tcp_v4_err() can restrict lookups to ehash table, and not to listeners.
Note this patch creates the infrastructure, but this means that ICMP
messages for request sockets are ignored until complete conversion.
New tcp_req_err() helper is exported so that we can use it in IPv6
in following patch.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is a low hanging fruit, as we'll get rid of syn_wait_lock eventually.
We hold syn_wait_lock for such small sections, that it makes no sense to use
a read/write lock. A spin lock is simply faster.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
listener can be source of false sharing. request sock has some
useful information like : ireq->ir_iif, ireq->ir_num, ireq->ireq_net
This patch does not solve the major problem of having to read
sk->sk_protocol which is sharing a cache line with sk->sk_wmem_alloc.
(This same field is read later in ip_build_and_send_pkt())
One idea would be to move sk_protocol close to sk_family
(using 8 bits instead of 16 for sk_family seems enough)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
It is not needed, and req->sk_listener points to the listener anyway.
request_sock argument can be const.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Cache listen_sock_qlen() to limit false sharing, and read
rskq_defer_accept once as it might change under us.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pablo Neira Ayuso says:
====================
Netfilter fixes for net
The following patchset contains Netfilter fixes for your net tree,
they are:
1) Fix missing initialization of tuple structure in nfnetlink_cthelper
to avoid mismatches when looking up to attach userspace helpers to
flows, from Ian Wilson.
2) Fix potential crash in nft_hash when we hit -EAGAIN in
nft_hash_walk(), from Herbert Xu.
3) We don't need to indicate the hook information to update the
basechain default policy in nf_tables.
4) Restore tracing over nfnetlink_log due to recent rework to
accomodate logging infrastructure into nf_tables.
5) Fix wrong IP6T_INV_PROTO check in xt_TPROXY.
6) Set IP6T_F_PROTO flag in nft_compat so we can use SYNPROXY6 and
REJECT6 from xt over nftables.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
The br_netfilter frag output function calls skb_cow_head() so in
case it needs a larger headroom to e.g. re-add a previously stripped PPPOE
or VLAN header things will still work (at cost of reallocation).
We can then move nf_bridge_encap_header_len to br_netfilter.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
This reverts commit ca10b9e9a8.
No longer needed after commit eb8895debe
("tcp: tcp_make_synack() should use sock_wmalloc")
When under SYNFLOOD, we build lot of SYNACK and hit false sharing
because of multiple modifications done on sk_listener->sk_wmem_alloc
Since tcp_make_synack() uses sock_wmalloc(), there is no need
to call skb_set_owner_w() again, as this adds two atomic operations.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts:
drivers/net/ethernet/emulex/benet/be_main.c
net/core/sysctl_net_core.c
net/ipv4/inet_diag.c
The be_main.c conflict resolution was really tricky. The conflict
hunks generated by GIT were very unhelpful, to say the least. It
split functions in half and moved them around, when the real actual
conflict only existed solely inside of one function, that being
be_map_pci_bars().
So instead, to resolve this, I checked out be_main.c from the top
of net-next, then I applied the be_main.c changes from 'net' since
the last time I merged. And this worked beautifully.
The inet_diag.c and sysctl_net_core.c conflicts were simple
overlapping changes, and were easily to resolve.
Signed-off-by: David S. Miller <davem@davemloft.net>
tcp_send_fin() does not account for the memory it allocates properly, so
sk_forward_alloc can be negative in cases where we've sent a FIN:
ss example output (ss -amn | grep -B1 f4294):
tcp FIN-WAIT-1 0 1 192.168.0.1:45520 192.0.2.1:8080
skmem:(r0,rb87380,t0,tb87380,f4294966016,w1280,o0,bl0)
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
One of the major issue for TCP is the SYNACK rtx handling,
done by inet_csk_reqsk_queue_prune(), fired by the keepalive
timer of a TCP_LISTEN socket.
This function runs for awful long times, with socket lock held,
meaning that other cpus needing this lock have to spin for hundred of ms.
SYNACK are sent in huge bursts, likely to cause severe drops anyway.
This model was OK 15 years ago when memory was very tight.
We now can afford to have a timer per request sock.
Timer invocations no longer need to lock the listener,
and can be run from all cpus in parallel.
With following patch increasing somaxconn width to 32 bits,
I tested a listener with more than 4 million active request sockets,
and a steady SYNFLOOD of ~200,000 SYN per second.
Host was sending ~830,000 SYNACK per second.
This is ~100 times more what we could achieve before this patch.
Later, we will get rid of the listener hash and use ehash instead.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When request sock are put in ehash table, the whole notion
of having a previous request to update dl_next is pointless.
Also, following patch will get rid of big purge timer,
so we want to delete a request sock without holding listener lock.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since fab4085 ("netfilter: log: nf_log_packet() as real unified
interface"), the loginfo structure that is passed to nf_log_packet() is
used to explicitly indicate the logger type you want to use.
This is a problem for people tracing rules through nfnetlink_log since
packets are always routed to the NF_LOG_TYPE logger after the
aforementioned patch.
We can fix this by removing the trace loginfo structures, but that still
changes the log level from 4 to 5 for tracing messages and there may be
someone relying on this outthere. So let's just introduce a new
nf_log_trace() function that restores the former behaviour.
Reported-by: Markus Kötter <koetter@rrzn.uni-hannover.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
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>
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>
The seq_printf/seq_puts/seq_putc return values, because they
are frequently misused, will eventually be converted to void.
See: commit 1f33c41c03 ("seq_file: Rename seq_overflow() to
seq_has_overflowed() and make public")
Miscellanea:
o realign arguments
Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
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>
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>
Steffen Klassert says:
====================
pull request (net): ipsec 2015-03-16
1) Fix the network header offset in _decode_session6
when multiple IPv6 extension headers are present.
From Hajime Tazaki.
2) Fix an interfamily tunnel crash. We set outer mode
protocol too early and may dispatch to the wrong
address family. Move the setting of the outer mode
protocol behind the last accessing of the inner mode
to fix the crash.
3) Most callers of xfrm_lookup() expect that dst_orig
is released on error. But xfrm_lookup_route() may
need dst_orig to handle certain error cases. So
introduce a flag that tells what should be done in
case of error. From Huaibin Wang.
Please pull or let me know if there are problems.
====================
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>
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>
inet_diag_dump_one_icsk() allocates too small skb.
Add inet_sk_attr_size() helper right before inet_sk_diag_fill()
so that it can be updated if/when new attributes are added.
iproute2/ss currently does not use this dump_one() interface,
this might explain nobody noticed this problem yet.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Now that all of the operations are safe on a single hash table
accross network namespaces, allocate a single global hash table
and update the code to use it.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Rewrite tcp_metrics_flush_all so that it can cope with entries from
different network namespaces on it's hash chain.
This is based on the logic in tcp_metrics_nl_cmd_del for deleting
a selection of entries from a tcp metrics hash chain.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
tcp_metrics_flush_all always returns 0. Remove the unnecessary return code.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In preparation for using one tcp metrics hash table for all network
namespaces add a field tcpm_net to struct tcp_metrics_block, and
verify that field on all hash table lookups.
Make the field tcpm_net of type possible_net_t so it takes no space
when network namespaces are disabled.
Further add a function tm_net to read that field so we can be
efficient when network namespaces are disabled and concise
the rest of the time.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In preparation for using one hash table for all network namespaces
mix the network namespace into the hash value.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There is not a practical way to cleanup during boot so
just panic if there is a problem initializing tcp_metrics.
That will at least give us a clear place to start debugging
if something does go wrong.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Before inserting request socks into general hash table,
fill their socket family.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
ireq->ir_num contains local port, use it.
Also, get_openreq4() dumping listen_sk->refcnt makes litle sense.
inet_diag_fill_req() can also use ireq->ir_num
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
sock_edemux() & sock_gen_put() should be ready to cope with request socks.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
I forgot to update dccp_v6_conn_request() & cookie_v6_check().
They both need to set ireq->ireq_net and ireq->ir_cookie
Lets clear ireq->ir_cookie in inet_reqsk_alloc()
Signed-off-by: Eric Dumazet <edumazet@google.com>
Fixes: 33cf7c90fe ("net: add real socket cookies")
Signed-off-by: David S. Miller <davem@davemloft.net>
This change makes it so that we should always have a deterministic ordering
for the main and local aliases within the merged table when two leaves
overlap.
So for example if we have a leaf with a key of 192.168.254.0. If we
previously added two aliases with a prefix length of 24 from both local and
main the first entry would be first and the second would be second. When I
was coding this I had added a WARN_ON should such a situation occur as I
wasn't sure how likely it would be. However this WARN_ON has been
triggered so this is something that should be addressed.
With this patch the ordering of the aliases is as follows. First they are
sorted on prefix length, then on their table ID, then tos, and finally
priority. This way what we end up doing is essentially interleaving the
two tables on what used to be leaf_info structure boundaries.
Fixes: 0ddcf43d5 ("ipv4: FIB Local/MAIN table collapse")
Reported-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The function fib_unmerge assumed the local table had already been
allocated. If that is not the case however when custom rules are applied
then this can result in a NULL pointer dereference.
In order to prevent this we must check the value of the local table pointer
and if it is NULL simply return 0 as there is no local table to separate
from the main.
Fixes: 0ddcf43d5 ("ipv4: FIB Local/MAIN table collapse")
Reported-by: Madhu Challa <challa@noironetworks.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Having to say
> #ifdef CONFIG_NET_NS
> struct net *net;
> #endif
in structures is a little bit wordy and a little bit error prone.
Instead it is possible to say:
> typedef struct {
> #ifdef CONFIG_NET_NS
> struct net *net;
> #endif
> } possible_net_t;
And then in a header say:
> possible_net_t net;
Which is cleaner and easier to use and easier to test, as the
possible_net_t is always there no matter what the compile options.
Further this allows read_pnet and write_pnet to be functions in all
cases which is better at catching typos.
This change adds possible_net_t, updates the definitions of read_pnet
and write_pnet, updates optional struct net * variables that
write_pnet uses on to have the type possible_net_t, and finally fixes
up the b0rked users of read_pnet and write_pnet.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
hold_net and release_net were an idea that turned out to be useless.
The code has been disabled since 2008. Kill the code it is long past due.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
John reported that my previous commit added a regression
on his router.
This is because sender_cpu & napi_id share a common location,
so get_xps_queue() can see garbage and perform an out of bound access.
We need to make sure sender_cpu is cleared before doing the transmit,
otherwise any NIC busy poll enabled (skb_mark_napi_id()) can trigger
this bug.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: John <jw@nuclearfallout.net>
Bisected-by: John <jw@nuclearfallout.net>
Fixes: 2bd82484bb ("xps: fix xps for stacked devices")
Signed-off-by: David S. Miller <davem@davemloft.net>
I forgot to use write_pnet() in three locations.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Fixes: 33cf7c90fe ("net: add real socket cookies")
Reported-by: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
A long standing problem in netlink socket dumps is the use
of kernel socket addresses as cookies.
1) It is a security concern.
2) Sockets can be reused quite quickly, so there is
no guarantee a cookie is used once and identify
a flow.
3) request sock, establish sock, and timewait socks
for a given flow have different cookies.
Part of our effort to bring better TCP statistics requires
to switch to a different allocator.
In this patch, I chose to use a per network namespace 64bit generator,
and to use it only in the case a socket needs to be dumped to netlink.
(This might be refined later if needed)
Note that I tried to carry cookies from request sock, to establish sock,
then timewait sockets.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Eric Salo <salo@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When we merged the tries for local and main I had overlooked the iterator
for /proc/net/route. As a result it was outputting both local and main
when the two tries were merged.
This patch resolves that by only providing output for aliases that are
actually in the main trie. As a result we should go back to the original
behavior which I assume will be necessary to maintain legacy support.
Fixes: 0ddcf43d5 ("ipv4: FIB Local/MAIN table collapse")
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The 0-day kernel test infrastructure reported a use of uninitialized
variable warning for local_table due to the fact that the local and main
allocations had been swapped from the original setup. This change corrects
that by making it so that we free the main table if the local table
allocation fails.
Fixes: 0ddcf43d5 ("ipv4: FIB Local/MAIN table collapse")
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 814d488c61 ("tcp: fix the timid additive increase on stretch
ACKs") fixed a bug where tcp_cong_avoid_ai() would either credit a
connection with an increase of snd_cwnd_cnt, or increase snd_cwnd, but
not both, resulting in cwnd increasing by 1 packet on at most every
alternate invocation of tcp_cong_avoid_ai().
Although the commit correctly implemented the CUBIC algorithm, which
can increase cwnd by as much as 1 packet per 1 packet ACKed (2x per
RTT), in practice that could be too aggressive: in tests on network
paths with small buffers, YouTube server retransmission rates nearly
doubled.
This commit restores CUBIC to a maximum cwnd growth rate of 1 packet
per 2 packets ACKed (1.5x per RTT). In YouTube tests this restored
retransmit rates to low levels.
Testing: This patch has been tested in datacenter netperf transfers
and live youtube.com and google.com servers.
Fixes: 9cd981dcf1 ("tcp: fix stretch ACK bugs in CUBIC")
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The recent change to tcp_cong_avoid_ai() to handle stretch ACKs
introduced a bug where snd_cwnd_cnt could accumulate a very large
value while w was large, and then if w was reduced snd_cwnd could be
incremented by a large delta, leading to a large burst and high packet
loss. This was tickled when CUBIC's bictcp_update() sets "ca->cnt =
100 * cwnd".
This bug crept in while preparing the upstream version of
814d488c61.
Testing: This patch has been tested in datacenter netperf transfers
and live youtube.com and google.com servers.
Fixes: 814d488c61 ("tcp: fix the timid additive increase on stretch ACKs")
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Move rtnl_lock() before the call to fib4_rules_exit so that
fib_table_flush_external is called under RTNL.
Fixes: 104616e74e ("switchdev: don't support custom ip rules, for now")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Acked-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Reviewed-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch is meant to collapse local and main into one by converting
tb_data from an array to a pointer. Doing this allows us to point the
local table into the main while maintaining the same variables in the
table.
As such the tb_data was converted from an array to a pointer, and a new
array called data is added in order to still provide an object for tb_data
to point to.
In order to track the origin of the fib aliases a tb_id value was added in
a hole that existed on 64b systems. Using this we can also reverse the
merge in the event that custom FIB rules are enabled.
With this patch I am seeing an improvement of 20ns to 30ns for routing
lookups as long as custom rules are not enabled, with custom rules enabled
we fall back to split tables and the original behavior.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If the inflate call failed it would return NULL. As a result tp would be
set to NULL and cause use to trigger a NULL pointer dereference in
should_halve if the inflate failed on the first attempt.
In order to prevent this we should decrement max_work before we actually
attempt to inflate as this will force us to exit before attempting to halve
a node we should have inflated. In order to keep things symmetric between
inflate and halve I went ahead and also moved the decrement of max_work for
the halve case as well so we take care of that before we actually attempt
to halve the tnode.
Fixes: 88bae714 ("fib_trie: Add key vector to root, return parent key_vector in resize")
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In the case of a trie that had no tnodes with a key of 0 the initial
look-up would fail resulting in an out-of-bounds cindex on the first tnode.
This resulted in an entire trie being skipped.
In order resolve this I have updated the cindex logic in the initial
look-up so that if the key is zero we will always traverse the child zero
path.
Fixes: 8be33e95 ("fib_trie: Fib walk rcu should take a tnode and key instead of a trie and a leaf")
Reported-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Tested-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Remove all inline keywords, add some const, and cleanup style.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pablo Neira Ayuso says:
====================
Netfilter fixes for net-next
The following batch contains a couple of fixes to address some fallout
from the previous pull request, they are:
1) Address link problems in the bridge code after e5de75b. Fix it by
using rcu hook to address to avoid ifdef pollution and hard
dependency between bridge and br_netfilter.
2) Address sparse warnings in the netfilter reject code, patch from
Florian Westphal.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
make C=1 CF=-D__CHECK_ENDIAN__ shows following:
net/bridge/netfilter/nft_reject_bridge.c:65:50: warning: incorrect type in argument 3 (different base types)
net/bridge/netfilter/nft_reject_bridge.c:65:50: expected restricted __be16 [usertype] protocol [..]
net/bridge/netfilter/nft_reject_bridge.c:102:37: warning: cast from restricted __be16
net/bridge/netfilter/nft_reject_bridge.c:102:37: warning: incorrect type in argument 1 (different base types) [..]
net/bridge/netfilter/nft_reject_bridge.c:121:50: warning: incorrect type in argument 3 (different base types) [..]
net/bridge/netfilter/nft_reject_bridge.c:168:52: warning: incorrect type in argument 3 (different base types) [..]
net/bridge/netfilter/nft_reject_bridge.c:233:52: warning: incorrect type in argument 3 (different base types) [..]
Caused by two (harmless) errors:
1. htons() instead of ntohs()
2. __be16 for protocol in nf_reject_ipXhdr_put API, use u8 instead.
Reported-by: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Pass in the netlink flags (NLM_F_*) into switchdev driver for IPv4 FIB add op
to allow driver to 1) optimize hardware updates, 2) handle ip route prepend
and append commands correctly.
Suggested-by: Jamal Hadi Salim <jhs@mojatatu.com>
Suggested-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: Scott Feldman <sfeldma@gmail.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Acked-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts:
drivers/net/ethernet/cadence/macb.c
Overlapping changes in macb driver, mostly fixes and cleanups
in 'net' overlapping with the integration of at91_ether into
macb in 'net-next'.
Signed-off-by: David S. Miller <davem@davemloft.net>
After my change to neigh_hh_init to obtain the protocol from the
neigh_table there are no more users of protocol in struct dst_ops.
Remove the protocol field from dst_ops and all of it's initializers.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pablo Neira Ayuso says:
====================
Netfilter updates for net-next
The following patchset contains Netfilter updates for your net-next
tree. Basically, improvements for the packet rejection infrastructure,
deprecation of CLUSTERIP, cleanups for nf_tables and some untangling for
br_netfilter. More specifically they are:
1) Send packet to reset flow if checksum is valid, from Florian Westphal.
2) Fix nf_tables reject bridge from the input chain, also from Florian.
3) Deprecate the CLUSTERIP target, the cluster match supersedes it in
functionality and it's known to have problems.
4) A couple of cleanups for nf_tables rule tracing infrastructure, from
Patrick McHardy.
5) Another cleanup to place transaction declarations at the bottom of
nf_tables.h, also from Patrick.
6) Consolidate Kconfig dependencies wrt. NF_TABLES.
7) Limit table names to 32 bytes in nf_tables.
8) mac header copying in bridge netfilter is already required when
calling ip_fragment(), from Florian Westphal.
9) move nf_bridge_update_protocol() to br_netfilter.c, also from
Florian.
10) Small refactor in br_netfilter in the transmission path, again from
Florian.
11) Move br_nf_pre_routing_finish_bridge_slow() to br_netfilter.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
When reading from the error queue, msg_name and msg_control are only
populated for some errors. A new exception for empty timestamp skbs
added a false positive on icmp errors without payload.
`traceroute -M udpconn` only displayed gateways that return payload
with the icmp error: the embedded network headers are pulled before
sock_queue_err_skb, leaving an skb with skb->len == 0 otherwise.
Fix this regression by refining when msg_name and msg_control
branches are taken. The solutions for the two fields are independent.
msg_name only makes sense for errors that configure serr->port and
serr->addr_offset. Test the first instead of skb->len. This also fixes
another issue. saddr could hold the wrong data, as serr->addr_offset
is not initialized in some code paths, pointing to the start of the
network header. It is only valid when serr->port is set (non-zero).
msg_control support differs between IPv4 and IPv6. IPv4 only honors
requests for ICMP and timestamps with SOF_TIMESTAMPING_OPT_CMSG. The
skb->len test can simply be removed, because skb->dev is also tested
and never true for empty skbs. IPv6 honors requests for all errors
aside from local errors and timestamps on empty skbs.
In both cases, make the policy more explicit by moving this logic to
a new function that decides whether to process msg_control and that
optionally prepares the necessary fields in skb->cb[]. After this
change, the IPv4 and IPv6 paths are more similar.
The last case is rxrpc. Here, simply refine to only match timestamps.
Fixes: 49ca0d8bfa ("net-timestamp: no-payload option")
Reported-by: Jan Niehusmann <jan@gondor.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
----
Changes
v1->v2
- fix local origin test inversion in ip6_datagram_support_cmsg
- make v4 and v6 code paths more similar by introducing analogous
ipv4_datagram_support_cmsg
- fix compile bug in rxrpc
Signed-off-by: David S. Miller <davem@davemloft.net>
This change makes it so that the root of the trie contains a key_vector, by
doing this we make room to essentially collapse the entire trie by at least
one cache line as we can store the information about the tnode or leaf that
is pointed to in the root.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This change pulls the parent pointer from the key_vector and places it in
the tnode structure.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This pulls the information about the child array out of the key_vector and
places it in the tnode since that is where it is needed.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
RCU is only needed once for the entire node, not once per key_vector so we
can pull that out and move it to the tnode structure.
In addition add accessors to be used inside the RCU functions so that we
can more easily get from the key vector to either the tnode or the trie
pointers.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This change pulls the fields not explicitly needed in the key_vector and
placed them in the new tnode structure. By doing this we will eventually
be able to reduce the key_vector down to 16 bytes on 64 bit systems, and
12 bytes on 32 bit systems.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We are now checking the length of a key_vector instead of a tnode so it
makes sense to probably just rename this to child_length since it would
probably even be applicable to a leaf.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
I am replacing the tnode_get_child call with get_child since we are
techically pulling the child out of a key_vector now and not a tnode.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Rename the tnode to key_vector. The key_vector will be the eventual
container for all of the information needed by either a leaf or a tnode.
The final result should be much smaller than the 40 bytes currently needed
for either one.
This also updates the trie struct so that it contains an array of size 1 of
tnode pointers. This is to bring the structure more inline with how an
actual tnode itself is configured.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Resize related functions now all return a pointer to the pointer that
references the object that was resized.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This change just does a couple of minor cleanups on
fib_table_flush_external. Specifically it addresses the fact that resize
was being called even though nothing was being removed from the table, and
it drops an unecessary indent since we could just call continue on the
inverse of the fi && flag check.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
As per RFC4821 7.3. Selecting Probe Size, a probe timer should
be armed once probing has converged. Once this timer expired,
probing again to take advantage of any path PMTU change. The
recommended probing interval is 10 minutes per RFC1981. Probing
interval could be sysctled by sysctl_tcp_probe_interval.
Eric Dumazet suggested to implement pseudo timer based on 32bits
jiffies tcp_time_stamp instead of using classic timer for such
rare event.
Signed-off-by: Fan Du <fan.du@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Current probe_size is chosen by doubling mss_cache,
the probing process will end shortly with a sub-optimal
mss size, and the link mtu will not be taken full
advantage of, in return, this will make user to tweak
tcp_base_mss with care.
Use binary search to choose probe_size in a fine
granularity manner, an optimal mss will be found
to boost performance as its maxmium.
In addition, introduce a sysctl_tcp_probe_threshold
to control when probing will stop in respect to
the width of search range.
Test env:
Docker instance with vxlan encapuslation(82599EB)
iperf -c 10.0.0.24 -t 60
before this patch:
1.26 Gbits/sec
After this patch: increase 26%
1.59 Gbits/sec
Signed-off-by: Fan Du <fan.du@intel.com>
Acked-by: John Heffner <johnwheffner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
net/ipv4/fib_trie.c: In function ‘fib_table_flush_external’:
net/ipv4/fib_trie.c:1572:6: warning: unused variable ‘found’ [-Wunused-variable]
int found = 0;
^
net/ipv4/fib_trie.c:1571:16: warning: unused variable ‘slen’ [-Wunused-variable]
unsigned char slen;
^
Signed-off-by: David S. Miller <davem@davemloft.net>
Call into the switchdev driver any time an IPv4 fib entry is
added/modified/deleted from the kernel's FIB. The switchdev driver may or
may not install the route to the offload device. In the case where the
driver tries to install the route and something goes wrong (device's routing
table is full, etc), then all of the offloaded routes will be flushed from the
device, route forwarding falls back to the kernel, and no more routes are
offloading.
We can refine this logic later. For now, use the simplist model of offloading
routes up to the point of failure, and then on failure, undo everything and
mark IPv4 offloading disabled.
Signed-off-by: Scott Feldman <sfeldma@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Keep switchdev FIB offload model simple for now and don't allow custom ip
rules.
Signed-off-by: Scott Feldman <sfeldma@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
timewait sockets now share a common base with established sockets.
inet_twsk_diag_dump() can use inet_diag_bc_sk() instead of duplicating
code, granted that inet_diag_bc_sk() does proper userlocks
initialization.
twsk_build_assert() will catch any future changes that could break
the assumptions.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
With some mss values, it is possible tcp_xmit_size_goal() puts
one segment more in TSO packet than tcp_tso_autosize().
We send then one TSO packet followed by one single MSS.
It is not a serious bug, but we can do slightly better, especially
for drivers using netif_set_gso_max_size() to lower gso_max_size.
Using same formula avoids these corner cases and makes
tcp_xmit_size_goal() a bit faster.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Fixes: 605ad7f184 ("tcp: refine TSO autosizing")
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
ip_check_defrag() may be used by af_packet to defragment outgoing packets.
skb_network_offset() of af_packet's outgoing packets is not zero.
Signed-off-by: Alexander Drozdov <al.drozdov@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
xt_cluster supersedes ipt_CLUSTERIP since it can be also used in
gateway configurations (not only from the backend side).
ipt_CLUSTER is also known to leak the netdev that it uses on
device removal, which requires a rather large fix to workaround
the problem: http://patchwork.ozlabs.org/patch/358629/
So let's deprecate this so we can probably kill code this in the
future.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
This patch adds code to prevent us from attempting to allocate a tnode with
a size larger than what can be represented by size_t.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This change updates the fib_table_lookup function so that it is in sync
with the fib_find_node function in terms of the explanation for the index
check based on the bits value.
I have also updated it from doing a mask to just doing a compare as I have
found that seems to provide more options to the compiler as I have seen it
turn this into a shift of the value and test under some circumstances.
In addition I addressed one minor issue in which we kept computing the key
^ n->key when checking the fib aliases. I pulled the xor out of the loop
in order to reduce the number of memory reads in the lookup. As a result
we should save a couple cycles since the xor is only done once much earlier
in the lookup.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The fib_table was wrapped in several places with an
rcu_read_lock/rcu_read_unlock however after looking over the code I found
several spots where the tables were being accessed as just standard
pointers without any protections. This change fixes that so that all of
the proper protections are in place when accessing the table to take RCU
replacement or removal of the table into account.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If we are going to compact the leaf and tnode we first need to make sure
the fields are all in the same place. In that regard I am moving the leaf
pointer which represents the fib_alias hash list to occupy what is
currently the first key_vector pointer.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This change makes it so that the insert and delete functions make use of
the tnode pointer returned in the fib_find_node call. By doing this we
will not have to rely on the parent pointer in the leaf which will be going
away soon.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This change makes it so that the parent pointer is returned by reference in
fib_find_node. By doing this I can use it to find the parent node when I
am performing an insertion and I don't have to look for it again in
fib_insert_node.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This change makes it so that leaf_walk_rcu takes a tnode and a key instead
of the trie and a leaf.
The main idea behind this is to avoid using the leaf parent pointer as that
can have additional overhead in the future as I am trying to reduce the
size of a leaf down to 16 bytes on 64b systems and 12b on 32b systems.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This change makes it so that we only call resize on the tnodes, instead of
from each of the leaves. By doing this we can significantly reduce the
amount of time spent resizing as we can update all of the leaves in the
tnode first before we make any determinations about resizing. As a result
we can simply free the tnode in the case that all of the leaves from a
given tnode are flushed instead of resizing with each leaf removed.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
1. For an IPv4 ping socket, ping_check_bind_addr does not check
the family of the socket address that's passed in. Instead,
make it behave like inet_bind, which enforces either that the
address family is AF_INET, or that the family is AF_UNSPEC and
the address is 0.0.0.0.
2. For an IPv6 ping socket, ping_check_bind_addr returns EINVAL
if the socket family is not AF_INET6. Return EAFNOSUPPORT
instead, for consistency with inet6_bind.
3. Make ping_v4_sendmsg and ping_v6_sendmsg return EAFNOSUPPORT
instead of EINVAL if an incorrect socket address structure is
passed in.
4. Make IPv6 ping sockets be IPv6-only. The code does not support
IPv4, and it cannot easily be made to support IPv4 because
the protocol numbers for ICMP and ICMPv6 are different. This
makes connect(::ffff:192.0.2.1) fail with EAFNOSUPPORT instead
of making the socket unusable.
Among other things, this fixes an oops that can be triggered by:
int s = socket(AF_INET, SOCK_DGRAM, IPPROTO_ICMP);
struct sockaddr_in6 sin6 = {
.sin6_family = AF_INET6,
.sin6_addr = in6addr_any,
};
bind(s, (struct sockaddr *) &sin6, sizeof(sin6));
Change-Id: If06ca86d9f1e4593c0d6df174caca3487c57a241
Signed-off-by: Lorenzo Colitti <lorenzo@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
While looking at the mpls code I found myself writing yet another
version of neigh_lookup_noref. We currently have __ipv4_lookup_noref
and __ipv6_lookup_noref.
So to make my work a little easier and to make it a smidge easier to
verify/maintain the mpls code in the future I stopped and wrote
___neigh_lookup_noref. Then I rewote __ipv4_lookup_noref and
__ipv6_lookup_noref in terms of this new function. I tested my new
version by verifying that the same code is generated in
ip_finish_output2 and ip6_finish_output2 where these functions are
inlined.
To get to ___neigh_lookup_noref I added a new neighbour cache table
function key_eq. So that the static size of the key would be
available.
I also added __neigh_lookup_noref for people who want to to lookup
a neighbour table entry quickly but don't know which neibhgour table
they are going to look up.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts:
drivers/net/ethernet/rocker/rocker.c
The rocker commit was two overlapping changes, one to rename
the ->vport member to ->pport, and another making the bitmask
expression use '1ULL' instead of plain '1'.
Signed-off-by: David S. Miller <davem@davemloft.net>
If an over-MTU UDP datagram is sent through a SOCK_RAW socket to a
UFO-capable device, ip_ufo_append_data() sets skb->ip_summed to
CHECKSUM_PARTIAL unconditionally as all GSO code assumes transport layer
checksum is to be computed on segmentation. However, in this case,
skb->csum_start and skb->csum_offset are never set as raw socket
transmit path bypasses udp_send_skb() where they are usually set. As a
result, driver may access invalid memory when trying to calculate the
checksum and store the result (as observed in virtio_net driver).
Moreover, the very idea of modifying the userspace provided UDP header
is IMHO against raw socket semantics (I wasn't able to find a document
clearly stating this or the opposite, though). And while allowing
CHECKSUM_NONE in the UFO case would be more efficient, it would be a bit
too intrusive change just to handle a corner case like this. Therefore
disallowing UFO for packets from SOCK_DGRAM seems to be the best option.
Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
tcp resets are never emitted if the packet that triggers the
reject/reset has an invalid checksum.
For icmp error responses there was no such check.
It allows to distinguish icmp response generated via
iptables -I INPUT -p udp --dport 42 -j REJECT
and those emitted by network stack (won't respond if csum is invalid,
REJECT does).
Arguably its possible to avoid this by using conntrack and only
using REJECT with -m conntrack NEW/RELATED.
However, this doesn't work when connection tracking is not in use
or when using nf_conntrack_checksum=0.
Furthermore, sending errors in response to invalid csums doesn't make
much sense so just add similar test as in nf_send_reset.
Validate csum if needed and only send the response if it is ok.
Reference: http://bugzilla.redhat.com/show_bug.cgi?id=1169829
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
- Add protocol to neigh_tbl so that dst->ops->protocol is not needed
- Acquire the device from neigh->dev
This results in a neigh_hh_init that will cache the samve values
regardless of the packets flowing through it.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There are no more callers so kill this function.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The special case has been pushed out into ax25_neigh_construct so there
is no need to keep this code in arp.c
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
After TIPC doesn't depend on iocb argument in its internal
implementations of sendmsg() and recvmsg() hooks defined in proto
structure, no any user is using iocb argument in them at all now.
Then we can drop the redundant iocb argument completely from kinds of
implementations of both sendmsg() and recvmsg() in the entire
networking stack.
Cc: Christoph Hellwig <hch@lst.de>
Suggested-by: Al Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
As part of an effort to move skb->dropcount to skb->cb[] use a common
macro in protocol families using skb->cb[] for ancillary data to
validate available room in skb->cb[].
Signed-off-by: Eyal Birger <eyal.birger@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
tcp_fastopen_create_child() is static and should not be exported.
tcp4_gso_segment() and tcp6_gso_segment() should be static.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Another TCP issue is triggered by ECN.
Under pressure, receiver gets ECN marks, and send back ACK packets
with ECE TCP flag. Senders enter CA_CWR state.
In this state, tcp_tso_should_defer() is short cut :
if (icsk->icsk_ca_state != TCP_CA_Open)
goto send_now;
This means that about all ACK packets we receive are triggering
a partial send, and because cwnd is kept small, we can only send
a small amount of data for each incoming ACK,
which in return generate more ACK packets.
Allowing CA_Open and CA_CWR states to enable TSO defer in
tcp_tso_should_defer() brings performance back :
TSO autodefer has more chance to defer under pressure.
This patch increases TSO and LRO/GRO efficiency back to normal levels,
and does not impact overall ECN behavior.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
With sysctl_tcp_min_tso_segs being 4, it is very possible
that tcp_tso_should_defer() decides not sending last 2 MSS
of initial window of 10 packets. This also applies if
autosizing decides to send X MSS per GSO packet, and cwnd
is not a multiple of X.
This patch implements an heuristic based on age of first
skb in write queue : If it was sent very recently (less than half srtt),
we can predict that no ACK packet will come in less than half rtt,
so deferring might cause an under utilization of our window.
This is visible on initial send (IW10) on web servers,
but more generally on some RPC, as the last part of the message
might need an extra RTT to get delivered.
Tested:
Ran following packetdrill test
// A simple server-side test that sends exactly an initial window (IW10)
// worth of packets.
`sysctl -e -q net.ipv4.tcp_min_tso_segs=4`
0.000 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+0 bind(3, ..., ...) = 0
+0 listen(3, 1) = 0
+.1 < S 0:0(0) win 32792 <mss 1460,sackOK,nop,nop,nop,wscale 7>
+0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 6>
+.1 < . 1:1(0) ack 1 win 257
+0 accept(3, ..., ...) = 4
+0 write(4, ..., 14600) = 14600
+0 > . 1:5841(5840) ack 1 win 457
+0 > . 5841:11681(5840) ack 1 win 457
// Following packet should be sent right now.
+0 > P. 11681:14601(2920) ack 1 win 457
+.1 < . 1:1(0) ack 14601 win 257
+0 close(4) = 0
+0 > F. 14601:14601(0) ack 1
+.1 < F. 1:1(0) ack 14602 win 257
+0 > . 14602:14602(0) ack 2
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
TSO relies on ability to defer sending a small amount of packets.
Heuristic is to wait for future ACKS in hope to send more packets at once.
Current algorithm uses a per socket tso_deferred field as a pseudo timer.
This pseudo timer relies on future ACK, but there is no guarantee
we receive them in time.
Fix would be to use a real timer, but cost of such timer is probably too
expensive for typical cases.
This patch changes the logic to test the time of last transmit,
because we should not add bursts of more than 1ms for any given flow.
We've used this patch for about two years at Google, before FQ/pacing
as it would reduce a fair amount of bursts.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
At this point the leaf_info hash is redundant. By adding the suffix length
to the fib_alias hash list we no longer have need of leaf_info as we can
determine the prefix length from fa_slen. So we can compress things by
dropping the leaf_info structure from fib_trie and instead directly connect
the leaves to the fib_alias hash list.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Make use of an empty spot in the alias to store the suffix length so that
we don't need to pull that information from the leaf_info structure.
This patch also makes a slight change to the user statistics. Instead of
incrementing semantic_match_miss once per leaf_info miss we now just
increment it once per leaf if a match was not found.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This replaces the prefix length variable in the leaf_info structure with a
suffix length value, or host identifier length in bits. By doing this it
makes it easier to sort out since the tnodes and leaf are carrying this
value as well since it is compatible with the ->pos field in tnodes.
I also cleaned up one spot that had some list manipulation that could be
simplified. I basically updated it so that we just use hlist_add_head_rcu
instead of calling hlist_add_before_rcu on the first node in the list.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There isn't any advantage to having it as a list and by making it an hlist
we make the fib_alias more compatible with the list_info in terms of the
type of list used.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Joining multicast group on ethernet level via "ip maddr" command would
not work if we have an Ethernet switch that does igmp snooping since
the switch would not replicate multicast packets on ports that did not
have IGMP reports for the multicast addresses.
Linux vxlan interfaces created via "ip link add vxlan" have the group option
that enables then to do the required join.
By extending ip address command with option "autojoin" we can get similar
functionality for openvswitch vxlan interfaces as well as other tunneling
mechanisms that need to receive multicast traffic. The kernel code is
structured similar to how the vxlan driver does a group join / leave.
example:
ip address add 224.1.1.10/24 dev eth5 autojoin
ip address del 224.1.1.10/24 dev eth5
Signed-off-by: Madhu Challa <challa@noironetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In the unlikely event that skb_get_hash is unable to deduce a hash
in udp_flow_src_port we use a consistent random value instead.
This is specified in GRE/UDP draft section 3.2.1:
https://tools.ietf.org/html/draft-ietf-tsvwg-gre-in-udp-encap-04
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
tcp_should_expand_sndbuf() does not expand the send buffer if we have
filled the congestion window.
However, it should use tcp_packets_in_flight() instead of
tp->packets_out to make this check.
Testing has established that the difference matters a lot if there are
many SACKed packets, causing a needless performance shortfall.
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Nandita Dukkipati <nanditad@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There is a need to perform igmp join/leave operations while RTNL is
held.
Make ip_mc_{join|leave}_group() wrappers around
__ip_mc_{join|leave}_group() to avoid the proliferation of work queues.
For example, vxlan_igmp_join() could possibly be removed.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
skb_copy_bits() returns zero on success and negative value on error,
so it is needed to invert the condition in ip_check_defrag().
Fixes: 1bf3751ec9 ("ipv4: ip_check_defrag must not modify skb before unsharing")
Signed-off-by: Alexander Drozdov <al.drozdov@gmail.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This message isn't really needed it justs waits time/space.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull networking updates from David Miller:
1) Missing netlink attribute validation in nft_lookup, from Patrick
McHardy.
2) Restrict ipv6 partial checksum handling to UDP, since that's the
only case it works for. From Vlad Yasevich.
3) Clear out silly device table sentinal macros used by SSB and BCMA
drivers. From Joe Perches.
4) Make sure the remote checksum code never creates a situation where
the remote checksum is applied yet the tunneling metadata describing
the remote checksum transformation is still present. Otherwise an
external entity might see this and apply the checksum again. From
Tom Herbert.
5) Use msecs_to_jiffies() where applicable, from Nicholas Mc Guire.
6) Don't explicitly initialize timer struct fields, use setup_timer()
and mod_timer() instead. From Vaishali Thakkar.
7) Don't invoke tg3_halt() without the tp->lock held, from Jun'ichi
Nomura.
8) Missing __percpu annotation in ipvlan driver, from Eric Dumazet.
9) Don't potentially perform skb_get() on shared skbs, also from Eric
Dumazet.
10) Fix COW'ing of metrics for non-DST_HOST routes in ipv6, from Martin
KaFai Lau.
11) Fix merge resolution error between the iov_iter changes in vhost and
some bug fixes that occurred at the same time. From Jason Wang.
12) If rtnl_configure_link() fails we have to perform a call to
->dellink() before unregistering the device. From WANG Cong.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (39 commits)
net: dsa: Set valid phy interface type
rtnetlink: call ->dellink on failure when ->newlink exists
com20020-pci: add support for eae single card
vhost_net: fix wrong iter offset when setting number of buffers
net: spelling fixes
net/core: Fix warning while make xmldocs caused by dev.c
net: phy: micrel: disable NAND-tree for KSZ8021, KSZ8031, KSZ8051, KSZ8081
ipv6: fix ipv6_cow_metrics for non DST_HOST case
openvswitch: Fix key serialization.
r8152: restore hw settings
hso: fix rx parsing logic when skb allocation fails
tcp: make sure skb is not shared before using skb_get()
bridge: netfilter: Move sysctl-specific error code inside #ifdef
ipv6: fix possible deadlock in ip6_fl_purge / ip6_fl_gc
ipvlan: add a missing __percpu pcpu_stats
tg3: Hold tp->lock before calling tg3_halt() from tg3_init_one()
bgmac: fix device initialization on Northstar SoCs (condition typo)
qlcnic: Delete existing multicast MAC list before adding new
net/mlx5_core: Fix configuration of log_uar_page_sz
sunvnet: don't change gso data on clones
...
Spelling errors caught by codespell.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
IPv6 can keep a copy of SYN message using skb_get() in
tcp_v6_conn_request() so that caller wont free the skb when calling
kfree_skb() later.
Therefore TCP fast open has to clone the skb it is queuing in
child->sk_receive_queue, as all skbs consumed from receive_queue are
freed using __kfree_skb() (ie assuming skb->users == 1)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Fixes: 5b7ed0892f ("tcp: move fastopen functions to tcp_fastopen.c")
Signed-off-by: David S. Miller <davem@davemloft.net>
Move memcg_socket_limit_enabled decrement to tcp_destroy_cgroup (called
from memcg_destroy_kmem -> mem_cgroup_sockets_destroy) and zap a bunch of
wrapper functions.
Although this patch moves static keys decrement from __mem_cgroup_free to
mem_cgroup_css_free, it does not introduce any functional changes, because
the keys are incremented on setting the limit (tcp or kmem), which can
only happen after successful mem_cgroup_css_online.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: Glauber Costa <glommer@parallels.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujtisu.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pull security layer updates from James Morris:
"Highlights:
- Smack adds secmark support for Netfilter
- /proc/keys is now mandatory if CONFIG_KEYS=y
- TPM gets its own device class
- Added TPM 2.0 support
- Smack file hook rework (all Smack users should review this!)"
* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/linux-security: (64 commits)
cipso: don't use IPCB() to locate the CIPSO IP option
SELinux: fix error code in policydb_init()
selinux: add security in-core xattr support for pstore and debugfs
selinux: quiet the filesystem labeling behavior message
selinux: Remove unused function avc_sidcmp()
ima: /proc/keys is now mandatory
Smack: Repair netfilter dependency
X.509: silence asn1 compiler debug output
X.509: shut up about included cert for silent build
KEYS: Make /proc/keys unconditional if CONFIG_KEYS=y
MAINTAINERS: email update
tpm/tpm_tis: Add missing ifdef CONFIG_ACPI for pnp_acpi_device
smack: fix possible use after frees in task_security() callers
smack: Add missing logging in bidirectional UDS connect check
Smack: secmark support for netfilter
Smack: Rework file hooks
tpm: fix format string error in tpm-chip.c
char/tpm/tpm_crb: fix build error
smack: Fix a bidirectional UDS connect check typo
smack: introduce a special case for tmpfs in smack_d_instantiate()
...
The unified hierarchy interface for memory cgroups will no longer use "-1"
to mean maximum possible resource value. In preparation for this, make
the string an argument and let the caller supply it.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Cc: Greg Thelen <gthelen@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Change remote checksum handling to set checksum partial as default
behavior. Added an iflink parameter to configure not using
checksum partial (calling csum_partial to update checksum).
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds infrastructure so that remote checksum offload can
set CHECKSUM_PARTIAL instead of calling csum_partial and writing
the modfied checksum field.
Add skb_remcsum_adjust_partial function to set an skb for using
CHECKSUM_PARTIAL with remote checksum offload. Changed
skb_remcsum_process and skb_gro_remcsum_process to take a boolean
argument to indicate if checksum partial can be set or the
checksum needs to be modified using the normal algorithm.
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Properly set GSO types and skb->encapsulation in the UDP tunnel GRO
complete so that packets are properly represented for GSO. This sets
SKB_GSO_UDP_TUNNEL or SKB_GSO_UDP_TUNNEL_CSUM depending on whether
non-zero checksums were received, and sets SKB_GSO_TUNNEL_REMCSUM if
the remote checksum option was processed.
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Remote checksum offload processing is currently the same for both
the GRO and non-GRO path. When the remote checksum offload option
is encountered, the checksum field referred to is modified in
the packet. So in the GRO case, the packet is modified in the
GRO path and then the operation is skipped when the packet goes
through the normal path based on skb->remcsum_offload. There is
a problem in that the packet may be modified in the GRO path, but
then forwarded off host still containing the remote checksum option.
A remote host will again perform RCO but now the checksum verification
will fail since GRO RCO already modified the checksum.
To fix this, we ensure that GRO restores a packet to it's original
state before returning. In this model, when GRO processes a remote
checksum option it still changes the checksum per the algorithm
but on return from lower layer processing the checksum is restored
to its original value.
In this patch we add define gro_remcsum structure which is passed
to skb_gro_remcsum_process to save offset and delta for the checksum
being changed. After lower layer processing, skb_gro_remcsum_cleanup
is called to restore the checksum before returning from GRO.
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Using the IPCB() macro to get the IPv4 options is convenient, but
unfortunately NetLabel often needs to examine the CIPSO option outside
of the scope of the IP layer in the stack. While historically IPCB()
worked above the IP layer, due to the inclusion of the inet_skb_param
struct at the head of the {tcp,udp}_skb_cb structs, recent commit
971f10ec ("tcp: better TCP_SKB_CB layout to reduce cache line misses")
reordered the tcp_skb_cb struct and invalidated this IPCB() trick.
This patch fixes the problem by creating a new function,
cipso_v4_optptr(), which locates the CIPSO option inside the IP header
without calling IPCB(). Unfortunately, this isn't as fast as a simple
lookup so some additional tweaks were made to limit the use of this
new function.
Cc: <stable@vger.kernel.org> # 3.18
Reported-by: Casey Schaufler <casey@schaufler-ca.com>
Signed-off-by: Paul Moore <pmoore@redhat.com>
Tested-by: Casey Schaufler <casey@schaufler-ca.com>
Packetization Layer Path MTU Discovery works separately beside
Path MTU Discovery at IP level, different net namespace has
various requirements on which one to chose, e.g., a virutalized
container instance would require TCP PMTU to probe an usable
effective mtu for underlying tunnel, while the host would
employ classical ICMP based PMTU to function.
Hence making TCP PMTU mechanism per net namespace to decouple
two functionality. Furthermore the probe base MSS should also
be configured separately for each namespace.
Signed-off-by: Fan Du <fan.du@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If a server has enabled Fast Open and it receives a pure SYN-data
packet (without a Fast Open option), it won't accept the data but it
incorrectly returns a SYN-ACK with a Fast Open cookie and also
increments the SNMP stat LINUX_MIB_TCPFASTOPENPASSIVEFAIL.
This patch makes the server include a Fast Open cookie in SYN-ACK
only if the SYN has some Fast Open option (i.e., when client
requests or presents a cookie).
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We set the outer mode protocol too early. As a result, the
local error handler might dispatch to the wrong address family
and report the error to a wrong socket type. We fix this by
setting the outer protocol to the skb after we accessed the
inner mode for the last time, right before we do the atcual
encapsulation where we switch finally to the outer mode.
Reported-by: Chris Ruehl <chris.ruehl@gtsys.com.hk>
Tested-by: Chris Ruehl <chris.ruehl@gtsys.com.hk>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Receive Flow Steering is a nice solution but suffers from
hash collisions when a mix of connected and unconnected traffic
is received on the host, when flow hash table is populated.
Also, clearing flow in inet_release() makes RFS not very good
for short lived flows, as many packets can follow close().
(FIN , ACK packets, ...)
This patch extends the information stored into global hash table
to not only include cpu number, but upper part of the hash value.
I use a 32bit value, and dynamically split it in two parts.
For host with less than 64 possible cpus, this gives 6 bits for the
cpu number, and 26 (32-6) bits for the upper part of the hash.
Since hash bucket selection use low order bits of the hash, we have
a full hash match, if /proc/sys/net/core/rps_sock_flow_entries is big
enough.
If the hash found in flow table does not match, we fallback to RPS (if
it is enabled for the rxqueue).
This means that a packet for an non connected flow can avoid the
IPI through a unrelated/victim CPU.
This also means we no longer have to clear the table at socket
close time, and this helps short lived flows performance.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
encap.sport and encap.dport are __be16, use nla_{get,put}_be16 instead
of nla_{get,put}_u16.
Fixes the sparse warnings:
warning: incorrect type in assignment (different base types)
expected restricted __be32 [addressable] [usertype] o_key
got restricted __be16 [addressable] [usertype] i_flags
warning: incorrect type in assignment (different base types)
expected restricted __be16 [usertype] sport
got unsigned short
warning: incorrect type in assignment (different base types)
expected restricted __be16 [usertype] dport
got unsigned short
warning: incorrect type in argument 3 (different base types)
expected unsigned short [unsigned] [usertype] value
got restricted __be16 [usertype] sport
warning: incorrect type in argument 3 (different base types)
expected unsigned short [unsigned] [usertype] value
got restricted __be16 [usertype] dport
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Ensure that in state FIN_WAIT2 or TIME_WAIT, where the connection is
represented by a tcp_timewait_sock, we rate limit dupacks in response
to incoming packets (a) with TCP timestamps that fail PAWS checks, or
(b) with sequence numbers that are out of the acceptable window.
We do not send a dupack in response to out-of-window packets if it has
been less than sysctl_tcp_invalid_ratelimit (default 500ms) since we
last sent a dupack in response to an out-of-window packet.
Reported-by: Avery Fay <avery@mixpanel.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Ensure that in state ESTABLISHED, where the connection is represented
by a tcp_sock, we rate limit dupacks in response to incoming packets
(a) with TCP timestamps that fail PAWS checks, or (b) with sequence
numbers or ACK numbers that are out of the acceptable window.
We do not send a dupack in response to out-of-window packets if it has
been less than sysctl_tcp_invalid_ratelimit (default 500ms) since we
last sent a dupack in response to an out-of-window packet.
There is already a similar (although global) rate-limiting mechanism
for "challenge ACKs". When deciding whether to send a challence ACK,
we first consult the new per-connection rate limit, and then the
global rate limit.
Reported-by: Avery Fay <avery@mixpanel.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In the SYN_RECV state, where the TCP connection is represented by
tcp_request_sock, we now rate-limit SYNACKs in response to a client's
retransmitted SYNs: we do not send a SYNACK in response to client SYN
if it has been less than sysctl_tcp_invalid_ratelimit (default 500ms)
since we last sent a SYNACK in response to a client's retransmitted
SYN.
This allows the vast majority of legitimate client connections to
proceed unimpeded, even for the most aggressive platforms, iOS and
MacOS, which actually retransmit SYNs 1-second intervals for several
times in a row. They use SYN RTO timeouts following the progression:
1,1,1,1,1,2,4,8,16,32.
Reported-by: Avery Fay <avery@mixpanel.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Helpers for mitigating ACK loops by rate-limiting dupacks sent in
response to incoming out-of-window packets.
This patch includes:
- rate-limiting logic
- sysctl to control how often we allow dupacks to out-of-window packets
- SNMP counter for cases where we rate-limited our dupack sending
The rate-limiting logic in this patch decides to not send dupacks in
response to out-of-window segments if (a) they are SYNs or pure ACKs
and (b) the remote endpoint is sending them faster than the configured
rate limit.
We rate-limit our responses rather than blocking them entirely or
resetting the connection, because legitimate connections can rely on
dupacks in response to some out-of-window segments. For example, zero
window probes are typically sent with a sequence number that is below
the current window, and ZWPs thus expect to thus elicit a dupack in
response.
We allow dupacks in response to TCP segments with data, because these
may be spurious retransmissions for which the remote endpoint wants to
receive DSACKs. This is safe because segments with data can't
realistically be part of ACK loops, which by their nature consist of
each side sending pure/data-less ACKs to each other.
The dupack interval is controlled by a new sysctl knob,
tcp_invalid_ratelimit, given in milliseconds, in case an administrator
needs to dial this upward in the face of a high-rate DoS attack. The
name and units are chosen to be analogous to the existing analogous
knob for ICMP, icmp_ratelimit.
The default value for tcp_invalid_ratelimit is 500ms, which allows at
most one such dupack per 500ms. This is chosen to be 2x faster than
the 1-second minimum RTO interval allowed by RFC 6298 (section 2, rule
2.4). We allow the extra 2x factor because network delay variations
can cause packets sent at 1 second intervals to be compressed and
arrive much closer.
Reported-by: Avery Fay <avery@mixpanel.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts:
drivers/net/vxlan.c
drivers/vhost/net.c
include/linux/if_vlan.h
net/core/dev.c
The net/core/dev.c conflict was the overlap of one commit marking an
existing function static whilst another was adding a new function.
In the include/linux/if_vlan.h case, the type used for a local
variable was changed in 'net', whereas the function got rewritten
to fix a stacked vlan bug in 'net-next'.
In drivers/vhost/net.c, Al Viro's iov_iter conversions in 'net-next'
overlapped with an endainness fix for VHOST 1.0 in 'net'.
In drivers/net/vxlan.c, vxlan_find_vni() added a 'flags' parameter
in 'net-next' whereas in 'net' there was a bug fix to pass in the
correct network namespace pointer in calls to this function.
Signed-off-by: David S. Miller <davem@davemloft.net>
When we added pacing to TCP, we decided to let sch_fq take care
of actual pacing.
All TCP had to do was to compute sk->pacing_rate using simple formula:
sk->pacing_rate = 2 * cwnd * mss / rtt
It works well for senders (bulk flows), but not very well for receivers
or even RPC :
cwnd on the receiver can be less than 10, rtt can be around 100ms, so we
can end up pacing ACK packets, slowing down the sender.
Really, only the sender should pace, according to its own logic.
Instead of adding a new bit in skb, or call yet another flow
dissection, we tweak skb->truesize to a small value (2), and
we instruct sch_fq to use new helper and not pace pure ack.
Note this also helps TCP small queue, as ack packets present
in qdisc/NIC do not prevent sending a data packet (RPC workload)
This helps to reduce tx completion overhead, ack packets can use regular
sock_wfree() instead of tcp_wfree() which is a bit more expensive.
This has no impact in the case packets are sent to loopback interface,
as we do not coalesce ack packets (were we would detect skb->truesize
lie)
In case netem (with a delay) is used, skb_orphan_partial() also sets
skb->truesize to 1.
This patch is a combination of two patches we used for about one year at
Google.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds skb_remcsum_process and skb_gro_remcsum_process to
perform the appropriate adjustments to the skb when receiving
remote checksum offload.
Updated vxlan and gue to use these functions.
Tested: Ran TCP_RR and TCP_STREAM netperf for VXLAN and GUE, did
not see any change in performance.
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
That takes care of the majority of ->sendmsg() instances - most of them
via memcpy_to_msg() or assorted getfrag() callbacks. One place where we
still keep memcpy_fromiovecend() is tipc - there we potentially read the
same data over and over; separate patch, that...
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
patch is actually smaller than it seems to be - most of it is unindenting
the inner loop body in tcp_sendmsg() itself...
the bit in tcp_input.c is going to get reverted very soon - that's what
memcpy_from_msg() will become, but not in this commit; let's keep it
reasonably contained...
There's one potentially subtle change here: in case of short copy from
userland, mainline tcp_send_syn_data() discards the skb it has allocated
and falls back to normal path, where we'll send as much as possible after
rereading the same data again. This patch trims SYN+data skb instead -
that way we don't need to copy from the same place twice.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
One deployment requirement of DCTCP is to be able to run
in a DC setting along with TCP traffic. As Glenn Judd's
NSDI'15 paper "Attaining the Promise and Avoiding the Pitfalls
of TCP in the Datacenter" [1] (tba) explains, one way to
solve this on switch side is to split DCTCP and TCP traffic
in two queues per switch port based on the DSCP: one queue
soley intended for DCTCP traffic and one for non-DCTCP traffic.
For the DCTCP queue, there's the marking threshold K as
explained in commit e3118e8359 ("net: tcp: add DCTCP congestion
control algorithm") for RED marking ECT(0) packets with CE.
For the non-DCTCP queue, there's f.e. a classic tail drop queue.
As already explained in e3118e8359, running DCTCP at scale
when not marking SYN/SYN-ACK packets with ECT(0) has severe
consequences as for non-ECT(0) packets, traversing the RED
marking DCTCP queue will result in a severe reduction of
connection probability.
This is due to the DCTCP queue being dominated by ECT(0) traffic
and switches handle non-ECT traffic in the RED marking queue
after passing K as drops, where K is usually a low watermark
in order to leave enough tailroom for bursts. Splitting DCTCP
traffic among several queues (ECN and non-ECN queue) is being
considered a terrible idea in the network community as it
splits single flows across multiple network paths.
Therefore, commit e3118e8359 implements this on Linux as
ECT(0) marked traffic, as we argue that marking all packets
of a DCTCP flow is the only viable solution and also doesn't
speak against the draft.
However, recently, a DCTCP implementation for FreeBSD hit also
their mainline kernel [2]. In order to let them play well
together with Linux' DCTCP, we would need to loosen the
requirement that ECT(0) has to be asserted during the 3WHS as
not implemented in FreeBSD. This simplifies the ECN test and
lets DCTCP work together with FreeBSD.
Joint work with Daniel Borkmann.
[1] https://www.usenix.org/conference/nsdi15/technical-sessions/presentation/judd
[2] 8ad8794452
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Glenn Judd <glenn.judd@morganstanley.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add timestamping option SOF_TIMESTAMPING_OPT_TSONLY. For transmit
timestamps, this loops timestamps on top of empty packets.
Doing so reduces the pressure on SO_RCVBUF. Payload inspection and
cmsg reception (aside from timestamps) are no longer possible. This
works together with a follow on patch that allows administrators to
only allow tx timestamping if it does not loop payload or metadata.
Signed-off-by: Willem de Bruijn <willemb@google.com>
----
Changes (rfc -> v1)
- add documentation
- remove unnecessary skb->len test (thanks to Richard Cochran)
Signed-off-by: David S. Miller <davem@davemloft.net>
In commit be9f4a44e7 ("ipv4: tcp: remove per net tcp_sock")
I tried to address contention on a socket lock, but the solution
I chose was horrible :
commit 3a7c384ffd ("ipv4: tcp: unicast_sock should not land outside
of TCP stack") addressed a selinux regression.
commit 0980e56e50 ("ipv4: tcp: set unicast_sock uc_ttl to -1")
took care of another regression.
commit b5ec8eeac4 ("ipv4: fix ip_send_skb()") fixed another regression.
commit 811230cd85 ("tcp: ipv4: initialize unicast_sock sk_pacing_rate")
was another shot in the dark.
Really, just use a proper socket per cpu, and remove the skb_orphan()
call, to re-enable flow control.
This solves a serious problem with FQ packet scheduler when used in
hostile environments, as we do not want to allocate a flow structure
for every RST packet sent in response to a spoofed packet.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Get rid of nr_cpu_ids and use modern percpu allocation.
Note that the sockets themselves are not yet allocated
using NUMA affinity.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Current behavior only passes RTTs from sequentially acked data to CC.
If sender gets a combined ACK for segment 1 and SACK for segment 3, then the
computed RTT for CC is the time between sending segment 1 and receiving SACK
for segment 3.
Pass the minimum computed RTT from any acked data to CC, i.e. time between
sending segment 3 and receiving SACK for segment 3.
Signed-off-by: Kenneth Klette Jonassen <kennetkl@ifi.uio.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
They are all either written once or extremly rarely (e.g. from init
code), so we can move them to the .data..read_mostly section.
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
RFC 1191 said, "a host MUST not increase its estimate of the Path
MTU in response to the contents of a Datagram Too Big message."
Signed-off-by: Li Wei <lw@cn.fujitsu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When I added sk_pacing_rate field, I forgot to initialize its value
in the per cpu unicast_sock used in ip_send_unicast_reply()
This means that for sch_fq users, RST packets, or ACK packets sent
on behalf of TIME_WAIT sockets might be sent to slowly or even dropped
once we reach the per flow limit.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Fixes: 95bd09eb27 ("tcp: TSO packets automatic sizing")
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently, it isn't possible to request checksums on the outer UDP
header of tunnels - the TUNNEL_CSUM flag is ignored. This adds
support for requesting that UDP checksums be computed on transmit
and properly reported if they are present on receive.
Signed-off-by: Jesse Gross <jesse@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch fixes a bug in CUBIC that causes cwnd to increase slightly
too slowly when multiple ACKs arrive in the same jiffy.
If cwnd is supposed to increase at a rate of more than once per jiffy,
then CUBIC was sometimes too slow. Because the bic_target is
calculated for a future point in time, calculated with time in
jiffies, the cwnd can increase over the course of the jiffy while the
bic_target calculated as the proper CUBIC cwnd at time
t=tcp_time_stamp+rtt does not increase, because tcp_time_stamp only
increases on jiffy tick boundaries.
So since the cnt is set to:
ca->cnt = cwnd / (bic_target - cwnd);
as cwnd increases but bic_target does not increase due to jiffy
granularity, the cnt becomes too large, causing cwnd to increase
too slowly.
For example:
- suppose at the beginning of a jiffy, cwnd=40, bic_target=44
- so CUBIC sets:
ca->cnt = cwnd / (bic_target - cwnd) = 40 / (44 - 40) = 40/4 = 10
- suppose we get 10 acks, each for 1 segment, so tcp_cong_avoid_ai()
increases cwnd to 41
- so CUBIC sets:
ca->cnt = cwnd / (bic_target - cwnd) = 41 / (44 - 41) = 41 / 3 = 13
So now CUBIC will wait for 13 packets to be ACKed before increasing
cwnd to 42, insted of 10 as it should.
The fix is to avoid adjusting the slope (determined by ca->cnt)
multiple times within a jiffy, and instead skip to compute the Reno
cwnd, the "TCP friendliness" code path.
Reported-by: Eyal Perry <eyalpe@mellanox.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Change CUBIC to properly handle stretch ACKs in additive increase mode
by passing in the count of ACKed packets to tcp_cong_avoid_ai().
In addition, because we are now precisely accounting for stretch ACKs,
including delayed ACKs, we can now remove the delayed ACK tracking and
estimation code that tracked recent delayed ACK behavior in
ca->delayed_ack.
Reported-by: Eyal Perry <eyalpe@mellanox.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Change Reno to properly handle stretch ACKs in additive increase mode
by passing in the count of ACKed packets to tcp_cong_avoid_ai().
In addition, if snd_cwnd crosses snd_ssthresh during slow start
processing, and we then exit slow start mode, we need to carry over
any remaining "credit" for packets ACKed and apply that to additive
increase by passing this remaining "acked" count to
tcp_cong_avoid_ai().
Reported-by: Eyal Perry <eyalpe@mellanox.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
tcp_cong_avoid_ai() was too timid (snd_cwnd increased too slowly) on
"stretch ACKs" -- cases where the receiver ACKed more than 1 packet in
a single ACK. For example, suppose w is 10 and we get a stretch ACK
for 20 packets, so acked is 20. We ought to increase snd_cwnd by 2
(since acked/w = 20/10 = 2), but instead we were only increasing cwnd
by 1. This patch fixes that behavior.
Reported-by: Eyal Perry <eyalpe@mellanox.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
LRO, GRO, delayed ACKs, and middleboxes can cause "stretch ACKs" that
cover more than the RFC-specified maximum of 2 packets. These stretch
ACKs can cause serious performance shortfalls in common congestion
control algorithms that were designed and tuned years ago with
receiver hosts that were not using LRO or GRO, and were instead
politely ACKing every other packet.
This patch series fixes Reno and CUBIC to handle stretch ACKs.
This patch prepares for the upcoming stretch ACK bug fix patches. It
adds an "acked" parameter to tcp_cong_avoid_ai() to allow for future
fixes to tcp_cong_avoid_ai() to correctly handle stretch ACKs, and
changes all congestion control algorithms to pass in 1 for the ACKed
count. It also changes tcp_slow_start() to return the number of packet
ACK "credits" that were not processed in slow start mode, and can be
processed by the congestion control module in additive increase mode.
In future patches we will fix tcp_cong_avoid_ai() to handle stretch
ACKs, and fix Reno and CUBIC handling of stretch ACKs in slow start
and additive increase mode.
Reported-by: Eyal Perry <eyalpe@mellanox.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts:
arch/arm/boot/dts/imx6sx-sdb.dts
net/sched/cls_bpf.c
Two simple sets of overlapping changes.
Signed-off-by: David S. Miller <davem@davemloft.net>
An exception is seen in ICMP ping receive path where the skb
destructor sock_rfree() tries to access a freed socket. This happens
because ping_rcv() releases socket reference with sock_put() and this
internally frees up the socket. Later icmp_rcv() will try to free the
skb and as part of this, skb destructor is called and which leads
to a kernel panic as the socket is freed already in ping_rcv().
-->|exception
-007|sk_mem_uncharge
-007|sock_rfree
-008|skb_release_head_state
-009|skb_release_all
-009|__kfree_skb
-010|kfree_skb
-011|icmp_rcv
-012|ip_local_deliver_finish
Fix this incorrect free by cloning this skb and processing this cloned
skb instead.
This patch was suggested by Eric Dumazet
Signed-off-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
While working on rhashtable walking I noticed that the UDP diag
dumping code is buggy. In particular, the socket skipping within
a chain never happens, even though we record the number of sockets
that should be skipped.
As this code was supposedly copied from TCP, this patch does what
TCP does and resets num before we walk a chain.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Not caching dst_entries which cause redirects could be exploited by hosts
on the same subnet, causing a severe DoS attack. This effect aggravated
since commit f886497212 ("ipv4: fix dst race in sk_dst_get()").
Lookups causing redirects will be allocated with DST_NOCACHE set which
will force dst_release to free them via RCU. Unfortunately waiting for
RCU grace period just takes too long, we can end up with >1M dst_entries
waiting to be released and the system will run OOM. rcuos threads cannot
catch up under high softirq load.
Attaching the flag to emit a redirect later on to the specific skb allows
us to cache those dst_entries thus reducing the pressure on allocation
and deallocation.
This issue was discovered by Marcelo Leitner.
Cc: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Marcelo Leitner <mleitner@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
While doing further work on the fib_trie I noted a few items.
First I was using calls that were far more complicated than they needed to
be for determining when to push/pull the suffix length. I have updated the
code to reflect the simplier logic.
The second issue is that I realised we weren't necessarily handling the
case of a leaf_info struct surviving a flush. I have updated the logic so
that now we will call pull_suffix in the event of having a leaf info value
left in the leaf after flushing it.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The function fib_find_alias is only accessed by functions in fib_trie.c as
such it makes sense to relocate it and cast it as static so that the
compiler can take advantage of optimizations it can do to it as a local
function.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
It doesn't make much sense to count the pointers ourselves when
empty_children already has a count for the number of NULL pointers stored
in the tnode. As such save ourselves the cycles and just use
empty_children.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch really does two things.
First it pulls the logic for determining if we should collapse one node out
of the tree and the actual code doing the collapse into a separate pair of
functions. This helps to make the changes to these areas more readable.
Second it encodes the upper 32b of the empty_children value onto the
full_children value in the case of bits == KEYLENGTH. By doing this we are
able to handle the case of a 32b node where empty_children would appear to
be 0 when it was actually 1ul << 32.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This change corrects an issue where if inflate or halve fails we were
exiting the resize function without at least updating the slen for the
node. To correct this I have moved the update of max_size into the while
loop so that it is only decremented on a successful call to either inflate
or halve.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch addresses two issues.
The first issue is the fact that I believe I had the RCU freeing sequence
slightly out of order. As a result we could get into an issue if a caller
went into a child of a child of the new node, then backtraced into the to be
freed parent, and then attempted to access a child of a child that may have
been consumed in a resize of one of the new nodes children. To resolve this I
have moved the resize after we have freed the oldtnode. The only side effect
of this is that we will now be calling resize on more nodes in the case of
inflate due to the fact that we don't have a good way to test to see if a
full_tnode on the new node was there before or after the allocation. This
should have minimal impact however since the node should already be
correctly size so it is just the cost of calling should_inflate that we
will be taking on the node which is only a couple of cycles.
The second issue is the fact that inflate and halve were essentially doing
the same thing after the new node was added to the trie replacing the old
one. As such it wasn't really necessary to keep the code in both functions
so I have split it out into two other functions, called replace and
update_children.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In doing performance testing and analysis of the changes I recently found
that by shifting the index I had created an unnecessary dependency.
I have updated the code so that we instead shift a mask by bits and then
just test against that as that should save us about 2 CPU cycles since we
can generate the mask while the key and pos are being processed.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The UDP tunnel transmit functions udp_tunnel_xmit_skb and
udp_tunnel6_xmit_skb include a socket argument. The socket being
passed to the functions (from VXLAN) is a UDP created for receive
side. The only thing that the socket is used for in the transmit
functions is to get the setting for checksum (enabled or zero).
This patch removes the argument and and adds a nocheck argument
for checksum setting. This eliminates the unnecessary dependency
on a UDP socket for UDP tunnel transmit.
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The logic to configure a network interface for kernel IP
auto-configuration is very simplistic, and does not handle the case
where a device is stacked onto another such as with DSA. This causes the
kernel not to open and configure the master network device in a DSA
switch tree, and therefore slave network devices using this master
network devices as conduit device cannot be open.
This restriction comes from a check in net/dsa/slave.c, which is
basically checking the master netdev flags for IFF_UP and returns
-ENETDOWN if it is not the case.
Automatically bringing-up DSA master network devices allows DSA slave
network devices to be used as valid interfaces for e.g: NFS root booting
by allowing kernel IP autoconfiguration to succeed on these interfaces.
On the reverse path, make sure we do not attempt to close a DSA-enabled
device as this would implicitely prevent the slave DSA network device
from operating.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Implement rtnl_link_ops->get_link_net() callback so that IFLA_LINK_NETNSID is
added to rtnetlink messages.
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 053c095a82 ("netlink: make nlmsg_end() and genlmsg_end()
void") didn't catch all of the cases where callers were breaking out
on the return value being equal to zero, which they no longer should
when zero means success.
Fix all such cases.
Reported-by: Marcel Holtmann <marcel@holtmann.org>
Reported-by: Scott Feldman <sfeldma@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Contrary to common expectations for an "int" return, these functions
return only a positive value -- if used correctly they cannot even
return 0 because the message header will necessarily be in the skb.
This makes the very common pattern of
if (genlmsg_end(...) < 0) { ... }
be a whole bunch of dead code. Many places also simply do
return nlmsg_end(...);
and the caller is expected to deal with it.
This also commonly (at least for me) causes errors, because it is very
common to write
if (my_function(...))
/* error condition */
and if my_function() does "return nlmsg_end()" this is of course wrong.
Additionally, there's not a single place in the kernel that actually
needs the message length returned, and if anyone needs it later then
it'll be very easy to just use skb->len there.
Remove this, and make the functions void. This removes a bunch of dead
code as described above. The patch adds lines because I did
- return nlmsg_end(...);
+ nlmsg_end(...);
+ return 0;
I could have preserved all the function's return values by returning
skb->len, but instead I've audited all the places calling the affected
functions and found that none cared. A few places actually compared
the return value with <= 0 in dump functionality, but that could just
be changed to < 0 with no change in behaviour, so I opted for the more
efficient version.
One instance of the error I've made numerous times now is also present
in net/phonet/pn_netlink.c in the route_dumpit() function - it didn't
check for <0 or <=0 and thus broke out of the loop every single time.
I've preserved this since it will (I think) have caused the messages to
userspace to be formatted differently with just a single message for
every SKB returned to userspace. It's possible that this isn't needed
for the tools that actually use this, but I don't even know what they
are so couldn't test that changing this behaviour would be acceptable.
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The sockaddr is returned in IP(V6)_RECVERR as part of errhdr. That
structure is defined and allocated on the stack as
struct {
struct sock_extended_err ee;
struct sockaddr_in(6) offender;
} errhdr;
The second part is only initialized for certain SO_EE_ORIGIN values.
Always initialize it completely.
An MTU exceeded error on a SOCK_RAW/IPPROTO_RAW is one example that
would return uninitialized bytes.
Signed-off-by: Willem de Bruijn <willemb@google.com>
----
Also verified that there is no padding between errhdr.ee and
errhdr.offender that could leak additional kernel data.
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
RAW sockets with hdrinc suffer from contention on rt_uncached_lock
spinlock.
One solution is to use percpu lists, since most routes are destroyed
by the cpu that created them.
It is unclear why we even have to put these routes in uncached_list,
as all outgoing packets should be freed when a device is dismantled.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Fixes: caacf05e5a ("ipv4: Properly purge netdev references on uncached routes.")
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts:
drivers/net/xen-netfront.c
Minor overlapping changes in xen-netfront.c, mostly to do
with some buffer management changes alongside the split
of stats into TX and RX.
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch introduces udp_offload_callbacks which has the same
GRO functions (but not a GSO function) as offload_callbacks,
except there is an argument to a udp_offload struct passed to
gro_receive and gro_complete functions. This additional argument
can be used to retrieve the per port structure of the encapsulation
for use in gro processing (mostly by doing container_of on the
structure).
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The same macros are used for rx as well. So rename it.
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
With TLP, the peer may reply to a probe with an
ACK+D-SACK, with ack value set to tlp_high_seq. In the current code,
such ACK+DSACK will be missed and only at next, higher ack will the TLP
episode be considered done. Since the DSACK is not present anymore,
this will cost a cwnd reduction.
This patch ensures that this scenario does not cause a cwnd reduction, since
receiving an ACK+DSACK indicates that both the initial segment and the probe
have been received by the peer.
The following packetdrill test, from Neal Cardwell, validates this patch:
// Establish a connection.
0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+0 bind(3, ..., ...) = 0
+0 listen(3, 1) = 0
+0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
+0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 6>
+.020 < . 1:1(0) ack 1 win 257
+0 accept(3, ..., ...) = 4
// Send 1 packet.
+0 write(4, ..., 1000) = 1000
+0 > P. 1:1001(1000) ack 1
// Loss probe retransmission.
// packets_out == 1 => schedule PTO in max(2*RTT, 1.5*RTT + 200ms)
// In this case, this means: 1.5*RTT + 200ms = 230ms
+.230 > P. 1:1001(1000) ack 1
+0 %{ assert tcpi_snd_cwnd == 10 }%
// Receiver ACKs at tlp_high_seq with a DSACK,
// indicating they received the original packet and probe.
+.020 < . 1:1(0) ack 1001 win 257 <sack 1:1001,nop,nop>
+0 %{ assert tcpi_snd_cwnd == 10 }%
// Send another packet.
+0 write(4, ..., 1000) = 1000
+0 > P. 1001:2001(1000) ack 1
// Receiver ACKs above tlp_high_seq, which should end the TLP episode
// if we haven't already. We should not reduce cwnd.
+.020 < . 1:1(0) ack 2001 win 257
+0 %{ assert tcpi_snd_cwnd == 10, tcpi_snd_cwnd }%
Credits:
-Gregory helped in finding that tcp_process_tlp_ack was where the cwnd
got reduced in our MPTCP tests.
-Neal wrote the packetdrill test above
-Yuchung reworked the patch to make it more readable.
Cc: Gregory Detal <gregory.detal@uclouvain.be>
Cc: Nandita Dukkipati <nanditad@google.com>
Tested-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Yuchung Cheng <ycheng@google.com>
Reviewed-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Sébastien Barré <sebastien.barre@uclouvain.be>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pablo Neira Ayuso says:
====================
netfilter/ipvs fixes for net
The following patchset contains netfilter/ipvs fixes, they are:
1) Small fix for the FTP helper in IPVS, a diff variable may be left
unset when CONFIG_IP_VS_IPV6 is set. Patch from Dan Carpenter.
2) Fix nf_tables port NAT in little endian archs, patch from leroy
christophe.
3) Fix race condition between conntrack confirmation and flush from
userspace. This is the second reincarnation to resolve this problem.
4) Make sure inner messages in the batch come with the nfnetlink header.
5) Relax strict check from nfnetlink_bind() that may break old userspace
applications using all 1s group mask.
6) Schedule removal of chains once no sets and rules refer to them in
the new nf_tables ruleset flush command. Reported by Asbjoern Sloth
Toennesen.
Note that this batch comes later than usual because of the short
winter holidays.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
This work adds the possibility to define a per route/destination
congestion control algorithm. Generally, this opens up the possibility
for a machine with different links to enforce specific congestion
control algorithms with optimal strategies for each of them based
on their network characteristics, even transparently for a single
application listening on all links.
For our specific use case, this additionally facilitates deployment
of DCTCP, for example, applications can easily serve internal
traffic/dsts in DCTCP and external one with CUBIC. Other scenarios
would also allow for utilizing e.g. long living, low priority
background flows for certain destinations/routes while still being
able for normal traffic to utilize the default congestion control
algorithm. We also thought about a per netns setting (where different
defaults are possible), but given its actually a link specific
property, we argue that a per route/destination setting is the most
natural and flexible.
The administrator can utilize this through ip-route(8) by appending
"congctl [lock] <name>", where <name> denotes the name of a
congestion control algorithm and the optional lock parameter allows
to enforce the given algorithm so that applications in user space
would not be allowed to overwrite that algorithm for that destination.
The dst metric lookups are being done when a dst entry is already
available in order to avoid a costly lookup and still before the
algorithms are being initialized, thus overhead is very low when the
feature is not being used. While the client side would need to drop
the current reference on the module, on server side this can actually
even be avoided as we just got a flat-copied socket clone.
Joint work with Florian Westphal.
Suggested-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds the minimum necessary for the RTAX_CC_ALGO congestion
control metric to be set up and dumped back to user space.
While the internal representation of RTAX_CC_ALGO is handled as a u32
key, we avoided to expose this implementation detail to user space, thus
instead, we chose the netlink attribute that is being exchanged between
user space to be the actual congestion control algorithm name, similarly
as in the setsockopt(2) API in order to allow for maximum flexibility,
even for 3rd party modules.
It is a bit unfortunate that RTAX_QUICKACK used up a whole RTAX slot as
it should have been stored in RTAX_FEATURES instead, we first thought
about reusing it for the congestion control key, but it brings more
complications and/or confusion than worth it.
Joint work with Florian Westphal.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds necessary infrastructure to the congestion control
framework for later per route congestion control support.
For a per route congestion control possibility, our aim is to store
a unique u32 key identifier into dst metrics, which can then be
mapped into a tcp_congestion_ops struct. We argue that having a
RTAX key entry is the most simple, generic and easy way to manage,
and also keeps the memory footprint of dst entries lower on 64 bit
than with storing a pointer directly, for example. Having a unique
key id also allows for decoupling actual TCP congestion control
module management from the FIB layer, i.e. we don't have to care
about expensive module refcounting inside the FIB at this point.
We first thought of using an IDR store for the realization, which
takes over dynamic assignment of unused key space and also performs
the key to pointer mapping in RCU. While doing so, we stumbled upon
the issue that due to the nature of dynamic key distribution, it
just so happens, arguably in very rare occasions, that excessive
module loads and unloads can lead to a possible reuse of previously
used key space. Thus, previously stale keys in the dst metric are
now being reassigned to a different congestion control algorithm,
which might lead to unexpected behaviour. One way to resolve this
would have been to walk FIBs on the actually rare occasion of a
module unload and reset the metric keys for each FIB in each netns,
but that's just very costly.
Therefore, we argue a better solution is to reuse the unique
congestion control algorithm name member and map that into u32 key
space through jhash. For that, we split the flags attribute (as it
currently uses 2 bits only anyway) into two u32 attributes, flags
and key, so that we can keep the cacheline boundary of 2 cachelines
on x86_64 and cache the precalculated key at registration time for
the fast path. On average we might expect 2 - 4 modules being loaded
worst case perhaps 15, so a key collision possibility is extremely
low, and guaranteed collision-free on LE/BE for all in-tree modules.
Overall this results in much simpler code, and all without the
overhead of an IDR. Due to the deterministic nature, modules can
now be unloaded, the congestion control algorithm for a specific
but unloaded key will fall back to the default one, and on module
reload time it will switch back to the expected algorithm
transparently.
Joint work with Florian Westphal.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We can just move this to an extra function and make the code
a bit more readable, no functional change.
Joint work with Florian Westphal.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add ip_cmsg_recv_offset function which takes an offset argument
that indicates the starting offset in skb where data is being received
from. This will be useful in the case of UDP and provided checksum
to user space.
ip_cmsg_recv is an inline call to ip_cmsg_recv_offset with offset of
zero.
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add ip_cmsg_recv_offset function which takes an offset argument
that indicates the starting offset in skb where data is being received
from. This will be useful in the case of UDP and provided checksum
to user space.
ip_cmsg_recv is an inline call to ip_cmsg_recv_offset with offset of
zero.
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Move the IP_CMSG_* constants from ip_sockglue.c to inet_sock.h so that
they can be referenced in other source files.
Restructure ip_cmsg_recv to not go through flags using shift, check
for flags by 'and'. This eliminates both the shift and a conditional
per flag check.
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Move convert_csum from udp_sock to inet_sock. This allows the
possibility that we can use convert checksum for different types
of sockets and also allows convert checksum to be enabled from
inet layer (what we'll want to do when enabling IP_CHECKSUM cmsg).
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When searching for an existing socket to reuse, the address family
is not taken into account - only port number. This means that an
IPv4 socket could be used for IPv6 traffic and vice versa, which
is sure to cause problems when passing packets.
It is not possible to trigger this problem currently because the
only user of Geneve creates just IPv4 sockets. However, that is
likely to change in the near future.
Signed-off-by: Jesse Gross <jesse@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The hash table for open Geneve ports is used only on creation and
deletion time. It is not performance critical and is not likely to
grow to a large number of items. Therefore, this can be changed
to use a simple linked list.
Signed-off-by: Jesse Gross <jesse@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The existing Geneve locking scheme was pulled over directly from
VXLAN. However, VXLAN has a number of built in mechanisms which make
the locking more complex and are unlikely to be necessary with Geneve.
This simplifies the locking to use a basic scheme of a mutex
when doing updates plus RCU on receive.
In addition to making the code easier to read, this also avoids the
possibility of a race when creating or destroying sockets since
UDP sockets and the list of Geneve sockets are protected by different
locks. After this change, the entire operation is atomic.
Signed-off-by: Jesse Gross <jesse@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The work queue is used only to free the UDP socket upon destruction.
This is not necessary with Geneve and generally makes the code more
difficult to reason about. It also introduces nondeterministic
behavior such as when a socket is rapidly deleted and recreated, which
could fail as the the deletion happens asynchronously.
Signed-off-by: Jesse Gross <jesse@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Thomas Jarosch reported IPsec TCP stalls when a PMTU event occurs.
In fact the problem was completely unrelated to IPsec. The bug is
also reproducible if you just disable TSO/GSO.
The problem is that when the MSS goes down, existing queued packet
on the TX queue that have not been transmitted yet all look like
TSO packets and get treated as such.
This then triggers a bug where tcp_mss_split_point tells us to
generate a zero-sized packet on the TX queue. Once that happens
we're screwed because the zero-sized packet can never be removed
by ACKs.
Fixes: 1485348d24 ("tcp: Apply device TSO segment limit earlier")
Reported-by: Thomas Jarosch <thomas.jarosch@intra2net.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Cheers,
Signed-off-by: David S. Miller <davem@davemloft.net>
This results in an approximately 30% increase in throughput
when handling encapsulated bulk traffic.
Signed-off-by: Joe Stringer <joestringer@nicira.com>
Signed-off-by: Jesse Gross <jesse@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This change adds a tracking value for the maximum suffix length of all
prefixes stored in any given tnode. With this value we can determine if we
need to backtrace or not based on if the suffix is greater than the pos
value.
By doing this we can reduce the CPU overhead for lookups in the local table
as many of the prefixes there are 32b long and have a suffix length of 0
meaning we can immediately backtrace to the root node without needing to
test any of the nodes between it and where we ended up.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
For some reason the compiler doesn't seem to understand that when we are in
a loop that runs from tnode_child_length - 1 to 0 we don't expect the value
of tn->bits to change. As such every call to tnode_get_child was rerunning
tnode_chile_length which ended up consuming quite a bit of space in the
resultant assembly code.
I have gone though and verified that in all cases where tnode_get_child
is used we are either winding though a fixed loop from tnode_child_length -
1 to 0, or are in a fastpath case where we are verifying the value by
either checking for any remaining bits after shifting index by bits and
testing for leaf, or by using tnode_child_length.
size net/ipv4/fib_trie.o
Before:
text data bss dec hex filename
15506 376 8 15890 3e12 net/ipv4/fib_trie.o
After:
text data bss dec hex filename
14827 376 8 15211 3b6b net/ipv4/fib_trie.o
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This change pulls the node_set_parent functionality out of put_child_reorg
and instead leaves that to the function to take care of as well. By doing
this we can fully construct the new cluster of tnodes and all of the
pointers out of it before we start routing pointers into it.
I am suspecting this will likely fix some concurency issues though I don't
have a good test to show as such.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This change pushes the tnode freeing down into the inflate and halve
functions. It makes more sense here as we have a better grasp of what is
going on and when a given cluster of nodes is ready to be freed.
I believe this may address a bug in the freeing logic as well. For some
reason if the freelist got to a certain size we would call
synchronize_rcu(). I'm assuming that what they meant to do is call
synchronize_rcu() after they had handed off that much memory via
call_rcu(). As such that is what I have updated the behavior to be.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This change makes it so that the assignment of the tnode to the parent is
handled directly within whatever function is currently handling the node be
it inflate, halve, or resize. By doing this we can avoid some of the need
to set NULL pointers in the tree while we are resizing the subnodes.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This change pulls the logic for if we should inflate/halve the nodes out
into separate functions. It also addresses what I believe is a bug where 1
full node is all that is needed to keep a node from ever being halved.
Simple script to reproduce the issue:
modprobe dummy; ifconfig dummy0 up
for i in `seq 0 255`; do ifconfig dummy0:$i 10.0.${i}.1/24 up; done
ifconfig dummy0:256 10.0.255.33/16 up
for i in `seq 0 254`; do ifconfig dummy0:$i down; done
Results from /proc/net/fib_triestat
Before:
Local:
Aver depth: 3.00
Max depth: 4
Leaves: 17
Prefixes: 18
Internal nodes: 11
1: 8 2: 2 10: 1
Pointers: 1048
Null ptrs: 1021
Total size: 11 kB
After:
Local:
Aver depth: 3.41
Max depth: 5
Leaves: 17
Prefixes: 18
Internal nodes: 12
1: 8 2: 3 3: 1
Pointers: 36
Null ptrs: 8
Total size: 3 kB
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This change consists of a cut/paste of resize to behind inflate and halve
so that I could remove the two function prototypes.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This change is to start cleaning up some of the rcu_read_lock/unlock
handling. I realized while reviewing the code there are several spots that
I don't believe are being handled correctly or are masking warnings by
locally calling rcu_read_lock/unlock instead of calling them at the correct
level.
A common example is a call to fib_get_table followed by fib_table_lookup.
The rcu_read_lock/unlock ought to wrap both but there are several spots where
they were not wrapped.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This change makes it so that anything that can be shifted by, or compared
to a value shifted by bits is updated to be an unsigned long. This is
mostly a precaution against an insanely huge address space that somehow
starts coming close to the 2^32 root node size which would require
something like 1.5 billion addresses.
I chose unsigned long instead of unsigned long long since I do not believe
it is possible to allocate a 32 bit tnode on a 32 bit system as the memory
consumed would be 16GB + 28B which exceeds the addressible space for any
one process.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This change moves the pos value to the other side of the "bits" field. By
doing this it actually simplifies a significant amount of code in the trie.
For example when halving a tree we know that the bit lost exists at
oldnode->pos, and if we inflate the tree the new bit being add is at
tn->pos. Previously to find those bits you would have to subtract pos and
bits from the keylength or start with a value of (1 << 31) and then shift
that.
There are a number of spots throughout the code that benefit from this. In
the case of the hot-path searches the main advantage is that we can drop 2
or more operations from the search path as we no longer need to compute the
value for the index to be shifted by and can instead just use the raw pos
value.
In addition the tkey_extract_bits is now defunct and can be replaced by
get_index since the two operations were doing the same thing, but now
get_index does it much more quickly as it is only an xor and shift versus a
pair of shifts and a subtraction.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch updates the fib_table_insert function to take advantage of the
changes made to improve the performance of fib_table_lookup. As a result
the code should be smaller and run faster then the original.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch makes use of the same features I made use of for
fib_table_lookup to streamline fib_find_node. The resultant code should be
smaller and run faster than the original.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch is meant to reduce the complexity of fib_table_lookup by reducing
the number of variables to the bare minimum while still keeping the same if
not improved functionality versus the original.
Most of this change was started off by the desire to rid the function of
chopped_off and current_prefix_length as they actually added very little to
the function since they only applied when computing the cindex. I was able
to replace them mostly with just a check for the prefix match. As long as
the prefix between the key and the node being tested was the same we know
we can search the tnode fully versus just testing cindex 0.
The second portion of the change ended up being a massive reordering.
Originally the calls to check_leaf were up near the start of the loop, and
the backtracing and descending into lower levels of tnodes was later. This
didn't make much sense as the structure of the tree means the leaves are
always the last thing to be tested. As such I reordered things so that we
instead have a loop that will delve into the tree and only exit when we
have either found a leaf or we have exhausted the tree. The advantage of
rearranging things like this is that we can fully inline check_leaf since
there is now only one reference to it in the function.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This change makes it so that leaf and tnode are the same struct. As a
result there is no need for rt_trie_node anymore since everyting can be
merged into tnode.
On 32b systems this results in the leaf being 4 bytes larger, however I
don't know if that is really an issue as this and an eariler patch that
added bits & pos have increased the size from 20 to 28. If I am not
mistaken slub/slab allocate on power of 2 sizes so 20 was likely being
rounded up to 32 anyway.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Both the leaf and the tnode had an rcu_head in them, but they had them in
slightly different places. Since we now have them in the same spot and
know that any node with bits == 0 is a leaf and the rest are either vmalloc
or kmalloc tnodes depending on the value of bits it makes it easy to combine
the functions and reduce overhead.
In addition I have taken advantage of the rcu_head pointer to go ahead and
put together a simple linked list instead of using the tnode pointer as
this way we can merge either type of structure for freeing.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This change makes some fundamental changes to the way leaves and tnodes are
constructed. The big differences are:
1. Leaves now populate pos and bits indicating their full key size.
2. Trie nodes now mask out their lower bits to be consistent with the leaf
3. Both structures have been reordered so that rt_trie_node now consisists
of a much larger region including the pos, bits, and rcu portions of
the tnode structure.
On 32b systems this will result in the leaf being 4B larger as the pos and
bits values were added to a hole created by the key as it was only 4B in
length.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The trie usage stats were currently being shared by all threads that were
calling fib_table_lookup. As a result when multiple threads were
performing lookups simultaneously the trie would begin to cache bounce
between those threads.
In order to prevent this I have updated the usage stats to use a set of
percpu variables. By doing this we should be able to avoid the cache
bouncing and still make use of these stats.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The GRE tap device supports Ethernet over GRE, but doesn't
care about the source address of the tunnel, therefore it
can be changed without bring device down.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Today vport-send has complex error handling because it involves
freeing skb and updating stats depending on return value from
vport send implementation.
This can be simplified by delegating responsibility of freeing
skb to the vport implementation for all cases. So that
vport-send needs just update stats.
Fixes: 91b7514cdf ("openvswitch: Unify vport error stats
handling")
Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Make sure this fetches 16-bits port data from the register.
Remove casting to make sparse happy, not needed anymore.
Signed-off-by: leroy christophe <christophe.leroy@c-s.fr>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Currently, searching for a socket to add a reference to is not
synchronized with deletion of sockets. This can result in use
after free if there is another operation that is removing a
socket at the same time. Solving this requires both holding the
appropriate lock and checking the refcount to ensure that it
has not already hit zero.
Inspired by a related (but not exactly the same) issue in the
VXLAN driver.
Fixes: 0b5e8b8e ("net: Add Geneve tunneling protocol driver")
CC: Andy Zhou <azhou@nicira.com>
Signed-off-by: Jesse Gross <jesse@nicira.com>
Acked-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Sockets aren't currently removed from the the global list when
they are destroyed. In addition, offload handlers need to be cleaned
up as well.
Fixes: 0b5e8b8e ("net: Add Geneve tunneling protocol driver")
CC: Andy Zhou <azhou@nicira.com>
Signed-off-by: Jesse Gross <jesse@nicira.com>
Acked-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
The encap->type comes straight from Netlink. Validate it against
max supported encap types just like ip_encap_hlen() already does.
Fixes: a8c5f9 ("ip_tunnel: Ops registration for secondary encap (fou, gue)")
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
The symbols are exported and could be used by external modules.
Fixes: a8c5f9 ("ip_tunnel: Ops registration for secondary encap (fou, gue)")
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
The NBMA GRE tunnels temporarily push GRE header that contain the
per-packet NBMA destination on the skb via header ops early in xmit
path. It is the later pulled before the real GRE header is constructed.
The inner mac was thus set differently in nbma case: the GRE header
has been pushed by neighbor layer, and mac header points to beginning
of the temporary gre header (set by dev_queue_xmit).
Now that the offloads expect mac header to point to the gre payload,
fix the xmit patch to:
- pull first the temporary gre header away
- and reset mac header to point to gre payload
This fixes tso to work again with nbma tunnels.
Fixes: 14051f0452 ("gre: Use inner mac length when computing tunnel length")
Signed-off-by: Timo Teräs <timo.teras@iki.fi>
Cc: Tom Herbert <therbert@google.com>
Cc: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch addresses an issue with the level compression of the fib_trie.
Specifically in the case of adding a new leaf that triggers a new node to
be added that takes the place of the old node. The result is a trie where
the 1 child tnode is on one side and one leaf is on the other which gives
you a very deep trie. Below is the script I used to generate a trie on
dummy0 with a 10.X.X.X family of addresses.
ip link add type dummy
ipval=184549374
bit=2
for i in `seq 1 23`
do
ifconfig dummy0:$bit $ipval/8
ipval=`expr $ipval - $bit`
bit=`expr $bit \* 2`
done
cat /proc/net/fib_triestat
Running the script before the patch:
Local:
Aver depth: 10.82
Max depth: 23
Leaves: 29
Prefixes: 30
Internal nodes: 27
1: 26 2: 1
Pointers: 56
Null ptrs: 1
Total size: 5 kB
After applying the patch and repeating:
Local:
Aver depth: 4.72
Max depth: 9
Leaves: 29
Prefixes: 30
Internal nodes: 12
1: 3 2: 2 3: 7
Pointers: 70
Null ptrs: 30
Total size: 4 kB
What this fix does is start the rebalance at the newly created tnode
instead of at the parent tnode. This way if there is a gap between the
parent and the new node it doesn't prevent the new tnode from being
coalesced with any pre-existing nodes that may have been pushed into one
of the new nodes child branches.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull networking updates from David Miller:
1) New offloading infrastructure and example 'rocker' driver for
offloading of switching and routing to hardware.
This work was done by a large group of dedicated individuals, not
limited to: Scott Feldman, Jiri Pirko, Thomas Graf, John Fastabend,
Jamal Hadi Salim, Andy Gospodarek, Florian Fainelli, Roopa Prabhu
2) Start making the networking operate on IOV iterators instead of
modifying iov objects in-situ during transfers. Thanks to Al Viro
and Herbert Xu.
3) A set of new netlink interfaces for the TIPC stack, from Richard
Alpe.
4) Remove unnecessary looping during ipv6 routing lookups, from Martin
KaFai Lau.
5) Add PAUSE frame generation support to gianfar driver, from Matei
Pavaluca.
6) Allow for larger reordering levels in TCP, which are easily
achievable in the real world right now, from Eric Dumazet.
7) Add a variable of napi_schedule that doesn't need to disable cpu
interrupts, from Eric Dumazet.
8) Use a doubly linked list to optimize neigh_parms_release(), from
Nicolas Dichtel.
9) Various enhancements to the kernel BPF verifier, and allow eBPF
programs to actually be attached to sockets. From Alexei
Starovoitov.
10) Support TSO/LSO in sunvnet driver, from David L Stevens.
11) Allow controlling ECN usage via routing metrics, from Florian
Westphal.
12) Remote checksum offload, from Tom Herbert.
13) Add split-header receive, BQL, and xmit_more support to amd-xgbe
driver, from Thomas Lendacky.
14) Add MPLS support to openvswitch, from Simon Horman.
15) Support wildcard tunnel endpoints in ipv6 tunnels, from Steffen
Klassert.
16) Do gro flushes on a per-device basis using a timer, from Eric
Dumazet. This tries to resolve the conflicting goals between the
desired handling of bulk vs. RPC-like traffic.
17) Allow userspace to ask for the CPU upon what a packet was
received/steered, via SO_INCOMING_CPU. From Eric Dumazet.
18) Limit GSO packets to half the current congestion window, from Eric
Dumazet.
19) Add a generic helper so that all drivers set their RSS keys in a
consistent way, from Eric Dumazet.
20) Add xmit_more support to enic driver, from Govindarajulu
Varadarajan.
21) Add VLAN packet scheduler action, from Jiri Pirko.
22) Support configurable RSS hash functions via ethtool, from Eyal
Perry.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1820 commits)
Fix race condition between vxlan_sock_add and vxlan_sock_release
net/macb: fix compilation warning for print_hex_dump() called with skb->mac_header
net/mlx4: Add support for A0 steering
net/mlx4: Refactor QUERY_PORT
net/mlx4_core: Add explicit error message when rule doesn't meet configuration
net/mlx4: Add A0 hybrid steering
net/mlx4: Add mlx4_bitmap zone allocator
net/mlx4: Add a check if there are too many reserved QPs
net/mlx4: Change QP allocation scheme
net/mlx4_core: Use tasklet for user-space CQ completion events
net/mlx4_core: Mask out host side virtualization features for guests
net/mlx4_en: Set csum level for encapsulated packets
be2net: Export tunnel offloads only when a VxLAN tunnel is created
gianfar: Fix dma check map error when DMA_API_DEBUG is enabled
cxgb4/csiostor: Don't use MASTER_MUST for fw_hello call
net: fec: only enable mdio interrupt before phy device link up
net: fec: clear all interrupt events to support i.MX6SX
net: fec: reset fep link status in suspend function
net: sock: fix access via invalid file descriptor
net: introduce helper macro for_each_cmsghdr
...
Introduce helper macro for_each_cmsghdr as a wrapper of the enumerating
cmsghdr from msghdr, just cleanup.
Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Merge first patchbomb from Andrew Morton:
- a few minor cifs fixes
- dma-debug upadtes
- ocfs2
- slab
- about half of MM
- procfs
- kernel/exit.c
- panic.c tweaks
- printk upates
- lib/ updates
- checkpatch updates
- fs/binfmt updates
- the drivers/rtc tree
- nilfs
- kmod fixes
- more kernel/exit.c
- various other misc tweaks and fixes
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (190 commits)
exit: pidns: fix/update the comments in zap_pid_ns_processes()
exit: pidns: alloc_pid() leaks pid_namespace if child_reaper is exiting
exit: exit_notify: re-use "dead" list to autoreap current
exit: reparent: call forget_original_parent() under tasklist_lock
exit: reparent: avoid find_new_reaper() if no children
exit: reparent: introduce find_alive_thread()
exit: reparent: introduce find_child_reaper()
exit: reparent: document the ->has_child_subreaper checks
exit: reparent: s/while_each_thread/for_each_thread/ in find_new_reaper()
exit: reparent: fix the cross-namespace PR_SET_CHILD_SUBREAPER reparenting
exit: reparent: fix the dead-parent PR_SET_CHILD_SUBREAPER reparenting
exit: proc: don't try to flush /proc/tgid/task/tgid
exit: release_task: fix the comment about group leader accounting
exit: wait: drop tasklist_lock before psig->c* accounting
exit: wait: don't use zombie->real_parent
exit: wait: cleanup the ptrace_reparented() checks
usermodehelper: kill the kmod_thread_locker logic
usermodehelper: don't use CLONE_VFORK for ____call_usermodehelper()
fs/hfs/catalog.c: fix comparison bug in hfs_cat_keycmp
nilfs2: fix the nilfs_iget() vs. nilfs_new_inode() races
...
Memory is internally accounted in bytes, using spinlock-protected 64-bit
counters, even though the smallest accounting delta is a page. The
counter interface is also convoluted and does too many things.
Introduce a new lockless word-sized page counter API, then change all
memory accounting over to it. The translation from and to bytes then only
happens when interfacing with userspace.
The removed locking overhead is noticable when scaling beyond the per-cpu
charge caches - on a 4-socket machine with 144-threads, the following test
shows the performance differences of 288 memcgs concurrently running a
page fault benchmark:
vanilla:
18631648.500498 task-clock (msec) # 140.643 CPUs utilized ( +- 0.33% )
1,380,638 context-switches # 0.074 K/sec ( +- 0.75% )
24,390 cpu-migrations # 0.001 K/sec ( +- 8.44% )
1,843,305,768 page-faults # 0.099 M/sec ( +- 0.00% )
50,134,994,088,218 cycles # 2.691 GHz ( +- 0.33% )
<not supported> stalled-cycles-frontend
<not supported> stalled-cycles-backend
8,049,712,224,651 instructions # 0.16 insns per cycle ( +- 0.04% )
1,586,970,584,979 branches # 85.176 M/sec ( +- 0.05% )
1,724,989,949 branch-misses # 0.11% of all branches ( +- 0.48% )
132.474343877 seconds time elapsed ( +- 0.21% )
lockless:
12195979.037525 task-clock (msec) # 133.480 CPUs utilized ( +- 0.18% )
832,850 context-switches # 0.068 K/sec ( +- 0.54% )
15,624 cpu-migrations # 0.001 K/sec ( +- 10.17% )
1,843,304,774 page-faults # 0.151 M/sec ( +- 0.00% )
32,811,216,801,141 cycles # 2.690 GHz ( +- 0.18% )
<not supported> stalled-cycles-frontend
<not supported> stalled-cycles-backend
9,999,265,091,727 instructions # 0.30 insns per cycle ( +- 0.10% )
2,076,759,325,203 branches # 170.282 M/sec ( +- 0.12% )
1,656,917,214 branch-misses # 0.08% of all branches ( +- 0.55% )
91.369330729 seconds time elapsed ( +- 0.45% )
On top of improved scalability, this also gets rid of the icky long long
types in the very heart of memcg, which is great for 32 bit and also makes
the code a lot more readable.
Notable differences between the old and new API:
- res_counter_charge() and res_counter_charge_nofail() become
page_counter_try_charge() and page_counter_charge() resp. to match
the more common kernel naming scheme of try_do()/do()
- res_counter_uncharge_until() is only ever used to cancel a local
counter and never to uncharge bigger segments of a hierarchy, so
it's replaced by the simpler page_counter_cancel()
- res_counter_set_limit() is replaced by page_counter_limit(), which
expects its callers to serialize against themselves
- res_counter_memparse_write_strategy() is replaced by
page_counter_limit(), which rounds down to the nearest page size -
rather than up. This is more reasonable for explicitely requested
hard upper limits.
- to keep charging light-weight, page_counter_try_charge() charges
speculatively, only to roll back if the result exceeds the limit.
Because of this, a failing bigger charge can temporarily lock out
smaller charges that would otherwise succeed. The error is bounded
to the difference between the smallest and the biggest possible
charge size, so for memcg, this means that a failing THP charge can
send base page charges into reclaim upto 2MB (4MB) before the limit
would have been reached. This should be acceptable.
[akpm@linux-foundation.org: add includes for WARN_ON_ONCE and memparse]
[akpm@linux-foundation.org: add includes for WARN_ON_ONCE, memparse, strncmp, and PAGE_SIZE]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pull VFS changes from Al Viro:
"First pile out of several (there _definitely_ will be more). Stuff in
this one:
- unification of d_splice_alias()/d_materialize_unique()
- iov_iter rewrite
- killing a bunch of ->f_path.dentry users (and f_dentry macro).
Getting that completed will make life much simpler for
unionmount/overlayfs, since then we'll be able to limit the places
sensitive to file _dentry_ to reasonably few. Which allows to have
file_inode(file) pointing to inode in a covered layer, with dentry
pointing to (negative) dentry in union one.
Still not complete, but much closer now.
- crapectomy in lustre (dead code removal, mostly)
- "let's make seq_printf return nothing" preparations
- assorted cleanups and fixes
There _definitely_ will be more piles"
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (63 commits)
copy_from_iter_nocache()
new helper: iov_iter_kvec()
csum_and_copy_..._iter()
iov_iter.c: handle ITER_KVEC directly
iov_iter.c: convert copy_to_iter() to iterate_and_advance
iov_iter.c: convert copy_from_iter() to iterate_and_advance
iov_iter.c: get rid of bvec_copy_page_{to,from}_iter()
iov_iter.c: convert iov_iter_zero() to iterate_and_advance
iov_iter.c: convert iov_iter_get_pages_alloc() to iterate_all_kinds
iov_iter.c: convert iov_iter_get_pages() to iterate_all_kinds
iov_iter.c: convert iov_iter_npages() to iterate_all_kinds
iov_iter.c: iterate_and_advance
iov_iter.c: macros for iterating over iov_iter
kill f_dentry macro
dcache: fix kmemcheck warning in switch_names
new helper: audit_file()
nfsd_vfs_write(): use file_inode()
ncpfs: use file_inode()
kill f_dentry uses
lockd: get rid of ->f_path.dentry->d_sb
...
Conflicts:
drivers/net/ethernet/amd/xgbe/xgbe-desc.c
drivers/net/ethernet/renesas/sh_eth.c
Overlapping changes in both conflict cases.
Signed-off-by: David S. Miller <davem@davemloft.net>
When I cooked commit c3658e8d0f ("tcp: fix possible NULL dereference in
tcp_vX_send_reset()") I missed other spots we could deref a NULL
skb_dst(skb)
Again, if a socket is provided, we do not need skb_dst() to get a
pointer to network namespace : sock_net(sk) is good enough.
Reported-by: Dann Frazier <dann.frazier@canonical.com>
Bisected-by: Dann Frazier <dann.frazier@canonical.com>
Tested-by: Dann Frazier <dann.frazier@canonical.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Fixes: ca777eff51 ("tcp: remove dst refcount false sharing for prequeue mode")
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 95bd09eb27 ("tcp: TSO packets automatic sizing") tried to
control TSO size, but did this at the wrong place (sendmsg() time)
At sendmsg() time, we might have a pessimistic view of flow rate,
and we end up building very small skbs (with 2 MSS per skb).
This is bad because :
- It sends small TSO packets even in Slow Start where rate quickly
increases.
- It tends to make socket write queue very big, increasing tcp_ack()
processing time, but also increasing memory needs, not necessarily
accounted for, as fast clones overhead is currently ignored.
- Lower GRO efficiency and more ACK packets.
Servers with a lot of small lived connections suffer from this.
Lets instead fill skbs as much as possible (64KB of payload), but split
them at xmit time, when we have a precise idea of the flow rate.
skb split is actually quite efficient.
Patch looks bigger than necessary, because TCP Small Queue decision now
has to take place after the eventual split.
As Neal suggested, introduce a new tcp_tso_autosize() helper, so that
tcp_tso_should_defer() can be synchronized on same goal.
Rename tp->xmit_size_goal_segs to tp->gso_segs, as this variable
contains number of mss that we can put in GSO packet, and is not
related to the autosizing goal anymore.
Tested:
40 ms rtt link
nstat >/dev/null
netperf -H remote -l -2000000 -- -s 1000000
nstat | egrep "IpInReceives|IpOutRequests|TcpOutSegs|IpExtOutOctets"
Before patch :
Recv Send Send
Socket Socket Message Elapsed
Size Size Size Time Throughput
bytes bytes bytes secs. 10^6bits/s
87380 2000000 2000000 0.36 44.22
IpInReceives 600 0.0
IpOutRequests 599 0.0
TcpOutSegs 1397 0.0
IpExtOutOctets 2033249 0.0
After patch :
Recv Send Send
Socket Socket Message Elapsed
Size Size Size Time Throughput
bytes bytes bytes secs. 10^6bits/sec
87380 2000000 2000000 0.36 44.27
IpInReceives 221 0.0
IpOutRequests 232 0.0
TcpOutSegs 1397 0.0
IpExtOutOctets 2013953 0.0
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Note that the code _using_ ->msg_iter at that point will be very
unhappy with anything other than unshifted iovec-backed iov_iter.
We still need to convert users to proper primitives.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
In commit 2b4636a5f8 ("tcp_cubic: make the delay threshold of HyStart
less sensitive"), HYSTART_DELAY_MIN was changed to 4 ms.
The remaining problem is that using delay_min + (delay_min/16) as the
threshold is too sensitive.
6.25 % of variation is too small for rtt above 60 ms, which are not
uncommon.
Lets use 12.5 % instead (delay_min + (delay_min/8))
Tested:
80 ms RTT between peers, FQ/pacing packet scheduler on sender.
10 bulk transfers of 10 seconds :
nstat >/dev/null
for i in `seq 1 10`
do
netperf -H remote -- -k THROUGHPUT | grep THROUGHPUT
done
nstat | grep Hystart
With the 6.25 % threshold :
THROUGHPUT=20.66
THROUGHPUT=249.38
THROUGHPUT=254.10
THROUGHPUT=14.94
THROUGHPUT=251.92
THROUGHPUT=237.73
THROUGHPUT=19.18
THROUGHPUT=252.89
THROUGHPUT=21.32
THROUGHPUT=15.58
TcpExtTCPHystartTrainDetect 2 0.0
TcpExtTCPHystartTrainCwnd 4756 0.0
TcpExtTCPHystartDelayDetect 5 0.0
TcpExtTCPHystartDelayCwnd 180 0.0
With the 12.5 % threshold
THROUGHPUT=251.09
THROUGHPUT=247.46
THROUGHPUT=250.92
THROUGHPUT=248.91
THROUGHPUT=250.88
THROUGHPUT=249.84
THROUGHPUT=250.51
THROUGHPUT=254.15
THROUGHPUT=250.62
THROUGHPUT=250.89
TcpExtTCPHystartTrainDetect 1 0.0
TcpExtTCPHystartTrainCwnd 3175 0.0
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Tested-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When deploying FQ pacing, one thing we noticed is that CUBIC Hystart
triggers too soon.
Having SNMP counters to have an idea of how often the various Hystart
methods trigger is useful prior to any modifications.
This patch adds SNMP counters tracking, how many time "ack train" or
"Delay" based Hystart triggers, and cumulative sum of cwnd at the time
Hystart decided to end SS (Slow Start)
myhost:~# nstat -a | grep Hystart
TcpExtTCPHystartTrainDetect 9 0.0
TcpExtTCPHystartTrainCwnd 20650 0.0
TcpExtTCPHystartDelayDetect 10 0.0
TcpExtTCPHystartDelayCwnd 360 0.0
->
Train detection was triggered 9 times, and average cwnd was
20650/9=2294,
Delay detection was triggered 10 times and average cwnd was 36
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
