Age | Commit message (Collapse) | Author |
|
Also, make the argument to be only the needed size of the header
we're altering, no need to pull in the full packet into linear area.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
.. so skb_make_writable can be removed.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
.. so skb_make_writable can be removed soon.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
like previous patches -- convert conntrack to use the core helper.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
It does the same thing, use it instead so we can remove skb_make_writable.
Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
Back in the day, skb_ensure_writable did not exist. By now, both functions
have the same precondition:
I. skb_make_writable will test in this order:
1. wlen > skb->len -> error
2. if not cloned and wlen <= headlen -> OK
3. If cloned and wlen bytes of clone writeable -> OK
After those checks, skb is either not cloned but needs to pull from
nonlinear area, or writing to head would also alter data of another clone.
In both cases skb_make_writable will then call __pskb_pull_tail, which will
kmalloc a new memory area to use for skb->head.
IOW, after successful skb_make_writable call, the requested length is in
linear area and can be modified, even if skb was cloned.
II. skb_ensure_writable will do this instead:
1. call pskb_may_pull. This handles case 1 above.
After this, wlen is in linear area, but skb might be cloned.
2. return if skb is not cloned
3. return if wlen byte of clone are writeable.
4. fully copy the skb.
So post-conditions are the same:
*len bytes are writeable in linear area without altering any payload data
of a clone, all header pointers might have been changed.
Only differences are that skb_ensure_writable is in the core, whereas
skb_make_writable lives in netfilter core and the inverted return value.
skb_make_writable returns 0 on error, whereas skb_ensure_writable returns
negative value.
For the normal cases performance is similar:
A. skb is not cloned and in linear area:
pskb_may_pull is inline helper, so neither function copies.
B. skb is cloned, write is in linear area and clone is writeable:
both funcions return with step 3.
This series removes skb_make_writable from the kernel.
While at it, pass the needed value instead, its less confusing that way:
There is no special-handling of "0-length" argument in either
skb_make_writable or skb_ensure_writable.
bridge already makes sure ethernet header is in linear area, only purpose
of the make_writable() is is to copy skb->head in case of cloned skbs.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
No need to use synchronize_rcu() here, just swap the two pointers
and have the release occur from work queue after commit has completed.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
The oifidx in the struct flow_offload_tuple is not used anymore.
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
The XT_OWNER_SUPPL_GROUPS flag causes GIDs specified with XT_OWNER_GID
to be also checked in the supplementary groups of a process.
f_cred->group_info cannot be modified during its lifetime and f_cred
holds a reference to it so it's safe to use.
Signed-off-by: Lukasz Pawelczyk <l.pawelczyk@samsung.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
Recognize UDP tunnels in received ICMP errors and
properly strip the tunnel headers. GUE is what we
have for now.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
Add ip_vs_find_tunnel() to match tunnel headers
by family, address and optional port. Use it to
properly find the tunnel real server used in
received ICMP errors.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
Before now rs_table was used only for NAT real servers.
Change it to allow TUN real severs from different types,
possibly hashed with different port key.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
Since the new parameter block is initialised to 0 by kzmalloc we don't
need to mask & clear unused operational mode bits, they are already
unset.
Drop the pointless code.
Signed-off-by: Kevin Darbyshire-Bryant <ldir@darbyshire-bryant.me.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
In case a call to dsa_tree_setup() fails, an attempt to cleanup is made
by calling dsa_tree_remove_switch(), which should take care of
removing/unregistering any resources previously allocated. This does not
happen because it is conditioned by dst->setup being true, which is set
only after _all_ setup steps were performed successfully.
This is especially interesting when the internal MDIO bus is registered
but afterwards, a port setup fails and the mdiobus_unregister() is never
called. This leads to a BUG_ON() complaining about the fact that it's
trying to free an MDIO bus that's still registered.
Add proper error handling in all functions branching from
dsa_tree_setup().
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Reported-by: kernel test robot <rong.a.chen@intel.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
The same skb_checksum_ops struct is defined twice in two different places,
leading to code duplication. Declare it as a global variable into a common
header instead of allocating it on the stack on each function call.
bloat-o-meter reports a slight code shrink.
add/remove: 1/1 grow/shrink: 0/10 up/down: 128/-1282 (-1154)
Function old new delta
sctp_csum_ops - 128 +128
crc32c_csum_ops 16 - -16
sctp_rcv 6616 6583 -33
sctp_packet_pack 4542 4504 -38
nf_conntrack_sctp_packet 4980 4926 -54
execute_masked_set_action 6453 6389 -64
tcf_csum_sctp 575 428 -147
sctp_gso_segment 1292 1126 -166
sctp_csum_check 579 412 -167
sctp_snat_handler 957 772 -185
sctp_dnat_handler 1321 1132 -189
l4proto_manip_pkt 2536 2313 -223
Total: Before=359297613, After=359296459, chg -0.00%
Reviewed-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: Matteo Croce <mcroce@redhat.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Commit 283c16a2dfd3 ("indirect call wrappers: helpers to speed-up
indirect calls of builtin") introduces some macros to avoid doing
indirect calls.
Use these helpers to remove two indirect calls in the L4 checksum
calculation for devices which don't have hardware support for it.
As a test I generate packets with pktgen out to a dummy interface
with HW checksumming disabled, to have the checksum calculated in
every sent packet.
The packet rate measured with an i7-6700K CPU and a single pktgen
thread raised from 6143 to 6608 Kpps, an increase by 7.5%
Suggested-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
This patch enables IPv4 and IPv6 conntrack from the bridge to deal with
local traffic. Hence, packets that are passed up to the local input path
are confirmed later on from the {ipv4,ipv6}_confirm() hooks.
For packets leaving the IP stack (ie. output path), fragmentation occurs
after the inet postrouting hook. Therefore, the bridge local out and
postrouting bridge hooks see fragments with conntrack objects, which is
inconsistent. In this case, we could defragment again from the bridge
output hook, but this is expensive. The recommended filtering spot for
outgoing locally generated traffic leaving through the bridge interface
is to use the classic IPv4/IPv6 output hook, which comes earlier.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
br_defrag() and br_fragment() indirections are added in case that IPv6
support comes as a module, to avoid pulling innecessary dependencies in.
The new fraglist iterator and fragment transformer APIs are used to
implement the refragmentation code.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
This patch adds basic connection tracking support for the bridge,
including initial IPv4 support.
This patch register two hooks to deal with the bridge forwarding path,
one from the bridge prerouting hook to call nf_conntrack_in(); and
another from the bridge postrouting hook to confirm the entry.
The conntrack bridge prerouting hook defragments packets before passing
them to nf_conntrack_in() to look up for an existing entry, otherwise a
new entry is allocated and it is attached to the skbuff. The conntrack
bridge postrouting hook confirms new conntrack entries, ie. if this is
the first packet seen, then it adds the entry to the hashtable and (if
needed) it refragments the skbuff into the original fragments, leaving
the geometry as is if possible. Exceptions are linearized skbuffs, eg.
skbuffs that are passed up to nfqueue and conntrack helpers, as well as
cloned skbuff for the local delivery (eg. tcpdump), also in case of
bridge port flooding (cloned skbuff too).
The packet defragmentation is done through the ip_defrag() call. This
forces us to save the bridge control buffer, reset the IP control buffer
area and then restore it after call. This function also bumps the IP
fragmentation statistics, it would be probably desiderable to have
independent statistics for the bridge defragmentation/refragmentation.
The maximum fragment length is stored in the control buffer and it is
used to refragment the skbuff from the postrouting path.
The new fraglist splitter and fragment transformer APIs are used to
implement the bridge refragmentation code. The br_ip_fragment() function
drops the packet in case the maximum fragment size seen is larger than
the output port MTU.
This patchset follows the principle that conntrack should not drop
packets, so users can do it through policy via invalid state matching.
Like br_netfilter, there is no refragmentation for packets that are
passed up for local delivery, ie. prerouting -> input path. There are
calls to nf_reset() already in several spots in the stack since time ago
already, eg. af_packet, that show that skbuff fraglist handling from the
netif_rx path is supported already.
The helpers are called from the postrouting hook, before confirmation,
from there we may see packet floods to bridge ports. Then, although
unlikely, this may result in exercising the helpers many times for each
clone. It would be good to explore how to pass all the packets in a list
to the conntrack hook to do this handle only once for this case.
Thanks to Florian Westphal for handing me over an initial patchset
version to add support for conntrack bridge.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
This patch adds infrastructure to register and to unregister bridge
support for the conntrack module via nf_ct_bridge_register() and
nf_ct_bridge_unregister().
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Deal with the IPCB() area away from the iterators.
The bridge codebase has its own control buffer layout, move specific
IP control buffer handling into the IPv4 codepath.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
This patch exposes a new API to refragment a skbuff. This allows you to
split either a linear skbuff or to force the refragmentation of an
existing fraglist using a different mtu. The API consists of:
* ip6_frag_init(), that initializes the internal state of the transformer.
* ip6_frag_next(), that allows you to fetch the next fragment. This function
internally allocates the skbuff that represents the fragment, it pushes
the IPv6 header, and it also copies the payload for each fragment.
The ip6_frag_state object stores the internal state of the splitter.
This code has been extracted from ip6_fragment(). Symbols are also
exported to allow to reuse this iterator from the bridge codepath to
build its own refragmentation routine by reusing the existing codebase.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
This patch exposes a new API to refragment a skbuff. This allows you to
split either a linear skbuff or to force the refragmentation of an
existing fraglist using a different mtu. The API consists of:
* ip_frag_init(), that initializes the internal state of the transformer.
* ip_frag_next(), that allows you to fetch the next fragment. This function
internally allocates the skbuff that represents the fragment, it pushes
the IPv4 header, and it also copies the payload for each fragment.
The ip_frag_state object stores the internal state of the splitter.
This code has been extracted from ip_do_fragment(). Symbols are also
exported to allow to reuse this iterator from the bridge codepath to
build its own refragmentation routine by reusing the existing codebase.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
This patch adds the skbuff fraglist split iterator. This API provides an
iterator to transform the fraglist into single skbuff objects, it
consists of:
* ip6_fraglist_init(), that initializes the internal state of the
fraglist iterator.
* ip6_fraglist_prepare(), that restores the IPv6 header on the fragment.
* ip6_fraglist_next(), that retrieves the fragment from the fraglist and
updates the internal state of the iterator to point to the next
fragment in the fraglist.
The ip6_fraglist_iter object stores the internal state of the iterator.
This code has been extracted from ip6_fragment(). Symbols are also
exported to allow to reuse this iterator from the bridge codepath to
build its own refragmentation routine by reusing the existing codebase.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
This patch adds the skbuff fraglist splitter. This API provides an
iterator to transform the fraglist into single skbuff objects, it
consists of:
* ip_fraglist_init(), that initializes the internal state of the
fraglist splitter.
* ip_fraglist_prepare(), that restores the IPv4 header on the
fragments.
* ip_fraglist_next(), that retrieves the fragment from the fraglist and
it updates the internal state of the splitter to point to the next
fragment skbuff in the fraglist.
The ip_fraglist_iter object stores the internal state of the iterator.
This code has been extracted from ip_do_fragment(). Symbols are also
exported to allow to reuse this iterator from the bridge codepath to
build its own refragmentation routine by reusing the existing codebase.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Add the ability to add a backup TFO key as:
# echo "x-x-x-x,x-x-x-x" > /proc/sys/net/ipv4/tcp_fastopen_key
The key before the comma acks as the primary TFO key and the key after the
comma is the backup TFO key. This change is intended to be backwards
compatible since if only one key is set, userspace will simply read back
that single key as follows:
# echo "x-x-x-x" > /proc/sys/net/ipv4/tcp_fastopen_key
# cat /proc/sys/net/ipv4/tcp_fastopen_key
x-x-x-x
Signed-off-by: Jason Baron <jbaron@akamai.com>
Signed-off-by: Christoph Paasch <cpaasch@apple.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Add support for get/set of an optional backup key via TCP_FASTOPEN_KEY, in
addition to the current 'primary' key. The primary key is used to encrypt
and decrypt TFO cookies, while the backup is only used to decrypt TFO
cookies. The backup key is used to maximize successful TFO connections when
TFO keys are rotated.
Currently, TCP_FASTOPEN_KEY allows a single 16-byte primary key to be set.
This patch now allows a 32-byte value to be set, where the first 16 bytes
are used as the primary key and the second 16 bytes are used for the backup
key. Similarly, for getsockopt(), we can receive a 32-byte value as output
if requested. If a 16-byte value is used to set the primary key via
TCP_FASTOPEN_KEY, then any previously set backup key will be removed.
Signed-off-by: Jason Baron <jbaron@akamai.com>
Signed-off-by: Christoph Paasch <cpaasch@apple.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
We would like to be able to rotate TFO keys while minimizing the number of
client cookies that are rejected. Currently, we have only one key which can
be used to generate and validate cookies, thus if we simply replace this
key clients can easily have cookies rejected upon rotation.
We propose having the ability to have both a primary key and a backup key.
The primary key is used to generate as well as to validate cookies.
The backup is only used to validate cookies. Thus, keys can be rotated as:
1) generate new key
2) add new key as the backup key
3) swap the primary and backup key, thus setting the new key as the primary
We don't simply set the new key as the primary key and move the old key to
the backup slot because the ip may be behind a load balancer and we further
allow for the fact that all machines behind the load balancer will not be
updated simultaneously.
We make use of this infrastructure in subsequent patches.
Suggested-by: Igor Lubashev <ilubashe@akamai.com>
Signed-off-by: Jason Baron <jbaron@akamai.com>
Signed-off-by: Christoph Paasch <cpaasch@apple.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Restructure __tcp_fastopen_cookie_gen() to take a 'struct crypto_cipher'
argument and rename it as __tcp_fastopen_cookie_gen_cipher(). Subsequent
patches will provide different ciphers based on which key is being used for
the cookie generation.
Signed-off-by: Christoph Paasch <cpaasch@apple.com>
Signed-off-by: Jason Baron <jbaron@akamai.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
The smp_store_release call in fqdir_exit cannot protect the setting
of fqdir->dead as claimed because its memory barrier is only
guaranteed to be one-way and the barrier precedes the setting of
fqdir->dead.
IOW it doesn't provide any barriers between fq->dir and the following
hash table destruction.
In fact, the code is safe anyway because call_rcu does provide both
the memory barrier as well as a guarantee that when the destruction
work starts executing all RCU readers will see the updated value for
fqdir->dead.
Therefore this patch removes the unnecessary smp_store_release call
as well as the corresponding READ_ONCE on the read-side in order to
not confuse future readers of this code. Comments have been added
in their places.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
For DSA switches that do not have an .adjust_link callback, aka those
who transitioned totally to the PHYLINK-compliant API, use PHYLINK to
drive the CPU/DSA ports.
The PHYLIB usage and .adjust_link are kept but deprecated, and users are
asked to transition from it. The reason why we can't do anything for
them is because PHYLINK does not wrap the fixed-link state behind a
phydev object, so we cannot wrap .phylink_mac_config into .adjust_link
unless we fabricate a phy_device structure.
For these ports, the newly introduced PHYLINK_DEV operation type is
used and the dsa_switch device structure is passed to PHYLINK for
printing purposes. The handling of the PHYLINK_NETDEV and PHYLINK_DEV
PHYLINK instances is common from the perspective of the driver.
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
In order to have a common handling of PHYLINK for the slave and non-user
ports, the DSA core glue logic (between PHYLINK and the driver) must use
an API that does not rely on a struct net_device.
These will also be called by the CPU-port-handling code in a further
patch.
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Suggested-by: Vladimir Oltean <olteanv@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
The phylink_config structure will encapsulate a pointer to a struct
device and the operation type requested for this instance of PHYLINK.
This patch does not make any functional changes, it just transitions the
PHYLINK internals and all its users to the new API.
A pointer to a phylink_config structure will be passed to
phylink_create() instead of the net_device directly. Also, the same
phylink_config pointer will be passed back to all phylink_mac_ops
callbacks instead of the net_device. Using this mechanism, a PHYLINK
user can get the original net_device using a structure such as
'to_net_dev(config->dev)' or directly the structure containing the
phylink_config using a container_of call.
At the moment, only the PHYLINK_NETDEV is defined as a valid operation
type for PHYLINK. In this mode, a valid reference to a struct device
linked to the original net_device should be passed to PHYLINK through
the phylink_config structure.
This API changes is mainly driven by the necessity of adding a new
operation type in PHYLINK that disconnects the phy_device from the
net_device and also works when the net_device is lacking.
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Tested-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
ctinfo is a new tc filter action module. It is designed to restore
information contained in firewall conntrack marks to other packet fields
and is typically used on packet ingress paths. At present it has two
independent sub-functions or operating modes, DSCP restoration mode &
skb mark restoration mode.
The DSCP restore mode:
This mode copies DSCP values that have been placed in the firewall
conntrack mark back into the IPv4/v6 diffserv fields of relevant
packets.
The DSCP restoration is intended for use and has been found useful for
restoring ingress classifications based on egress classifications across
links that bleach or otherwise change DSCP, typically home ISP Internet
links. Restoring DSCP on ingress on the WAN link allows qdiscs such as
but by no means limited to CAKE to shape inbound packets according to
policies that are easier to set & mark on egress.
Ingress classification is traditionally a challenging task since
iptables rules haven't yet run and tc filter/eBPF programs are pre-NAT
lookups, hence are unable to see internal IPv4 addresses as used on the
typical home masquerading gateway. Thus marking the connection in some
manner on egress for later restoration of classification on ingress is
easier to implement.
Parameters related to DSCP restore mode:
dscpmask - a 32 bit mask of 6 contiguous bits and indicate bits of the
conntrack mark field contain the DSCP value to be restored.
statemask - a 32 bit mask of (usually) 1 bit length, outside the area
specified by dscpmask. This represents a conditional operation flag
whereby the DSCP is only restored if the flag is set. This is useful to
implement a 'one shot' iptables based classification where the
'complicated' iptables rules are only run once to classify the
connection on initial (egress) packet and subsequent packets are all
marked/restored with the same DSCP. A mask of zero disables the
conditional behaviour ie. the conntrack mark DSCP bits are always
restored to the ip diffserv field (assuming the conntrack entry is found
& the skb is an ipv4/ipv6 type)
e.g. dscpmask 0xfc000000 statemask 0x01000000
|----0xFC----conntrack mark----000000---|
| Bits 31-26 | bit 25 | bit24 |~~~ Bit 0|
| DSCP | unused | flag |unused |
|-----------------------0x01---000000---|
| |
| |
---| Conditional flag
v only restore if set
|-ip diffserv-|
| 6 bits |
|-------------|
The skb mark restore mode (cpmark):
This mode copies the firewall conntrack mark to the skb's mark field.
It is completely the functional equivalent of the existing act_connmark
action with the additional feature of being able to apply a mask to the
restored value.
Parameters related to skb mark restore mode:
mask - a 32 bit mask applied to the firewall conntrack mark to mask out
bits unwanted for restoration. This can be useful where the conntrack
mark is being used for different purposes by different applications. If
not specified and by default the whole mark field is copied (i.e.
default mask of 0xffffffff)
e.g. mask 0x00ffffff to mask out the top 8 bits being used by the
aforementioned DSCP restore mode.
|----0x00----conntrack mark----ffffff---|
| Bits 31-24 | |
| DSCP & flag| some value here |
|---------------------------------------|
|
|
v
|------------skb mark-------------------|
| | |
| zeroed | |
|---------------------------------------|
Overall parameters:
zone - conntrack zone
control - action related control (reclassify | pipe | drop | continue |
ok | goto chain <CHAIN_INDEX>)
Signed-off-by: Kevin Darbyshire-Bryant <ldir@darbyshire-bryant.me.uk>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Allow the creation of nexthop groups which reference other nexthop
objects to create multipath routes:
+--------------+
+------------+ +--------------+ |
| nh nh_grp --->| nh_grp_entry |-+
+------------+ +---------|----+
^ | | +------------+
+----------------+ +--->| nh, weight |
nh_parent +------------+
A group entry points to a nexthop with a weight for that hop within the
group. The nexthop has a list_head, grp_list, for tracking which groups
it is a member of and the group entry has a reference back to the parent.
The grp_list is used when a nexthop is deleted - to efficiently remove
it from groups using it.
If a nexthop group spec is given, no other attributes can be set. Each
nexthop id in a group spec must already exist.
Similar to single nexthops, the specification of a nexthop group can be
updated so that data is managed with rcu locking.
Add path selection function to account for multiple paths and add
ipv{4,6}_good_nh helpers to know that if a neighbor entry exists it is
in a good state.
Update NETDEV event handling to rebalance multipath nexthop groups if
a nexthop is deleted due to a link event (down or unregister).
When a nexthop is removed any groups using it are updated. Groups using a
nexthop a tracked via a grp_list.
Nexthop dumps can be limited to groups only by adding NHA_GROUPS to the
request.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Add support for NHA_ENCAP and NHA_ENCAP_TYPE. Leverages the existing code
for lwtunnel within fib_nh_common, so the only change needed is handling
the attributes in the nexthop code.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Handle IPv6 gateway in a nexthop spec. If nh_family is set to AF_INET6,
NHA_GATEWAY is expected to be an IPv6 address. Add ipv6 option to gw in
nh_config to hold the address, add fib6_nh to nh_info to leverage the
ipv6 initialization and cleanup code. Update nh_fill_node to dump the v6
address.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Add support for IPv4 nexthops. If nh_family is set to AF_INET, then
NHA_GATEWAY is expected to be an IPv4 address.
Register for netdev events to be notified of admin up/down changes as
well as deletes. A hash table is used to track nexthop per devices to
quickly convert device events to the affected nexthops.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Barebones start point for nexthops. Implementation for RTM commands,
notifications, management of rbtree for holding nexthops by id, and
kernel side data structures for nexthops and nexthop config.
Nexthops are maintained in an rbtree sorted by id. Similar to routes,
nexthops are configured per namespace using netns_nexthop struct added
to struct net.
Nexthop notifications are sent when a nexthop is added or deleted,
but NOT if the delete is due to a device event or network namespace
teardown (which also involves device events). Applications are
expected to use the device down event to flush nexthops and any
routes used by the nexthops.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
As caught by syzbot [1], the rcu grace period that is respected
before fqdir_rwork_fn() proceeds and frees fqdir is not enough
to prevent inet_frag_destroy_rcu() being run after the freeing.
We need a proper rcu_barrier() synchronization to replace
the one we had in inet_frags_fini()
We also have to fix a potential problem at module removal :
inet_frags_fini() needs to make sure that all queued work queues
(fqdir_rwork_fn) have completed, otherwise we might
call kmem_cache_destroy() too soon and get another use-after-free.
[1]
BUG: KASAN: use-after-free in inet_frag_destroy_rcu+0xd9/0xe0 net/ipv4/inet_fragment.c:201
Read of size 8 at addr ffff88806ed47a18 by task swapper/1/0
CPU: 1 PID: 0 Comm: swapper/1 Not tainted 5.2.0-rc1+ #2
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
<IRQ>
__dump_stack lib/dump_stack.c:77 [inline]
dump_stack+0x172/0x1f0 lib/dump_stack.c:113
print_address_description.cold+0x7c/0x20d mm/kasan/report.c:188
__kasan_report.cold+0x1b/0x40 mm/kasan/report.c:317
kasan_report+0x12/0x20 mm/kasan/common.c:614
__asan_report_load8_noabort+0x14/0x20 mm/kasan/generic_report.c:132
inet_frag_destroy_rcu+0xd9/0xe0 net/ipv4/inet_fragment.c:201
__rcu_reclaim kernel/rcu/rcu.h:222 [inline]
rcu_do_batch kernel/rcu/tree.c:2092 [inline]
invoke_rcu_callbacks kernel/rcu/tree.c:2310 [inline]
rcu_core+0xba5/0x1500 kernel/rcu/tree.c:2291
__do_softirq+0x25c/0x94c kernel/softirq.c:293
invoke_softirq kernel/softirq.c:374 [inline]
irq_exit+0x180/0x1d0 kernel/softirq.c:414
exiting_irq arch/x86/include/asm/apic.h:536 [inline]
smp_apic_timer_interrupt+0x13b/0x550 arch/x86/kernel/apic/apic.c:1068
apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:806
</IRQ>
RIP: 0010:native_safe_halt+0xe/0x10 arch/x86/include/asm/irqflags.h:61
Code: ff ff 48 89 df e8 f2 95 8c fa eb 82 e9 07 00 00 00 0f 00 2d e4 45 4b 00 f4 c3 66 90 e9 07 00 00 00 0f 00 2d d4 45 4b 00 fb f4 <c3> 90 55 48 89 e5 41 57 41 56 41 55 41 54 53 e8 8e 18 42 fa e8 99
RSP: 0018:ffff8880a98e7d78 EFLAGS: 00000282 ORIG_RAX: ffffffffffffff13
RAX: 1ffffffff1164e11 RBX: ffff8880a98d4340 RCX: 0000000000000000
RDX: dffffc0000000000 RSI: 0000000000000006 RDI: ffff8880a98d4bbc
RBP: ffff8880a98e7da8 R08: ffff8880a98d4340 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000001
R13: ffffffff88b27078 R14: 0000000000000001 R15: 0000000000000000
arch_cpu_idle+0xa/0x10 arch/x86/kernel/process.c:571
default_idle_call+0x36/0x90 kernel/sched/idle.c:94
cpuidle_idle_call kernel/sched/idle.c:154 [inline]
do_idle+0x377/0x560 kernel/sched/idle.c:263
cpu_startup_entry+0x1b/0x20 kernel/sched/idle.c:354
start_secondary+0x34e/0x4c0 arch/x86/kernel/smpboot.c:267
secondary_startup_64+0xa4/0xb0 arch/x86/kernel/head_64.S:243
Allocated by task 8877:
save_stack+0x23/0x90 mm/kasan/common.c:71
set_track mm/kasan/common.c:79 [inline]
__kasan_kmalloc mm/kasan/common.c:489 [inline]
__kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:462
kasan_kmalloc+0x9/0x10 mm/kasan/common.c:503
kmem_cache_alloc_trace+0x151/0x750 mm/slab.c:3555
kmalloc include/linux/slab.h:547 [inline]
kzalloc include/linux/slab.h:742 [inline]
fqdir_init include/net/inet_frag.h:115 [inline]
ipv6_frags_init_net+0x48/0x460 net/ipv6/reassembly.c:513
ops_init+0xb3/0x410 net/core/net_namespace.c:130
setup_net+0x2d3/0x740 net/core/net_namespace.c:316
copy_net_ns+0x1df/0x340 net/core/net_namespace.c:439
create_new_namespaces+0x400/0x7b0 kernel/nsproxy.c:107
unshare_nsproxy_namespaces+0xc2/0x200 kernel/nsproxy.c:206
ksys_unshare+0x440/0x980 kernel/fork.c:2692
__do_sys_unshare kernel/fork.c:2760 [inline]
__se_sys_unshare kernel/fork.c:2758 [inline]
__x64_sys_unshare+0x31/0x40 kernel/fork.c:2758
do_syscall_64+0xfd/0x680 arch/x86/entry/common.c:301
entry_SYSCALL_64_after_hwframe+0x49/0xbe
Freed by task 17:
save_stack+0x23/0x90 mm/kasan/common.c:71
set_track mm/kasan/common.c:79 [inline]
__kasan_slab_free+0x102/0x150 mm/kasan/common.c:451
kasan_slab_free+0xe/0x10 mm/kasan/common.c:459
__cache_free mm/slab.c:3432 [inline]
kfree+0xcf/0x220 mm/slab.c:3755
fqdir_rwork_fn+0x33/0x40 net/ipv4/inet_fragment.c:154
process_one_work+0x989/0x1790 kernel/workqueue.c:2269
worker_thread+0x98/0xe40 kernel/workqueue.c:2415
kthread+0x354/0x420 kernel/kthread.c:255
ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:352
The buggy address belongs to the object at ffff88806ed47a00
which belongs to the cache kmalloc-512 of size 512
The buggy address is located 24 bytes inside of
512-byte region [ffff88806ed47a00, ffff88806ed47c00)
The buggy address belongs to the page:
page:ffffea0001bb51c0 refcount:1 mapcount:0 mapping:ffff8880aa400940 index:0x0
flags: 0x1fffc0000000200(slab)
raw: 01fffc0000000200 ffffea000282a788 ffffea0001bb53c8 ffff8880aa400940
raw: 0000000000000000 ffff88806ed47000 0000000100000006 0000000000000000
page dumped because: kasan: bad access detected
Memory state around the buggy address:
ffff88806ed47900: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
ffff88806ed47980: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
>ffff88806ed47a00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
^
ffff88806ed47a80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
ffff88806ed47b00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
Fixes: 3c8fc8782044 ("inet: frags: rework rhashtable dismantle")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Both IPv6 and 6lowpan are calling inet_frags_fini() too soon.
inet_frags_fini() is dismantling a kmem_cache, that might be needed
later when unregister_pernet_subsys() eventually has to remove
frags queues from hash tables and free them.
This fixes potential use-after-free, and is a prereq for the following patch.
Fixes: d4ad4d22e7ac ("inet: frags: use kmem_cache for inet_frag_queue")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
fqdir_init() is not fast path and is getting bigger.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
The pointer n is being assigned a value however this value is
never read in the code block and the end of the code block
continues to the next loop iteration. Clean up the code by
removing the redundant assignment.
Fixes: 1bff1a0c9bbda ("ipv4: Add function to send route updates")
Addresses-Coverity: ("Unused value")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
syszbot found an interesting use-after-free [1] happening
while IPv4 fragment rhashtable was destroyed at netns dismantle.
While no insertions can possibly happen at the time a dismantling
netns is destroying this rhashtable, timers can still fire and
attempt to remove elements from this rhashtable.
This is forbidden, since rhashtable_free_and_destroy() has
no synchronization against concurrent inserts and deletes.
Add a new fqdir->dead flag so that timers do not attempt
a rhashtable_remove_fast() operation.
We also have to respect an RCU grace period before starting
the rhashtable_free_and_destroy() from process context,
thus we use rcu_work infrastructure.
This is a refinement of a prior rough attempt to fix this bug :
https://marc.info/?l=linux-netdev&m=153845936820900&w=2
Since the rhashtable cleanup is now deferred to a work queue,
netns dismantles should be slightly faster.
[1]
BUG: KASAN: use-after-free in __read_once_size include/linux/compiler.h:194 [inline]
BUG: KASAN: use-after-free in rhashtable_last_table+0x162/0x180 lib/rhashtable.c:212
Read of size 8 at addr ffff8880a6497b70 by task kworker/0:0/5
CPU: 0 PID: 5 Comm: kworker/0:0 Not tainted 5.2.0-rc1+ #2
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Workqueue: events rht_deferred_worker
Call Trace:
__dump_stack lib/dump_stack.c:77 [inline]
dump_stack+0x172/0x1f0 lib/dump_stack.c:113
print_address_description.cold+0x7c/0x20d mm/kasan/report.c:188
__kasan_report.cold+0x1b/0x40 mm/kasan/report.c:317
kasan_report+0x12/0x20 mm/kasan/common.c:614
__asan_report_load8_noabort+0x14/0x20 mm/kasan/generic_report.c:132
__read_once_size include/linux/compiler.h:194 [inline]
rhashtable_last_table+0x162/0x180 lib/rhashtable.c:212
rht_deferred_worker+0x111/0x2030 lib/rhashtable.c:411
process_one_work+0x989/0x1790 kernel/workqueue.c:2269
worker_thread+0x98/0xe40 kernel/workqueue.c:2415
kthread+0x354/0x420 kernel/kthread.c:255
ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:352
Allocated by task 32687:
save_stack+0x23/0x90 mm/kasan/common.c:71
set_track mm/kasan/common.c:79 [inline]
__kasan_kmalloc mm/kasan/common.c:489 [inline]
__kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:462
kasan_kmalloc+0x9/0x10 mm/kasan/common.c:503
__do_kmalloc_node mm/slab.c:3620 [inline]
__kmalloc_node+0x4e/0x70 mm/slab.c:3627
kmalloc_node include/linux/slab.h:590 [inline]
kvmalloc_node+0x68/0x100 mm/util.c:431
kvmalloc include/linux/mm.h:637 [inline]
kvzalloc include/linux/mm.h:645 [inline]
bucket_table_alloc+0x90/0x480 lib/rhashtable.c:178
rhashtable_init+0x3f4/0x7b0 lib/rhashtable.c:1057
inet_frags_init_net include/net/inet_frag.h:109 [inline]
ipv4_frags_init_net+0x182/0x410 net/ipv4/ip_fragment.c:683
ops_init+0xb3/0x410 net/core/net_namespace.c:130
setup_net+0x2d3/0x740 net/core/net_namespace.c:316
copy_net_ns+0x1df/0x340 net/core/net_namespace.c:439
create_new_namespaces+0x400/0x7b0 kernel/nsproxy.c:107
unshare_nsproxy_namespaces+0xc2/0x200 kernel/nsproxy.c:206
ksys_unshare+0x440/0x980 kernel/fork.c:2692
__do_sys_unshare kernel/fork.c:2760 [inline]
__se_sys_unshare kernel/fork.c:2758 [inline]
__x64_sys_unshare+0x31/0x40 kernel/fork.c:2758
do_syscall_64+0xfd/0x680 arch/x86/entry/common.c:301
entry_SYSCALL_64_after_hwframe+0x49/0xbe
Freed by task 7:
save_stack+0x23/0x90 mm/kasan/common.c:71
set_track mm/kasan/common.c:79 [inline]
__kasan_slab_free+0x102/0x150 mm/kasan/common.c:451
kasan_slab_free+0xe/0x10 mm/kasan/common.c:459
__cache_free mm/slab.c:3432 [inline]
kfree+0xcf/0x220 mm/slab.c:3755
kvfree+0x61/0x70 mm/util.c:460
bucket_table_free+0x69/0x150 lib/rhashtable.c:108
rhashtable_free_and_destroy+0x165/0x8b0 lib/rhashtable.c:1155
inet_frags_exit_net+0x3d/0x50 net/ipv4/inet_fragment.c:152
ipv4_frags_exit_net+0x73/0x90 net/ipv4/ip_fragment.c:695
ops_exit_list.isra.0+0xaa/0x150 net/core/net_namespace.c:154
cleanup_net+0x3fb/0x960 net/core/net_namespace.c:553
process_one_work+0x989/0x1790 kernel/workqueue.c:2269
worker_thread+0x98/0xe40 kernel/workqueue.c:2415
kthread+0x354/0x420 kernel/kthread.c:255
ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:352
The buggy address belongs to the object at ffff8880a6497b40
which belongs to the cache kmalloc-1k of size 1024
The buggy address is located 48 bytes inside of
1024-byte region [ffff8880a6497b40, ffff8880a6497f40)
The buggy address belongs to the page:
page:ffffea0002992580 refcount:1 mapcount:0 mapping:ffff8880aa400ac0 index:0xffff8880a64964c0 compound_mapcount: 0
flags: 0x1fffc0000010200(slab|head)
raw: 01fffc0000010200 ffffea0002916e88 ffffea000218fe08 ffff8880aa400ac0
raw: ffff8880a64964c0 ffff8880a6496040 0000000100000005 0000000000000000
page dumped because: kasan: bad access detected
Memory state around the buggy address:
ffff8880a6497a00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
ffff8880a6497a80: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
>ffff8880a6497b00: fc fc fc fc fc fc fc fc fb fb fb fb fb fb fb fb
^
ffff8880a6497b80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
ffff8880a6497c00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
Fixes: 648700f76b03 ("inet: frags: use rhashtables for reassembly units")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Following patch will add rcu grace period before fqdir
rhashtable destruction, so we need to dynamically allocate
fqdir structures to not force expensive synchronize_rcu() calls
in netns dismantle path.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
fqdir will soon be dynamically allocated.
We need to reach the struct net pointer from fqdir,
so add it, and replace the various container_of() constructs
by direct access to the new field.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
And pass an extra parameter, since we will soon
dynamically allocate fqdir structures.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
(struct net *)->ieee802154_lowpan.fqdir will soon be a pointer, so make
sure lowpan_frags_ns_ctl_table[] does not reference init_net.
lowpan_frags_ns_sysctl_register() can perform the needed initialization
for all netns.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
nf_ct_frag6_sysctl_table
(struct net *)->nf_frag.fqdir will soon be a pointer, so make
sure nf_ct_frag6_sysctl_table[] does not reference init_net.
nf_ct_frag6_sysctl_register() can perform the needed initialization
for all netns.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|