app/flow-perf: add memory dump to app

Introduce new feature to dump memory statistics of each socket
and a total for all before and after the creation.

This will give two main advantage:
1- Check the memory consumption for large number of flows
"insertion rate scenario alone"

2- Check that no memory leackage after doing insertion then
deletion.

Signed-off-by: Suanming Mou <suanmingm@mellanox.com>
Signed-off-by: Wisam Jaddo <wisamm@mellanox.com>
Acked-by: Xiaoyu Min <jackmin@mellanox.com>

app/flow-perf: add deletion rate calculation

Add the ability to test deletion rate for flow performance
application.

This feature is disabled by default, and can be enabled by
add "--deletion-rate" in the application command line options.

Signed-off-by: Wisam Jaddo <wisamm@mellanox.com>
Acked-by: Xiaoyu Min <jackmin@mellanox.com>

app/flow-perf: add insertion rate calculation

Add insertion rate calculation feature into flow
performance application.

The application now provide the ability to test
insertion rate of specific rte_flow rule, by
stressing it to the NIC, and calculate the
insertion rate.

The application offers some options in the command
line, to configure which rule to apply.

After that the application will start producing
rules with same pattern but increasing the outer IP
source address by 1 each time, thus it will give
different flow each time, and all other items will
have open masks.

The current design have single core insertion rate.

Signed-off-by: Wisam Jaddo <wisamm@mellanox.com>
Acked-by: Xiaoyu Min <jackmin@mellanox.com>

app/flow-perf: add flow performance skeleton

Add flow performance application skeleton.

Signed-off-by: Wisam Jaddo <wisamm@mellanox.com>
Reviewed-by: Andrew Rybchenko <arybchenko@solarflare.com>
Acked-by: Xiaoyu Min <jackmin@mellanox.com>

mbuf: add dump of free dynamic flags

Add support to dump free_flags as below format:

Free bit in mbuf->ol_flags (0 = occupied, 1 = free):
  0000: 0 0 0 0 0 0 0 0
  0008: 0 0 0 0 0 0 0 0
  0010: 0 0 0 0 0 0 0 1
  0018: 1 1 1 1 1 1 1 1
  0020: 1 1 1 1 1 1 1 1
  0028: 1 0 0 0 0 0 0 0
  0030: 0 0 0 0 0 0 0 0
  0038: 0 0 0 0 0 0 0 0

Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>

mbuf: fix dynamic field dump log

For each mbuf byte, free_space[i] == 0 means the space is occupied,
free_space[i] != 0 means space is free.

Fixes: 4958ca3a443a ("mbuf: support dynamic fields and flags")
Cc: stable@dpdk.org
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>

mbuf: fix free space update for dynamic field

The value free_space[i] is used to save the size of biggest aligned
element that can fit in the zone, current implementation has one flaw,
for example, if user registers dynfield1 (size = 4, align = 4, req = 124)
first, the free_space would be as below after registration:

  0070: 08 08 08 08 08 08 08 08
  0078: 08 08 08 08 00 00 00 00

Then if user continues to register dynfield2 (size = 4, align = 4),
free_space would become:

  0070: 00 00 00 00 04 04 04 04
  0078: 04 04 04 04 00 00 00 00

Further request dynfield3 (size = 8, align = 8) would fail to register
due to alignment requirement can't be satisfied, though there is enough
space remained in mbuf.

This patch fixes above issue by saving alignment only in aligned zone,
after the fix, above registrations order can be satisfied, free_space
would be like:

After dynfield1 registration:

  0070: 08 08 08 08 08 08 08 08
  0078: 04 04 04 04 00 00 00 00

After dynfield2 registration:

  0070: 08 08 08 08 08 08 08 08
  0078: 00 00 00 00 00 00 00 00

After dynfield3 registration:

  0070: 00 00 00 00 00 00 00 00
  0078: 00 00 00 00 00 00 00 00

This patch also reduces iterations in process_score() by jumping align
steps in each loop.

Fixes: 4958ca3a443a ("mbuf: support dynamic fields and flags")
Cc: stable@dpdk.org
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>

mbuf: fix error code in dynamic field/flag registration

Set rte_errno as ENOMEM when allocation failure.

Fixes: 4958ca3a443a ("mbuf: support dynamic fields and flags")
Cc: stable@dpdk.org
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>

mbuf: fix boundary check at dynamic field registration

We should make sure off + size < sizeof(struct rte_mbuf) to avoid
possible out-of-bounds access of free_space array, there is no issue
currently due to the low bits of free_flags (which is adjacent to
free_space) are always set to 0. But we shouldn't rely on it since it's
fragile and layout of struct mbuf_dyn_shm may be changed in the future.
This patch adds boundary check explicitly to avoid potential risk of
out-of-bounds access.

Fixes: 4958ca3a443a ("mbuf: support dynamic fields and flags")
Cc: stable@dpdk.org
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>

bus/pci: fix VF memory access

To fix CVE-2020-12888, the linux vfio-pci module will invalidate mmaps
and block MMIO access on disabled memory, it will send a SIGBUS to the
application:
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=abafbc551fdd

When the application opens the vfio PCI device, the vfio-pci module will
enable the bus memory space through PCI read/write access. According to
the PCIe specification, the 'Memory Space Enable' is always zero for VF:

             Table 9-13 Command Register Changes

Bit Location | PF and VF Register Differences | PF         | VF
             | From Base                      | Attributes | Attributes
-------------+--------------------------------+------------+-----------
             | Memory Space Enable - Does not |            |
             | apply to VFs. Must be hardwired|  Base      |  0b
     1       | to 0b for VFs. VF Memory Space |            |
             | is controlled by the VF MSE bit|            |
             | in the VF Control register.    |            |
-------------+--------------------------------+------------+-----------

Afterwards the vfio-pci will initialize its own virtual PCI config space
data ('vconfig') by reading the VF's physical PCI config space, then the
'Memory Space Enable' bit in vconfig will always be 0b value. This will
make the vfio-pci treat the BAR memory space as disabled, and the SIGBUS
will be triggered if access these BARs.

By investigation, the VF PCI device *passthrough* into the Guest OS by
QEMU has the 'Memory Space Enable' with 1b value. That's because every
PCI driver will start to enable the memory space, and this action will
be hooked by vfio-pci virtual PCI read/write to set the 'Memory Space
Enable' in vconfig space to 1b. So VF runs in guest OS has 'Mem+', but
VF runs in host OS has 'Mem-'.

Align with PCI working mode in Guest/QEMU/Host, in DPDK, enable the PCI
bus memory space explicitly to avoid access on disabled memory.

Fixes: 33604c31354a ("vfio: refactor PCI BAR mapping")
Cc: stable@dpdk.org
Signed-off-by: Haiyue Wang <haiyue.wang@intel.com>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
Tested-by: Harman Kalra <hkalra@marvell.com>
Tested-by: David Marchand <david.marchand@redhat.com>
Tested-by: Thierry Martin <thierry.martin.public@gmail.com>

test/bitops: fix command name

Caught by code review, bitops test name is incorrect.

Fixes: 7660614c11e2 ("test/bitops: add bit operations test case")

Signed-off-by: David Marchand <david.marchand@redhat.com>
Acked-by: Phil Yang <phil.yang@arm.com>

eal: remove redundant newline in alert message

rte_eal_init_alert() already appends a newline.

Fixes: 0a529578f162 ("eal: clean up unused files on initialization")
Cc: stable@dpdk.org
Signed-off-by: David Marchand <david.marchand@redhat.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

usertools: fix telemetry user socket path

The path to the socket when running the script as a regular user needed
to be updated to match the logic in EAL.

Fixes: 6a2967c112a3 ("usertools: add new telemetry script")
Cc: stable@dpdk.org
Signed-off-by: Ciara Power <ciara.power@intel.com>
Reviewed-by: Bruce Richardson <bruce.richardson@intel.com>

bus/vmbus: fix ring buffer mapping

vmbus_map_addr is used as the next start virtual address for mapping ring
buffer. However it's updated based on ring_buf, which is a pointer to an
address on the stack. The next ring buffer may be mapped to an unexpected
address.

Fix this by calculating vmbus_map_addr based on returned virtual address.

Fixes: 3f9277031a2e ("bus/vmbus: fix check for mmap failure")
Cc: stable@dpdk.org
Signed-off-by: Long Li <longli@microsoft.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>

sched: fix 64-bit rate

64-bit support was missing from the functions pipe_profile_check
and rte_sched_subport_config_pipe_profile_table.

Fixes: 68c1f26d4236 ("sched: support 64-bit values")
Cc: stable@dpdk.org
Signed-off-by: Archit Pandey <architpandeynitk@gmail.com>
Acked-by: Jasvinder Singh <jasvinder.singh@intel.com>

sched: fix subport freeing

In function rte_sched_subport_free, there is code to free all allocated
stuff related to scheduler subport.
First there are some checks, and in the end, rte_bitmap_free is called.

Now, rte_bitmap_free is a dummy function, and it just checks if
provided pointer to bitmap is valid or not. So, actual memory for
subport is not freed.

This patch fixes this by removing call to rte_bitmap_free, and
instead calling rte_free.

Fixes: d9213b829a31 ("sched: remove pipe params config from port level")
Cc: stable@dpdk.org
Signed-off-by: Hrvoje Habjanic <hrvoje.habjanic@zg.ht.hr>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Jasvinder Singh <jasvinder.singh@intel.com>

examples: add flush after stats printing

When printf()'s stdout is line-buffered for terminal, it is fully
buffered for pipes. So, stdout listener can only get the output
when it is flushed (on program termination, when buffer is filled or
manual flush).

stdout buffer might fill slowly since every stats report could be small.

Also when it is fully filled it might contain a part of the last stats
report which makes it very inconvenient for any automation which reads
and parses the output.

Fixes: af75078fece3 ("first public release")
Cc: stable@dpdk.org
Signed-off-by: Georgiy Levashov <georgiy.levashov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>

bus/pci: optimize bus scan

In order to optimize the PCI management, RTE_KDRV_NONE based
device driver probing removed by not adding them to list in
the scan phase.

The legacy virtio is the only consumer of RTE_KDRV_NONE based device
driver probe scheme. The legacy virtio support will be available
through the existing VFIO/UIO based kernel driver scheme.

This patch also removes the deprecation notice for the same.

Signed-off-by: Jerin Jacob <jerinj@marvell.com>

net: fix IPv4 checksum

0xffff is invalid for IPv4 checksum (RFC1624)

Fixes: 6006818cfb26 ("net: new checksum functions")
Cc: stable@dpdk.org
Signed-off-by: Hongzhi Guo <guohongzhi1@huawei.com>
Reviewed-by: Morten Brørup <mb@smartsharesystems.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>

bpf/x86: support packet data load instructions

Make x86 JIT to generate native code for
(BPF_ABS | <size> | BPF_LD) and (BPF_IND | <size> | BPF_LD)
instructions.

Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Acked-by: Morten Brørup <mb@smartsharesystems.com>

bpf: support packet data load instructions

To fill the gap with linux kernel eBPF implementation,
add support for two non-generic instructions:
(BPF_ABS | <size> | BPF_LD) and (BPF_IND | <size> | BPF_LD)
which are used to access packet data.
These instructions can only be used when BPF context is a pointer
to 'struct rte_mbuf' (i.e: RTE_BPF_ARG_PTR_MBUF type).

Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>

bpf: fix add/sub min/max estimations

eval_add()/eval_sub() not always correctly estimate
minimum and maximum possible values of add/sub operations.

Fixes: 8021917293d0 ("bpf: add extra validation for input BPF program")
Cc: stable@dpdk.org
Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>

test/bpf: fix few small issues

Address for few small issues:
 - unreachable return statement
 - failed test-case can finish with 'success' status

Also use unified cmp_res() function to check return value.

Cc: stable@dpdk.org
Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>

eal/windows: support exit and panic

Support the debug functions in eal_common_debug.c for Windows.

Implementation of rte_dump_stack to get a backtrace similarly to Unix
and of rte_eal_cleanup in eal.c.

Signed-off-by: Tal Shnaiderman <talshn@mellanox.com>
Tested-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>

eal: move OS common debug functions to single file

Move common functions between Unix and Windows to eal_common_debug.c.

Those functions are rte_exit, __rte_panic and rte_dump_registers
which has the same implementation on Unix and Windows.

Signed-off-by: Tal Shnaiderman <talshn@mellanox.com>

eal/linux: fix epoll fd list rebuild for interrupts

An issue has been observed where epoll file descriptor
list rebuilds every time an interrupt/alarm event is
received.

eal_intr_process_interrupts() should notify pipe fd only
if any source is removed from the source list i.e (rv > 0)

Fixes: 0c7ce182a760 ("eal: add pending interrupt callback unregister")
Cc: stable@dpdk.org
Signed-off-by: Harman Kalra <hkalra@marvell.com>

maintainers: update for interrupt subsystem

Updating MAINTAINERS file for interrupt subsystem.

Signed-off-by: Harman Kalra <hkalra@marvell.com>

meter: remove inline functions from export list

The code didn't compile when using exported meter functions under Windows.

error LNK2001: unresolved external symbol
rte_meter_srtcm_color_aware_check
error LNK2001: unresolved external symbol
rte_meter_srtcm_color_blind_check
error LNK2001: unresolved external symbol
rte_meter_trtcm_color_aware_check
error LNK2001: unresolved external symbol
rte_meter_trtcm_color_blind_check
error LNK2001: unresolved external symbol
rte_meter_trtcm_rfc4115_color_aware_check
error LNK2001: unresolved external symbol
rte_meter_trtcm_rfc4115_color_blind_check

The cause was that there were some inline functions that were included in
the export list.
To solve this the functions were removed from rte_meter_version.map export
list which are implemented in the header and shouldn't be exported.

Fixes: 655796d2b5fb ("meter: support RFC4115 trTCM")
Fixes: 9d41beed24b0 ("lib: provide initial versioning")
Cc: stable@dpdk.org
Signed-off-by: Fady Bader <fady@mellanox.com>

timer: support EAL functions on Windows

Implemented the needed Windows eal timer functions.

Signed-off-by: Fady Bader <fady@mellanox.com>
Reviewed-by: Tal Shnaiderman <talshn@mellanox.com>
Tested-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
Acked-by: Ranjit Menon <ranjit.menon@intel.com>

timer: move from common to Unix directory

EAL common timer doesn't compile under Windows.

Compilation log:
error LNK2019:
unresolved external symbol nanosleep referenced in function
rte_delay_us_sleep
error LNK2019:
unresolved external symbol get_tsc_freq referenced in function set_tsc_freq
error LNK2019:
unresolved external symbol sleep referenced in function set_tsc_freq

The reason was that some functions called POSIX functions.
The solution was to move POSIX dependent functions from common to Unix.

Signed-off-by: Fady Bader <fady@mellanox.com>
Reviewed-by: Tal Shnaiderman <talshn@mellanox.com>
Acked-by: Ranjit Menon <ranjit.menon@intel.com>

doc: clarify compilation with MinGW-w64

Provide a more direct link for installer download and clarify thread
model choice during installation. As pthread is not a requirement,
remove notice about its possible runtime dependency.

Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
Acked-by: Pallavi Kadam <pallavi.kadam@intel.com>

config/x86: remove path for MinGW-w64 cross toolchain

Absolute paths in Meson cross-file impose unnecessary limitation
on build environment, remove them.

Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
Acked-by: Pallavi Kadam <pallavi.kadam@intel.com>

config: never link with pthread on Windows

Even if pthread is provided by the toolchain, it is not needed for DPDK
on Windows, because internal shim is used. As a side-effect, this
enables cross-build with MinGW configured with non-POSIX thread library,
e.g. mcfgthread, which is the default on some distributions.

Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
Acked-by: Pallavi Kadam <pallavi.kadam@intel.com>

net/cxgbe: always enable HASH filter support

Disable all unused firmware resources during init time to give
more resources for HASH (exact-match) filter region and always
request firmware to enable HASH filter support when resources
are available.

Signed-off-by: Karra Satwik <kaara.satwik@chelsio.com>
Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>

net/mlx5/linux: add memory region callbacks to Verbs

Create a set of verbs callbacks in 'struct mlx5_verbs_ops'
and add MR operations to it (file net/mlx5/linux/mlx5_verbs.c).

Signed-off-by: Ophir Munk <ophirmu@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>

net/mlx5: add memory region callbacks in per-device cache

Prior to this commit MR operations were verbs based and hard coded under
common/mlx5/linux directory. This commit enables upper layers (e.g.
net/mlx5) to determine which MR operations to use. For example the net
layer could set devx based MR operations in non-Linux environments. The
reg_mr and dereg_mr callbacks are added to the global per-device MR
cache 'struct mlx5_mr_share_cache'.

Signed-off-by: Ophir Munk <ophirmu@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>

common/mlx5: export memory region Verbs operations

The glue verbs operations reg_mr and dereg_mr are wrapped and exported
in functions mlx5_common_verbs_reg_mr and mlx5_common_verbs_dereg_mr
respectively.  The exported functions are added to a new file
linux/mlx5_common_verbs.c.

Signed-off-by: Ophir Munk <ophirmu@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>

common/mlx5: remove memory region dependency on Verbs

Replace 'struct ibv_mr *' (in 'struct mlx5_mr') with a new 'struct
mlx5_pmd_mr'.  The new struct contains the required MR field: lkey,
addr, len and is independent of ibv.

Signed-off-by: Ophir Munk <ophirmu@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>

net/cxgbe: ignore flow default masks for unrequested fields

commit 536db938a444 ("net/cxgbe: add devargs to control filtermode and
filtermask") allows configuring hardware to select specific combination
of header fields to match in the incoming packets. However, the default
mask is set for all fields in the requested pattern items, even if the
field is not explicitly set in the combination and results in
validation errors. To prevent this, ignore setting the default masks
for the unrequested fields and the hardware will also ignore them in
validation, accordingly. Also, tweak the filter spec before finalizing
the masks.

Fixes: 536db938a444 ("net/cxgbe: add devargs to control filtermode and filtermask")
Cc: stable@dpdk.org
Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>

net/cxgbe: fix SMT leak in filter error and free path

Free up Source MAC Table (SMT) entry properly during filter create
failure and filter delete.

Fixes: 993541b2fa4f ("net/cxgbe: support flow API for source MAC rewrite")
Cc: stable@dpdk.org
Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>

net/cxgbe: fix double MPS alloc by flow validate and create

The Multi Port Switch (MPS) entry is allocated twice when both
flow validate and create are invoked, but only freed once during
flow destroy. Avoid double alloc by moving MPS entry allocation
closer to when the filter create request is sent to hardware and
will be ignored for filter validate request.

Fixes: fefee7a619a4 ("net/cxgbe: add flow ops to match based on dest MAC")
Cc: stable@dpdk.org
Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>

net/cxgbe: fix L2T leak in filter error and free path

Free up Layer 2 Table (L2T) entry properly during filter create
failure and filter delete.

Fixes: 1decc62b1cbe ("net/cxgbe: add flow operations to offload VLAN actions")
Cc: stable@dpdk.org
Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>

net/cxgbe: fix CLIP leak in filter error path

Free up Compressed Local IP (CLIP) entry properly during filter
creation failure path. Also consolidate all various tables
cleanup to a common function and invoke it from both wild-card
and exact-match filter paths.

Fixes: af44a577988b ("net/cxgbe: support to offload flows to HASH region")
Cc: stable@dpdk.org
Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>

net/ice/base: remove PPPoD from PPPoE bitmap

Remove PPPoD's packet type from PPPoE's ptype bitmap.

Signed-off-by: Dan Nowlin <dan.nowlin@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: update IPv4 and IPv6 flow packet type masks

In the flow API, add ability to add IPV4/IPV6 rules that match on
packets with or without inner L4 protocols.

Signed-off-by: Dan Nowlin <dan.nowlin@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: add 1G SGMII PHY type

There isn't a case for 1G SGMII in ice_get_media_type() so add
the handling for it.

Also handle the special case where some direct attach
cables may report that they support 1G SGMII, but
that is erroneous since SGMII is supposed to be a
backplane media type (between a MAC and a PHY). If
the driver doesn't handle this special case then a
user could see the 'Port' in ethtool change from
'Direct attach Copper' to 'Backplane' when they have
forced the speed to 1G, but the cable hasn't changed.

Lastly, change ice_aq_get_phy_caps() to save the
module_type info if the function was called with
ICE_AQC_REPORT_TOPO_CAP. This call uses the media
information to populate the module_type. If no
media is present then the values in module_type
will be 0.

Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: support E823L devices

Add support for E823L devices.

Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: fix initializing resource for field vector

This patch add initialization for prof_res_bm_init flag
to zero in order that the possible resource for field vector
in the package file can be initialized.(in ice_init_prof_result_bm)

Fixes: 453d087ccaff ("net/ice/base: add common functions")
Cc: stable@dpdk.org
Signed-off-by: Wei Zhao <wei.zhao1@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: add more tunnel type for IPv4 and IPv6

This patch add more tunnel type definition ipv4/ipv6 packet,
it enable tcp/udp layer of ipv4/ipv6 as L4 payload but without
L4 dst/src port number as input set for switch filter rule.

For example:
we can download a switch rule to direct ipv4 packet with specific
source and destination ip address to queue index 1.
"eth / ipv4 src is 192.168.0.1 dst is 192.168.0.2 / udp /
end actions queue index 1 / end"
this type of rule will be matched with ipv4/udp file only.

Signed-off-by: Wei Zhao <wei.zhao1@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: fix reference count on VSI list update

The parameter ref_cnt is used for tracking how many
rules are reusing this VSI list, so it can only be
updated when a rule which using this list be deleted.

Fixes: f89aa3affa9e ("net/ice/base: support removing advanced rule")
Cc: stable@dpdk.org
Signed-off-by: Wei Zhao <wei.zhao1@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: remove unused code for VSI list free

When free vsi list resource after vsi list update to empty, some
useless code in function ice_remove_vsi_list_rule() should be deleted.

Signed-off-by: Wei Zhao <wei.zhao1@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: add command to LLDP

Add support for LLDP forwarding to SW programming in FW
LLDP Filter Control is 0x0A0A.

Signed-off-by: Sharon Haroni <sharon.haroni@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: distribute Tx queues evenly

Distribute the tx queues evenly across all queue groups. This will
help the queues to get more equal sharing among the queues when all
are in use.

In the previous algorithm, the next queue group node will be picked up
only after the previous one filled with max children.
For example: if VSI is configured with 9 queues, the first 8 queues
will be assigned to queue group 1 and the 9th queue will be assigned to
queue group 2.

The 2 queue groups split the bandwidth between them equally (50:50).
The first queue group node will share the 50% bandwidth with all of
its children (8 queues). And the second queue group node will share
the entire 50% bandwidth with its only children.

Signed-off-by: Victor Raj <victor.raj@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: adjust scheduler default bandwidth weight

By default the queues are configured in legacy mode. The default
bandwidth settings for legacy/advanced modes are different. The existing
code was using the advanced mode default value of 1 which was
incorrect. This caused the unbalanced BW sharing among siblings.
The recommended default value is applied.

Signed-off-by: Tarun Singh <tarun.k.singh@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: clear error status before set FC

ice_set_fc takes a u8 pointer 'aq_failures' as an input parameter. If
this function encounters an error, in addition to returning an
appropriate ice_status enum code, it also populates aq_failures with a
link specific error value.

If the caller does not initialize this variable to 0 before calling
ice_set_fc, it would appear as if ice_set_fc returned an error code in
this variable. So initialize it to 0.

Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: avoid PPPoE IPv4 overlap

When PPPoE header is not selected, PPPoE should not be included in
ipv4 ptype bitmaps.

Signed-off-by: Yahui Cao <yahui.cao@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: support checking all autoneg enable bits

struct ice_aqc_get_phy_caps_data has multiple autoneg enable bits.
ice_is_phy_caps_an_enabled checks all bits and returns true if any
autoneg enable bits are set.

Signed-off-by: Paul Greenwalt <paul.greenwalt@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: remove unimplemented function prototypes

There are no implementations for these two functions so remove the
prototypes.

Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: add entries in profile TCAM with priority

The profile TCAM tables are implemented such that entries with a smaller
index in the table have a higher priority. When records to be added to
the table have flags to differentiate between standard PTG and VSIG
records, then these entries need to have higher priority in order to be
found and processed first.

Signed-off-by: Dan Nowlin <dan.nowlin@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: fix memory leak on error path

Handles memory leaks during control queue initialization and
buffer allocation failures. The MACRO - ICE_FREE_CQ_BUFS is modified to
re-use for this fix.

Fixes: 6c1f26be50a2 ("net/ice/base: add control queue information")
Cc: stable@dpdk.org
Signed-off-by: Surabhi Boob <surabhi.boob@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: remove unneeded variable

The variable 'adj' is initialized to 0 and later used in an addition,
but the value is never changed from 0. Remove the variable since it's
doing nothing.

Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: fix return value

Function ice_rem_adv_rule_id return incorrect error code (ICE_ERR_PARAM)
whereas it should have returned ICE_ERR_DOES_NOT_EXIST return code
if filter list is empty or unable to find "rule" in list

Fixes: f89aa3affa9e ("net/ice/base: support removing advanced rule")
Cc: stable@dpdk.org
Signed-off-by: Kiran Patil <kiran.patil@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: update VSI handle to remaining VSI

When removing VSI from VSI list, if only one VSI left, we need
to downgrade a switch rule's action from "to VSI LIST" to "to VSI",
So, needs to update the VSI handle to the last remaining VSI for the
new action but not the first VSI be added to the list.

Signed-off-by: Haiyue Wang <haiyue.wang@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: add rate limiter profile bit mask check

Mask bits before accessing the rate limiting profile type field.

Signed-off-by: Tarun Singh <tarun.k.singh@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: reset capabilities before parsing

The capability flags used to report whether an NVM component has
a pending update are stored as simple booleans. If ice_parse_caps finds
the relevant capability then the boolean is set to true.

If the capability is not provided by firmware, then the boolean value
will be left alone. This works during initialization because the
capabilities structure is zero-initialized.

However, this does not work if capabilities are updated by calling
ice_get_caps again after driver load. For example, consider if firmware
had a pending update, and then an EMPR was triggered. The update will
complete, and firmware will no longer report these capabilities.

However, the device driver will have already set the pending flags.
After an EMPR, new capabilities are read. However, because the pending
flags in the dev_caps.common_cap structure have already been set, they
will remain true.

Fix this by clearing the capabilities structures in ice_parse_caps
before processing any capabilities.

This ensures that the capabilities structure will always be refreshed to
match the state of the device or function capabilities reported by
firmware.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: fix advanced switch rule stale information

To avoid having stale information about "adv_rule" per recipe, when all
rules associated to a given recipe are deleted, reset the "adv_rule"
flag otherwise it causes problem later on when decisions about filter
rules being present or not are made based on "adv_rule" flag.

Removed setting "adv_rule = 1" when recipe is created. It is set
correctly when advanced switch rule is added referring to the recipe
which was created as a result of adding advanced switch rule.

Signed-off-by: Kiran Patil <kiran.patil@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: support more PPPoE packet type

This patch add more dummy packet type for PPPoE packet,
it enable tcp/udp layer of IPv4/IPv6 for PPPoE payload,
so we can use L4 dst/src port as input set for switch
filter.

Signed-off-by: Wei Zhao <wei.zhao1@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: remove unnecessary case branches

Remove unnecessary case branch, since the switch and pipeline stage is
not designed to be handled by the flow module.

Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: return correct error code

Return ICE_ERR_DOES_NOT_EXIST return code if admin command error code is
ICE_AQ_RC_ENOENT (not exist). ice_aq_sw_rules is used when switch
rule is getting added/deleted/updated. In case of delete/update
switch rule, admin command can return ICE_AQ_RC_ENOENT error code
if such rule does not exist, hence return ICE_ERR_DOES_NOT_EXIST error
code from ice_aq_sw_rule, so that caller of this function can decide
how to handle ICE_ERR_DOES_NOT_EXIST.

Allow proper cleanup of internal data structures from ice_rem_adv_rule
function if ice_aq_sw_rules return error code ICE_ERR_DOES_NOT_EXIST
otherwise per recipe:rule list will never become empty.

Signed-off-by: Kiran Patil <kiran.patil@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: add debug logs

Add debug logs for ice_aq_get_phy_caps(), and format
ice_aq_set_phy_cfg() and ice_aq_get_link_info() debug logs to make them
more readable.

Signed-off-by: Paul Greenwalt <paul.greenwalt@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: use macro for sizeof

The definition of ICE_SW_RULE_RX_TX_ETH_HDR_SIZE open codes the size of
a structure field. Replace this with the use of FIELD_SIZEOF.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: support RSS IPv6 prefix

Some IPv6 prefix related fields are defined in this patch, so that we
can use prefixes instead of full IPv6 address for RSS. These prefixes
include the first 32, 48, 64 bits of both SRC and DST IPV6 address.

Signed-off-by: Junfeng Guo <junfeng.guo@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: adjust function signature style format

Where possible, cuddle multiple lines of function signatures to be
consistent throughout the code.

Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: remove unnecessary braces

This patch mainly does cleanups related to unnecessary braces.
There might be different opinion to keep braces if more than
single line, but the purpose here is trying to sync DPDK's base
code with kernel's copy and its more convenient for future update.

Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: give time for package download after PF reset

To allow for resets during package download, increase the timeout period
after performing a PF Reset. The time waited is the global config lock
timeout plus the normal PFSWR timeout.

Signed-off-by: Dan Nowlin <dan.nowlin@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: allow GENEVE and VXLAN rules with VLAN

When programming GENEVE and VXLAN switch rules, there are some instances
where both VLAN tagged packets plus non-VLAN tagged packets are needed
to match the rule.

In order to perform this action in one rule, the switch code needs
to setup the packet flag mask to ignore the VLAN packet flag. This
will allow the rule to match both VLAN and non-VLAN packets.

Signed-off-by: Dan Nowlin <dan.nowlin@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: add NVM helper functions

Add couple functions that DPDK would like to use for accessing the
NVM.

Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: initialize PHY configuration FEC fields

Currently the caller needs to initialize the ice_cfg_phy_fec() parameter
ice_aqc_set_phy_cfg_data FEC fields before calling. However, this is not
necessary since ice_cfg_phy_fec() calls Get PHY Capabilities.

Initialize ice_aqc_set_phy_cfg_data FEC capabilities and FEC option
fields from Get PHY Capabilities with media/topology in
ice_cfg_phy_fec().

Signed-off-by: Paul Greenwalt <paul.greenwalt@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: add flow director completion report option

This patch introduces comp_report variable so that the called can
determine whether to report completion on error or on all cases.

Signed-off-by: Yahui Cao <yahui.cao@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: support FDIR for L2TPV3 ESP AH and PFCP

FDIR can forward:
- L2TPV3 packets with session id.
- IPSEC ESP packets with security parameter index.
- IPSEC AH packets with security parameter index.
- NAT_T ESP packets with security parameter index.
- PFCP packets with s field value.

Signed-off-by: Yahui Cao <yahui.cao@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: cleanup comment formatting

Add missing space between end of comment text and comment terminator,
and remove unnecessary punctuation.

Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: group function prototypes together

There are some function prototypes at the beginning of the file and
some at the end, group them all together so that they are in one
consistent location.

Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: change IPv6 training packet

Add additional UDP payload to allow for additional headers such as ESP.

Signed-off-by: Dan Nowlin <dan.nowlin@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: refactor flow director filter swap

Move the swap of flow director addresses and ports into training packet
generation. This reduces the code written for ACL.

Signed-off-by: Henry Tieman <henry.w.tieman@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: consolidate VF promiscuous mode

Consolidate the Promiscuous rule for SMBM on the chosen logical port.

Signed-off-by: Shibin Koikkara Reeny <shibin.koikkara.reeny@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: update maximum PHY type high index

As currently, we are supporting only 5 PHY_SPEEDs for phy_type_high.
Thus, we should adjust the value of ICE_PHY_TYPE_HIGH_MAX_INDEX to 5.

Signed-off-by: Chinh T Cao <chinh.t.cao@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: fix ACL rules index

A u8 idx in ice_acl_add_entry  causes the code to truncate the values
greater than 255 to 255 or less when calling ice_aq_program_acl_entry()
resulting in the wrong TCAM index being programmed for the specified
rule. The result is that the rule action doesn't work correctly
(packets don't get routed to the correct queue or dropped if that
is the action). Fix the issue by changing the variable to be a u16
again.

Fixes: f3202a097f12 ("net/ice/base: add ACL module")
Cc: stable@dpdk.org
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: add AUI media type

Add and report AUI PHY types as an AUI media type

Signed-off-by: Doug Dziggel <douglas.a.dziggel@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: improve VSI filters rebuild

This change improve VSI filter configuration rebuild for
multiport configuration, ie. where 1 PF includes more than
one logical port. For some functions, association between
port and corresponding switch_info or port_info structure
has been lost because by default the pointer to the first
element of array (switch, port etc.) is passed as function
argument. With this change, pointer to proper element is
added an extra argument in relevant functions.

Signed-off-by: Grzegorz Nitka <grzegorz.nitka@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: gate devices from FW link override

Currently, the FW link override feature is only permitted for E810
devices.  However, the ice_fw_supports_link_override() guards against FW
versions irrespective of the device. This assumes FW versions between
the families are aligned, which is not the case.

Signed-off-by: Jeb Cramer <jeb.j.cramer@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: report AOC PHY types as fiber

Report AOC types as fiber instead of unknown

Signed-off-by: Doug Dziggel <douglas.a.dziggel@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: consolidate MAC config set

Consolidate implementation of ice_aq_set_mac_cfg for switch mode
and NIC mode. As per the specification, the driver needs to call
set_mac_cfg (opcode 0x0603) to be able to exercise jumbo frames.

Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Signed-off-by: Jeb Cramer <jeb.j.cramer@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: avoid undefined behavior

When writing the driver's struct ice_tlan_ctx structure, do not write
the 8-bit element int_q_state with the associated internal-to-hardware
field which is 122-bits, otherwise the helper function ice_write_byte()
will use undefined behavior when setting the mask used for that write.
This should not cause any functional change and will avoid use of
undefined behavior.  Also, update a comment to highlight this structure
element is not written.

Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: disable profile merge for flow director

For Flow Director, we don't want to re-use an existed profile with the
same field vector and mask. Merging two different flow_type’s field
vector will also make them sharing trained rule and cause rule
interference.

For example:
issue rule A: IPV4_TCP matching tcp src&dst port 80  to queue 8
issue rule B: IPV6_TCP matching tcp src&dst port 200 to queue 20
Below behavior is found but not expected:
IPV4_TCP pkt with src&dst port 200 hits rule B and goes to queue 20
IPV6_TCP pkt with src&dst port 80  hits rule A and goes to queue 8

Signed-off-by: Yahui Cao <yahui.cao@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: add macros to parse flow director Rx desc

Add descriptor field offset and mask definition. It is used to parse
FDIR Rx descriptor field value.

Signed-off-by: Yahui Cao <yahui.cao@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/ice/base: support flow director for non-IP packets

FDIR can forward Ethernet packets with non-IP ethertype.

Signed-off-by: Yahui Cao <yahui.cao@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>

net/mlx5: fix LRO checksum

The TCP checksum includes IPV4 pseudo-header checksum and L3
payload checksum which include TCP header and TCP payload.
When mlx5 LRO is enabled, HW will calculate the TCP payload
checksum, PMD need complete the IPV4 pseudo-header checksum
and the TCP header checksum.

The mlx5_lro_update_tcp_hdr function completes the TCP header
checksum, but this function using lower 4 bits of data-offset
field in TCP header to get the whole TCP header length, this
will cause TCP header checksum wrong calculation.

Update the code using higher 4 bits of data-offset field
instead of lower 4 bits.

Fixes: e4c2a16eb1de ("net/mlx5: handle LRO packets in Rx queue")
Cc: stable@dpdk.org
Signed-off-by: Dong Zhou <dongz@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>

net/mlx5: fix descriptors number adjustment

The number of descriptors to configure in a Rx/Tx queue is passed to
the mlx5_tx/rx_queue_pre_setup() function by value. That means any
adjustments of this variable are local and cannot affect the actual
value that is used to allocate mbufs in the mlx5_txq/rxq_new()
functions. Pass the number as a reference to actually update it.

Fixes: 6218063b39a6 ("net/mlx5: refactor Rx data path")
Fixes: 1d88ba171942 ("net/mlx5: refactor Tx data path")
Cc: stable@dpdk.org
Signed-off-by: Alexander Kozyrev <akozyrev@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>

net/mlx5: do not select legacy MPW implicitly

The Legacy MPW (multi-packet write) should not be engaged implicitly.
We should exclude this function from a Tx burst routine selection
process unless it is requested specifically by setting the txq_mpw_en
devarg.  Exclude this function from the selection process the same way
it is done for the Enhanced MPW in the mlx5_select_tx_function()
routine.

Fixes: eb8121ab9dac ("net/mlx5: introduce Tx burst routine template")
Cc: stable@dpdk.org
Signed-off-by: Alexander Kozyrev <akozyrev@mellanox.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>

net/mlx5: refactor statistics

mlx5 statistics are calculated by several methods:
1. In software when packets go through datapath.
2. Calling ioctl with ETHTOOL command (Linux specific).
3. Reading counters from SYSFS device path (Linux specific).

The Linux related functions are moved to file linux/mlx5_os.c.

Signed-off-by: Ophir Munk <ophirmu@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>