Currently, all filters with the same priority are linked in a doubly
linked list. Every filter should have a unique handle. To make the
handle unique, we need to iterate the list every time to see if the
handle exists or not when inserting a new filter. It is time-consuming.
For example, it takes about 5m3.169s to insert 64K rules.

This patch changes cls_flower to use IDR. With this patch, it
takes about 0m1.127s to insert 64K rules. The improvement is huge.

But please note that in this testing, all filters share the same action.
If every filter has a unique action, that is another bottleneck.
Follow-up patch in this patchset addresses that.
Signed-off-by: NChris Mi <chrism@mellanox.com>
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Acked-by: NJamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch handles a default IFE type if it's not given by user space
netlink api. The default IFE type will be the registered ethertype by
IEEE for IFE ForCES.
Signed-off-by: NAlexander Aring <aring@mojatatu.com>
Acked-by: NJamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The commit 520ac30f ("net_sched: drop packets after root qdisc lock
is released) made a big change of tc for performance. But there are
some points which are not changed in SFQ enqueue operation.
1. Fail to find the SFQ hash slot;
2. When the queue is full;

Now use qdisc_drop instead free skb directly.
Signed-off-by: NGao Feng <gfree.wind@vip.163.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

It is ugly to hide a u32-filter-specific pointer inside Qdisc,
this breaks the TC layers:

1. Qdisc is a generic representation, should not have any specific
   data of any type

2. Qdisc layer is above filter layer, should only save filters in
   the list of struct tcf_proto.

This pointer is used as the head of the chain of u32 hash tables,
that is struct tc_u_hnode, because u32 filter is very special,
it allows to create multiple hash tables within one qdisc and
across multiple u32 filters.

Instead of using this ugly pointer, we can just save it in a global
hash table key'ed by (dev ifindex, qdisc handle), therefore we can
still treat it as a per qdisc basis data structure conceptually.

Of course, because of network namespaces, this key is not unique
at all, but it is fine as we already have a pointer to Qdisc in
struct tc_u_common, we can just compare the pointers when collision.

And this only affects slow paths, has no impact to fast path,
thanks to the pointer ->tp_c.

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: NCong Wang <xiyou.wangcong@gmail.com>
Acked-by: NJiri Pirko <jiri@mellanox.com>
Acked-by: NJamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

For TC classes, their ->get() and ->put() are always paired, and the
reference counting is completely useless, because:

1) For class modification and dumping paths, we already hold RTNL lock,
   so all of these ->get(),->change(),->put() are atomic.

2) For filter bindiing/unbinding, we use other reference counter than
   this one, and they should have RTNL lock too.

3) For ->qlen_notify(), it is special because it is called on ->enqueue()
   path, but we already hold qdisc tree lock there, and we hold this
   tree lock when graft or delete the class too, so it should not be gone
   or changed until we release the tree lock.

Therefore, this patch removes ->get() and ->put(), but:

1) Adds a new ->find() to find the pointer to a class by classid, no
   refcnt.

2) Move the original class destroy upon the last refcnt into ->delete(),
   right after releasing tree lock. This is fine because the class is
   already removed from hash when holding the lock.

For those who also use ->put() as ->unbind(), just rename them to reflect
this change.

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: NCong Wang <xiyou.wangcong@gmail.com>
Acked-by: NJiri Pirko <jiri@mellanox.com>
Acked-by: NJamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Like for TC actions, ->delete() is a special case,
we have to prepare and fill the notification before delete
otherwise would get use-after-free after we remove the
reference count.
Signed-off-by: NCong Wang <xiyou.wangcong@gmail.com>
Acked-by: NJamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This is not needed if we move them up properly.
Signed-off-by: NCong Wang <xiyou.wangcong@gmail.com>
Acked-by: NJiri Pirko <jiri@mellanox.com>
Acked-by: NJamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

High order GFP_KERNEL allocations can stress the host badly.

Use modern kvmalloc_array()/kvfree() instead of custom
allocations.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Acked-by: NAlexei Starovoitov <ast@kernel.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

As we know in some target's checkentry it may dereference par.entryinfo
to check entry stuff inside. But when sched action calls xt_check_target,
par.entryinfo is set with NULL. It would cause kernel panic when calling
some targets.

It can be reproduce with:
  # tc qd add dev eth1 ingress handle ffff:
  # tc filter add dev eth1 parent ffff: u32 match u32 0 0 action xt \
    -j ECN --ecn-tcp-remove

It could also crash kernel when using target CLUSTERIP or TPROXY.

By now there's no proper value for par.entryinfo in ipt_init_target,
but it can not be set with NULL. This patch is to void all these
panics by setting it with an ipt_entry obj with all members = 0.

Note that this issue has been there since the very beginning.
Signed-off-by: NXin Long <lucien.xin@gmail.com>
Acked-by: NPablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The dereference before check is wrong and leads to an oops when
p_filter_chain is NULL. The check needs to be done on the pointer to
prevent NULL dereference.

Fixes: f93e1cdc ("net/sched: fix filter flushing")
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Acked-by: NCong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

I made a stupid mistake using TC_CLSFLOWER_STATS instead of
TC_SETUP_CLSFLOWER. Funny thing is that both are defined as "2" so it
actually did not cause any harm. Anyway, fixing it now.

Fixes: 2572ac53 ("net: sched: make type an argument for ndo_setup_tc")
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The main purpose of this tracepoint is to monitor bulk dequeue
in the network qdisc layer, as it cannot be deducted from the
existing qdisc stats.

The txq_state can be used for determining the reason for zero packet
dequeues, see enum netdev_queue_state_t.

Notice all packets doesn't necessary activate this tracepoint. As
qdiscs with flag TCQ_F_CAN_BYPASS, can directly invoke
sch_direct_xmit() when qdisc_qlen is zero.

Remember that perf record supports filters like:

 perf record -e qdisc:qdisc_dequeue \
  --filter 'ifindex == 4 && (packets > 1 || txq_state > 0)'
Signed-off-by: NJesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Any move comment abount update_vf() into right place.
Signed-off-by: NKonstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This callback is used for deactivating class in parent qdisc.
This is cheaper to test queue length right here.

Also this allows to catch draining screwed backlog and prevent
second deactivation of already inactive parent class which will
crash kernel for sure. Kernel with print warning at destruction
of child qdisc where no packets but backlog is not zero.
Signed-off-by: NKonstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

It was added in commit e57a784d ("pkt_sched: set root qdisc
before change() in attach_default_qdiscs()") to hide duplicates
from "tc qdisc show" for incative deivices.

After 59cc1f61 ("net: sched: convert qdisc linked list to hashtable")
it triggered when classful qdisc is added to inactive device because
default qdiscs are added before switching root qdisc.

Anyway after commit ea327469 ("net: sched: avoid duplicates in
qdisc dump") duplicates are filtered right in dumper.
Signed-off-by: NKonstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When sfq_enqueue() drops head packet or packet from another queue it
have to update backlog at upper qdiscs too.

Fixes: 2ccccf5f ("net_sched: update hierarchical backlog too")
Signed-off-by: NKonstantin Khlebnikov <khlebnikov@yandex-team.ru>
Acked-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Traffic filters could keep direct pointers to classes in classful qdisc,
thus qdisc destruction first removes all filters before freeing classes.
Class destruction methods also tries to free attached filters but now
this isn't safe because tcf_block_put() unlike to tcf_destroy_chain()
cannot be called second time.

This patch set class->block to NULL after first tcf_block_put() and
turn second call into no-op.

Fixes: 6529eaba ("net: sched: introduce tcf block infractructure")
Signed-off-by: NKonstantin Khlebnikov <khlebnikov@yandex-team.ru>
Acked-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Without this filters cannot be attached.
Signed-off-by: NKonstantin Khlebnikov <khlebnikov@yandex-team.ru>
Fixes: 6529eaba ("net: sched: introduce tcf block infractructure")
Acked-by: NCong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

cops->tcf_cl_offload is no longer needed, as the drivers check what they
can and cannot offload using the classid identify helpers. So remove this.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Commit 55917a21 ("netfilter: x_tables: add context to know if
extension runs from nft_compat") introduced a member nft_compat to
xt_tgchk_param structure.

But it didn't set it's value for ipt_init_target. With unexpected
value in par.nft_compat, it may return unexpected result in some
target's checkentry.

This patch is to set all it's fields as 0 and only initialize the
non-zero fields in ipt_init_target.

v1->v2:
  As Wang Cong's suggestion, fix it by setting all it's fields as
  0 and only initializing the non-zero fields.

Fixes: 55917a21 ("netfilter: x_tables: add context to know if extension runs from nft_compat")
Suggested-by: NCong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: NXin Long <lucien.xin@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This change allows us to later indicate to rtnetlink core that certain
doit functions should be called without acquiring rtnl_mutex.

This change should have no effect, we simply replace the last (now
unused) calcit argument with the new flag.
Signed-off-by: NFlorian Westphal <fw@strlen.de>
Reviewed-by: NHannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Now xt_tgchk_param par in ipt_init_target is a local varibale,
par.net is not initialized there. Later when xt_check_target
calls target's checkentry in which it may access par.net, it
would cause kernel panic.

Jaroslav found this panic when running:

  # ip link add TestIface type dummy
  # tc qd add dev TestIface ingress handle ffff:
  # tc filter add dev TestIface parent ffff: u32 match u32 0 0 \
    action xt -j CONNMARK --set-mark 4

This patch is to pass net param into ipt_init_target and set
par.net with it properly in there.

v1->v2:
  As Wang Cong pointed, I missed ipt_net_id != xt_net_id, so fix
  it by also passing net_id to __tcf_ipt_init.
v2->v3:
  Missed the fixes tag, so add it.

Fixes: ecb2421b ("netfilter: add and use nf_ct_netns_get/put")
Reported-by: NJaroslav Aster <jaster@redhat.com>
Signed-off-by: NXin Long <lucien.xin@gmail.com>
Acked-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

If we move up tcf_fill_node() we can get rid of these
forward declarations.

Also, move down tfilter_notify_chain() to group them together.
Reported-by: NJamal Hadi Salim <jhs@mojatatu.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: NCong Wang <xiyou.wangcong@gmail.com>
Acked-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Now we use 'unsigned long fh' as a pointer in every place,
it is safe to convert it to a void pointer now. This gets
rid of many casts to pointer.

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: NCong Wang <xiyou.wangcong@gmail.com>
Acked-by: NJamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

It is confusing to use 'unsigned long fh' as both a handle
and a pointer, especially commit 9ee78374
("net sched filters: fix notification of filter delete with proper handle").

This patch introduces tfilter_del_notify() so that we can
pass it as a pointer as before, and we don't need to check
RTM_DELTFILTER in tcf_fill_node() any more.

This prepares for the next patch.

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: NCong Wang <xiyou.wangcong@gmail.com>
Acked-by: NJamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Get rid of struct tc_to_netdev which is now just unnecessary container
and rather pass per-type structures down to drivers directly.
Along with that, consolidate the naming of per-type structure variables
in cls_*.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Acked-by: NJamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

prio is not cls_flower specific, but it is meaningful for all
classifiers. Seems that only mlxsw cares about the value. Obviously,
cls offload in other drivers is broken.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Acked-by: NJamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

As ndo_setup_tc is generic offload op for whole tc subsystem, does not
really make sense to have cls-specific args. So move them under
cls_common structurure which is embedded in all cls structs.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Acked-by: NJamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Since this is specific to flower now, make it part of the flower offload
struct.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Acked-by: NJamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In order to be aligned with the rest of the types, rename
TC_SETUP_MATCHALL to TC_SETUP_CLSMATCHALL.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Acked-by: NJamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Since the type is always present, push it to be a separate argument to
ndo_setup_tc. On the way, name the type enum and use it for arg type.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Acked-by: NJamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

tcf_exts_change is always called on newly created exts, which are not used
on fastpath. Therefore, simple struct copy is enough.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

As the n struct was allocated right before u32_set_parms call,
no need to use tcf_exts_change to do atomic change, and we can just
fill-up the unused exts struct directly by tcf_exts_validate.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

As the f struct was allocated right before route4_set_parms call,
no need to use tcf_exts_change to do atomic change, and we can just
fill-up the unused exts struct directly by tcf_exts_validate.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

As the fnew struct just was allocated, so no need to use tcf_exts_change
to do atomic change, and we can just fill-up the unused exts struct
directly by tcf_exts_validate.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

As the new struct just was allocated, so no need to use tcf_exts_change
to do atomic change, and we can just fill-up the unused exts struct
directly by tcf_exts_validate.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

As the prog struct was allocated right before cls_bpf_set_parms call,
no need to use tcf_exts_change to do atomic change, and we can just
fill-up the unused exts struct directly by tcf_exts_validate.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

As the f struct was allocated right before basic_set_parms call, no need
to use tcf_exts_change to do atomic change, and we can just fill-up
the unused exts struct directly by tcf_exts_validate.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

As the head struct was allocated right before mall_set_parms call,
no need to use tcf_exts_change to do atomic change, and we can just
fill-up the unused exts struct directly by tcf_exts_validate.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

As the f struct was allocated right before fw_set_parms call, no need
to use tcf_exts_change to do atomic change, and we can just fill-up
the unused exts struct directly by tcf_exts_validate.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>