This work adds BPF_CALL_<n>() macros and converts all the eBPF helper functions
to use them, in a similar fashion like we do with SYSCALL_DEFINE<n>() macros
that are used today. Motivation for this is to hide all the register handling
and all necessary casts from the user, so that it is done automatically in the
background when adding a BPF_CALL_<n>() call.
This makes current helpers easier to review, eases to write future helpers,
avoids getting the casting mess wrong, and allows for extending all helpers at
once (f.e. build time checks, etc). It also helps detecting more easily in
code reviews that unused registers are not instrumented in the code by accident,
breaking compatibility with existing programs.
BPF_CALL_<n>() internals are quite similar to SYSCALL_DEFINE<n>() ones with some
fundamental differences, for example, for generating the actual helper function
that carries all u64 regs, we need to fill unused regs, so that we always end up
with 5 u64 regs as an argument.
I reviewed several 0-5 generated BPF_CALL_<n>() variants of the .i results and
they look all as expected. No sparse issue spotted. We let this also sit for a
few days with Fengguang's kbuild test robot, and there were no issues seen. On
s390, it barked on the "uses dynamic stack allocation" notice, which is an old
one from bpf_perf_event_output{,_tp}() reappearing here due to the conversion
to the call wrapper, just telling that the perf raw record/frag sits on stack
(gcc with s390's -mwarn-dynamicstack), but that's all. Did various runtime tests
and they were fine as well. All eBPF helpers are now converted to use these
macros, getting rid of a good chunk of all the raw castings.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add BPF_SIZEOF() and BPF_FIELD_SIZEOF() macros to improve the code a bit
which otherwise often result in overly long bytes_to_bpf_size(sizeof())
and bytes_to_bpf_size(FIELD_SIZEOF()) lines. So place them into a macro
helper instead. Moreover, we currently have a BUILD_BUG_ON(BPF_FIELD_SIZEOF())
check in convert_bpf_extensions(), but we should rather make that generic
as well and add a BUILD_BUG_ON() test in all BPF_SIZEOF()/BPF_FIELD_SIZEOF()
users to detect any rewriter size issues at compile time. Note, there are
currently none, but we want to assert that it stays this way.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
David Howells says:
====================
rxrpc: Rewrite data and ack handling
This patch set constitutes the main portion of the AF_RXRPC rewrite. It
consists of five fix/helper patches:
(1) Fix ASSERTCMP's and ASSERTIFCMP's handling of signed values.
(2) Update some protocol definitions slightly.
(3) Use of an hlist for RCU purposes.
(4) Removal of per-call sk_buff accounting (not really needed when skbs
aren't being queued on the main queue).
(5) Addition of a tracepoint to log incoming packets in the data_ready
callback and to log the end of the data_ready callback.
And then there are two patches that form the main part:
(6) Preallocation of resources for incoming calls so that in patch (7) the
data_ready handler can be made to fully instantiate an incoming call
and make it live. This extends through into AFS so that AFS can
preallocate its own incoming call resources.
The preallocation size is capped at the listen() backlog setting - and
that is capped at a sysctl limit which can be set between 4 and 32.
The preallocation is (re)charged either by accepting/rejecting pending
calls or, in the case of AFS, manually. If insufficient preallocation
resources exist, a BUSY packet will be transmitted.
The advantage of using this preallocation is that once a call is set
up in the data_ready handler, DATA packets can be queued on it
immediately rather than the DATA packets being queued for a background
work item to do all the allocation and then try and sort out the DATA
packets whilst other DATA packets may still be coming in and going
either to the background thread or the new call.
(7) Rewrite the handling of DATA, ACK and ABORT packets.
In the receive phase, DATA packets are now held in per-call circular
buffers with deduplication, out of sequence detection and suchlike
being done in data_ready. Since there is only one producer and only
once consumer, no locks need be used on the receive queue.
Received ACK and ABORT packets are now parsed and discarded in
data_ready to recycle resources as fast as possible.
sk_buffs are no longer pulled, trimmed or cloned, but rather the
offset and size of the content is tracked. This particularly affects
jumbo DATA packets which need insertion into the receive buffer in
multiple places. Annotations are kept to track which bit is which.
Packets are no longer queued on the socket receive queue; rather,
calls are queued. Dummy packets to convey events therefore no longer
need to be invented and metadata packets can be discarded as soon as
parsed rather then being pushed onto the socket receive queue to
indicate terminal events.
The preallocation facility added in (6) is now used to set up incoming
calls with very little locking required and no calls to the allocator
in data_ready.
Decryption and verification is now handled in recvmsg() rather than in
a background thread. This allows for the future possibility of
decrypting directly into the user buffer.
With this patch, the code is a lot simpler and most of the mass of
call event and state wangling code in call_event.c is gone.
With this, the majority of the AF_RXRPC rewrite is complete. However,
there are still things to be done, including:
(*) Limit the number of active service calls to prevent an attacker from
filling up a server's memory.
(*) Limit the number of calls on the rebuff-with-BUSY queue.
(*) Transmit delayed/deferred ACKs from recvmsg() if possible, rather than
punting to the background thread. Ideally, the background thread
shouldn't run at all, but data_ready can't call kernel_sendmsg() and
we can't rely on recvmsg() attending to the call in a timely fashion.
(*) Prevent the call at the front of the socket queue from hogging
recvmsg()'s attention if there's a sufficiently continuous supply of
data.
(*) Distribute ICMP errors by connection rather than by call. Possibly
parse the ICMP packet to try and pin down the exact connection and
call.
(*) Encrypt/decrypt directly between user buffers and socket buffers where
possible.
(*) IPv6.
(*) Service ID upgrade. This is a facility whereby a special flag bit is
set in the DATA packet header when making a call that tells the server
that it is allowed to change the service ID to an upgraded one and
reply with an equivalent call from the upgraded service.
This is used, for example, to override certain AFS calls so that IPv6
addresses can be returned.
(*) Allow userspace to preallocate call user IDs for incoming calls.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Over the years, TCP BDP has increased by several orders of magnitude,
and some people are considering to reach the 2 Gbytes limit.
Even with current window scale limit of 14, ~1 Gbytes maps to ~740,000
MSS.
In presence of packet losses (or reorders), TCP stores incoming packets
into an out of order queue, and number of skbs sitting there waiting for
the missing packets to be received can be in the 10^5 range.
Most packets are appended to the tail of this queue, and when
packets can finally be transferred to receive queue, we scan the queue
from its head.
However, in presence of heavy losses, we might have to find an arbitrary
point in this queue, involving a linear scan for every incoming packet,
throwing away cpu caches.
This patch converts it to a RB tree, to get bounded latencies.
Yaogong wrote a preliminary patch about 2 years ago.
Eric did the rebase, added ofo_last_skb cache, polishing and tests.
Tested with network dropping between 1 and 10 % packets, with good
success (about 30 % increase of throughput in stress tests)
Next step would be to also use an RB tree for the write queue at sender
side ;)
Signed-off-by: Yaogong Wang <wygivan@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Acked-By: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is to simplify using double tagged vlans. This function allows all
valid vlan ethertypes to be checked in a single function call.
Also replace some instances that check for both ETH_P_8021Q and
ETH_P_8021AD.
Patch based on one originally by Thomas F Herbert.
Signed-off-by: Thomas F Herbert <thomasfherbert@gmail.com>
Signed-off-by: Eric Garver <e@erig.me>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
openvswitch: Add support for 8021.AD
Change the description of the VLAN tpid field.
Signed-off-by: Thomas F Herbert <thomasfherbert@gmail.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
This adds the capability for a process that has CAP_NET_ADMIN on
a socket to see the socket mark in socket dumps.
Commit a52e95abf7 ("net: diag: allow socket bytecode filters to
match socket marks") recently gave privileged processes the
ability to filter socket dumps based on mark. This patch is
complementary: it ensures that the mark is also passed to
userspace in the socket's netlink attributes. It is useful for
tools like ss which display information about sockets.
Tested: https://android-review.googlesource.com/270210
Signed-off-by: Lorenzo Colitti <lorenzo@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Steffen Klassert says:
====================
ipsec-next 2016-09-08
1) Constify the xfrm_replay structures. From Julia Lawall
2) Protect xfrm state hash tables with rcu, lookups
can be done now without acquiring xfrm_state_lock.
From Florian Westphal.
3) Protect xfrm policy hash tables with rcu, lookups
can be done now without acquiring xfrm_policy_lock.
From Florian Westphal.
4) We don't need to have a garbage collector list per
namespace anymore, so use a global one instead.
From Florian Westphal.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Rewrite the data and ack handling code such that:
(1) Parsing of received ACK and ABORT packets and the distribution and the
filing of DATA packets happens entirely within the data_ready context
called from the UDP socket. This allows us to process and discard ACK
and ABORT packets much more quickly (they're no longer stashed on a
queue for a background thread to process).
(2) We avoid calling skb_clone(), pskb_pull() and pskb_trim(). We instead
keep track of the offset and length of the content of each packet in
the sk_buff metadata. This means we don't do any allocation in the
receive path.
(3) Jumbo DATA packet parsing is now done in data_ready context. Rather
than cloning the packet once for each subpacket and pulling/trimming
it, we file the packet multiple times with an annotation for each
indicating which subpacket is there. From that we can directly
calculate the offset and length.
(4) A call's receive queue can be accessed without taking locks (memory
barriers do have to be used, though).
(5) Incoming calls are set up from preallocated resources and immediately
made live. They can than have packets queued upon them and ACKs
generated. If insufficient resources exist, DATA packet #1 is given a
BUSY reply and other DATA packets are discarded).
(6) sk_buffs no longer take a ref on their parent call.
To make this work, the following changes are made:
(1) Each call's receive buffer is now a circular buffer of sk_buff
pointers (rxtx_buffer) rather than a number of sk_buff_heads spread
between the call and the socket. This permits each sk_buff to be in
the buffer multiple times. The receive buffer is reused for the
transmit buffer.
(2) A circular buffer of annotations (rxtx_annotations) is kept parallel
to the data buffer. Transmission phase annotations indicate whether a
buffered packet has been ACK'd or not and whether it needs
retransmission.
Receive phase annotations indicate whether a slot holds a whole packet
or a jumbo subpacket and, if the latter, which subpacket. They also
note whether the packet has been decrypted in place.
(3) DATA packet window tracking is much simplified. Each phase has just
two numbers representing the window (rx_hard_ack/rx_top and
tx_hard_ack/tx_top).
The hard_ack number is the sequence number before base of the window,
representing the last packet the other side says it has consumed.
hard_ack starts from 0 and the first packet is sequence number 1.
The top number is the sequence number of the highest-numbered packet
residing in the buffer. Packets between hard_ack+1 and top are
soft-ACK'd to indicate they've been received, but not yet consumed.
Four macros, before(), before_eq(), after() and after_eq() are added
to compare sequence numbers within the window. This allows for the
top of the window to wrap when the hard-ack sequence number gets close
to the limit.
Two flags, RXRPC_CALL_RX_LAST and RXRPC_CALL_TX_LAST, are added also
to indicate when rx_top and tx_top point at the packets with the
LAST_PACKET bit set, indicating the end of the phase.
(4) Calls are queued on the socket 'receive queue' rather than packets.
This means that we don't need have to invent dummy packets to queue to
indicate abnormal/terminal states and we don't have to keep metadata
packets (such as ABORTs) around
(5) The offset and length of a (sub)packet's content are now passed to
the verify_packet security op. This is currently expected to decrypt
the packet in place and validate it.
However, there's now nowhere to store the revised offset and length of
the actual data within the decrypted blob (there may be a header and
padding to skip) because an sk_buff may represent multiple packets, so
a locate_data security op is added to retrieve these details from the
sk_buff content when needed.
(6) recvmsg() now has to handle jumbo subpackets, where each subpacket is
individually secured and needs to be individually decrypted. The code
to do this is broken out into rxrpc_recvmsg_data() and shared with the
kernel API. It now iterates over the call's receive buffer rather
than walking the socket receive queue.
Additional changes:
(1) The timers are condensed to a single timer that is set for the soonest
of three timeouts (delayed ACK generation, DATA retransmission and
call lifespan).
(2) Transmission of ACK and ABORT packets is effected immediately from
process-context socket ops/kernel API calls that cause them instead of
them being punted off to a background work item. The data_ready
handler still has to defer to the background, though.
(3) A shutdown op is added to the AF_RXRPC socket so that the AFS
filesystem can shut down the socket and flush its own work items
before closing the socket to deal with any in-progress service calls.
Future additional changes that will need to be considered:
(1) Make sure that a call doesn't hog the front of the queue by receiving
data from the network as fast as userspace is consuming it to the
exclusion of other calls.
(2) Transmit delayed ACKs from within recvmsg() when we've consumed
sufficiently more packets to avoid the background work item needing to
run.
Signed-off-by: David Howells <dhowells@redhat.com>
Make it possible for the data_ready handler called from the UDP transport
socket to completely instantiate an rxrpc_call structure and make it
immediately live by preallocating all the memory it might need. The idea
is to cut out the background thread usage as much as possible.
[Note that the preallocated structs are not actually used in this patch -
that will be done in a future patch.]
If insufficient resources are available in the preallocation buffers, it
will be possible to discard the DATA packet in the data_ready handler or
schedule a BUSY packet without the need to schedule an attempt at
allocation in a background thread.
To this end:
(1) Preallocate rxrpc_peer, rxrpc_connection and rxrpc_call structs to a
maximum number each of the listen backlog size. The backlog size is
limited to a maxmimum of 32. Only this many of each can be in the
preallocation buffer.
(2) For userspace sockets, the preallocation is charged initially by
listen() and will be recharged by accepting or rejecting pending
new incoming calls.
(3) For kernel services {,re,dis}charging of the preallocation buffers is
handled manually. Two notifier callbacks have to be provided before
kernel_listen() is invoked:
(a) An indication that a new call has been instantiated. This can be
used to trigger background recharging.
(b) An indication that a call is being discarded. This is used when
the socket is being released.
A function, rxrpc_kernel_charge_accept() is called by the kernel
service to preallocate a single call. It should be passed the user ID
to be used for that call and a callback to associate the rxrpc call
with the kernel service's side of the ID.
(4) Discard the preallocation when the socket is closed.
(5) Temporarily bump the refcount on the call allocated in
rxrpc_incoming_call() so that rxrpc_release_call() can ditch the
preallocation ref on service calls unconditionally. This will no
longer be necessary once the preallocation is used.
Note that this does not yet control the number of active service calls on a
client - that will come in a later patch.
A future development would be to provide a setsockopt() call that allows a
userspace server to manually charge the preallocation buffer. This would
allow user call IDs to be provided in advance and the awkward manual accept
stage to be bypassed.
Signed-off-by: David Howells <dhowells@redhat.com>
Add two tracepoints:
(1) Record the RxRPC protocol header of packets retrieved from the UDP
socket by the data_ready handler.
(2) Record the outcome of the data_ready handler.
Signed-off-by: David Howells <dhowells@redhat.com>
Remove the sk_buff count from the rxrpc_call struct as it's less useful
once we stop queueing sk_buffs.
Signed-off-by: David Howells <dhowells@redhat.com>
Update the protocol definitions in include/rxrpc/packet.h slightly:
(1) Get rid of RXRPC_PROCESS_MAXCALLS as it's redundant (same as
RXRPC_MAXCALLS).
(2) In struct rxrpc_jumbo_header, put _rsvd in a union with a field called
cksum to match struct rxrpc_wire_header.
(3) Provide RXRPC_JUMBO_SUBPKTLEN which is the total of the amount of data
in a non-terminal subpacket plus the following secondary header for
the next packet included in the jumbo packet.
Signed-off-by: David Howells <dhowells@redhat.com>
Add a tracepoint for working out where local aborts happen. Each
tracepoint call is labelled with a 3-letter code so that they can be
distinguished - and the DATA sequence number is added too where available.
rxrpc_kernel_abort_call() also takes a 3-letter code so that AFS can
indicate the circumstances when it aborts a call.
Signed-off-by: David Howells <dhowells@redhat.com>
Improve the call tracking tracepoint by showing more differentiation
between some of the put and get events, including:
(1) Getting and putting refs for the socket call user ID tree.
(2) Getting and putting refs for queueing and failing to queue the call
processor work item.
Note that these aren't necessarily used in this patch, but will be taken
advantage of in future patches.
An enum is added for the event subtype numbers rather than coding them
directly as decimal numbers and a table of 3-letter strings is provided
rather than a sequence of ?: operators.
Signed-off-by: David Howells <dhowells@redhat.com>
David Howells says:
====================
rxrpc: Small fixes
Here's a set of small fix patches:
(1) Fix some uninitialised variables.
(2) Set the client call state before making it live by attaching it to the
conn struct.
(3) Randomise the epoch and starting client conn ID values, and don't
change the epoch when the client conn ID rolls round.
(4) Replace deprecated create_singlethread_workqueue() calls.
====================
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. Most relevant updates are the removal of per-conntrack timers to
use a workqueue/garbage collection approach instead from Florian
Westphal, the hash and numgen expression for nf_tables from Laura
Garcia, updates on nf_tables hash set to honor the NLM_F_EXCL flag,
removal of ip_conntrack sysctl and many other incremental updates on our
Netfilter codebase.
More specifically, they are:
1) Retrieve only 4 bytes to fetch ports in case of non-linear skb
transport area in dccp, sctp, tcp, udp and udplite protocol
conntrackers, from Gao Feng.
2) Missing whitespace on error message in physdev match, from Hangbin Liu.
3) Skip redundant IPv4 checksum calculation in nf_dup_ipv4, from Liping Zhang.
4) Add nf_ct_expires() helper function and use it, from Florian Westphal.
5) Replace opencoded nf_ct_kill() call in IPVS conntrack support, also
from Florian.
6) Rename nf_tables set implementation to nft_set_{name}.c
7) Introduce the hash expression to allow arbitrary hashing of selector
concatenations, from Laura Garcia Liebana.
8) Remove ip_conntrack sysctl backward compatibility code, this code has
been around for long time already, and we have two interfaces to do
this already: nf_conntrack sysctl and ctnetlink.
9) Use nf_conntrack_get_ht() helper function whenever possible, instead
of opencoding fetch of hashtable pointer and size, patch from Liping Zhang.
10) Add quota expression for nf_tables.
11) Add number generator expression for nf_tables, this supports
incremental and random generators that can be combined with maps,
very useful for load balancing purpose, again from Laura Garcia Liebana.
12) Fix a typo in a debug message in FTP conntrack helper, from Colin Ian King.
13) Introduce a nft_chain_parse_hook() helper function to parse chain hook
configuration, this is used by a follow up patch to perform better chain
update validation.
14) Add rhashtable_lookup_get_insert_key() to rhashtable and use it from the
nft_set_hash implementation to honor the NLM_F_EXCL flag.
15) Missing nulls check in nf_conntrack from nf_conntrack_tuple_taken(),
patch from Florian Westphal.
16) Don't use the DYING bit to know if the conntrack event has been already
delivered, instead a state variable to track event re-delivery
states, also from Florian.
17) Remove the per-conntrack timer, use the workqueue approach that was
discussed during the NFWS, from Florian Westphal.
18) Use the netlink conntrack table dump path to kill stale entries,
again from Florian.
19) Add a garbage collector to get rid of stale conntracks, from
Florian.
20) Reschedule garbage collector if eviction rate is high.
21) Get rid of the __nf_ct_kill_acct() helper.
22) Use ARPHRD_ETHER instead of hardcoded 1 from ARP logger.
23) Make nf_log_set() interface assertive on unsupported families.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Create a random epoch value rather than a time-based one on startup and set
the top bit to indicate that this is the case.
Also create a random starting client connection ID value. This will be
incremented from here as new client connections are created.
Signed-off-by: David Howells <dhowells@redhat.com>
This patch fixes the retun value of switchdev_port_fdb_dump() when
CONFIG_NET_SWITCHDEV is not set. This avoids getting "warning: return makes
integer from pointer without a cast [-Wint-conversion]" when building
when CONFIG_NET_SWITCHDEV is not set under several compiler versions.
This warning is due to commit d297653dd6
("rtnetlink: fdb dump: optimize by saving last interface markers").
Signed-off-by: Rami Rosen <rami.rosen@intel.com>
Acked-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Reported-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Allow attaching BPF_PROG_TYPE_PERF_EVENT programs to sw and hw perf events
via overflow_handler mechanism.
When program is attached the overflow_handlers become stacked.
The program acts as a filter.
Returning zero from the program means that the normal perf_event_output handler
will not be called and sampling event won't be stored in the ring buffer.
The overflow_handler_context==NULL is an additional safety check
to make sure programs are not attached to hw breakpoints and watchdog
in case other checks (that prevent that now anyway) get accidentally
relaxed in the future.
The program refcnt is incremented in case perf_events are inhereted
when target task is forked.
Similar to kprobe and tracepoint programs there is no ioctl to
detach the program or swap already attached program. The user space
expected to close(perf_event_fd) like it does right now for kprobe+bpf.
That restriction simplifies the code quite a bit.
The invocation of overflow_handler in __perf_event_overflow() is now
done via READ_ONCE, since that pointer can be replaced when the program
is attached while perf_event itself could have been active already.
There is no need to do similar treatment for event->prog, since it's
assigned only once before it's accessed.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Introduce BPF_PROG_TYPE_PERF_EVENT programs that can be attached to
HW and SW perf events (PERF_TYPE_HARDWARE and PERF_TYPE_SOFTWARE
correspondingly in uapi/linux/perf_event.h)
The program visible context meta structure is
struct bpf_perf_event_data {
struct pt_regs regs;
__u64 sample_period;
};
which is accessible directly from the program:
int bpf_prog(struct bpf_perf_event_data *ctx)
{
... ctx->sample_period ...
... ctx->regs.ip ...
}
The bpf verifier rewrites the accesses into kernel internal
struct bpf_perf_event_data_kern which allows changing
struct perf_sample_data without affecting bpf programs.
New fields can be added to the end of struct bpf_perf_event_data
in the future.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Access the priv member of the dsa_switch structure directly, instead of
having an unnecessary helper.
Signed-off-by: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add a per-port flag to control the unknown multicast flood, similar to the
unknown unicast flood flag and break a few long lines in the netlink flag
exports.
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
fdb dumps spanning multiple skb's currently restart from the first
interface again for every skb. This results in unnecessary
iterations on the already visited interfaces and their fdb
entries. In large scale setups, we have seen this to slow
down fdb dumps considerably. On a system with 30k macs we
see fdb dumps spanning across more than 300 skbs.
To fix the problem, this patch replaces the existing single fdb
marker with three markers: netdev hash entries, netdevs and fdb
index to continue where we left off instead of restarting from the
first netdev. This is consistent with link dumps.
In the process of fixing the performance issue, this patch also
re-implements fix done by
commit 472681d57a ("net: ndo_fdb_dump should report -EMSGSIZE to rtnl_fdb_dump")
(with an internal fix from Wilson Kok) in the following ways:
- change ndo_fdb_dump handlers to return error code instead
of the last fdb index
- use cb->args strictly for dump frag markers and not error codes.
This is consistent with other dump functions.
Below results were taken on a system with 1000 netdevs
and 35085 fdb entries:
before patch:
$time bridge fdb show | wc -l
15065
real 1m11.791s
user 0m0.070s
sys 1m8.395s
(existing code does not return all macs)
after patch:
$time bridge fdb show | wc -l
35085
real 0m2.017s
user 0m0.113s
sys 0m1.942s
Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: Wilson Kok <wkok@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add the const for the parameter of flow_keys_have_l4 for the readability.
Signed-off-by: Gao Feng <fgao@ikuai8.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Don't expose skbs to in-kernel users, such as the AFS filesystem, but
instead provide a notification hook the indicates that a call needs
attention and another that indicates that there's a new call to be
collected.
This makes the following possibilities more achievable:
(1) Call refcounting can be made simpler if skbs don't hold refs to calls.
(2) skbs referring to non-data events will be able to be freed much sooner
rather than being queued for AFS to pick up as rxrpc_kernel_recv_data
will be able to consult the call state.
(3) We can shortcut the receive phase when a call is remotely aborted
because we don't have to go through all the packets to get to the one
cancelling the operation.
(4) It makes it easier to do encryption/decryption directly between AFS's
buffers and sk_buffs.
(5) Encryption/decryption can more easily be done in the AFS's thread
contexts - usually that of the userspace process that issued a syscall
- rather than in one of rxrpc's background threads on a workqueue.
(6) AFS will be able to wait synchronously on a call inside AF_RXRPC.
To make this work, the following interface function has been added:
int rxrpc_kernel_recv_data(
struct socket *sock, struct rxrpc_call *call,
void *buffer, size_t bufsize, size_t *_offset,
bool want_more, u32 *_abort_code);
This is the recvmsg equivalent. It allows the caller to find out about the
state of a specific call and to transfer received data into a buffer
piecemeal.
afs_extract_data() and rxrpc_kernel_recv_data() now do all the extraction
logic between them. They don't wait synchronously yet because the socket
lock needs to be dealt with.
Five interface functions have been removed:
rxrpc_kernel_is_data_last()
rxrpc_kernel_get_abort_code()
rxrpc_kernel_get_error_number()
rxrpc_kernel_free_skb()
rxrpc_kernel_data_consumed()
As a temporary hack, sk_buffs going to an in-kernel call are queued on the
rxrpc_call struct (->knlrecv_queue) rather than being handed over to the
in-kernel user. To process the queue internally, a temporary function,
temp_deliver_data() has been added. This will be replaced with common code
between the rxrpc_recvmsg() path and the kernel_rxrpc_recv_data() path in a
future patch.
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Today mpls iptunnel lwtunnel_output redirect expects the tunnel
output function to handle fragmentation. This is ok but can be
avoided if we did not do the mpls output redirect too early.
ie we could wait until ip fragmentation is done and then call
mpls output for each ip fragment.
To make this work we will need,
1) the lwtunnel state to carry encap headroom
2) and do the redirect to the encap output handler on the ip fragment
(essentially do the output redirect after fragmentation)
This patch adds tunnel headroom in lwtstate to make sure we
account for tunnel data in mtu calculations during fragmentation
and adds new xmit redirect handler to redirect to lwtunnel xmit func
after ip fragmentation.
This includes IPV6 and some mtu fixes and testing from David Ahern.
Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pass struct socket * to more rxrpc kernel interface functions. They should
be starting from this rather than the socket pointer in the rxrpc_call
struct if they need to access the socket.
I have left:
rxrpc_kernel_is_data_last()
rxrpc_kernel_get_abort_code()
rxrpc_kernel_get_error_number()
rxrpc_kernel_free_skb()
rxrpc_kernel_data_consumed()
unmodified as they're all about to be removed (and, in any case, don't
touch the socket).
Signed-off-by: David Howells <dhowells@redhat.com>
Provide a function so that kernel users, such as AFS, can ask for the peer
address of a call:
void rxrpc_kernel_get_peer(struct rxrpc_call *call,
struct sockaddr_rxrpc *_srx);
In the future the kernel service won't get sk_buffs to look inside.
Further, this allows us to hide any canonicalisation inside AF_RXRPC for
when IPv6 support is added.
Also propagate this through to afs_find_server() and issue a warning if we
can't handle the address family yet.
Signed-off-by: David Howells <dhowells@redhat.com>
The nf_log_set is an interface function, so it should do the strict sanity
check of parameters. Convert the return value of nf_log_set as int instead
of void. When the pf is invalid, return -EOPNOTSUPP.
Signed-off-by: Gao Feng <fgao@ikuai8.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
After timer removal this just calls nf_ct_delete so remove the __ prefix
version and make nf_ct_kill a shorthand for nf_ct_delete.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
With stats enabled this eats 80 bytes on x86_64 per nf_conn entry, as
Eric Dumazet pointed out during netfilter workshop 2016.
Eric also says: "Another reason was the fact that Thomas was about to
change max timer range [..]" (500462a9de, 'timers: Switch to
a non-cascading wheel').
Remove the timer and use a 32bit jiffies value containing timestamp until
entry is valid.
During conntrack lookup, even before doing tuple comparision, check
the timeout value and evict the entry in case it is too old.
The dying bit is used as a synchronization point to avoid races where
multiple cpus try to evict the same entry.
Because lookup is always lockless, we need to bump the refcnt once
when we evict, else we could try to evict already-dead entry that
is being recycled.
This is the standard/expected way when conntrack entries are destroyed.
Followup patches will introduce garbage colliction via work queue
and further places where we can reap obsoleted entries (e.g. during
netlink dumps), this is needed to avoid expired conntracks from hanging
around for too long when lookup rate is low after a busy period.
Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
The reliable event delivery mode currently (ab)uses the DYING bit to
detect which entries on the dying list have to be skipped when
re-delivering events from the eache worker in reliable event mode.
Currently when we delete the conntrack from main table we only set this
bit if we could also deliver the netlink destroy event to userspace.
If we fail we move it to the dying list, the ecache worker will
reattempt event delivery for all confirmed conntracks on the dying list
that do not have the DYING bit set.
Once timer is gone, we can no longer use if (del_timer()) to detect
when we 'stole' the reference count owned by the timer/hash entry, so
we need some other way to avoid racing with other cpu.
Pablo suggested to add a marker in the ecache extension that skips
entries that have been unhashed from main table but are still waiting
for the last reference count to be dropped (e.g. because one skb waiting
on nfqueue verdict still holds a reference).
We do this by adding a tristate.
If we fail to deliver the destroy event, make a note of this in the
eache extension. The worker can then skip all entries that are in
a different state. Either they never delivered a destroy event,
e.g. because the netlink backend was not loaded, or redelivery took
place already.
Once the conntrack timer is removed we will now be able to replace
del_timer() test with test_and_set_bit(DYING, &ct->status) to avoid
racing with other cpu that tries to evict the same conntrack.
Because DYING will then be set right before we report the destroy event
we can no longer skip event reporting when dying bit is set.
Suggested-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Pull networking fixes from David Miller:
1) Segregate namespaces properly in conntrack dumps, from Liping Zhang.
2) tcp listener refcount fix in netfilter tproxy, from Eric Dumazet.
3) Fix timeouts in qed driver due to xmit_more, from Yuval Mintz.
4) Fix use-after-free in tcp_xmit_retransmit_queue().
5) Userspace header fixups (use of __u32, missing includes, etc.) from
Mikko Rapeli.
6) Further refinements to fragmentation wrt gso and tunnels, from
Shmulik Ladkani.
7) Trigger poll correctly for zero length UDP packets, from Eric
Dumazet.
8) TCP window scaling fix, also from Eric Dumazet.
9) SLAB_DESTROY_BY_RCU is not relevant any more for UDP sockets.
10) Module refcount leak in qdisc_create_dflt(), from Eric Dumazet.
11) Fix deadlock in cp_rx_poll() of 8139cp driver, from Gao Feng.
12) Memory leak in rhashtable's alloc_bucket_locks(), from Eric Dumazet.
13) Add new device ID to alx driver, from Owen Lin.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (83 commits)
Add Killer E2500 device ID in alx driver.
net: smc91x: fix SMC accesses
Documentation: networking: dsa: Remove platform device TODO
net/mlx5: Increase number of ethtool steering priorities
net/mlx5: Add error prints when validate ETS failed
net/mlx5e: Fix memory leak if refreshing TIRs fails
net/mlx5e: Add ethtool counter for TX xmit_more
net/mlx5e: Fix ethtool -g/G rx ring parameter report with striding RQ
net/mlx5e: Don't wait for SQ completions on close
net/mlx5e: Don't post fragmented MPWQE when RQ is disabled
net/mlx5e: Don't wait for RQ completions on close
net/mlx5e: Limit UMR length to the device's limitation
rhashtable: fix a memory leak in alloc_bucket_locks()
sfc: fix potential stack corruption from running past stat bitmask
team: loadbalance: push lacpdus to exact delivery
net: hns: dereference ppe_cb->ppe_common_cb if it is non-null
8139cp: Fix one possible deadloop in cp_rx_poll
i40e: Change some init flow for the client
Revert "phy: IRQ cannot be shared"
net: dsa: bcm_sf2: Fix race condition while unmasking interrupts
...
This patch enhances ethtool link mode bitmap to include
missing interface modes for 1G/10G speeds
Changes:
1000baseX is the mode introduced to cover all 1G Fiber cases.
All modes under 1000BaseX i.e. 1000BASE-SX, 1000BASE-LX, 1000BASE-LX10
and 1000BASE-BX10 are not explicitly defined at this moment.
10G CR,SR,LR and ER link modes are included for 10G speed..
Issue:
ethtool on 1G/10G SFP port reports Base-T
as this port supports 1000baseX,10G CR, SR and LR modes.
root@tor-02$ ethtool swp1
Settings for swp1:
Supported ports: [ FIBRE ]
Supported link modes: 1000baseT/Full
10000baseT/Full
Supported pause frame use: Symmetric Receive-only
Supports auto-negotiation: Yes
Advertised link modes: 1000baseT/Full
Advertised pause frame use: No
Advertised auto-negotiation: No
Speed: 10000Mb/s
Duplex: Full
Port: FIBRE
PHYAD: 0
Transceiver: external
Auto-negotiation: off
Current message level: 0x00000000 (0)
Link detected: yes
After fix:
root@tor-02$ ethtool swp1
Settings for swp1:
Supported ports: [ FIBRE ]
Supported link modes: 1000baseX/Full
10000baseCR/Full
10000baseSR/Full
10000baseLR/Full
10000baseER/Full
Supported pause frame use: Symmetric Receive-only
Supports auto-negotiation: Yes
Advertised link modes: 1000baseT/Full
Advertised pause frame use: No
Advertised auto-negotiation: No
Speed: 10000Mb/s
Duplex: Full
Port: FIBRE
PHYAD: 0
Transceiver: external
Auto-negotiation: off
Current message level: 0x00000000 (0)
Link detected: yes
Signed-off-by: Vidya Sagar Ravipati <vidya@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When TCP operates in lossy environments (between 1 and 10 % packet
losses), many SACK blocks can be exchanged, and I noticed we could
drop them on busy senders, if these SACK blocks have to be queued
into the socket backlog.
While the main cause is the poor performance of RACK/SACK processing,
we can try to avoid these drops of valuable information that can lead to
spurious timeouts and retransmits.
Cause of the drops is the skb->truesize overestimation caused by :
- drivers allocating ~2048 (or more) bytes as a fragment to hold an
Ethernet frame.
- various pskb_may_pull() calls bringing the headers into skb->head
might have pulled all the frame content, but skb->truesize could
not be lowered, as the stack has no idea of each fragment truesize.
The backlog drops are also more visible on bidirectional flows, since
their sk_rmem_alloc can be quite big.
Let's add some room for the backlog, as only the socket owner
can selectively take action to lower memory needs, like collapsing
receive queues or partial ofo pruning.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit b70661c708 ("net: smc91x: use run-time configuration on all ARM
machines") broke some ARM platforms through several mistakes. Firstly,
the access size must correspond to the following rule:
(a) at least one of 16-bit or 8-bit access size must be supported
(b) 32-bit accesses are optional, and may be enabled in addition to
the above.
Secondly, it provides no emulation of 16-bit accesses, instead blindly
making 16-bit accesses even when the platform specifies that only 8-bit
is supported.
Reorganise smc91x.h so we can make use of the existing 16-bit access
emulation already provided - if 16-bit accesses are supported, use
16-bit accesses directly, otherwise if 8-bit accesses are supported,
use the provided 16-bit access emulation. If neither, BUG(). This
exactly reflects the driver behaviour prior to the commit being fixed.
Since the conversion incorrectly cut down the available access sizes on
several platforms, we also need to go through every platform and fix up
the overly-restrictive access size: Arnd assumed that if a platform can
perform 32-bit, 16-bit and 8-bit accesses, then only a 32-bit access
size needed to be specified - not so, all available access sizes must
be specified.
This likely fixes some performance regressions in doing this: if a
platform does not support 8-bit accesses, 8-bit accesses have been
emulated by performing a 16-bit read-modify-write access.
Tested on the Intel Assabet/Neponset platform, which supports only 8-bit
accesses, which was broken by the original commit.
Fixes: b70661c708 ("net: smc91x: use run-time configuration on all ARM machines")
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Tested-by: Robert Jarzmik <robert.jarzmik@free.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
kcm and strparser need to work with any type of stream socket not just
TCP. Eliminate references to TCP and call generic proto_ops functions of
read_sock and peek_len. Also in strp_init check if the socket support
the proto_ops read_sock and peek_len.
Signed-off-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In inet_stream_ops we set read_sock to tcp_read_sock and peek_len to
tcp_peek_len (which is just a stub function that calls tcp_inq).
Signed-off-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add new function in proto_ops structure. This includes moving the
typedef got sk_read_actor into net.h and removing the definition from
tcp.h.
Signed-off-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull drm fixes from Dave Airlie:
"A bunch of fixes covering i915, amdgpu, one tegra and some core DRM
ones. Nothing too strange at this point"
* tag 'drm-fixes-for-4.8-rc4' of git://people.freedesktop.org/~airlied/linux: (21 commits)
drm/atomic: Don't potentially reset color_mgmt_changed on successive property updates.
drm: Protect fb_defio in drivers with CONFIG_KMS_FBDEV_EMULATION
drm/amdgpu: skip TV/CV in display parsing
drm/amdgpu: avoid a possible array overflow
drm/amdgpu: fix lru size grouping v2
drm/tegra: dsi: Enhance runtime power management
drm/i915: Fix botched merge that downgrades CSR versions.
drm/i915/skl: Ensure pipes with changed wms get added to the state
drm/i915/gen9: Only copy WM results for changed pipes to skl_hw
drm/i915/skl: Add support for the SAGV, fix underrun hangs
drm/i915/gen6+: Interpret mailbox error flags
drm/i915: Reattach comment, complete type specification
drm/i915: Unconditionally flush any chipset buffers before execbuf
drm/i915/gen9: Drop invalid WARN() during data rate calculation
drm/i915/gen9: Initialize intel_state->active_crtcs during WM sanitization (v2)
drm: Reject page_flip for !DRIVER_MODESET
drm/amdgpu: fix timeout value check in amd_sched_job_recovery
drm/amdgpu: fix sdma_v2_4_ring_test_ib
drm/amdgpu: fix amdgpu_move_blit on 32bit systems
drm/radeon: fix radeon_move_blit on 32bit systems
...
Pull KVM fixes from Paolo Bonzini:
"ARM:
- fixes for ITS init issues, error handling, IRQ leakage, race
conditions
- an erratum workaround for timers
- some removal of misleading use of errors and comments
- a fix for GICv3 on 32-bit guests
MIPS:
- fix for where the guest could wrongly map the first page of
physical memory
x86:
- nested virtualization fixes"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
MIPS: KVM: Check for pfn noslot case
kvm: nVMX: fix nested tsc scaling
KVM: nVMX: postpone VMCS changes on MSR_IA32_APICBASE write
KVM: nVMX: fix msr bitmaps to prevent L2 from accessing L0 x2APIC
arm64: KVM: report configured SRE value to 32-bit world
arm64: KVM: remove misleading comment on pmu status
KVM: arm/arm64: timer: Workaround misconfigured timer interrupt
arm64: Document workaround for Cortex-A72 erratum #853709
KVM: arm/arm64: Change misleading use of is_error_pfn
KVM: arm64: ITS: avoid re-mapping LPIs
KVM: arm64: check for ITS device on MSI injection
KVM: arm64: ITS: move ITS registration into first VCPU run
KVM: arm64: vgic-its: Make updates to propbaser/pendbaser atomic
KVM: arm64: vgic-its: Plug race in vgic_put_irq
KVM: arm64: vgic-its: Handle errors from vgic_add_lpi
KVM: arm64: ITS: return 1 on successful MSI injection
Pull rdma fixes from Doug Ledford:
"Round one of 4.8 rc fixes.
This should be the bulk of the -rc fixes for 4.8. I only have a few
things that are still outstanding (two ipoib bugs for which the
solution is not yet fully known, and a few queued items that came in
after my last push and I didn't want to delay this pull request for
late comers again).
Even though the patch count is kind of high, everything is minor fixes
so the overall churn is pretty low.
Summary:
- minor fixes to cxgb4
- minor fixes to mlx4
- one minor fix each to core, rxe, isert, srpt, mlx5, ocrdma, and usnic
- six or so fixes to i40iw fixes
- the rest are hfi1 fixes"
* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (34 commits)
i40iw: Send last streaming mode message for loopback connections
IB/srpt: Update sport->port_guid with each port refresh
RDMA/ocrdma: Fix the max_sge reported from FW
i40iw: Avoid writing to freed memory
i40iw: Fix double free of allocated_buffer
IB/mlx5: Remove superfluous include of io-mapping.h
i40iw: Do not set self-referencing pointer to NULL after kfree
i40iw: Add missing NULL check for MPA private data
iw_cxgb4: Fix cxgb4 arm CQ logic w/IB_CQ_REPORT_MISSED_EVENTS
i40iw: Add missing check for interface already open
i40iw: Protect req_resource_num update
i40iw: Change mem_resources pointer to a u8
IB/core: Use memdup_user() rather than duplicating its implementation
IB/qib: Use memdup_user() rather than duplicating its implementation
iw_cxgb4: use the MPA initiator's IRD if < our ORD
iw_cxgb4: limit IRD/ORD advertised to ULP by device max.
IB/hfi1: Fix mm_struct use after free
IB/rdmvat: Fix double vfree() in rvt_create_qp() error path
IB/hfi1: Improve J_KEY generation
IB/hfi1: Return invalid field for non-QSFP CableInfo queries
...
Add UDP bearer options to netlink bearer get message. This is used by
the tipc user space tool to display UDP options.
The UDP bearer information is passed using either a sockaddr_in or
sockaddr_in6 structs. This means the user space receiver should
intermediately store the retrieved data in a large enough struct
(sockaddr_strage) before casting to the proper IP version type.
Signed-off-by: Richard Alpe <richard.alpe@ericsson.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
