When a networking device is taken down that has a non-trivial number
of VLAN devices configured under it, we eat a full synchronize_net()
for every such VLAN device.
This is because of the call chain:
NETDEV_DOWN notifier
--> vlan_device_event()
--> dev_change_flags()
--> __dev_change_flags()
--> __dev_close()
--> __dev_close_many()
--> dev_deactivate_many()
--> synchronize_net()
This is kind of rediculous because we already have infrastructure for
batching doing operation X to a list of net devices so that we only
incur one sync.
So make use of that by exporting dev_close_many() and adjusting it's
interfaace so that the caller can fully manage the batch list. Use
this in vlan_device_event() and all the overhead goes away.
Reported-by: Salam Noureddine <noureddine@arista.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
On a large hash table, we can easily spend seconds to
walk over all entries. Add a cond_resched() to yield
cpu if necessary.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Similar to port id allow netdevices to specify port names and export
the name via sysfs. Drivers can implement the netdevice operation to
assist udev in having sane default names for the devices using the
rule:
$ cat /etc/udev/rules.d/80-net-setup-link.rules
SUBSYSTEM=="net", ACTION=="add", ATTR{phys_port_name}!="",
NAME="$attr{phys_port_name}"
Use of phys_name versus phys_id was suggested-by Jiri Pirko.
Signed-off-by: David Ahern <dsahern@gmail.com>
Acked-by: Jiri Pirko <jiri@resnulli.us>
Acked-by: Scott Feldman <sfeldma@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
in favor of their inner __ ones, which doesn't grab rtnl.
As these functions need to operate on a locked socket, we can't be
grabbing rtnl by then. It's too late and doing so causes reversed
locking.
So this patch:
- move rtnl handling to callers instead while already fixing some
reversed locking situations, like on vxlan and ipvs code.
- renames __ ones to not have the __ mark:
__ip_mc_{join,leave}_group -> ip_mc_{join,leave}_group
__ipv6_sock_mc_{join,drop} -> ipv6_sock_mc_{join,drop}
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
There are some setsockopt operations in ipv4 and ipv6 that are grabbing
rtnl after having grabbed the socket lock. Yet this makes it impossible
to do operations that have to lock the socket when already within a rtnl
protected scope, like ndo dev_open and dev_stop.
We normally take coarse grained locks first but setsockopt inverted that.
So this patch invert the lock logic for these operations and makes
setsockopt grab rtnl if it will be needed prior to grabbing socket lock.
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
In order to be able to use sk_ehashfn() for request socks,
we need to initialize their IPv6/IPv4 addresses.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We now always call __inet_hash_nolisten(), no need to pass it
as an argument.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We can now use inet_hash() and __inet_hash() instead of private
functions.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Intent is to converge IPv4 & IPv6 inet_hash functions to
factorize code.
IPv4 sockets initialize sk_rcv_saddr and sk_v6_daddr
in this patch, thanks to new sk_daddr_set() and sk_rcv_saddr_set()
helpers.
__inet6_hash can now use sk_ehashfn() instead of a private
inet6_sk_ehashfn() and will simply use __inet_hash() in a
following patch.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Goal is to unify IPv4/IPv6 inet_hash handling, and use common helpers
for all kind of sockets (full sockets, timewait and request sockets)
inet_sk_ehashfn() becomes sk_ehashfn() but still only copes with IPv4
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
const qualifiers ease code review by making clear
which objects are not written in a function.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This adds a tx_maxrate attribute to the tx queue sysfs entry allowing
for max-rate limiting. Along with DCB-ETS and BQL this provides another
knob to tune queue performance. The limit units are Mbps.
By default it is disabled. To disable the rate limitation after it
has been set for a queue, it should be set to zero.
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch converts tipc to use rhashtable max/min_size instead of
the obsolete max/min_shift.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch converts netlink to use rhashtable max_size instead
of the obsolete max_shift.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
The TIPC topology server is a per namespace service associated with the
tipc name {1, 1}. When a namespace is deleted, that name must be withdrawn
before we call sk_release_kernel because the kernel socket release is
done in init_net and trying to withdraw a TIPC name published in another
namespace will fail with an error as:
[ 170.093264] Unable to remove local publication
[ 170.093264] (type=1, lower=1, ref=2184244004, key=2184244005)
We fix this by breaking the association between the topology server name
and socket before calling sk_release_kernel.
Signed-off-by: Ying Xue <ying.xue@windriver.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When the TIPC module is loaded, we launch a topology server in kernel
space, which in its turn is creating TIPC sockets for communication
with topology server users. Because both the socket's creator and
provider reside in the same module, it is necessary that the TIPC
module's reference count remains zero after the server is started and
the socket created; otherwise it becomes impossible to perform "rmmod"
even on an idle module.
Currently, we achieve this by defining a separate "tipc_proto_kern"
protocol struct, that is used only for kernel space socket allocations.
This structure has the "owner" field set to NULL, which restricts the
module reference count from being be bumped when sk_alloc() for local
sockets is called. Furthermore, we have defined three kernel-specific
functions, tipc_sock_create_local(), tipc_sock_release_local() and
tipc_sock_accept_local(), to avoid the module counter being modified
when module local sockets are created or deleted. This has worked well
until we introduced name space support.
However, after name space support was introduced, we have observed that
a reference count leak occurs, because the netns counter is not
decremented in tipc_sock_delete_local().
This commit remedies this problem. But instead of just modifying
tipc_sock_delete_local(), we eliminate the whole parallel socket
handling infrastructure, and start using the regular sk_create_kern(),
kernel_accept() and sk_release_kernel() calls. Since those functions
manipulate the module counter, we must now compensate for that by
explicitly decrementing the counter after module local sockets are
created, and increment it just before calling sk_release_kernel().
Fixes: a62fbccecd ("tipc: make subscriber server support net namespace")
Signed-off-by: Ying Xue <ying.xue@windriver.com>
Reviewed-by: Jon Maloy <jon.maloy@ericson.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reported-by: Cong Wang <cwang@twopensource.com>
Tested-by: Erik Hugne <erik.hugne@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
While testing last patch series, I found req sock refcounting was wrong.
We must set skc_refcnt to 1 for all request socks added in hashes,
but also on request sockets created by FastOpen or syncookies.
It is tricky because we need to defer this initialization so that
future RCU lookups do not try to take a refcount on a not yet
fully initialized request socket.
Also get rid of ireq_refcnt alias.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Fixes: 13854e5a60 ("inet: add proper refcounting to request sock")
Signed-off-by: David S. Miller <davem@davemloft.net>
It is not because a TCP listener is FastOpen ready that
all incoming sockets actually used FastOpen.
Avoid taking queue->fastopenq->lock if not needed.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The listener field in struct tcp_request_sock is a pointer
back to the listener. We now have req->rsk_listener, so TCP
only needs one boolean and not a full pointer.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Once we'll be able to lookup request sockets in ehash table,
we'll need to get access to listener which created this request.
This avoid doing a lookup to find the listener, which benefits
for a more solid SO_REUSEPORT, and is needed once we no
longer queue request sock into a listener private queue.
Note that 'struct tcp_request_sock'->listener could be reduced
to a single bit, as TFO listener should match req->rsk_listener.
TFO will no longer need to hold a reference on the listener.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
inet_reqsk_alloc() is becoming fat and should not be inlined.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
listener socket can be used to set net pointer, and will
be later used to hold a reference on listener.
Add a const qualifier to first argument (struct request_sock_ops *),
and factorize all write_pnet(&ireq->ireq_net, sock_net(sk));
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
tcp_oow_rate_limited() is hardly used in fast path, there is
no point inlining it.
Signed-of-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This big helper is called once from tcp_conn_request(), there is no
point having it in an include. Compiler will inline it anyway.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
TCP request socks soon will be visible in ehash table.
xt_socket will be able to match them, but first we need
to make sure to not consider them as full sockets.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
TCP request socks soon will be visible in ehash table.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Upcoming request sockets have TCP_NEW_SYN_RECV state and should
be special cased a bit like TCP_TIME_WAIT sockets.
Signed-off-by; Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
as a follow on to patch 70006af955 ("bpf: allow eBPF access skb fields")
this patch allows 'protocol' and 'vlan_tci' fields to be accessible
from extended BPF programs.
The usage of 'protocol', 'vlan_present' and 'vlan_tci' fields is the same as
corresponding SKF_AD_PROTOCOL, SKF_AD_VLAN_TAG_PRESENT and SKF_AD_VLAN_TAG
accesses in classic BPF.
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Changes in tcp_metric hash table are protected by tcp_metrics_lock
only, not by genl_mutex
While we are at it use deref_locked() instead of rcu_dereference()
in tcp_new() to avoid unnecessary barrier, as we hold tcp_metrics_lock
as well.
Reported-by: Andrew Vagin <avagin@parallels.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Fixes: 098a697b49 ("tcp_metrics: Use a single hash table for all network namespaces.")
Reviewed-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This would fix randconfig compile error:
net/built-in.o: In function `netdev_switch_fib_ipv4_abort':
(.text+0xf7811): undefined reference to `fib_flush_external'
Also it fixes following warnings:
warning: (NET_DSA) selects NET_SWITCHDEV which has unmet direct dependencies (NET && INET)
warning: (NET_DSA_MV88E6060 && NET_DSA_MV88E6131 && NET_DSA_MV88E6123_61_65 && NET_DSA_MV88E6171 && NET_DSA_MV88E6352 && NET_DSA_BCM_SF2) selects NET_DSA which has unmet direct dependencies (NET && HAVE_NET_DSA && NET_SWITCHDEV)
Reported-by: Randy Dunlap <rdunlap@infradead.org>
Suggested-by: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
Creating a kernel socket with sock_create_kern() happens in "init_net"
namespace, however, releasing it with sk_release_kernel() occurs in
the current namespace which may be different with "init_net" namespace.
Therefore, we should guarantee that the namespace in which a kernel
socket is created is same as the socket is created.
Signed-off-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
reqsk_put() is the generic function that should be used
to release a refcount (and automatically call reqsk_free())
reqsk_free() might be called if refcount is known to be 0
or undefined.
refcnt is set to one in inet_csk_reqsk_queue_add()
As request socks are not yet in global ehash table,
I added temporary debugging checks in reqsk_put() and reqsk_free()
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
sock_edemux() is not used in fast path, and should
really call sock_gen_put() to save some code.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
inet_diag_fill_req() is renamed to inet_req_diag_fill()
and moved up, so that it can be called fom sk_diag_fill()
inet_diag_bc_sk() is ready to handle request socks.
inet_twsk_diag_dump() is no longer needed.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When a request socket is created, we do not cache ip route
dst entry, like for timewait sockets.
Let's use sk_fullsock() helper.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Move swdev wrappers over to new swdev ops (from previous ndo ops). No
functional changes to the implementation.
Signed-off-by: Scott Feldman <sfeldma@gmail.com>
rocker: move to new swdev ops
Signed-off-by: Scott Feldman <sfeldma@gmail.com>
dsa: move to new swdev ops
Signed-off-by: Scott Feldman <sfeldma@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
introduce user accessible mirror of in-kernel 'struct sk_buff':
struct __sk_buff {
__u32 len;
__u32 pkt_type;
__u32 mark;
__u32 queue_mapping;
};
bpf programs can do:
int bpf_prog(struct __sk_buff *skb)
{
__u32 var = skb->pkt_type;
which will be compiled to bpf assembler as:
dst_reg = *(u32 *)(src_reg + 4) // 4 == offsetof(struct __sk_buff, pkt_type)
bpf verifier will check validity of access and will convert it to:
dst_reg = *(u8 *)(src_reg + offsetof(struct sk_buff, __pkt_type_offset))
dst_reg &= 7
since skb->pkt_type is a bitfield.
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds the possibility to obtain raw_smp_processor_id() in
eBPF. Currently, this is only possible in classic BPF where commit
da2033c282 ("filter: add SKF_AD_RXHASH and SKF_AD_CPU") has added
facilities for this.
Perhaps most importantly, this would also allow us to track per CPU
statistics with eBPF maps, or to implement a poor-man's per CPU data
structure through eBPF maps.
Example function proto-type looks like:
u32 (*smp_processor_id)(void) = (void *)BPF_FUNC_get_smp_processor_id;
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
This work is similar to commit 4cd3675ebf ("filter: added BPF
random opcode") and adds a possibility for packet sampling in eBPF.
Currently, this is only possible in classic BPF and useful to
combine sampling with f.e. packet sockets, possible also with tc.
Example function proto-type looks like:
u32 (*prandom_u32)(void) = (void *)BPF_FUNC_get_prandom_u32;
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit cd28a1a9ba ("net: dsa: fully divert PHY reads/writes if
requested") introduced a check for particular PHYs that need to be
accessed using the slave MII bus created by DSA, but this check was too
inclusive. This would prevent fixed PHYs from being successfully
registered because those should not go through the slave MII bus created
by DSA.
Make sure we check that the PHY is not a fixed PHY to prevent that from
happening.
Fixes: cd28a1a9ba ("net: dsa: fully divert PHY reads/writes if requested")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Now the three type of sockets share a common base, we can factorize
code in inet_diag_msg_common_fill().
inet_diag_entry no longer requires saddr_storage & daddr_storage
and the extra copies.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
inet_sk_diag_fill() only copes with non timewait and non request socks
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Once request socks will be in ehash table, they will need to have
a valid ir_iff field.
This is currently true only for IPv6. This patch extends support
for IPv4 as well.
This means inet_diag_fill_req() can now properly use ir_iif,
which is better for IPv6 link locals anyway, as request sockets
and established sockets will propagate consistent netlink idiag_if.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Messages transferred by TIPC are assigned an "importance priority", -an
integer value indicating how to treat the message when there is link or
destination socket congestion.
There is no separate header field for this value. Instead, the message
user values have been chosen in ascending order according to perceived
importance, so that the message user field can be used for this.
This is not a good solution. First, we have many more users than the
needed priority levels, so we end up with treating more priority
levels than necessary. Second, the user field cannot always
accurately reflect the priority of the message. E.g., a message
fragment packet should really have the priority of the enveloped
user data message, and not the priority of the MSG_FRAGMENTER user.
Until now, we have been working around this problem in different ways,
but it is now time to implement a consistent way of handling such
priorities, although still within the constraint that we cannot
allocate any more bits in the regular data message header for this.
In this commit, we define a new priority level, TIPC_SYSTEM_IMPORTANCE,
that will be the only one used apart from the four (lower) user data
levels. All non-data messages map down to this priority. Furthermore,
we take some free bits from the MSG_FRAGMENTER header and allocate
them to store the priority of the enveloped message. We then adjust
the functions msg_importance()/msg_set_importance() so that they
read/set the correct header fields depending on user type.
This small protocol change is fully compatible, because the code at
the receiving end of a link currently reads the importance level
only from user data messages, where there is no change.
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
struct tipc_link contains one single queue for outgoing packets,
where both transmitted and waiting packets are queued.
This infrastructure is hard to maintain, because we need
to keep a number of fields to keep track of which packets are
sent or unsent, and the number of packets in each category.
A lot of code becomes simpler if we split this queue into a transmission
queue, where sent/unacknowledged packets are kept, and a backlog queue,
where we keep the not yet sent packets.
In this commit we do this separation.
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The unicast packet header contains a broadcast acknowledge sequence
number, that may need to be conveyed to the broadcast link for proper
treatment. Currently, the function tipc_rcv(), which is on the most
critical data path, calls the function tipc_bclink_acknowledge() to
have this done. This call is made for each received packet, and results
in the unconditional grabbing of the broadcast link spinlock.
This is unnecessary, since we can see directly from tipc_rcv() if
the acknowledged number differs from what has been previously acked
from the node in question. In the vast majority of cases the numbers
won't differ, and there is nothing to update.
We now make the call to tipc_bclink_acknowledge() conditional
to that the two ack values differ.
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When we currently extract a bundled buffer from a message bundle in
the function tipc_msg_extract(), we allocate a new buffer and explicitly
copy the linear data area.
This is unnecessary, since we can just clone the buffer and do
skb_pull() on the clone to move the data pointer to the correct
position.
This is what we do in this commit.
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently, TIPC linearizes all incoming buffers directly at reception
before passing them upwards in the stack. This is clearly a waste of
CPU resources, and must be avoided.
In this commit, we eliminate this unnecessary linearization. We still
ensure that at least the message header is linear, and that the buffer
is linearized where this is still needed, i.e. when unbundling and when
reversing messages.
In addition, we ensure that fragmented messages are validated after
reassembly before delivering them upwards in the stack.
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The function link_buf_validate() is in reality re-entrant and context
independent, and will in later commits be called from several locations.
Therefore, we move it to msg.c, make it outline and rename the it to
tipc_msg_validate().
We also redesign the function to make proper use of pskb_may_pull()
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
