After this change conntrack operations (lookup, creation, matching from
ruleset) only access one instead of two sk_buff cache lines.

This works for normal conntracks because those are allocated from a slab
that guarantees hw cacheline or 8byte alignment (whatever is larger)
so the 3 bits needed for ctinfo won't overlap with nf_conn addresses.

Template allocation now does manual address alignment (see previous change)
on arches that don't have sufficent kmalloc min alignment.

Some spots intentionally use skb->_nfct instead of skb_nfct() helpers,
this is to avoid undoing the skb_nfct() use when we remove untracked
conntrack object in the future.
Signed-off-by: NFlorian Westphal <fw@strlen.de>
Signed-off-by: NPablo Neira Ayuso <pablo@netfilter.org>

Followup patch renames skb->nfct and changes its type so add a helper to
avoid intrusive rename change later.
Signed-off-by: NFlorian Westphal <fw@strlen.de>
Signed-off-by: NPablo Neira Ayuso <pablo@netfilter.org>

ktime_set(S,N) was required for the timespec storage type and is still
useful for situations where a Seconds and Nanoseconds part of a time value
needs to be converted. For anything where the Seconds argument is 0, this
is pointless and can be replaced with a simple assignment.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>

In UDP RX handler, we currently clear skb->dev before skb
is added to receive queue, because device pointer is no longer
available once we exit from RCU section.

Since this first cache line is always hot, lets reuse this space
to store skb->truesize and thus avoid a cache line miss at
udp_recvmsg()/udp_skb_destructor time while receive queue
spinlock is held.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Under UDP flood, many softirq producers try to add packets to
UDP receive queue, and one user thread is burning one cpu trying
to dequeue packets as fast as possible.

Two parts of the per packet cost are :
- copying payload from kernel space to user space,
- freeing memory pieces associated with skb.

If socket is under pressure, softirq handler(s) can try to pull in
skb->head the payload of the packet if it fits.

Meaning the softirq handler(s) can free/reuse the page fragment
immediately, instead of letting udp_recvmsg() do this hundreds of usec
later, possibly from another node.

Additional gains :
- We reduce skb->truesize and thus can store more packets per SO_RCVBUF
- We avoid cache line misses at copyout() time and consume_skb() time,
and avoid one put_page() with potential alien freeing on NUMA hosts.

This comes at the cost of a copy, bounded to available tail room, which
is usually small. (We might have to fix GRO_MAX_HEAD which looks bigger
than necessary)

This patch gave me about 5 % increase in throughput in my tests.

skb_condense() helper could probably used in other contexts.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Cc: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

1) cast to "int" is unnecessary:
   u8 will be promoted to int before decrementing,
   small positive numbers fit into "int", so their values won't be changed
   during promotion.

   Once everything is int including loop counters, signedness doesn't
   matter: 32-bit operations will stay 32-bit operations.

   But! Someone tried to make this loop smart by making everything of
   the same type apparently in an attempt to optimise it.
   Do the optimization, just differently.
   Do the cast where it matters. :^)

2) frag size is unsigned entity and sum of fragments sizes is also
   unsigned.

Make everything unsigned, leave no MOVSX instruction behind.

	add/remove: 0/0 grow/shrink: 0/3 up/down: 0/-4 (-4)
	function                                     old     new   delta
	skb_cow_data                                 835     834      -1
	ip_do_fragment                              2549    2548      -1
	ip6_fragment                                3130    3128      -2
	Total: Before=154865032, After=154865028, chg -0.00%
Signed-off-by: NAlexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

A new argument is added to __skb_recv_datagram to provide
an explicit skb destructor, invoked under the receive queue
lock.
The UDP protocol uses such argument to perform memory
reclaiming on dequeue, so that the UDP protocol does not
set anymore skb->desctructor.
Instead explicit memory reclaiming is performed at close() time and
when skbs are removed from the receive queue.
The in kernel UDP protocol users now need to call a
skb_recv_udp() variant instead of skb_recv_datagram() to
properly perform memory accounting on dequeue.

Overall, this allows acquiring only once the receive queue
lock on dequeue.

Tested using pktgen with random src port, 64 bytes packet,
wire-speed on a 10G link as sender and udp_sink as the receiver,
using an l4 tuple rxhash to stress the contention, and one or more
udp_sink instances with reuseport.

nr sinks	vanilla		patched
1		440		560
3		2150		2300
6		3650		3800
9		4450		4600
12		6250		6450

v1 -> v2:
 - do rmem and allocated memory scheduling under the receive lock
 - do bulk scheduling in first_packet_length() and in udp_destruct_sock()
 - avoid the typdef for the dequeue callback
Suggested-by: NEric Dumazet <edumazet@google.com>
Acked-by: NHannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: NPaolo Abeni <pabeni@redhat.com>
Acked-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NFlorian Westphal <fw@strlen.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The skbuff and sock structure both had missing parameter annotation
values.
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

since pipe_lock is the outermost now, we don't need to drop/regain
socket locks around the call of splice_to_pipe() from skb_splice_bits(),
which kills the need to have a socket-specific callback; we can just
call splice_to_pipe() and be done with that.
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

This exports the functionality of extracting the tag from the payload,
without moving next vlan tag into hw accel tag.
Signed-off-by: NShmulik Ladkani <shmulik.ladkani@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This work implements direct packet access for helpers and direct packet
write in a similar fashion as already available for XDP types via commits
4acf6c0b ("bpf: enable direct packet data write for xdp progs") and
6841de8b ("bpf: allow helpers access the packet directly"), and as a
complementary feature to the already available direct packet read for tc
(cls/act) programs.

For enabling this, we need to introduce two helpers, bpf_skb_pull_data()
and bpf_csum_update(). The first is generally needed for both, read and
write, because they would otherwise only be limited to the current linear
skb head. Usually, when the data_end test fails, programs just bail out,
or, in the direct read case, use bpf_skb_load_bytes() as an alternative
to overcome this limitation. If such data sits in non-linear parts, we
can just pull them in once with the new helper, retest and eventually
access them.

At the same time, this also makes sure the skb is uncloned, which is, of
course, a necessary condition for direct write. As this needs to be an
invariant for the write part only, the verifier detects writes and adds
a prologue that is calling bpf_skb_pull_data() to effectively unclone the
skb from the very beginning in case it is indeed cloned. The heuristic
makes use of a similar trick that was done in 233577a2 ("net: filter:
constify detection of pkt_type_offset"). This comes at zero cost for other
programs that do not use the direct write feature. Should a program use
this feature only sparsely and has read access for the most parts with,
for example, drop return codes, then such write action can be delegated
to a tail called program for mitigating this cost of potential uncloning
to a late point in time where it would have been paid similarly with the
bpf_skb_store_bytes() as well. Advantage of direct write is that the
writes are inlined whereas the helper cannot make any length assumptions
and thus needs to generate a call to memcpy() also for small sizes, as well
as cost of helper call itself with sanity checks are avoided. Plus, when
direct read is already used, we don't need to cache or perform rechecks
on the data boundaries (due to verifier invalidating previous checks for
helpers that change skb->data), so more complex programs using rewrites
can benefit from switching to direct read plus write.

For direct packet access to helpers, we save the otherwise needed copy into
a temp struct sitting on stack memory when use-case allows. Both facilities
are enabled via may_access_direct_pkt_data() in verifier. For now, we limit
this to map helpers and csum_diff, and can successively enable other helpers
where we find it makes sense. Helpers that definitely cannot be allowed for
this are those part of bpf_helper_changes_skb_data() since they can change
underlying data, and those that write into memory as this could happen for
packet typed args when still cloned. bpf_csum_update() helper accommodates
for the fact that we need to fixup checksum_complete when using direct write
instead of bpf_skb_store_bytes(), meaning the programs can use available
helpers like bpf_csum_diff(), and implement csum_add(), csum_sub(),
csum_block_add(), csum_block_sub() equivalents in eBPF together with the
new helper. A usage example will be provided for iproute2's examples/bpf/
directory.
Signed-off-by: NDaniel Borkmann <daniel@iogearbox.net>
Acked-by: NAlexei Starovoitov <ast@kernel.org>
Signed-off-by: NDavid 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: NYaogong Wang <wygivan@google.com>
Signed-off-by: NEric 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: NIlpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

switchdev_port_fwd_mark_set() is used to set the 'offload_fwd_mark' of
port netdevs so that packets being flooded by the device won't be
flooded twice.

It works by assigning a unique identifier (the ifindex of the first
bridge port) to bridge ports sharing the same parent ID. This prevents
packets from being flooded twice by the same switch, but will flood
packets through bridge ports belonging to a different switch.

This method is problematic when stacked devices are taken into account,
such as VLANs. In such cases, a physical port netdev can have upper
devices being members in two different bridges, thus requiring two
different 'offload_fwd_mark's to be configured on the port netdev, which
is impossible.

The main problem is that packet and netdev marking is performed at the
physical netdev level, whereas flooding occurs between bridge ports,
which are not necessarily port netdevs.

Instead, packet and netdev marking should really be done in the bridge
driver with the switch driver only telling it which packets it already
forwarded. The bridge driver will mark such packets using the mark
assigned to the ingress bridge port and will prevent the packet from
being forwarded through any bridge port sharing the same mark (i.e.
having the same parent ID).

Remove the current switchdev 'offload_fwd_mark' implementation and
instead implement the proposed method. In addition, make rocker - the
sole user of the mark - use the proposed method.
Signed-off-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This work adds a bpf_skb_change_tail() helper for tc BPF programs. The
basic idea is to expand or shrink the skb in a controlled manner. The
eBPF program can then rewrite the rest via helpers like bpf_skb_store_bytes(),
bpf_lX_csum_replace() and others rather than passing a raw buffer for
writing here.

bpf_skb_change_tail() is really a slow path helper and intended for
replies with f.e. ICMP control messages. Concept is similar to other
helpers like bpf_skb_change_proto() helper to keep the helper without
protocol specifics and let the BPF program mangle the remaining parts.
A flags field has been added and is reserved for now should we extend
the helper in future.
Signed-off-by: NDaniel Borkmann <daniel@iogearbox.net>
Acked-by: NAlexei Starovoitov <ast@kernel.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

bpf_skb_store_bytes() invocations above L2 header need BPF_F_RECOMPUTE_CSUM
flag for updates, so that CHECKSUM_COMPLETE will be fixed up along the way.
Where we ran into an issue with bpf_skb_store_bytes() is when we did a
single-byte update on the IPv6 hoplimit despite using BPF_F_RECOMPUTE_CSUM
flag; simple ping via ICMPv6 triggered a hw csum failure as a result. The
underlying issue has been tracked down to a buffer alignment issue.

Meaning, that csum_partial() computations via skb_postpull_rcsum() and
skb_postpush_rcsum() pair invoked had a wrong result since they operated on
an odd address for the hoplimit, while other computations were done on an
even address. This mix doesn't work as-is with skb_postpull_rcsum(),
skb_postpush_rcsum() pair as it always expects at least half-word alignment
of input buffers, which is normally the case. Thus, instead of these helpers
using csum_sub() and (implicitly) csum_add(), we need to use csum_block_sub(),
csum_block_add(), respectively. For unaligned offsets, they rotate the sum
to align it to a half-word boundary again, otherwise they work the same as
csum_sub() and csum_add().

Adding __skb_postpull_rcsum(), __skb_postpush_rcsum() variants that take the
offset as an input and adapting bpf_skb_store_bytes() to them fixes the hw
csum failures again. The skb_postpull_rcsum(), skb_postpush_rcsum() helpers
use a 0 constant for offset so that the compiler optimizes the offset & 1
test away and generates the same code as with csum_sub()/_add().

Fixes: 608cd71a ("tc: bpf: generalize pedit action")
Signed-off-by: NDaniel Borkmann <daniel@iogearbox.net>
Acked-by: NAlexei Starovoitov <ast@kernel.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Suggested-by: NDaniel Borkmann <daniel@iogearbox.net>
Signed-off-by: NJamal Hadi Salim <jhs@mojatatu.com>
Acked-by: NDaniel Borkmann <daniel@iogearbox.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Similar to commit 9b368814 ("net: fix bridge multicast packet checksum validation")
we need to fixup the checksum for CHECKSUM_COMPLETE when
pushing skb on RX path. Otherwise we get similar splats.

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Tom Herbert <tom@herbertland.com>
Signed-off-by: NCong Wang <xiyou.wangcong@gmail.com>
Acked-by: NJamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

People who use PACKET_FANOUT_HASH want a symmetric hash, meaning that
they want packets going in both directions on a flow to hash to the
same bucket.

The core kernel SKB hash became non-symmetric when the ipv6 flow label
and other entities were incorporated into the standard flow hash order
to increase entropy.

But there are no users of PACKET_FANOUT_HASH who want an assymetric
hash, they all want a symmetric one.

Therefore, use the flow dissector to compute a flat symmetric hash
over only the protocol, addresses and ports.  This hash does not get
installed into and override the normal skb hash, so this change has
no effect whatsoever on the rest of the stack.
Reported-by: NEric Leblond <eric@regit.org>
Tested-by: NEric Leblond <eric@regit.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

SCTP has this pecualiarity that its packets cannot be just segmented to
(P)MTU. Its chunks must be contained in IP segments, padding respected.
So we can't just generate a big skb, set gso_size to the fragmentation
point and deliver it to IP layer.

This patch takes a different approach. SCTP will now build a skb as it
would be if it was received using GRO. That is, there will be a cover
skb with protocol headers and children ones containing the actual
segments, already segmented to a way that respects SCTP RFCs.

With that, we can tell skb_segment() to just split based on frag_list,
trusting its sizes are already in accordance.

This way SCTP can benefit from GSO and instead of passing several
packets through the stack, it can pass a single large packet.

v2:
- Added support for receiving GSO frames, as requested by Dave Miller.
- Clear skb->cb if packet is GSO (otherwise it's not used by SCTP)
- Added heuristics similar to what we have in TCP for not generating
  single GSO packets that fills cwnd.
v3:
- consider sctphdr size in skb_gso_transport_seglen()
- rebased due to 5c7cdf33 ("gso: Remove arbitrary checks for
  unsupported GSO")
Signed-off-by: NMarcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Tested-by: NXin Long <lucien.xin@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

skb_gso_network_seglen is not enough for checking fragment sizes if
skb is using GSO_BY_FRAGS as we have to check frag per frag.

This patch introduces skb_gso_validate_mtu, based on the former, which
will wrap the use case inside it as all calls to skb_gso_network_seglen
were to validate if it fits on a given TMU, and improve the check.
Signed-off-by: NMarcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Tested-by: NXin Long <lucien.xin@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch allows segmenting a skb based on its frags sizes instead of
based on a fixed value.
Signed-off-by: NMarcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Tested-by: NXin Long <lucien.xin@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Noticed an allocation failure in a network driver the other day on a 32 bit
system:

DMA-API: debugging out of memory - disabling
bnx2fc: adapter_lookup: hba NULL
lldpad: page allocation failure. order:0, mode:0x4120
Pid: 4556, comm: lldpad Not tainted 2.6.32-639.el6.i686.debug #1
Call Trace:
 [<c08a4086>] ? printk+0x19/0x23
 [<c05166a4>] ? __alloc_pages_nodemask+0x664/0x830
 [<c0649d02>] ? free_object+0x82/0xa0
 [<fb4e2c9b>] ? ixgbe_alloc_rx_buffers+0x10b/0x1d0 [ixgbe]
 [<fb4e2fff>] ? ixgbe_configure_rx_ring+0x29f/0x420 [ixgbe]
 [<fb4e228c>] ? ixgbe_configure_tx_ring+0x15c/0x220 [ixgbe]
 [<fb4e3709>] ? ixgbe_configure+0x589/0xc00 [ixgbe]
 [<fb4e7be7>] ? ixgbe_open+0xa7/0x5c0 [ixgbe]
 [<fb503ce6>] ? ixgbe_init_interrupt_scheme+0x5b6/0x970 [ixgbe]
 [<fb4e8e54>] ? ixgbe_setup_tc+0x1a4/0x260 [ixgbe]
 [<fb505a9f>] ? ixgbe_dcbnl_set_state+0x7f/0x90 [ixgbe]
 [<c088d80d>] ? dcb_doit+0x10ed/0x16d0
...

Thought that perhaps the big splat in the logs wasn't really necessecary, as
all call sites for dev_alloc_skb:

a) check the return code for the function

and

b) either print their own error message or have a recovery path that makes the
warning moot.

Fix it by modifying dev_alloc_pages to pass __GFP_NOWARN as a gfp flag to
suppress the warning

applies to the net tree
Signed-off-by: NNeil Horman <nhorman@tuxdriver.com>
CC: "David S. Miller" <davem@davemloft.net>
CC: Eric Dumazet <eric.dumazet@gmail.com>
CC: Alexander Duyck <alexander.duyck@gmail.com>
Acked-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch defines two new GSO definitions SKB_GSO_IPXIP4 and
SKB_GSO_IPXIP6 along with corresponding NETIF_F_GSO_IPXIP4 and
NETIF_F_GSO_IPXIP6. These are used to described IP in IP
tunnel and what the outer protocol is. The inner protocol
can be deduced from other GSO types (e.g. SKB_GSO_TCPV4 and
SKB_GSO_TCPV6). The GSO types of SKB_GSO_IPIP and SKB_GSO_SIT
are removed (these are both instances of SKB_GSO_IPXIP4).
SKB_GSO_IPXIP6 will be used when support for GSO with IP
encapsulation over IPv6 is added.
Signed-off-by: NTom Herbert <tom@herbertland.com>
Acked-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Locally generated TCP GSO packets having to go through a GRE/SIT/IPIP
tunnel have to go through an expensive skb_unclone()

Reallocating skb->head is a lot of work.

Test should really check if a 'real clone' of the packet was done.

TCP does not care if the original gso_type is changed while the packet
travels in the stack.

This adds skb_header_unclone() which is a variant of skb_clone()
using skb_header_cloned() check instead of skb_cloned().

This variant can probably be used from other points.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The SKBTX_ACK_TSTAMP flag is set in skb_shinfo->tx_flags when
the timestamp of the TCP acknowledgement should be reported on
error queue. Since accessing skb_shinfo is likely to incur a
cache-line miss at the time of receiving the ack, the
txstamp_ack bit was added in tcp_skb_cb, which is set iff
the SKBTX_ACK_TSTAMP flag is set for an skb. This makes
SKBTX_ACK_TSTAMP flag redundant.

Remove the SKBTX_ACK_TSTAMP and instead use the txstamp_ack bit
everywhere.

Note that this frees one bit in shinfo->tx_flags.
Signed-off-by: NSoheil Hassas Yeganeh <soheil@google.com>
Acked-by: NMartin KaFai Lau <kafai@fb.com>
Suggested-by: NWillem de Bruijn <willemb@google.com>
Acked-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

A pattern of skb usage seen in modules such as RDS-TCP is to
extract `to_copy' bytes from the received TCP segment, starting
at some offset `off' into a new skb `clone'. This is done in
the ->data_ready callback, where the clone skb is queued up for rx on
the PF_RDS socket, while the parent TCP segment is returned unchanged
back to the TCP engine.

The existing code uses the sequence
	clone = skb_clone(..);
	pskb_pull(clone, off, ..);
	pskb_trim(clone, to_copy, ..);
with the intention of discarding the first `off' bytes. However,
skb_clone() + pskb_pull() implies pksb_expand_head(), which ends
up doing a redundant memcpy of bytes that will then get discarded
in __pskb_pull_tail().

To avoid this inefficiency, this commit adds pskb_extract() that
creates the clone, and memcpy's only the relevant header/frag/frag_list
to the start of `clone'. pskb_trim() is then invoked to trim clone
down to the requested to_copy bytes.
Signed-off-by: NSowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds support for something I am referring to as GSO partial.
The basic idea is that we can support a broader range of devices for
segmentation if we use fixed outer headers and have the hardware only
really deal with segmenting the inner header.  The idea behind the naming
is due to the fact that everything before csum_start will be fixed headers,
and everything after will be the region that is handled by hardware.

With the current implementation it allows us to add support for the
following GSO types with an inner TSO_MANGLEID or TSO6 offload:
NETIF_F_GSO_GRE
NETIF_F_GSO_GRE_CSUM
NETIF_F_GSO_IPIP
NETIF_F_GSO_SIT
NETIF_F_UDP_TUNNEL
NETIF_F_UDP_TUNNEL_CSUM

In the case of hardware that already supports tunneling we may be able to
extend this further to support TSO_TCPV4 without TSO_MANGLEID if the
hardware can support updating inner IPv4 headers.
Signed-off-by: NAlexander Duyck <aduyck@mirantis.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds support for TSO using IPv4 headers with a fixed IP ID
field.  This is meant to allow us to do a lossless GRO in the case of TCP
flows that use a fixed IP ID such as those that convert IPv6 header to IPv4
headers.

In addition I am adding a feature that for now I am referring to TSO with
IP ID mangling.  Basically when this flag is enabled the device has the
option to either output the flow with incrementing IP IDs or with a fixed
IP ID regardless of what the original IP ID ordering was.  This is useful
in cases where the DF bit is set and we do not care if the original IP ID
value is maintained.
Signed-off-by: NAlexander Duyck <aduyck@mirantis.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Enable peeking at UDP datagrams at the offset specified with socket
option SOL_SOCKET/SO_PEEK_OFF. Peek at any datagram in the queue, up
to the end of the given datagram.

Implement the SO_PEEK_OFF semantics introduced in commit ef64a54f
("sock: Introduce the SO_PEEK_OFF sock option"). Increase the offset
on peek, decrease it on regular reads.

When peeking, always checksum the packet immediately, to avoid
recomputation on subsequent peeks and final read.

The socket lock is not held for the duration of udp_recvmsg, so
peek and read operations can run concurrently. Only the last store
to sk_peek_off is preserved.
Signed-off-by: NSam Kumar <samanthakumar@google.com>
Signed-off-by: NWillem de Bruijn <willemb@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The current reserved_tailroom calculation fails to take hlen and tlen into
account.

skb:
[__hlen__|__data____________|__tlen___|__extra__]
^                                               ^
head                                            skb_end_offset

In this representation, hlen + data + tlen is the size passed to alloc_skb.
"extra" is the extra space made available in __alloc_skb because of
rounding up by kmalloc. We can reorder the representation like so:

[__hlen__|__data____________|__extra__|__tlen___]
^                                               ^
head                                            skb_end_offset

The maximum space available for ip headers and payload without
fragmentation is min(mtu, data + extra). Therefore,
reserved_tailroom
= data + extra + tlen - min(mtu, data + extra)
= skb_end_offset - hlen - min(mtu, skb_end_offset - hlen - tlen)
= skb_tailroom - min(mtu, skb_tailroom - tlen) ; after skb_reserve(hlen)

Compare the second line to the current expression:
reserved_tailroom = skb_end_offset - min(mtu, skb_end_offset)
and we can see that hlen and tlen are not taken into account.

The min() in the third line can be expanded into:
if mtu < skb_tailroom - tlen:
	reserved_tailroom = skb_tailroom - mtu
else:
	reserved_tailroom = tlen

Depending on hlen, tlen, mtu and the number of multicast address records,
the current code may output skbs that have less tailroom than
dev->needed_tailroom or it may output more skbs than needed because not all
space available is used.

Fixes: 4c672e4b ("ipv6: mld: fix add_grhead skb_over_panic for devs with large MTUs")
Signed-off-by: NBenjamin Poirier <bpoirier@suse.com>
Acked-by: NHannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: NDaniel Borkmann <daniel@iogearbox.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

After commit 52bd2d62 ("net: better skb->sender_cpu and skb->napi_id cohabitation")
skb_sender_cpu_clear() becomes empty and can be removed.

Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: NCong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When we're dealing with clones and the area is not writeable, try
harder and get a copy via pskb_expand_head(). Replace also other
occurences in tc actions with the new skb_try_make_writable().
Reported-by: NAshhad Sheikh <ashhadsheikh394@gmail.com>
Signed-off-by: NDaniel Borkmann <daniel@iogearbox.net>
Acked-by: NAlexei Starovoitov <ast@kernel.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch takes advantage of several assumptions we can make about the
headers of the frame in order to reduce overall processing overhead for
computing the outer header checksum.

First we can assume the entire header is in the region pointed to by
skb->head as this is what csum_start is based on.

Second, as a result of our first assumption, we can just call csum_partial
instead of making a call to skb_checksum which would end up having to
configure things so that we could walk through the frags list.
Signed-off-by: NAlexander Duyck <aduyck@mirantis.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The arithmetic properties of the ones-complement checksum mean that a
 correctly checksummed inner packet, including its checksum, has a ones
 complement sum depending only on whatever value was used to initialise
 the checksum field before checksumming (in the case of TCP and UDP,
 this is the ones complement sum of the pseudo header, complemented).
Consequently, if we are going to offload the inner checksum with
 CHECKSUM_PARTIAL, we can compute the outer checksum based only on the
 packed data not covered by the inner checksum, and the initial value of
 the inner checksum field.
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The network stack defers SKBs free, in-case free happens in IRQ or
when IRQs are disabled. This happens in __dev_kfree_skb_irq() that
writes SKBs that were free'ed during IRQ to the softirq completion
queue (softnet_data.completion_queue).

These SKBs are naturally delayed, and cleaned up during NET_TX_SOFTIRQ
in function net_tx_action().  Take advantage of this a use the skb
defer and flush API, as we are already in softirq context.

For modern drivers this rarely happens. Although most drivers do call
dev_kfree_skb_any(), which detects the situation and calls
__dev_kfree_skb_irq() when needed.  This due to netpoll can call from
IRQ context.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: NJesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Discovered that network stack were hitting the kmem_cache/SLUB
slowpath when freeing SKBs.  Doing bulk free with kmem_cache_free_bulk
can speedup this slowpath.

NAPI context is a bit special, lets take advantage of that for bulk
free'ing SKBs.

In NAPI context we are running in softirq, which gives us certain
protection.  A softirq can run on several CPUs at once.  BUT the
important part is a softirq will never preempt another softirq running
on the same CPU.  This gives us the opportunity to access per-cpu
variables in softirq context.

Extend napi_alloc_cache (before only contained page_frag_cache) to be
a struct with a small array based stack for holding SKBs.  Introduce a
SKB defer and flush API for accessing this.

Introduce napi_consume_skb() as replacement for e.g. dev_consume_skb_any()
when running in NAPI context.  A small trick to handle/detect if we
are called from netpoll is to see if budget is 0.  In that case, we
need to invoke dev_consume_skb_irq().

Joint work with Alexander Duyck.
Signed-off-by: NJesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: NAlexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch makes it so that we can offload the checksums for a packet up
to a certain point and then begin computing the checksums via software.
Setting this up is fairly straight forward as all we need to do is reset
the values stored in csum and csum_start for the GSO context block.

One complication for this is remote checksum offload.  In order to allow
the inner checksums to be offloaded while computing the outer checksum
manually we needed to have some way of indicating that the offload wasn't
real.  In order to do that I replaced CHECKSUM_PARTIAL with
CHECKSUM_UNNECESSARY in the case of us computing checksums for the outer
header while skipping computing checksums for the inner headers.  We clean
up the ip_summed flag and set it to either CHECKSUM_PARTIAL or
CHECKSUM_NONE once we hand the packet off to the next lower level.
Signed-off-by: NAlexander Duyck <aduyck@mirantis.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>