INETFRAGS_HASHSZ ; i++)
- inet_evict_bucket(f, &f->hash[i]);
-
- local_bh_enable();
- cond_resched();
-
- if (read_seqretry(&f->rnd_seqlock, seq) ||
- sum_frag_mem_limit(nf))
- goto evict_again;
-}
-EXPORT_SYMBOL(inet_frags_exit_net);
-
-static struct inet_frag_bucket *
-get_frag_bucket_locked(struct inet_frag_queue *fq, struct inet_frags *f)
-__acquires(hb->chain_lock)
+static void inet_frags_free_cb(void *ptr, void *arg)
{
- struct inet_frag_bucket *hb;
- unsigned int seq, hash;
+ struct inet_frag_queue *fq = ptr;
- restart:
- seq = read_seqbegin(&f->rnd_seqlock);
-
- hash = inet_frag_hashfn(f, fq);
- hb = &f->hash[hash];
+ /* If we can not cancel the timer, it means this frag_queue
+ * is already disappearing, we have nothing to do.
+ * Otherwise, we own a refcount until the end of this function.
+ */
+ if (!del_timer(&fq->timer))
+ return;
- spin_lock(&hb->chain_lock);
- if (read_seqretry(&f->rnd_seqlock, seq)) {
- spin_unlock(&hb->chain_lock);
- goto restart;
+ spin_lock_bh(&fq->lock);
+ if (!(fq->flags & INET_FRAG_COMPLETE)) {
+ fq->flags |= INET_FRAG_COMPLETE;
+ atomic_dec(&fq->refcnt);
}
+ spin_unlock_bh(&fq->lock);
- return hb;
+ inet_frag_put(fq);
}
-static inline void fq_unlink(struct inet_frag_queue *fq)
+void inet_frags_exit_net(struct netns_frags *nf)
{
- struct inet_frag_bucket *hb;
+ nf->low_thresh = 0; /* prevent creation of new frags */
- hb = get_frag_bucket_locked(fq, fq->net->f);
- hlist_del(&fq->list);
- fq->flags |= INET_FRAG_COMPLETE;
- spin_unlock(&hb->chain_lock);
+ rhashtable_free_and_destroy(&nf->rhashtable, inet_frags_free_cb, NULL);
}
+EXPORT_SYMBOL(inet_frags_exit_net);
void inet_frag_kill(struct inet_frag_queue *fq)
{
@@ -281,12 +102,26 @@ void inet_frag_kill(struct inet_frag_queue *fq)
atomic_dec(&fq->refcnt);
if (!(fq->flags & INET_FRAG_COMPLETE)) {
- fq_unlink(fq);
+ struct netns_frags *nf = fq->net;
+
+ fq->flags |= INET_FRAG_COMPLETE;
+ rhashtable_remove_fast(&nf->rhashtable, &fq->node, nf->f->rhash_params);
atomic_dec(&fq->refcnt);
}
}
EXPORT_SYMBOL(inet_frag_kill);
+static void inet_frag_destroy_rcu(struct rcu_head *head)
+{
+ struct inet_frag_queue *q = container_of(head, struct inet_frag_queue,
+ rcu);
+ struct inet_frags *f = q->net->f;
+
+ if (f->destructor)
+ f->destructor(q);
+ kmem_cache_free(f->frags_cachep, q);
+}
+
void inet_frag_destroy(struct inet_frag_queue *q)
{
struct sk_buff *fp;
@@ -310,55 +145,21 @@ void inet_frag_destroy(struct inet_frag_queue *q)
}
sum = sum_truesize + f->qsize;
- if (f->destructor)
- f->destructor(q);
- kmem_cache_free(f->frags_cachep, q);
+ call_rcu(&q->rcu, inet_frag_destroy_rcu);
sub_frag_mem_limit(nf, sum);
}
EXPORT_SYMBOL(inet_frag_destroy);
-static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf,
- struct inet_frag_queue *qp_in,
- struct inet_frags *f,
- void *arg)
-{
- struct inet_frag_bucket *hb = get_frag_bucket_locked(qp_in, f);
- struct inet_frag_queue *qp;
-
-#ifdef CONFIG_SMP
- /* With SMP race we have to recheck hash table, because
- * such entry could have been created on other cpu before
- * we acquired hash bucket lock.
- */
- hlist_for_each_entry(qp, &hb->chain, list) {
- if (qp->net == nf && f->match(qp, arg)) {
- atomic_inc(&qp->refcnt);
- spin_unlock(&hb->chain_lock);
- qp_in->flags |= INET_FRAG_COMPLETE;
- inet_frag_put(qp_in);
- return qp;
- }
- }
-#endif
- qp = qp_in;
- if (!mod_timer(&qp->timer, jiffies + nf->timeout))
- atomic_inc(&qp->refcnt);
-
- atomic_inc(&qp->refcnt);
- hlist_add_head(&qp->list, &hb->chain);
-
- spin_unlock(&hb->chain_lock);
-
- return qp;
-}
-
static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
struct inet_frags *f,
void *arg)
{
struct inet_frag_queue *q;
+ if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh)
+ return NULL;
+
q = kmem_cache_zalloc(f->frags_cachep, GFP_ATOMIC);
if (!q)
return NULL;
@@ -369,64 +170,51 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
setup_timer(&q->timer, f->frag_expire, (unsigned long)q);
spin_lock_init(&q->lock);
- atomic_set(&q->refcnt, 1);
+ atomic_set(&q->refcnt, 3);
return q;
}
static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf,
- struct inet_frags *f,
void *arg)
{
+ struct inet_frags *f = nf->f;
struct inet_frag_queue *q;
+ int err;
q = inet_frag_alloc(nf, f, arg);
if (!q)
return NULL;
- return inet_frag_intern(nf, q, f, arg);
-}
+ mod_timer(&q->timer, jiffies + nf->timeout);
-struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
- struct inet_frags *f, void *key,
- unsigned int hash)
-{
- struct inet_frag_bucket *hb;
- struct inet_frag_queue *q;
- int depth = 0;
-
- if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh) {
- inet_frag_schedule_worker(f);
+ err = rhashtable_insert_fast(&nf->rhashtable, &q->node,
+ f->rhash_params);
+ if (err < 0) {
+ q->flags |= INET_FRAG_COMPLETE;
+ inet_frag_kill(q);
+ inet_frag_destroy(q);
return NULL;
}
+ return q;
+}
+EXPORT_SYMBOL(inet_frag_create);
- if (frag_mem_limit(nf) > nf->low_thresh)
- inet_frag_schedule_worker(f);
-
- hash &= (INETFRAGS_HASHSZ - 1);
- hb = &f->hash[hash];
-
- spin_lock(&hb->chain_lock);
- hlist_for_each_entry(q, &hb->chain, list) {
- if (q->net == nf && f->match(q, key)) {
- atomic_inc(&q->refcnt);
- spin_unlock(&hb->chain_lock);
- return q;
- }
- depth++;
- }
- spin_unlock(&hb->chain_lock);
-
- if (depth <= INETFRAGS_MAXDEPTH)
- return inet_frag_create(nf, f, key);
+/* TODO : call from rcu_read_lock() and no longer use refcount_inc_not_zero() */
+struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key)
+{
+ struct inet_frag_queue *fq;
- if (inet_frag_may_rebuild(f)) {
- if (!f->rebuild)
- f->rebuild = true;
- inet_frag_schedule_worker(f);
+ rcu_read_lock();
+ fq = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params);
+ if (fq) {
+ if (!atomic_inc_not_zero(&fq->refcnt))
+ fq = NULL;
+ rcu_read_unlock();
+ return fq;
}
-
- return ERR_PTR(-ENOBUFS);
+ rcu_read_unlock();
+ return inet_frag_create(nf, key);
}
EXPORT_SYMBOL(inet_frag_find);
@@ -434,8 +222,7 @@ void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
const char *prefix)
{
static const char msg[] = "inet_frag_find: Fragment hash bucket"
- " list length grew over limit " __stringify(INETFRAGS_MAXDEPTH)
- ". Dropping fragment.\n";
+ " list length grew over limit. Dropping fragment.\n";
if (PTR_ERR(q) == -ENOBUFS)
net_dbg_ratelimited("%s%s", prefix, msg);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index b6fe05e8a431..29038513f3ca 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -68,15 +68,9 @@ struct ipfrag_skb_cb
struct ipq {
struct inet_frag_queue q;
- u32 user;
- __be32 saddr;
- __be32 daddr;
- __be16 id;
- u8 protocol;
u8 ecn; /* RFC3168 support */
u16 max_df_size; /* largest frag with DF set seen */
int iif;
- int vif; /* L3 master device index */
unsigned int rid;
struct inet_peer *peer;
};
@@ -96,41 +90,6 @@ int ip_frag_mem(struct net *net)
static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
struct net_device *dev);
-struct ip4_create_arg {
- struct iphdr *iph;
- u32 user;
- int vif;
-};
-
-static unsigned int ipqhashfn(__be16 id, __be32 saddr, __be32 daddr, u8 prot)
-{
- net_get_random_once(&ip4_frags.rnd, sizeof(ip4_frags.rnd));
- return jhash_3words((__force u32)id << 16 | prot,
- (__force u32)saddr, (__force u32)daddr,
- ip4_frags.rnd);
-}
-
-static unsigned int ip4_hashfn(const struct inet_frag_queue *q)
-{
- const struct ipq *ipq;
-
- ipq = container_of(q, struct ipq, q);
- return ipqhashfn(ipq->id, ipq->saddr, ipq->daddr, ipq->protocol);
-}
-
-static bool ip4_frag_match(const struct inet_frag_queue *q, const void *a)
-{
- const struct ipq *qp;
- const struct ip4_create_arg *arg = a;
-
- qp = container_of(q, struct ipq, q);
- return qp->id == arg->iph->id &&
- qp->saddr == arg->iph->saddr &&
- qp->daddr == arg->iph->daddr &&
- qp->protocol == arg->iph->protocol &&
- qp->user == arg->user &&
- qp->vif == arg->vif;
-}
static void ip4_frag_init(struct inet_frag_queue *q, const void *a)
{
@@ -139,17 +98,12 @@ static void ip4_frag_init(struct inet_frag_queue *q, const void *a)
frags);
struct net *net = container_of(ipv4, struct net, ipv4);
- const struct ip4_create_arg *arg = a;
+ const struct frag_v4_compare_key *key = a;
- qp->protocol = arg->iph->protocol;
- qp->id = arg->iph->id;
- qp->ecn = ip4_frag_ecn(arg->iph->tos);
- qp->saddr = arg->iph->saddr;
- qp->daddr = arg->iph->daddr;
- qp->vif = arg->vif;
- qp->user = arg->user;
+ q->key.v4 = *key;
+ qp->ecn = 0;
qp->peer = q->net->max_dist ?
- inet_getpeer_v4(net->ipv4.peers, arg->iph->saddr, arg->vif, 1) :
+ inet_getpeer_v4(net->ipv4.peers, key->saddr, key->vif, 1) :
NULL;
}
@@ -232,7 +186,7 @@ static void ip_expire(unsigned long arg)
/* Only an end host needs to send an ICMP
* "Fragment Reassembly Timeout" message, per RFC792.
*/
- if (frag_expire_skip_icmp(qp->user) &&
+ if (frag_expire_skip_icmp(qp->q.key.v4.user) &&
(skb_rtable(head)->rt_type != RTN_LOCAL))
goto out;
@@ -260,17 +214,17 @@ static void ip_expire(unsigned long arg)
static struct ipq *ip_find(struct net *net, struct iphdr *iph,
u32 user, int vif)
{
+ struct frag_v4_compare_key key = {
+ .saddr = iph->saddr,
+ .daddr = iph->daddr,
+ .user = user,
+ .vif = vif,
+ .id = iph->id,
+ .protocol = iph->protocol,
+ };
struct inet_frag_queue *q;
- struct ip4_create_arg arg;
- unsigned int hash;
-
- arg.iph = iph;
- arg.user = user;
- arg.vif = vif;
- hash = ipqhashfn(iph->id, iph->saddr, iph->daddr, iph->protocol);
-
- q = inet_frag_find(&net->ipv4.frags, &ip4_frags, &arg, hash);
+ q = inet_frag_find(&net->ipv4.frags, &key);
if (IS_ERR_OR_NULL(q)) {
inet_frag_maybe_warn_overflow(q, pr_fmt());
return NULL;
@@ -659,7 +613,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
err = -ENOMEM;
goto out_fail;
out_oversize:
- net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->saddr);
+ net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->q.key.v4.saddr);
out_fail:
__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
return err;
@@ -897,15 +851,47 @@ static struct pernet_operations ip4_frags_ops = {
.exit = ipv4_frags_exit_net,
};
+
+static u32 ip4_key_hashfn(const void *data, u32 len, u32 seed)
+{
+ return jhash2(data,
+ sizeof(struct frag_v4_compare_key) / sizeof(u32), seed);
+}
+
+static u32 ip4_obj_hashfn(const void *data, u32 len, u32 seed)
+{
+ const struct inet_frag_queue *fq = data;
+
+ return jhash2((const u32 *)&fq->key.v4,
+ sizeof(struct frag_v4_compare_key) / sizeof(u32), seed);
+}
+
+static int ip4_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr)
+{
+ const struct frag_v4_compare_key *key = arg->key;
+ const struct inet_frag_queue *fq = ptr;
+
+ return !!memcmp(&fq->key, key, sizeof(*key));
+}
+
+static const struct rhashtable_params ip4_rhash_params = {
+ .head_offset = offsetof(struct inet_frag_queue, node),
+ .key_offset = offsetof(struct inet_frag_queue, key),
+ .key_len = sizeof(struct frag_v4_compare_key),
+ .hashfn = ip4_key_hashfn,
+ .obj_hashfn = ip4_obj_hashfn,
+ .obj_cmpfn = ip4_obj_cmpfn,
+ .automatic_shrinking = true,
+};
+
void __init ipfrag_init(void)
{
- ip4_frags.hashfn = ip4_hashfn;
ip4_frags.constructor = ip4_frag_init;
ip4_frags.destructor = ip4_frag_free;
ip4_frags.qsize = sizeof(struct ipq);
- ip4_frags.match = ip4_frag_match;
ip4_frags.frag_expire = ip_expire;
ip4_frags.frags_cache_name = ip_frag_cache_name;
+ ip4_frags.rhash_params = ip4_rhash_params;
if (inet_frags_init(&ip4_frags))
panic("IP: failed to allocate ip4_frags cache\n");
ip4_frags_ctl_register();
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 7ea2b4490672..314568d8b84a 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -152,23 +152,6 @@ static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h)
return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK);
}
-static unsigned int nf_hash_frag(__be32 id, const struct in6_addr *saddr,
- const struct in6_addr *daddr)
-{
- net_get_random_once(&nf_frags.rnd, sizeof(nf_frags.rnd));
- return jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr),
- (__force u32)id, nf_frags.rnd);
-}
-
-
-static unsigned int nf_hashfn(const struct inet_frag_queue *q)
-{
- const struct frag_queue *nq;
-
- nq = container_of(q, struct frag_queue, q);
- return nf_hash_frag(nq->id, &nq->saddr, &nq->daddr);
-}
-
static void nf_ct_frag6_expire(unsigned long data)
{
struct frag_queue *fq;
@@ -181,26 +164,19 @@ static void nf_ct_frag6_expire(unsigned long data)
}
/* Creation primitives. */
-static inline struct frag_queue *fq_find(struct net *net, __be32 id,
- u32 user, struct in6_addr *src,
- struct in6_addr *dst, int iif, u8 ecn)
+static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user,
+ const struct ipv6hdr *hdr, int iif)
{
+ struct frag_v6_compare_key key = {
+ .id = id,
+ .saddr = hdr->saddr,
+ .daddr = hdr->daddr,
+ .user = user,
+ .iif = iif,
+ };
struct inet_frag_queue *q;
- struct ip6_create_arg arg;
- unsigned int hash;
-
- arg.id = id;
- arg.user = user;
- arg.src = src;
- arg.dst = dst;
- arg.iif = iif;
- arg.ecn = ecn;
-
- local_bh_disable();
- hash = nf_hash_frag(id, src, dst);
- q = inet_frag_find(&net->nf_frag.frags, &nf_frags, &arg, hash);
- local_bh_enable();
+ q = inet_frag_find(&net->nf_frag.frags, &key);
if (IS_ERR_OR_NULL(q)) {
inet_frag_maybe_warn_overflow(q, pr_fmt());
return NULL;
@@ -592,8 +568,8 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
fhdr = (struct frag_hdr *)skb_transport_header(skb);
skb_orphan(skb);
- fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr,
- skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
+ fq = fq_find(net, fhdr->identification, user, hdr,
+ skb->dev ? skb->dev->ifindex : 0);
if (fq == NULL) {
pr_debug("Can't find and can't create new queue\n");
return -ENOMEM;
@@ -661,13 +637,12 @@ int nf_ct_frag6_init(void)
{
int ret = 0;
- nf_frags.hashfn = nf_hashfn;
nf_frags.constructor = ip6_frag_init;
nf_frags.destructor = NULL;
nf_frags.qsize = sizeof(struct frag_queue);
- nf_frags.match = ip6_frag_match;
nf_frags.frag_expire = nf_ct_frag6_expire;
nf_frags.frags_cache_name = nf_frags_cache_name;
+ nf_frags.rhash_params = ip6_rhash_params;
ret = inet_frags_init(&nf_frags);
if (ret)
goto out;
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 9fe99475bddf..8fe3836d1410 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -79,52 +79,13 @@ static struct inet_frags ip6_frags;
static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
struct net_device *dev);
-/*
- * callers should be careful not to use the hash value outside the ipfrag_lock
- * as doing so could race with ipfrag_hash_rnd being recalculated.
- */
-static unsigned int inet6_hash_frag(__be32 id, const struct in6_addr *saddr,
- const struct in6_addr *daddr)
-{
- net_get_random_once(&ip6_frags.rnd, sizeof(ip6_frags.rnd));
- return jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr),
- (__force u32)id, ip6_frags.rnd);
-}
-
-static unsigned int ip6_hashfn(const struct inet_frag_queue *q)
-{
- const struct frag_queue *fq;
-
- fq = container_of(q, struct frag_queue, q);
- return inet6_hash_frag(fq->id, &fq->saddr, &fq->daddr);
-}
-
-bool ip6_frag_match(const struct inet_frag_queue *q, const void *a)
-{
- const struct frag_queue *fq;
- const struct ip6_create_arg *arg = a;
-
- fq = container_of(q, struct frag_queue, q);
- return fq->id == arg->id &&
- fq->user == arg->user &&
- ipv6_addr_equal(&fq->saddr, arg->src) &&
- ipv6_addr_equal(&fq->daddr, arg->dst) &&
- (arg->iif == fq->iif ||
- !(ipv6_addr_type(arg->dst) & (IPV6_ADDR_MULTICAST |
- IPV6_ADDR_LINKLOCAL)));
-}
-EXPORT_SYMBOL(ip6_frag_match);
-
void ip6_frag_init(struct inet_frag_queue *q, const void *a)
{
struct frag_queue *fq = container_of(q, struct frag_queue, q);
- const struct ip6_create_arg *arg = a;
+ const struct frag_v6_compare_key *key = a;
- fq->id = arg->id;
- fq->user = arg->user;
- fq->saddr = *arg->src;
- fq->daddr = *arg->dst;
- fq->ecn = arg->ecn;
+ q->key.v6 = *key;
+ fq->ecn = 0;
}
EXPORT_SYMBOL(ip6_frag_init);
@@ -181,23 +142,22 @@ static void ip6_frag_expire(unsigned long data)
}
static struct frag_queue *
-fq_find(struct net *net, __be32 id, const struct in6_addr *src,
- const struct in6_addr *dst, int iif, u8 ecn)
+fq_find(struct net *net, __be32 id, const struct ipv6hdr *hdr, int iif)
{
+ struct frag_v6_compare_key key = {
+ .id = id,
+ .saddr = hdr->saddr,
+ .daddr = hdr->daddr,
+ .user = IP6_DEFRAG_LOCAL_DELIVER,
+ .iif = iif,
+ };
struct inet_frag_queue *q;
- struct ip6_create_arg arg;
- unsigned int hash;
-
- arg.id = id;
- arg.user = IP6_DEFRAG_LOCAL_DELIVER;
- arg.src = src;
- arg.dst = dst;
- arg.iif = iif;
- arg.ecn = ecn;
- hash = inet6_hash_frag(id, src, dst);
+ if (!(ipv6_addr_type(&hdr->daddr) & (IPV6_ADDR_MULTICAST |
+ IPV6_ADDR_LINKLOCAL)))
+ key.iif = 0;
- q = inet_frag_find(&net->ipv6.frags, &ip6_frags, &arg, hash);
+ q = inet_frag_find(&net->ipv6.frags, &key);
if (IS_ERR_OR_NULL(q)) {
inet_frag_maybe_warn_overflow(q, pr_fmt());
return NULL;
@@ -524,6 +484,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
struct frag_queue *fq;
const struct ipv6hdr *hdr = ipv6_hdr(skb);
struct net *net = dev_net(skb_dst(skb)->dev);
+ int iif;
if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED)
goto fail_hdr;
@@ -552,13 +513,14 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
return 1;
}
- fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr,
- skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
+ iif = skb->dev ? skb->dev->ifindex : 0;
+ fq = fq_find(net, fhdr->identification, hdr, iif);
if (fq) {
int ret;
spin_lock(&fq->q.lock);
+ fq->iif = iif;
ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff);
spin_unlock(&fq->q.lock);
@@ -732,17 +694,47 @@ static struct pernet_operations ip6_frags_ops = {
.exit = ipv6_frags_exit_net,
};
+static u32 ip6_key_hashfn(const void *data, u32 len, u32 seed)
+{
+ return jhash2(data,
+ sizeof(struct frag_v6_compare_key) / sizeof(u32), seed);
+}
+
+static u32 ip6_obj_hashfn(const void *data, u32 len, u32 seed)
+{
+ const struct inet_frag_queue *fq = data;
+
+ return jhash2((const u32 *)&fq->key.v6,
+ sizeof(struct frag_v6_compare_key) / sizeof(u32), seed);
+}
+
+static int ip6_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr)
+{
+ const struct frag_v6_compare_key *key = arg->key;
+ const struct inet_frag_queue *fq = ptr;
+
+ return !!memcmp(&fq->key, key, sizeof(*key));
+}
+
+const struct rhashtable_params ip6_rhash_params = {
+ .head_offset = offsetof(struct inet_frag_queue, node),
+ .hashfn = ip6_key_hashfn,
+ .obj_hashfn = ip6_obj_hashfn,
+ .obj_cmpfn = ip6_obj_cmpfn,
+ .automatic_shrinking = true,
+};
+EXPORT_SYMBOL(ip6_rhash_params);
+
int __init ipv6_frag_init(void)
{
int ret;
- ip6_frags.hashfn = ip6_hashfn;
ip6_frags.constructor = ip6_frag_init;
ip6_frags.destructor = NULL;
ip6_frags.qsize = sizeof(struct frag_queue);
- ip6_frags.match = ip6_frag_match;
ip6_frags.frag_expire = ip6_frag_expire;
ip6_frags.frags_cache_name = ip6_frag_cache_name;
+ ip6_frags.rhash_params = ip6_rhash_params;
ret = inet_frags_init(&ip6_frags);
if (ret)
goto out;
--
2.17.1
^ permalink raw reply related
* [PATCH stable 4.9 09/29] inet: frags: remove some helpers
From: Florian Fainelli @ 2018-10-09 22:49 UTC (permalink / raw)
To: netdev; +Cc: davem, gregkh, stable, edumazet, sthemmin
In-Reply-To: <20181009224924.30151-1-f.fainelli@gmail.com>
From: Eric Dumazet <edumazet@google.com>
Remove sum_frag_mem_limit(), ip_frag_mem() & ip6_frag_mem()
Also since we use rhashtable we can bring back the number of fragments
in "grep FRAG /proc/net/sockstat /proc/net/sockstat6" that was
removed in commit 434d305405ab ("inet: frag: don't account number
of fragment queues")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
(cherry picked from commit 6befe4a78b1553edb6eed3a78b4bcd9748526672)
---
include/net/inet_frag.h | 5 -----
include/net/ip.h | 1 -
include/net/ipv6.h | 7 -------
net/ipv4/ip_fragment.c | 5 -----
net/ipv4/proc.c | 6 +++---
net/ipv6/proc.c | 5 +++--
6 files changed, 6 insertions(+), 23 deletions(-)
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index b146f1e456a5..a49cdf25cef0 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -140,11 +140,6 @@ static inline void add_frag_mem_limit(struct netns_frags *nf, int i)
atomic_add(i, &nf->mem);
}
-static inline int sum_frag_mem_limit(struct netns_frags *nf)
-{
- return atomic_read(&nf->mem);
-}
-
/* RFC 3168 support :
* We want to check ECN values of all fragments, do detect invalid combinations.
* In ipq->ecn, we store the OR value of each ip4_frag_ecn() fragment value.
diff --git a/include/net/ip.h b/include/net/ip.h
index bc9b4deeb60e..8646da034851 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -548,7 +548,6 @@ static inline struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *s
return skb;
}
#endif
-int ip_frag_mem(struct net *net);
/*
* Functions provided by ip_forward.c
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 6b9b551f653b..7cb100d25bb5 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -330,13 +330,6 @@ static inline bool ipv6_accept_ra(struct inet6_dev *idev)
idev->cnf.accept_ra;
}
-#if IS_ENABLED(CONFIG_IPV6)
-static inline int ip6_frag_mem(struct net *net)
-{
- return sum_frag_mem_limit(&net->ipv6.frags);
-}
-#endif
-
#define IPV6_FRAG_HIGH_THRESH (4 * 1024*1024) /* 4194304 */
#define IPV6_FRAG_LOW_THRESH (3 * 1024*1024) /* 3145728 */
#define IPV6_FRAG_TIMEOUT (60 * HZ) /* 60 seconds */
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 29038513f3ca..8c4072b19296 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -82,11 +82,6 @@ static u8 ip4_frag_ecn(u8 tos)
static struct inet_frags ip4_frags;
-int ip_frag_mem(struct net *net)
-{
- return sum_frag_mem_limit(&net->ipv4.frags);
-}
-
static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
struct net_device *dev);
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 7143ca1a6af9..b7a2d002cb27 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -54,7 +54,6 @@
static int sockstat_seq_show(struct seq_file *seq, void *v)
{
struct net *net = seq->private;
- unsigned int frag_mem;
int orphans, sockets;
local_bh_disable();
@@ -74,8 +73,9 @@ static int sockstat_seq_show(struct seq_file *seq, void *v)
sock_prot_inuse_get(net, &udplite_prot));
seq_printf(seq, "RAW: inuse %d\n",
sock_prot_inuse_get(net, &raw_prot));
- frag_mem = ip_frag_mem(net);
- seq_printf(seq, "FRAG: inuse %u memory %u\n", !!frag_mem, frag_mem);
+ seq_printf(seq, "FRAG: inuse %u memory %u\n",
+ atomic_read(&net->ipv4.frags.rhashtable.nelems),
+ frag_mem_limit(&net->ipv4.frags));
return 0;
}
diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index e88bcb8ff0fd..5704ec3d3178 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -38,7 +38,6 @@
static int sockstat6_seq_show(struct seq_file *seq, void *v)
{
struct net *net = seq->private;
- unsigned int frag_mem = ip6_frag_mem(net);
seq_printf(seq, "TCP6: inuse %d\n",
sock_prot_inuse_get(net, &tcpv6_prot));
@@ -48,7 +47,9 @@ static int sockstat6_seq_show(struct seq_file *seq, void *v)
sock_prot_inuse_get(net, &udplitev6_prot));
seq_printf(seq, "RAW6: inuse %d\n",
sock_prot_inuse_get(net, &rawv6_prot));
- seq_printf(seq, "FRAG6: inuse %u memory %u\n", !!frag_mem, frag_mem);
+ seq_printf(seq, "FRAG6: inuse %u memory %u\n",
+ atomic_read(&net->ipv6.frags.rhashtable.nelems),
+ frag_mem_limit(&net->ipv6.frags));
return 0;
}
--
2.17.1
^ permalink raw reply related
* [PATCH stable 4.9 10/29] inet: frags: get rif of inet_frag_evicting()
From: Florian Fainelli @ 2018-10-09 22:49 UTC (permalink / raw)
To: netdev; +Cc: davem, gregkh, stable, edumazet, sthemmin
In-Reply-To: <20181009224924.30151-1-f.fainelli@gmail.com>
From: Eric Dumazet <edumazet@google.com>
This refactors ip_expire() since one indentation level is removed.
Note: in the future, we should try hard to avoid the skb_clone()
since this is a serious performance cost.
Under DDOS, the ICMP message wont be sent because of rate limits.
Fact that ip6_expire_frag_queue() does not use skb_clone() is
disturbing too. Presumably IPv6 should have the same
issue than the one we fixed in commit ec4fbd64751d
("inet: frag: release spinlock before calling icmp_send()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
(cherry picked from commit 399d1404be660d355192ff4df5ccc3f4159ec1e4)
---
include/net/inet_frag.h | 5 ----
net/ipv4/ip_fragment.c | 65 ++++++++++++++++++++---------------------
net/ipv6/reassembly.c | 4 ---
3 files changed, 32 insertions(+), 42 deletions(-)
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index a49cdf25cef0..7e984045b2b7 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -118,11 +118,6 @@ static inline void inet_frag_put(struct inet_frag_queue *q)
inet_frag_destroy(q);
}
-static inline bool inet_frag_evicting(struct inet_frag_queue *q)
-{
- return false;
-}
-
/* Memory Tracking Functions. */
static inline int frag_mem_limit(struct netns_frags *nf)
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 8c4072b19296..308592a8ba97 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -141,8 +141,11 @@ static bool frag_expire_skip_icmp(u32 user)
*/
static void ip_expire(unsigned long arg)
{
- struct ipq *qp;
+ struct sk_buff *clone, *head;
+ const struct iphdr *iph;
struct net *net;
+ struct ipq *qp;
+ int err;
qp = container_of((struct inet_frag_queue *) arg, struct ipq, q);
net = container_of(qp->q.net, struct net, ipv4.frags);
@@ -156,45 +159,41 @@ static void ip_expire(unsigned long arg)
ipq_kill(qp);
__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
- if (!inet_frag_evicting(&qp->q)) {
- struct sk_buff *clone, *head = qp->q.fragments;
- const struct iphdr *iph;
- int err;
+ head = qp->q.fragments;
- __IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT);
+ __IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT);
- if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !qp->q.fragments)
- goto out;
+ if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !head)
+ goto out;
- head->dev = dev_get_by_index_rcu(net, qp->iif);
- if (!head->dev)
- goto out;
+ head->dev = dev_get_by_index_rcu(net, qp->iif);
+ if (!head->dev)
+ goto out;
- /* skb has no dst, perform route lookup again */
- iph = ip_hdr(head);
- err = ip_route_input_noref(head, iph->daddr, iph->saddr,
+ /* skb has no dst, perform route lookup again */
+ iph = ip_hdr(head);
+ err = ip_route_input_noref(head, iph->daddr, iph->saddr,
iph->tos, head->dev);
- if (err)
- goto out;
+ if (err)
+ goto out;
- /* Only an end host needs to send an ICMP
- * "Fragment Reassembly Timeout" message, per RFC792.
- */
- if (frag_expire_skip_icmp(qp->q.key.v4.user) &&
- (skb_rtable(head)->rt_type != RTN_LOCAL))
- goto out;
-
- clone = skb_clone(head, GFP_ATOMIC);
-
- /* Send an ICMP "Fragment Reassembly Timeout" message. */
- if (clone) {
- spin_unlock(&qp->q.lock);
- icmp_send(clone, ICMP_TIME_EXCEEDED,
- ICMP_EXC_FRAGTIME, 0);
- consume_skb(clone);
- goto out_rcu_unlock;
- }
+ /* Only an end host needs to send an ICMP
+ * "Fragment Reassembly Timeout" message, per RFC792.
+ */
+ if (frag_expire_skip_icmp(qp->q.key.v4.user) &&
+ (skb_rtable(head)->rt_type != RTN_LOCAL))
+ goto out;
+
+ clone = skb_clone(head, GFP_ATOMIC);
+
+ /* Send an ICMP "Fragment Reassembly Timeout" message. */
+ if (clone) {
+ spin_unlock(&qp->q.lock);
+ icmp_send(clone, ICMP_TIME_EXCEEDED,
+ ICMP_EXC_FRAGTIME, 0);
+ consume_skb(clone);
+ goto out_rcu_unlock;
}
out:
spin_unlock(&qp->q.lock);
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 8fe3836d1410..629a45a4c79f 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -106,10 +106,6 @@ void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq)
goto out_rcu_unlock;
__IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
-
- if (inet_frag_evicting(&fq->q))
- goto out_rcu_unlock;
-
__IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT);
/* Don't send error if the first segment did not arrive. */
--
2.17.1
^ permalink raw reply related
* [PATCH stable 4.9 12/29] inet: frags: break the 2GB limit for frags storage
From: Florian Fainelli @ 2018-10-09 22:49 UTC (permalink / raw)
To: netdev; +Cc: davem, gregkh, stable, edumazet, sthemmin
In-Reply-To: <20181009224924.30151-1-f.fainelli@gmail.com>
From: Eric Dumazet <edumazet@google.com>
Some users are willing to provision huge amounts of memory to be able
to perform reassembly reasonnably well under pressure.
Current memory tracking is using one atomic_t and integers.
Switch to atomic_long_t so that 64bit arches can use more than 2GB,
without any cost for 32bit arches.
Note that this patch avoids an overflow error, if high_thresh was set
to ~2GB, since this test in inet_frag_alloc() was never true :
if (... || frag_mem_limit(nf) > nf->high_thresh)
Tested:
$ echo 16000000000 >/proc/sys/net/ipv4/ipfrag_high_thresh
<frag DDOS>
$ grep FRAG /proc/net/sockstat
FRAG: inuse 14705885 memory 16000002880
$ nstat -n ; sleep 1 ; nstat | grep Reas
IpReasmReqds 3317150 0.0
IpReasmFails 3317112 0.0
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
(cherry picked from commit 3e67f106f619dcfaf6f4e2039599bdb69848c714)
---
Documentation/networking/ip-sysctl.txt | 4 ++--
include/net/inet_frag.h | 20 ++++++++++----------
net/ieee802154/6lowpan/reassembly.c | 10 +++++-----
net/ipv4/ip_fragment.c | 10 +++++-----
net/ipv4/proc.c | 2 +-
net/ipv6/netfilter/nf_conntrack_reasm.c | 10 +++++-----
net/ipv6/proc.c | 2 +-
net/ipv6/reassembly.c | 6 +++---
8 files changed, 32 insertions(+), 32 deletions(-)
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 6cd632578ce8..dbdc4130e149 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -122,10 +122,10 @@ min_adv_mss - INTEGER
IP Fragmentation:
-ipfrag_high_thresh - INTEGER
+ipfrag_high_thresh - LONG INTEGER
Maximum memory used to reassemble IP fragments.
-ipfrag_low_thresh - INTEGER
+ipfrag_low_thresh - LONG INTEGER
(Obsolete since linux-4.17)
Maximum memory used to reassemble IP fragments before the kernel
begins to remove incomplete fragment queues to free up resources.
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 23161bf5d899..dea175f3418a 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -7,11 +7,11 @@ struct netns_frags {
struct rhashtable rhashtable ____cacheline_aligned_in_smp;
/* Keep atomic mem on separate cachelines in structs that include it */
- atomic_t mem ____cacheline_aligned_in_smp;
+ atomic_long_t mem ____cacheline_aligned_in_smp;
/* sysctls */
+ long high_thresh;
+ long low_thresh;
int timeout;
- int high_thresh;
- int low_thresh;
int max_dist;
struct inet_frags *f;
};
@@ -101,7 +101,7 @@ void inet_frags_fini(struct inet_frags *);
static inline int inet_frags_init_net(struct netns_frags *nf)
{
- atomic_set(&nf->mem, 0);
+ atomic_long_set(&nf->mem, 0);
return rhashtable_init(&nf->rhashtable, &nf->f->rhash_params);
}
void inet_frags_exit_net(struct netns_frags *nf);
@@ -118,19 +118,19 @@ static inline void inet_frag_put(struct inet_frag_queue *q)
/* Memory Tracking Functions. */
-static inline int frag_mem_limit(struct netns_frags *nf)
+static inline long frag_mem_limit(const struct netns_frags *nf)
{
- return atomic_read(&nf->mem);
+ return atomic_long_read(&nf->mem);
}
-static inline void sub_frag_mem_limit(struct netns_frags *nf, int i)
+static inline void sub_frag_mem_limit(struct netns_frags *nf, long val)
{
- atomic_sub(i, &nf->mem);
+ atomic_long_sub(val, &nf->mem);
}
-static inline void add_frag_mem_limit(struct netns_frags *nf, int i)
+static inline void add_frag_mem_limit(struct netns_frags *nf, long val)
{
- atomic_add(i, &nf->mem);
+ atomic_long_add(val, &nf->mem);
}
/* RFC 3168 support :
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index b54015981af9..122a625d9a66 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -410,23 +410,23 @@ int lowpan_frag_rcv(struct sk_buff *skb, u8 frag_type)
}
#ifdef CONFIG_SYSCTL
-static int zero;
+static long zero;
static struct ctl_table lowpan_frags_ns_ctl_table[] = {
{
.procname = "6lowpanfrag_high_thresh",
.data = &init_net.ieee802154_lowpan.frags.high_thresh,
- .maxlen = sizeof(int),
+ .maxlen = sizeof(unsigned long),
.mode = 0644,
- .proc_handler = proc_dointvec_minmax,
+ .proc_handler = proc_doulongvec_minmax,
.extra1 = &init_net.ieee802154_lowpan.frags.low_thresh
},
{
.procname = "6lowpanfrag_low_thresh",
.data = &init_net.ieee802154_lowpan.frags.low_thresh,
- .maxlen = sizeof(int),
+ .maxlen = sizeof(unsigned long),
.mode = 0644,
- .proc_handler = proc_dointvec_minmax,
+ .proc_handler = proc_doulongvec_minmax,
.extra1 = &zero,
.extra2 = &init_net.ieee802154_lowpan.frags.high_thresh
},
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 696bfef06caa..3dd19bebeb55 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -681,23 +681,23 @@ struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user)
EXPORT_SYMBOL(ip_check_defrag);
#ifdef CONFIG_SYSCTL
-static int zero;
+static long zero;
static struct ctl_table ip4_frags_ns_ctl_table[] = {
{
.procname = "ipfrag_high_thresh",
.data = &init_net.ipv4.frags.high_thresh,
- .maxlen = sizeof(int),
+ .maxlen = sizeof(unsigned long),
.mode = 0644,
- .proc_handler = proc_dointvec_minmax,
+ .proc_handler = proc_doulongvec_minmax,
.extra1 = &init_net.ipv4.frags.low_thresh
},
{
.procname = "ipfrag_low_thresh",
.data = &init_net.ipv4.frags.low_thresh,
- .maxlen = sizeof(int),
+ .maxlen = sizeof(unsigned long),
.mode = 0644,
- .proc_handler = proc_dointvec_minmax,
+ .proc_handler = proc_doulongvec_minmax,
.extra1 = &zero,
.extra2 = &init_net.ipv4.frags.high_thresh
},
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index b7a2d002cb27..aa1e52587bf5 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -73,7 +73,7 @@ static int sockstat_seq_show(struct seq_file *seq, void *v)
sock_prot_inuse_get(net, &udplite_prot));
seq_printf(seq, "RAW: inuse %d\n",
sock_prot_inuse_get(net, &raw_prot));
- seq_printf(seq, "FRAG: inuse %u memory %u\n",
+ seq_printf(seq, "FRAG: inuse %u memory %lu\n",
atomic_read(&net->ipv4.frags.rhashtable.nelems),
frag_mem_limit(&net->ipv4.frags));
return 0;
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 267f2ae2d05c..8bc0df9ad2ab 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -63,7 +63,7 @@ struct nf_ct_frag6_skb_cb
static struct inet_frags nf_frags;
#ifdef CONFIG_SYSCTL
-static int zero;
+static long zero;
static struct ctl_table nf_ct_frag6_sysctl_table[] = {
{
@@ -76,18 +76,18 @@ static struct ctl_table nf_ct_frag6_sysctl_table[] = {
{
.procname = "nf_conntrack_frag6_low_thresh",
.data = &init_net.nf_frag.frags.low_thresh,
- .maxlen = sizeof(unsigned int),
+ .maxlen = sizeof(unsigned long),
.mode = 0644,
- .proc_handler = proc_dointvec_minmax,
+ .proc_handler = proc_doulongvec_minmax,
.extra1 = &zero,
.extra2 = &init_net.nf_frag.frags.high_thresh
},
{
.procname = "nf_conntrack_frag6_high_thresh",
.data = &init_net.nf_frag.frags.high_thresh,
- .maxlen = sizeof(unsigned int),
+ .maxlen = sizeof(unsigned long),
.mode = 0644,
- .proc_handler = proc_dointvec_minmax,
+ .proc_handler = proc_doulongvec_minmax,
.extra1 = &init_net.nf_frag.frags.low_thresh
},
{ }
diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index 5704ec3d3178..dc04c024986c 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -47,7 +47,7 @@ static int sockstat6_seq_show(struct seq_file *seq, void *v)
sock_prot_inuse_get(net, &udplitev6_prot));
seq_printf(seq, "RAW6: inuse %d\n",
sock_prot_inuse_get(net, &rawv6_prot));
- seq_printf(seq, "FRAG6: inuse %u memory %u\n",
+ seq_printf(seq, "FRAG6: inuse %u memory %lu\n",
atomic_read(&net->ipv6.frags.rhashtable.nelems),
frag_mem_limit(&net->ipv6.frags));
return 0;
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 6de4cec69054..8a4ece339c19 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -546,15 +546,15 @@ static struct ctl_table ip6_frags_ns_ctl_table[] = {
{
.procname = "ip6frag_high_thresh",
.data = &init_net.ipv6.frags.high_thresh,
- .maxlen = sizeof(int),
+ .maxlen = sizeof(unsigned long),
.mode = 0644,
- .proc_handler = proc_dointvec_minmax,
+ .proc_handler = proc_doulongvec_minmax,
.extra1 = &init_net.ipv6.frags.low_thresh
},
{
.procname = "ip6frag_low_thresh",
.data = &init_net.ipv6.frags.low_thresh,
- .maxlen = sizeof(int),
+ .maxlen = sizeof(unsigned long),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
--
2.17.1
^ permalink raw reply related
* [PATCH stable 4.9 14/29] ipv6: frags: rewrite ip6_expire_frag_queue()
From: Florian Fainelli @ 2018-10-09 22:49 UTC (permalink / raw)
To: netdev; +Cc: davem, gregkh, stable, edumazet, sthemmin
In-Reply-To: <20181009224924.30151-1-f.fainelli@gmail.com>
From: Eric Dumazet <edumazet@google.com>
Make it similar to IPv4 ip_expire(), and release the lock
before calling icmp functions.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
(cherry picked from commit 05c0b86b9696802fd0ce5676a92a63f1b455bdf3)
---
net/ipv6/reassembly.c | 24 ++++++++++++++++--------
1 file changed, 16 insertions(+), 8 deletions(-)
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 8a4ece339c19..1cb45a0d1a0e 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -92,7 +92,9 @@ EXPORT_SYMBOL(ip6_frag_init);
void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq)
{
struct net_device *dev = NULL;
+ struct sk_buff *head;
+ rcu_read_lock();
spin_lock(&fq->q.lock);
if (fq->q.flags & INET_FRAG_COMPLETE)
@@ -100,28 +102,34 @@ void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq)
inet_frag_kill(&fq->q);
- rcu_read_lock();
dev = dev_get_by_index_rcu(net, fq->iif);
if (!dev)
- goto out_rcu_unlock;
+ goto out;
__IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
__IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT);
/* Don't send error if the first segment did not arrive. */
- if (!(fq->q.flags & INET_FRAG_FIRST_IN) || !fq->q.fragments)
- goto out_rcu_unlock;
+ head = fq->q.fragments;
+ if (!(fq->q.flags & INET_FRAG_FIRST_IN) || !head)
+ goto out;
/* But use as source device on which LAST ARRIVED
* segment was received. And do not use fq->dev
* pointer directly, device might already disappeared.
*/
- fq->q.fragments->dev = dev;
- icmpv6_send(fq->q.fragments, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0);
-out_rcu_unlock:
- rcu_read_unlock();
+ head->dev = dev;
+ skb_get(head);
+ spin_unlock(&fq->q.lock);
+
+ icmpv6_send(head, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0);
+ kfree_skb(head);
+ goto out_rcu_unlock;
+
out:
spin_unlock(&fq->q.lock);
+out_rcu_unlock:
+ rcu_read_unlock();
inet_frag_put(&fq->q);
}
EXPORT_SYMBOL(ip6_expire_frag_queue);
--
2.17.1
^ permalink raw reply related
* [PATCH stable 4.9 15/29] rhashtable: reorganize struct rhashtable layout
From: Florian Fainelli @ 2018-10-09 22:49 UTC (permalink / raw)
To: netdev; +Cc: davem, gregkh, stable, edumazet, sthemmin
In-Reply-To: <20181009224924.30151-1-f.fainelli@gmail.com>
From: Eric Dumazet <edumazet@google.com>
While under frags DDOS I noticed unfortunate false sharing between
@nelems and @params.automatic_shrinking
Move @nelems at the end of struct rhashtable so that first cache line
is shared between all cpus, because almost never dirtied.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
(cherry picked from commit e5d672a0780d9e7118caad4c171ec88b8299398d)
---
include/linux/rhashtable.h | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index 85d1ffc90285..4421e5ccb092 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -138,7 +138,6 @@ struct rhashtable_params {
/**
* struct rhashtable - Hash table handle
* @tbl: Bucket table
- * @nelems: Number of elements in table
* @key_len: Key length for hashfn
* @elasticity: Maximum chain length before rehash
* @p: Configuration parameters
@@ -146,10 +145,10 @@ struct rhashtable_params {
* @run_work: Deferred worker to expand/shrink asynchronously
* @mutex: Mutex to protect current/future table swapping
* @lock: Spin lock to protect walker list
+ * @nelems: Number of elements in table
*/
struct rhashtable {
struct bucket_table __rcu *tbl;
- atomic_t nelems;
unsigned int key_len;
unsigned int elasticity;
struct rhashtable_params p;
@@ -157,6 +156,7 @@ struct rhashtable {
struct work_struct run_work;
struct mutex mutex;
spinlock_t lock;
+ atomic_t nelems;
};
/**
--
2.17.1
^ permalink raw reply related
* [PATCH stable 4.9 17/29] inet: frags: get rid of ipfrag_skb_cb/FRAG_CB
From: Florian Fainelli @ 2018-10-09 22:49 UTC (permalink / raw)
To: netdev; +Cc: davem, gregkh, stable, edumazet, sthemmin
In-Reply-To: <20181009224924.30151-1-f.fainelli@gmail.com>
From: Eric Dumazet <edumazet@google.com>
ip_defrag uses skb->cb[] to store the fragment offset, and unfortunately
this integer is currently in a different cache line than skb->next,
meaning that we use two cache lines per skb when finding the insertion point.
By aliasing skb->ip_defrag_offset and skb->dev, we pack all the fields
in a single cache line and save precious memory bandwidth.
Note that after the fast path added by Changli Gao in commit
d6bebca92c66 ("fragment: add fast path for in-order fragments")
this change wont help the fast path, since we still need
to access prev->len (2nd cache line), but will show great
benefits when slow path is entered, since we perform
a linear scan of a potentially long list.
Also, note that this potential long list is an attack vector,
we might consider also using an rb-tree there eventually.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
(cherry picked from commit bf66337140c64c27fa37222b7abca7e49d63fb57)
---
include/linux/skbuff.h | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 1f207dd22757..c7cca35fcf6d 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -645,6 +645,11 @@ struct sk_buff {
};
struct rb_node rbnode; /* used in netem & tcp stack */
};
+
+ union {
+ int ip_defrag_offset;
+ };
+
struct sock *sk;
struct net_device *dev;
--
2.17.1
^ permalink raw reply related
* [PATCH stable 4.9 18/29] inet: frags: fix ip6frag_low_thresh boundary
From: Florian Fainelli @ 2018-10-09 22:49 UTC (permalink / raw)
To: netdev; +Cc: davem, gregkh, stable, edumazet, sthemmin
In-Reply-To: <20181009224924.30151-1-f.fainelli@gmail.com>
From: Eric Dumazet <edumazet@google.com>
Giving an integer to proc_doulongvec_minmax() is dangerous on 64bit arches,
since linker might place next to it a non zero value preventing a change
to ip6frag_low_thresh.
ip6frag_low_thresh is not used anymore in the kernel, but we do not
want to prematuraly break user scripts wanting to change it.
Since specifying a minimal value of 0 for proc_doulongvec_minmax()
is moot, let's remove these zero values in all defrag units.
Fixes: 6e00f7dd5e4e ("ipv6: frags: fix /proc/sys/net/ipv6/ip6frag_low_thresh")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Maciej Żenczykowski <maze@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
(cherry picked from commit 3d23401283e80ceb03f765842787e0e79ff598b7)
---
net/ieee802154/6lowpan/reassembly.c | 2 --
net/ipv4/ip_fragment.c | 40 ++++++++++---------------
net/ipv6/netfilter/nf_conntrack_reasm.c | 2 --
net/ipv6/reassembly.c | 4 +--
4 files changed, 17 insertions(+), 31 deletions(-)
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index 122a625d9a66..6fca75581e13 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -410,7 +410,6 @@ int lowpan_frag_rcv(struct sk_buff *skb, u8 frag_type)
}
#ifdef CONFIG_SYSCTL
-static long zero;
static struct ctl_table lowpan_frags_ns_ctl_table[] = {
{
@@ -427,7 +426,6 @@ static struct ctl_table lowpan_frags_ns_ctl_table[] = {
.maxlen = sizeof(unsigned long),
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
- .extra1 = &zero,
.extra2 = &init_net.ieee802154_lowpan.frags.high_thresh
},
{
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index e235f62dab58..73c0adc61a65 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -56,14 +56,6 @@
*/
static const char ip_frag_cache_name[] = "ip4-frags";
-struct ipfrag_skb_cb
-{
- struct inet_skb_parm h;
- int offset;
-};
-
-#define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb))
-
/* Describe an entry in the "incomplete datagrams" queue. */
struct ipq {
struct inet_frag_queue q;
@@ -351,13 +343,13 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
* this fragment, right?
*/
prev = qp->q.fragments_tail;
- if (!prev || FRAG_CB(prev)->offset < offset) {
+ if (!prev || prev->ip_defrag_offset < offset) {
next = NULL;
goto found;
}
prev = NULL;
for (next = qp->q.fragments; next != NULL; next = next->next) {
- if (FRAG_CB(next)->offset >= offset)
+ if (next->ip_defrag_offset >= offset)
break; /* bingo! */
prev = next;
}
@@ -368,7 +360,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
* any overlaps are eliminated.
*/
if (prev) {
- int i = (FRAG_CB(prev)->offset + prev->len) - offset;
+ int i = (prev->ip_defrag_offset + prev->len) - offset;
if (i > 0) {
offset += i;
@@ -385,8 +377,8 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
err = -ENOMEM;
- while (next && FRAG_CB(next)->offset < end) {
- int i = end - FRAG_CB(next)->offset; /* overlap is 'i' bytes */
+ while (next && next->ip_defrag_offset < end) {
+ int i = end - next->ip_defrag_offset; /* overlap is 'i' bytes */
if (i < next->len) {
int delta = -next->truesize;
@@ -399,7 +391,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
delta += next->truesize;
if (delta)
add_frag_mem_limit(qp->q.net, delta);
- FRAG_CB(next)->offset += i;
+ next->ip_defrag_offset += i;
qp->q.meat -= i;
if (next->ip_summed != CHECKSUM_UNNECESSARY)
next->ip_summed = CHECKSUM_NONE;
@@ -423,7 +415,13 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
}
}
- FRAG_CB(skb)->offset = offset;
+ /* Note : skb->ip_defrag_offset and skb->dev share the same location */
+ dev = skb->dev;
+ if (dev)
+ qp->iif = dev->ifindex;
+ /* Makes sure compiler wont do silly aliasing games */
+ barrier();
+ skb->ip_defrag_offset = offset;
/* Insert this fragment in the chain of fragments. */
skb->next = next;
@@ -434,11 +432,6 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
else
qp->q.fragments = skb;
- dev = skb->dev;
- if (dev) {
- qp->iif = dev->ifindex;
- skb->dev = NULL;
- }
qp->q.stamp = skb->tstamp;
qp->q.meat += skb->len;
qp->ecn |= ecn;
@@ -514,7 +507,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
}
WARN_ON(!head);
- WARN_ON(FRAG_CB(head)->offset != 0);
+ WARN_ON(head->ip_defrag_offset != 0);
/* Allocate a new buffer for the datagram. */
ihlen = ip_hdrlen(head);
@@ -677,7 +670,7 @@ struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user)
EXPORT_SYMBOL(ip_check_defrag);
#ifdef CONFIG_SYSCTL
-static long zero;
+static int dist_min;
static struct ctl_table ip4_frags_ns_ctl_table[] = {
{
@@ -694,7 +687,6 @@ static struct ctl_table ip4_frags_ns_ctl_table[] = {
.maxlen = sizeof(unsigned long),
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
- .extra1 = &zero,
.extra2 = &init_net.ipv4.frags.high_thresh
},
{
@@ -710,7 +702,7 @@ static struct ctl_table ip4_frags_ns_ctl_table[] = {
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
- .extra1 = &zero
+ .extra1 = &dist_min,
},
{ }
};
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 8bc0df9ad2ab..ff49d1f2c8cb 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -63,7 +63,6 @@ struct nf_ct_frag6_skb_cb
static struct inet_frags nf_frags;
#ifdef CONFIG_SYSCTL
-static long zero;
static struct ctl_table nf_ct_frag6_sysctl_table[] = {
{
@@ -79,7 +78,6 @@ static struct ctl_table nf_ct_frag6_sysctl_table[] = {
.maxlen = sizeof(unsigned long),
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
- .extra1 = &zero,
.extra2 = &init_net.nf_frag.frags.high_thresh
},
{
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 1cb45a0d1a0e..dbe726c9a2ae 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -548,7 +548,6 @@ static const struct inet6_protocol frag_protocol = {
};
#ifdef CONFIG_SYSCTL
-static int zero;
static struct ctl_table ip6_frags_ns_ctl_table[] = {
{
@@ -564,8 +563,7 @@ static struct ctl_table ip6_frags_ns_ctl_table[] = {
.data = &init_net.ipv6.frags.low_thresh,
.maxlen = sizeof(unsigned long),
.mode = 0644,
- .proc_handler = proc_dointvec_minmax,
- .extra1 = &zero,
+ .proc_handler = proc_doulongvec_minmax,
.extra2 = &init_net.ipv6.frags.high_thresh
},
{
--
2.17.1
^ permalink raw reply related
* [PATCH stable 4.9 20/29] net: speed up skb_rbtree_purge()
From: Florian Fainelli @ 2018-10-09 22:49 UTC (permalink / raw)
To: netdev; +Cc: davem, gregkh, stable, edumazet, sthemmin
In-Reply-To: <20181009224924.30151-1-f.fainelli@gmail.com>
From: Eric Dumazet <edumazet@google.com>
As measured in my prior patch ("sch_netem: faster rb tree removal"),
rbtree_postorder_for_each_entry_safe() is nice looking but much slower
than using rb_next() directly, except when tree is small enough
to fit in CPU caches (then the cost is the same)
Also note that there is not even an increase of text size :
$ size net/core/skbuff.o.before net/core/skbuff.o
text data bss dec hex filename
40711 1298 0 42009 a419 net/core/skbuff.o.before
40711 1298 0 42009 a419 net/core/skbuff.o
From: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
(cherry picked from commit 7c90584c66cc4b033a3b684b0e0950f79e7b7166)
---
net/core/skbuff.c | 11 +++++++----
1 file changed, 7 insertions(+), 4 deletions(-)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 84c731aef0d8..96a553da1518 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2433,12 +2433,15 @@ EXPORT_SYMBOL(skb_queue_purge);
*/
void skb_rbtree_purge(struct rb_root *root)
{
- struct sk_buff *skb, *next;
+ struct rb_node *p = rb_first(root);
- rbtree_postorder_for_each_entry_safe(skb, next, root, rbnode)
- kfree_skb(skb);
+ while (p) {
+ struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode);
- *root = RB_ROOT;
+ p = rb_next(p);
+ rb_erase(&skb->rbnode, root);
+ kfree_skb(skb);
+ }
}
/**
--
2.17.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox