Remove uplink representor netdevice private structure lookup, and use
mlx5 core handle directly from representor private structure to lookup
vxlan ports.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>

Move vxlan logic and objects to mlx5 core dirver.
Since it going to be used from different mlx5 interfaces.
e.g. mlx5e PF NIC netdev and mlx5e E-Switch representors.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>

Vxlan API can and will be called from different mlx5 modules, we should
not count on mlx5e private state lock only, hence we introduce a vxlan
private mutex to sync between add/del vxlan port operations.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>

For a better API mlx5_vxlan_{add/del}_port can fail, make them return
error values.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>

Rename vxlan functions from mlx5e_vxlan_* to mlx5_vxlan_*.
Rename mlx5e_vxlan_db to mlx5_vxlan and move it from en.h to vxlan.c
since it is not related to mlx5e anymore.

Allocate mlx5_vxlan structure dynamically in order to make it easier to
move later to core driver and to make it private in vxlan.c.

This is in preparation to move vxlan API to mlx5 core.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>

The name mlx5e_vxlan will be used in downstream patch to describe
mlx5 vxlan structure that will replace mlx5e_vxlan_db.

Hence we rename struct mlx5e_vxlan to mlx5_vxlan_port which describes a
mlx5 vxlan port.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>

Create a direct vxlan API to add and delete vxlan ports from HW.
+void mlx5e_vxlan_add_port(struct mlx5e_priv *priv, u16 port);
+void mlx5e_vxlan_del_port(struct mlx5e_priv *priv, u16 port);

And move vxlan_add/del_work to en_main.c since they are netdev only
logic.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>

Add direct vxlan delete function to be called from vxlan_delete_work.
Needed in downstream patch.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>

Cleanup the sa_family member of the vxlan work, it is unused/needed
anywhere in the code.
Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

The VXLAN database is accessed in the data path for each VXLAN TX skb in
order to check whether the UDP port is being offloaded or not.
The number of elements in the database is relatively small, we can
simplify the radix-tree to a hash table and speedup the lookup process.

Measuring mlx5e_vxlan_lookup_port execution time:

                  Radix Tree   Hash Table
 --------------- ------------ ------------
  Single Stream   161 ns       79  ns (51% improvement)
  Multi Stream    259 ns       136 ns (47% improvement)

Measuring UDP stream packet rate, single fully utilized TX core:
Radix Tree: 498,300 PPS
Hash Table: 555,468 PPS (11% improvement)
Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

The NIC has a limited number of offloaded VXLAN UDP ports (usually 4).
Instead of letting the firmware fail when trying to add more ports than
it can handle, let the driver check it on its own.
Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

The hardware offloads 4789 UDP port (default VXLAN port) automatically.
Add it to the software database as well in order to reflect the hardware
state appropriately.
Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

In case a chain is empty and not explicitly created by a user,
such chain should not exist. The only exception is if there is
an action "goto chain" pointing to it. In that case, don't show the
chain in the dump. Track the chain references held by actions and
use them to find out if a chain should or should not be shown
in chain dump.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Steffen Klassert says:

====================
pull request (net-next): ipsec-next 2018-07-27

1) Extend the output_mark to also support the input direction
   and masking the mark values before applying to the skb.

2) Add a new lookup key for the upcomming xfrm interfaces.

3) Extend the xfrm lookups to match xfrm interface IDs.

4) Add virtual xfrm interfaces. The purpose of these interfaces
   is to overcome the design limitations that the existing
   VTI devices have.

  The main limitations that we see with the current VTI are the
  following:

  VTI interfaces are L3 tunnels with configurable endpoints.
  For xfrm, the tunnel endpoint are already determined by the SA.
  So the VTI tunnel endpoints must be either the same as on the
  SA or wildcards. In case VTI tunnel endpoints are same as on
  the SA, we get a one to one correlation between the SA and
  the tunnel. So each SA needs its own tunnel interface.

  On the other hand, we can have only one VTI tunnel with
  wildcard src/dst tunnel endpoints in the system because the
  lookup is based on the tunnel endpoints. The existing tunnel
  lookup won't work with multiple tunnels with wildcard
  tunnel endpoints. Some usecases require more than on
  VTI tunnel of this type, for example if somebody has multiple
  namespaces and every namespace requires such a VTI.

  VTI needs separate interfaces for IPv4 and IPv6 tunnels.
  So when routing to a VTI, we have to know to which address
  family this traffic class is going to be encapsulated.
  This is a lmitation because it makes routing more complex
  and it is not always possible to know what happens behind the
  VTI, e.g. when the VTI is move to some namespace.

  VTI works just with tunnel mode SAs. We need generic interfaces
  that ensures transfomation, regardless of the xfrm mode and
  the encapsulated address family.

  VTI is configured with a combination GRE keys and xfrm marks.
  With this we have to deal with some extra cases in the generic
  tunnel lookup because the GRE keys on the VTI are actually
  not GRE keys, the GRE keys were just reused for something else.
  All extensions to the VTI interfaces would require to add
  even more complexity to the generic tunnel lookup.

  So to overcome this, we developed xfrm interfaces with the
  following design goal:

  It should be possible to tunnel IPv4 and IPv6 through the same
  interface.

  No limitation on xfrm mode (tunnel, transport and beet).

  Should be a generic virtual interface that ensures IPsec
  transformation, no need to know what happens behind the
  interface.

  Interfaces should be configured with a new key that must match a
  new policy/SA lookup key.

  The lookup logic should stay in the xfrm codebase, no need to
  change or extend generic routing and tunnel lookups.

  Should be possible to use IPsec hardware offloads of the underlying
  interface.

5) Remove xfrm pcpu policy cache. This was added after the flowcache
   removal, but it turned out to make things even worse.
   From Florian Westphal.

6) Allow to update the set mark on SA updates.
   From Nathan Harold.

7) Convert some timestamps to time64_t.
   From Arnd Bergmann.

8) Don't check the offload_handle in xfrm code,
   it is an opaque data cookie for the driver.
   From Shannon Nelson.

9) Remove xfrmi interface ID from flowi. After this pach
   no generic code is touched anymore to do xfrm interface
   lookups. From Benedict Wong.

10) Allow to update the xfrm interface ID on SA updates.
    From Nathan Harold.

11) Don't pass zero to ERR_PTR() in xfrm_resolve_and_create_bundle.
    From YueHaibing.

12) Return more detailed errors on xfrm interface creation.
    From Benedict Wong.

13) Use PTR_ERR_OR_ZERO instead of IS_ERR + PTR_ERR.
    From the kbuild test robot.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

net/xfrm/xfrm_interface.c:692:1-3: WARNING: PTR_ERR_OR_ZERO can be used

 Use PTR_ERR_OR_ZERO rather than if(IS_ERR(...)) + PTR_ERR

Generated by: scripts/coccinelle/api/ptr_ret.cocci

Fixes: 44e2b838 ("xfrm: Return detailed errors from xfrmi_newlink")
CC: Benedict Wong <benedictwong@google.com>
Signed-off-by: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>

Saeed Mahameed says:

====================
mlx5e-updates-2018-07-26 (XDP redirect)

This series from Tariq adds the support for device-out XDP redirect.

Start with a simple RX and XDP cleanups:
- Replace call to MPWQE free with dealloc in interface down flow
- Do not recycle RX pages in interface down flow
- Gather all XDP pre-requisite checks in a single function
- Restrict the combination of large MTU and XDP

Since now XDP logic is going to be called from TX side as well,
generic XDP TX logic is not RX only anymore, for that Tariq creates
a new xdp.c file and moves XDP related code into it, and generalizes
the code to support XDP TX for XDP redirect, such as the xdp tx sq
structures and xdp counters.

XDP redirect support:
Add implementation for the ndo_xdp_xmit callback.

Dedicate a new set of XDP-SQ instances to satisfy the XDP_REDIRECT
requests.  These instances are totally separated from the existing
XDP-SQ objects that satisfy local XDP_TX actions.

Performance tests:

xdp_redirect_map from ConnectX-5 to ConnectX-5.
CPU: Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz
Packet-rate of 64B packets.

Single queue: 7 Mpps.
Multi queue: 55 Mpps.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

The root directories of netdevsim should only be used by the core
to create per-device subdirectories, so limit their visibility to
the core file.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Tobin C. Harding says:

====================
docs: net: Convert netdev-FAQ to RST

Jon answered all the tree questions on v1 so if you will please take
this through your tree that would be awesome.

v2:
 - Fix typo 'canonical_path_format' (thanks Edward)
 - Add patch fixing references netdev-FAQ
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

File 'Documentation/networking/netdev-FAQ.txt' has been converted to RST
format.  We should update all links/references to point to the new file.

Update references to netdev-FAQ
Signed-off-by: Tobin C. Harding <me@tobin.cc>
Signed-off-by: David S. Miller <davem@davemloft.net>

Preferred kernel docs format is now restructured text.  Convert
netdev-FAQ.txt to restructured text.

 - Add SPDX license identifier.

 - Change file heading 'Information you need to know about netdev' to
  'netdev FAQ' to better suit displayed index (in HTML).

 - Change question/answer layout to suit rst.  Copy format in
   Documentation/bpf/bpf_devel_QA.rst

 - Fix indentation of code snippets

 - If multiple consecutive URLs appear put them in a list (to maintain
  whitespace).

 - Use uniform spelling of 'bug fix' throughout document (not bugfix or
   bug-fix).

 - Add double back ticks to 'net' and 'net-next' when referring to the
   trees.

 - Use rst references for Documentation/ links.

 - Add rst label 'netdev-FAQ' for referencing by other docs files.

 - Remove stale entry from Documentation/networking/00-INDEX
Signed-off-by: Tobin C. Harding <me@tobin.cc>
Signed-off-by: David S. Miller <davem@davemloft.net>

In preparation to convert Documentation/network/netdev-FAQ.rst to
restructured text format.  We would like to be able to reference 'the
canonical patch format' section.

Add rest label: 'the_canonical_patch_format'.
Signed-off-by: Tobin C. Harding <me@tobin.cc>
Signed-off-by: David S. Miller <davem@davemloft.net>

starfire_init_one() is never called in atomic context.
It calls mdelay() to busily wait, which is not necessary.
mdelay() can be replaced with msleep().

This is found by a static analysis tool named DCNS written by myself.
Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

hisax_cs_new() and hisax_cs_setup() are never called in atomic context.
They call kmalloc() and kzalloc() with GFP_ATOMIC, which is not necessary.
GFP_ATOMIC can be replaced with GFP_KERNEL.

This is found by a static analysis tool named DCNS written by myself.
Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

init_PStack() is never called in atomic context.
It calls kmalloc() with GFP_ATOMIC, which is not necessary.
GFP_ATOMIC can be replaced with GFP_KERNEL.

This is found by a static analysis tool named DCNS written by myself.
Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

nj_probe() is never called in atomic context.
It calls kzalloc() with GFP_ATOMIC, which is not necessary.
GFP_ATOMIC can be replaced with GFP_KERNEL.

This is found by a static analysis tool named DCNS written by myself.
Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

hfc_probe() is never called in atomic context.
It calls kzalloc() with GFP_ATOMIC, which is not necessary.
GFP_ATOMIC can be replaced with GFP_KERNEL.

This is found by a static analysis tool named DCNS written by myself.
Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

hns_dsaf_roce_reset is exported and used in hns_roce_hw_v1.c
In commit 336a443b ("net: hns: Make many functions static") I make
it static wrongly.

drivers/infiniband/hw/hns/hns_roce_hw_v1.o: In function `hns_roce_v1_reset':
hns_roce_hw_v1.c:(.text+0x37ac): undefined reference to `hns_dsaf_roce_reset'
hns_roce_hw_v1.c:(.text+0x37cc): undefined reference to `hns_dsaf_roce_reset'

Fixes: 336a443b ("net: hns: Make many functions static")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Use designated function mlx5e_dma_get() to get
the mlx5e_sq_dma object to be pushed into fifo.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

Pointers in DB are static, move them to read-only area so they
do not share a cacheline with fields modified in datapath.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

A loaded XDP program might write to the xdp_frame data area,
prefetchw() it to avoid a potential cache miss.

Performance tests:
ConnectX-5, XDP_TX packet rate, single ring.
CPU: Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz

Before: 13,172,976 pps
After:  13,456,248 pps
2% gain.

Fixes: 22f45398 ("net/mlx5e: Support XDP over Striding RQ")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

Add implementation for the ndo_xdp_xmit callback.

Dedicate a new set of XDP-SQ instances to satisfy the XDP_REDIRECT
requests.  These instances are totally separated from the existing
XDP-SQ objects that satisfy local XDP_TX actions.

Performance tests:

xdp_redirect_map from ConnectX-5 to ConnectX-5.
CPU: Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz
Packet-rate of 64B packets.

Single queue: 7 Mpps.
Multi queue: 55 Mpps.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

In the downstream patch that adds support to XDP_REDIRECT-out,
the XDP xmit frame function doesn't share the same run context as
the NAPI that polls the XDP-SQ completion queue.

Hence, need to re-order the XDP-SQ fields to avoid cacheline
false-sharing.

Take redirect_flush and doorbell out of DB, into separated
cachelines.

Add a cacheline breaker within the stats struct.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

Separate the XDP counters into two sets:
(1) One set reside in the RQ stats, and they monitor XDP stats
in the RQ side.
(2) Another set is per XDP-SQ, and they monitor XDP stats that
are related to XDP transmit flow.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

Convert the XDP xmit functions to use the generic xdp_frame API
in XDP_TX flow.
Same functions will be used later in this series to transmit
the XDP redirect-out packets as well.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

Add per-ring and total stats for received packets that
goes into XDP redirection.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

Take XDP code out of the general EN header and RX file into
new XDP files.

Currently, XDP-SQ resides only within an RQ and used from a
single flow (XDP_TX) triggered upon RX completions.
In a downstream patch, additional type of XDP-SQ instances will be
presented and used for the XDP_REDIRECT flow, totally unrelated to
the RX context.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

Add checks in control path upon an MTU change or an XDP program set,
to prevent reaching cases where large MTU and XDP are set simultaneously.

This is to make sure we allow XDP only with the linear RX memory scheme,
i.e. a received packet is not scattered to different pages.
Change mlx5e_rx_get_linear_frag_sz() accordingly, so that we make sure
the XDP configuration can really be set, instead of assuming that it is.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

Dedicate a function to all checks done when setting an XDP program.
Take indications from priv instead of netdev features.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

Keep all page-pool recycle calls within NAPI context.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

No need to expose the MPWQE free function to control path.
The dealloc function already exposed, use it.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>