Florian Fainelli says:

====================
net: broadcom: Adaptive interrupt coalescing

This patch series adds adaptive interrupt coalescing for the Gigabit Ethernet
drivers SYSTEMPORT and GENET.

This really helps lower the interrupt count and system load, as measured by
vmstat for a Gigabit TCP RX session:

SYSTEMPORT:

without:

 1  0      0 192188      0  25472    0    0     0     0 122100 38870  1 42 57  0  0
[ ID] Interval       Transfer     Bandwidth
[  4]  0.0-10.0 sec  1.03 GBytes   884 Mbits/sec

with:

 1  0      0 192288      0  25468    0    0     0     0 58806 44401  0 100  0  0  0
[  5]  0.0-10.0 sec  1.04 GBytes   888 Mbits/sec

GENET:

without:

 1  0      0 1170404      0  25420    0    0     0     0 130785 63402  2 85 12  0  0
[ ID] Interval       Transfer     Bandwidth
[  4]  0.0-10.0 sec  1.04 GBytes   888 Mbits/sec

with:

 1  0      0 1170560      0  25420    0    0     0     0 50610 48477  0 100  0  0  0
[  5]  0.0-10.0 sec  1.05 GBytes   899 Mbits/sec

Please look at the implementation and let me know if you see any problems, this
was largely inspired by bnxt_en.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Unlike the moder modern SYSTEMPORT hardware, we do not have a
configurable TDMA timeout, which limits us to implement adaptive RX
interrupt coalescing only. We have each of our RX rings implement a
bcmgenet_net_dim structure which holds an interrupt counter, number of
packets, bytes, and a container for a net_dim instance.
Signed-off-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Implement support for adaptive RX and TX interrupt coalescing using
net_dim. We have each of our TX ring and our single RX ring implement a
bcm_sysport_net_dim structure which holds an interrupt counter, number
of packets, bytes, and a container for a net_dim instance.
Signed-off-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Andrew Lunn says:

====================
Fixes to allow mv88e6xxx module to be reloaded

As reported by Uwe Kleine-König, the interrupt trigger is first
configured by DT and then reconfigured to edge. This results in a
failure on EPROBE_DEFER, or if the module is unloaded and reloaded.

A second crash happens on module reload due to a missing call to the
common IRQ free code when using polled interrupts.

With these fixes in place, it becomes possible to load and unload the
kernel modules a few times without it crashing.

v2: Fix the ü in Künig a couple of times
v3: But the ü should be an ö!
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When free'ing the polled IRQs, call the common irq free code.
Otherwise the interrupts are left registered, and when we come to load
the driver a second time, we get an Opps.
Signed-off-by: NAndrew Lunn <andrew@lunn.ch>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

By calling request_threaded_irq() with the flag IRQF_TRIGGER_FALLING
we override the trigger mode provided in device tree. And the
interrupt is actually active low, which is what all the current device
tree descriptions use.
Suggested-by: NUwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: NAndrew Lunn <andrew@lunn.ch>
Acked-by: NUwe Kleine-König <u.kleine-koenig@pengutronix.de>
Tested-by: NUwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Added extra test cases for control actions (reclassify, pipe etc.),
cookies, max index value and police args sanity check.
Signed-off-by: NRoman Mashak <mrv@mojatatu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Haiyang Zhang says:

====================
hv_netvsc: Fix/improve RX path error handling

Fix the status code returned to the host. Also add range
check for rx packet offset and length.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds range checking for rx packet offset and length.
It may only happen if there is a host side bug.
Signed-off-by: NHaiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

As defined in hyperv_net.h, the NVSP_STAT_SUCCESS is one not zero.
Some functions returns 0 when it actually means NVSP_STAT_SUCCESS.
This patch fixes them.

In netvsc_receive(), it puts the last RNDIS packet's receive status
for all packets in a vmxferpage which may contain multiple RNDIS
packets.
This patch puts NVSP_STAT_FAIL in the receive completion if one of
the packets in a vmxferpage fails.
Signed-off-by: NHaiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Yonghong Song says:

====================
net: permit skb_segment on head_frag frag_list skb

One of our in-house projects, bpf-based NAT, hits a kernel BUG_ON at
function skb_segment(), line 3667. The bpf program attaches to
clsact ingress, calls bpf_skb_change_proto to change protocol
from ipv4 to ipv6 or from ipv6 to ipv4, and then calls bpf_redirect
to send the changed packet out.
 ...
    3665                 while (pos < offset + len) {
    3666                         if (i >= nfrags) {
    3667                                 BUG_ON(skb_headlen(list_skb));
 ...

The triggering input skb has the following properties:
    list_skb = skb->frag_list;
    skb->nfrags != NULL && skb_headlen(list_skb) != 0
and skb_segment() is not able to handle a frag_list skb
if its headlen (list_skb->len - list_skb->data_len) is not 0.

Patch #1 provides a simple solution to avoid BUG_ON. If
list_skb->head_frag is true, its page-backed frag will
be processed before the list_skb->frags.
Patch #2 provides a test case in test_bpf module which
constructs a skb and calls skb_segment() directly. The test
case is able to trigger the BUG_ON without Patch #1.

The patch has been tested in the following setup:
  ipv6_host <-> nat_server <-> ipv4_host
where nat_server has a bpf program doing ipv4<->ipv6
translation and forwarding through clsact hook
bpf_skb_change_proto.

Changelog:
v5 -> v6:
  . Added back missed BUG_ON(!nfrags) for zero
    skb_headlen(skb) case, plus a couple of
    cosmetic changes, from Alexander.
v4 -> v5:
  . Replace local variable head_frag with
    a static inline function skb_head_frag_to_page_desc
    which gets the head_frag on-demand. This makes
    code more readable and also does not increase
    the stack size, from Alexander.
  . Remove the "if(nfrags)" guard for skb_orphan_frags
    and skb_zerocopy_clone as I found that they can
    handle zero-frag skb (with non-zero skb_headlen(skb))
    properly.
  . Properly release segment list from skb_segment()
    in the test, from Eric.
v3 -> v4:
  . Remove dynamic memory allocation and use rewinding
    for both index and frag to remove one branch in fast path,
    from Alexander.
  . Fix a bunch of issues in test_bpf skb_segment() test,
    including proper way to allocate skb, proper function
    argument for skb_add_rx_frag and not freeint skb, etc.,
    from Eric.
v2 -> v3:
  . Use starting frag index -1 (instead of 0) to
    special process head_frag before other frags in the skb,
    from Alexander Duyck.
v1 -> v2:
  . Removed never-hit BUG_ON, spotted by Linyu Yuan.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Without the previous commit,
"modprobe test_bpf" will have the following errors:
...
[   98.149165] ------------[ cut here ]------------
[   98.159362] kernel BUG at net/core/skbuff.c:3667!
[   98.169756] invalid opcode: 0000 [#1] SMP PTI
[   98.179370] Modules linked in:
[   98.179371]  test_bpf(+)
...
which triggers the bug the previous commit intends to fix.

The skbs are constructed to mimic what mlx5 may generate.
The packet size/header may not mimic real cases in production. But
the processing flow is similar.
Signed-off-by: NYonghong Song <yhs@fb.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

One of our in-house projects, bpf-based NAT, hits a kernel BUG_ON at
function skb_segment(), line 3667. The bpf program attaches to
clsact ingress, calls bpf_skb_change_proto to change protocol
from ipv4 to ipv6 or from ipv6 to ipv4, and then calls bpf_redirect
to send the changed packet out.

3472 struct sk_buff *skb_segment(struct sk_buff *head_skb,
3473                             netdev_features_t features)
3474 {
3475         struct sk_buff *segs = NULL;
3476         struct sk_buff *tail = NULL;
...
3665                 while (pos < offset + len) {
3666                         if (i >= nfrags) {
3667                                 BUG_ON(skb_headlen(list_skb));
3668
3669                                 i = 0;
3670                                 nfrags = skb_shinfo(list_skb)->nr_frags;
3671                                 frag = skb_shinfo(list_skb)->frags;
3672                                 frag_skb = list_skb;
...

call stack:
...
 #1 [ffff883ffef03558] __crash_kexec at ffffffff8110c525
 #2 [ffff883ffef03620] crash_kexec at ffffffff8110d5cc
 #3 [ffff883ffef03640] oops_end at ffffffff8101d7e7
 #4 [ffff883ffef03668] die at ffffffff8101deb2
 #5 [ffff883ffef03698] do_trap at ffffffff8101a700
 #6 [ffff883ffef036e8] do_error_trap at ffffffff8101abfe
 #7 [ffff883ffef037a0] do_invalid_op at ffffffff8101acd0
 #8 [ffff883ffef037b0] invalid_op at ffffffff81a00bab
    [exception RIP: skb_segment+3044]
    RIP: ffffffff817e4dd4  RSP: ffff883ffef03860  RFLAGS: 00010216
    RAX: 0000000000002bf6  RBX: ffff883feb7aaa00  RCX: 0000000000000011
    RDX: ffff883fb87910c0  RSI: 0000000000000011  RDI: ffff883feb7ab500
    RBP: ffff883ffef03928   R8: 0000000000002ce2   R9: 00000000000027da
    R10: 000001ea00000000  R11: 0000000000002d82  R12: ffff883f90a1ee80
    R13: ffff883fb8791120  R14: ffff883feb7abc00  R15: 0000000000002ce2
    ORIG_RAX: ffffffffffffffff  CS: 0010  SS: 0018
 #9 [ffff883ffef03930] tcp_gso_segment at ffffffff818713e7
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Jeff Kirsher says:

====================
10GbE Intel Wired LAN Driver Updates 2018-03-23

This series contains updates to ixgbe and ixgbevf only.

Paul adds status register reads to reduce a potential race condition
where registers can read 0xFFFFFFFF during a PCI reset, which in turn
causes the driver to remove the adapter.  Then fixes an assignment
operation with an "OR" operation.

Shannon Nelson provides several IPsec offload cleanups to ixgbe, as well as a
patch to enable TSO with IPsec offload.

Tony provides the much anticipated XDP support for ixgbevf.  Currently,
pass, drop and XDP_TX actions are supported, as well as meta data and
stats reporting.

Björn Töpel tweaks the page counting for XDP_REDIRECT, since a page can
have its reference count decreased via the xdp_do_redirect() call.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Intiyaz Basha says:

====================
liquidio: Tx queue cleanup

Moved some common function to octeon_network.h
Removed some unwanted functions and checks.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

For consistency renaming txqs_start to start_txqs
Signed-off-by: NIntiyaz Basha <intiyaz.basha@cavium.com>
Acked-by: NDerek Chickles <derek.chickles@cavium.com>
Signed-off-by: NFelix Manlunas <felix.manlunas@cavium.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

For consistency renaming txqs_stop to stop_txqs
Signed-off-by: NIntiyaz Basha <intiyaz.basha@cavium.com>
Acked-by: NDerek Chickles <derek.chickles@cavium.com>
Signed-off-by: NFelix Manlunas <felix.manlunas@cavium.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

For consistency renaming txqs_wake to wake_txqs
Signed-off-by: NIntiyaz Basha <intiyaz.basha@cavium.com>
Acked-by: NDerek Chickles <derek.chickles@cavium.com>
Signed-off-by: NFelix Manlunas <felix.manlunas@cavium.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Using skb_iq function for deriving queue from skb
Signed-off-by: NIntiyaz Basha <intiyaz.basha@cavium.com>
Acked-by: NDerek Chickles <derek.chickles@cavium.com>
Signed-off-by: NFelix Manlunas <felix.manlunas@cavium.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Removing one line function wake_q
Signed-off-by: NIntiyaz Basha <intiyaz.basha@cavium.com>
Acked-by: NDerek Chickles <derek.chickles@cavium.com>
Signed-off-by: NFelix Manlunas <felix.manlunas@cavium.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Removing one line function stop_q
Signed-off-by: NIntiyaz Basha <intiyaz.basha@cavium.com>
Acked-by: NDerek Chickles <derek.chickles@cavium.com>
Signed-off-by: NFelix Manlunas <felix.manlunas@cavium.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Removing checks for netif_is_multiqueue.
Configuring single queue will be a multiqueue netdev with one queues.
Signed-off-by: NIntiyaz Basha <intiyaz.basha@cavium.com>
Acked-by: NDerek Chickles <derek.chickles@cavium.com>
Signed-off-by: NFelix Manlunas <felix.manlunas@cavium.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Removing start_txq function from VF and PF files
Signed-off-by: NIntiyaz Basha <intiyaz.basha@cavium.com>
Acked-by: NDerek Chickles <derek.chickles@cavium.com>
Signed-off-by: NFelix Manlunas <felix.manlunas@cavium.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Removing one line function stop_txq
Signed-off-by: NIntiyaz Basha <intiyaz.basha@cavium.com>
Acked-by: NDerek Chickles <derek.chickles@cavium.com>
Signed-off-by: NFelix Manlunas <felix.manlunas@cavium.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Moving common function skb_iq to to octeon_network.h
Signed-off-by: NIntiyaz Basha <intiyaz.basha@cavium.com>
Acked-by: NDerek Chickles <derek.chickles@cavium.com>
Signed-off-by: NFelix Manlunas <felix.manlunas@cavium.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Moving common function txqs_start to octeon_network.h
Signed-off-by: NIntiyaz Basha <intiyaz.basha@cavium.com>
Acked-by: NDerek Chickles <derek.chickles@cavium.com>
Signed-off-by: NFelix Manlunas <felix.manlunas@cavium.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Moving common function txqs_wake to octeon_network.h
Signed-off-by: NIntiyaz Basha <intiyaz.basha@cavium.com>
Acked-by: NDerek Chickles <derek.chickles@cavium.com>
Signed-off-by: NFelix Manlunas <felix.manlunas@cavium.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Moving common function txqs_stop to octeon_network.h
Signed-off-by: NIntiyaz Basha <intiyaz.basha@cavium.com>
Acked-by: NDerek Chickles <derek.chickles@cavium.com>
Signed-off-by: NFelix Manlunas <felix.manlunas@cavium.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

use u16 in place of __be16 to suppress the following sparse warnings:

 net/sched/act_vlan.c:150:26: warning: incorrect type in assignment (different base types)
 net/sched/act_vlan.c:150:26: expected restricted __be16 [usertype] push_vid
 net/sched/act_vlan.c:150:26: got unsigned short
 net/sched/act_vlan.c:151:21: warning: restricted __be16 degrades to integer
 net/sched/act_vlan.c:208:26: warning: incorrect type in assignment (different base types)
 net/sched/act_vlan.c:208:26: expected unsigned short [unsigned] [usertype] tcfv_push_vid
 net/sched/act_vlan.c:208:26: got restricted __be16 [usertype] push_vid
Signed-off-by: NDavide Caratti <dcaratti@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

tcf_idr_cleanup() is no more used, so remove it.
Suggested-by: NCong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: NDavide Caratti <dcaratti@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In net commit 8175f7c4736f ("mlxsw: spectrum: Prevent duplicate
mirrors") we prevented the user from mirroring more than once from a
single binding point (port-direction pair).

The fix was essentially reverted in a merge conflict resolution when net
was merged into net-next. Restore it.

Fixes: 03fe2deb ("Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net")
Signed-off-by: NPetr Machata <petrm@mellanox.com>
Signed-off-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The current page counting scheme assumes that the reference count
cannot decrease until the received frame is sent to the upper layers
of the networking stack. This assumption does not hold for the
XDP_REDIRECT action, since a page (pointed out by xdp_buff) can have
its reference count decreased via the xdp_do_redirect call.

To work around that, we now start off by a large page count and then
don't allow a refcount less than two.
Signed-off-by: NBjörn Töpel <bjorn.topel@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

XDP stats are included in TX stats, however, they are not
reported in TX queue stats since they are setup on different
queues.  Add reporting for XDP queue stats to provide
consistency between the total stats and per queue stats.
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>
Acked-by: NJohn Fastabend <john.fastabend@gmail.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Add support for XDP meta data when using build skb.

Based on commit 366a88fe ("bpf, ixgbe: add meta data support")
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>
Acked-by: NJohn Fastabend <john.fastabend@gmail.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Current XDP implementation hits the tail on every XDP_TX; change the
driver to only hit the tail after packet processing is complete.

Based on
commit 7379f97a ("ixgbe: delay tail write to every 'n' packets")
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>
Acked-by: NJohn Fastabend <john.fastabend@gmail.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This implements the XDP_TX action which is modeled on the ixgbe
implementation. However instead of using CPU id to determine which XDP
queue to use, this uses the received RX queue index, which is similar
to i40e. Doing this eliminates the restriction that number of CPUs not
exceed number of XDP queues that ixgbe has.

Also, based on the number of queues available, the number of TX queues
may be reduced when an XDP program is loaded in order to accommodate the
XDP queues.

Based largely on
commit 33fdc82f ("ixgbe: add support for XDP_TX action")
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>
Acked-by: NJohn Fastabend <john.fastabend@gmail.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Implement XDP_PASS and XDP_DROP based on the ixgbe implementation.

Based largely on commit 92470808 ("ixgbe: add XDP support for pass and
drop actions").
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>
Acked-by: NJohn Fastabend <john.fastabend@gmail.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Fix things up to support TSO offload in conjunction
with IPsec hw offload.  This raises throughput with
IPsec offload on to nearly line rate.
Signed-off-by: NShannon Nelson <shannon.nelson@oracle.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

There is no need to calculate the trailer length if we're doing
a GSO/TSO, as there is no trailer added to the packet data.
Also, don't bother clearing the flags field as it was already
cleared earlier.
Signed-off-by: NShannon Nelson <shannon.nelson@oracle.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Since the ipsec data fields will be zero anyway in the non-ipsec
case, we can remove the conditional jump.
Suggested-by: NAlexander Duyck <alexander.duyck@gmail.com>
Signed-off-by: NShannon Nelson <shannon.nelson@oracle.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>