Commit Graph

916685 Commits

Author SHA1 Message Date
Mauro Carvalho Chehab
40e79150c1 docs: networking: convert lapb-module.txt to ReST
- add SPDX header;
- adjust title markup;
- mark code blocks and literals as such;
- mark tables as such;
- adjust identation, whitespaces and blank lines;
- add to networking/index.rst.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 12:56:35 -07:00
Mauro Carvalho Chehab
10ebb22137 docs: networking: convert l2tp.txt to ReST
- add SPDX header;
- add a document title;
- mark tables as such;
- adjust identation, whitespaces and blank lines;
- add to networking/index.rst.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 12:56:35 -07:00
David S. Miller
9f04960660 Merge branch 'inet_diag-add-cgroup-attribute-and-filter'
Dmitry Yakunin says:

====================
inet_diag: add cgroup attribute and filter

This patch series extends inet diag with cgroup v2 ID attribute and
filter. Which allows investigate sockets on per cgroup basis. Patch for
ss is already sent to iproute2-next mailing list.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 12:54:02 -07:00
Dmitry Yakunin
b1f3e43dbf inet_diag: add support for cgroup filter
This patch adds ability to filter sockets based on cgroup v2 ID.
Such filter is helpful in ss utility for filtering sockets by
cgroup pathname.

Signed-off-by: Dmitry Yakunin <zeil@yandex-team.ru>
Reviewed-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 12:54:02 -07:00
Dmitry Yakunin
6e3a401fc8 inet_diag: add cgroup id attribute
This patch adds cgroup v2 ID to common inet diag message attributes.
Cgroup v2 ID is kernfs ID (ino or ino+gen). This attribute allows filter
inet diag output by cgroup ID obtained by name_to_handle_at() syscall.
When net_cls or net_prio cgroup is activated this ID is equal to 1 (root
cgroup ID) for newly created sockets.

Some notes about this ID:

1) gets initialized in socket() syscall
2) incoming socket gets ID from listening socket
   (not during accept() syscall)
3) not changed when process get moved to another cgroup
4) can point to deleted cgroup (refcounting)

v2:
  - use CONFIG_SOCK_CGROUP_DATA instead if CONFIG_CGROUPS

v3:
  - fix attr size by using nla_total_size_64bit() (Eric Dumazet)
  - more detailed commit message (Konstantin Khlebnikov)

Signed-off-by: Dmitry Yakunin <zeil@yandex-team.ru>
Reviewed-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Acked-By: Tejun Heo <tj@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 12:54:01 -07:00
David S. Miller
8a769c65bb Merge branch 'stmmac-intel-Fixes-and-cleanups-after-dwmac-intel-split'
Andy Shevchenko says:

====================
stmmac: intel: Fixes and cleanups after dwmac-intel split

Seems the split of dwmac-intel didn't go well and on top of that new
functionality in the driver has not been properly tested.

Patch 1 fixes a nasty kernel crash due to missed error handling.
Patches 2 and 3 fix the incorrect split (clock and PCI bar handling).

Patch 4 converts driver to use new PCI IRQ allocation API.

The rest is a set of clean ups that may have been done in the initial
submission.

Series has been tested on couple of Elkhart Lake platforms with different
behaviour of ethernet hardware.

Changelog v3:
- added the cover letter (David)
- appended separate fix as a first patch
- marked patches 2 and 3 with Fixes tag
====================

Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 12:50:16 -07:00
Andy Shevchenko
29e0c2f39f stmmac: intel: Place object in the Makefile according to the order
Follow the order for the platform drivers, i.e. generic object are going first.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 12:50:16 -07:00
Andy Shevchenko
ccacb703b0 stmmac: intel: Fix indentation to put on one line affected code
There is no competition to get more LOCs into the kernel, and driver can look
better and have improved readability without those additional line breaks.

While at it, shorten info structures that they are all PCI, at the end it's
a PCI driver for Intel hardware.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 12:50:15 -07:00
Andy Shevchenko
d5383b0376 stmmac: intel: Eliminate useless conditions and variables
There are useless conditions like

	func()
	{
		...
		int ret;
		...
		ret = foo();
		if (ret)
			return ret;

		return 0;
	}

which may be replaced with direct return statement, what we have done here.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 12:50:15 -07:00
Andy Shevchenko
52c1f79484 stmmac: intel: Convert to use pci_alloc_irq_vectors() API
pci_enable_msi() is deprecated API, thus, switch to modern
pci_alloc_irq_vectors().

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 12:50:15 -07:00
Andy Shevchenko
e578f043ff stmmac: intel: Remove unnecessary loop for PCI BARs
Copy'n'paste without thinking is not a good idea and in this case it brought
unnecessary loop over PCI BAR resources which was needed to workaround one of
STMicro RVP boards. Remove unnecessary loops from Intel driver.

Fixes: 58da0cfa6c ("net: stmmac: create dwmac-intel.c to contain all Intel platform")
Cc: Voon Weifeng <weifeng.voon@intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 12:50:15 -07:00
Andy Shevchenko
09f012e64e stmmac: intel: Fix clock handling on error and remove paths
clk_prepare_enable() might fail, we have to check its returned value.
Besides that we have to call clk_disable_unprepare() on the error and
remove paths. Do above in the dwmac-intel driver.

While at it, remove leftover in stmmac_pci and remove unneeded condition
for NULL-aware clk_unregister_fixed_rate() call.

Fixes: 58da0cfa6c ("net: stmmac: create dwmac-intel.c to contain all Intel platform")
Cc: Voon Weifeng <weifeng.voon@intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 12:50:15 -07:00
Andy Shevchenko
801eb05018 stmmac: intel: Fix kernel crash due to wrong error path
Unfortunately sometimes ->probe() may fail. The commit b9663b7ca6
("net: stmmac: Enable SERDES power up/down sequence")
messed up with error handling and thus:

[   12.811311] ------------[ cut here ]------------
[   12.811993] kernel BUG at net/core/dev.c:9937!

Fix this by properly crafted error path.

Fixes: b9663b7ca6 ("net: stmmac: Enable SERDES power up/down sequence")
Cc: Voon Weifeng <weifeng.voon@intel.com>
Cc: Ong Boon Leong <boon.leong.ong@intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 12:50:15 -07:00
David S. Miller
fe4f961eb5 Merge branch 'net-smc-add-event-based-framework-for-LLC-msgs'
Karsten Graul says:

====================
net/smc: add event-based framework for LLC msgs

These patches are the next step towards SMC-R link failover support. They add
a new framework to handle Link Layer Control (LLC) messages and adapt the
existing code to use the new framework.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 12:44:34 -07:00
Karsten Graul
41a211d862 net/smc: remove obsolete link state DELETING
The connection layer in af_smc.c is now using the new LLC flow
framework, which made the link state DELETING obsolete. Remove the state
and the respective helpers.

Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Reviewed-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 12:44:34 -07:00
Karsten Graul
42d18acce9 net/smc: remove handling of CONFIRM_RKEY_CONTINUE
The new SMC-R multiple link support will support a maximum of 3 links,
and one CONFIRM_RKEY LLC message can transport 3 rkeys of an rmb buffer.
There is no need for the LLC message type CONFIRM_RKEY_CONTINUE which is
needed when more than 3 rkeys per rmb buffer needs to be exchanged.

Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Reviewed-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 12:44:34 -07:00
Karsten Graul
218b24fe38 net/smc: adapt SMC remote DELETE_RKEY processing to use the LLC flow
Use the LLC flow framework for the processing of DELETE_RKEY messages
that were received from the peer.

Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Reviewed-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 12:44:34 -07:00
Karsten Graul
3bc67e098c net/smc: adapt SMC remote CONFIRM_RKEY processing to use the LLC flow
Use the LLC flow framework for the processing of CONFIRM_RKEY messages
that were received from the peer.

Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Reviewed-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 12:44:34 -07:00
Karsten Graul
ba21abd22f net/smc: new smc_rtoken_set functions for multiple link support
Introduce smc_rtoken_set() to set the rtoken for a new link to an
existing rmb whose rtoken is given, and smc_rtoken_set2() to set an
rtoken for a new link whose link_id is given.

Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Reviewed-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 12:44:34 -07:00
Karsten Graul
56e8091c7a net/smc: move the TEST_LINK response processing into event handler
Get rid of the extra function and move the two-liner for the TEST_LINK
response processing into the event handler function.

Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Reviewed-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 12:44:33 -07:00
Karsten Graul
6d74c3a8a3 net/smc: multiple link support and LLC flow for smc_llc_do_delete_rkey
Adapt smc_llc_do_delete_rkey() to use the LLC flow and support multiple
links when deleting the rkeys for rmb buffers at the peer.

Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Reviewed-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 12:44:33 -07:00
Karsten Graul
3d88a21b0c net/smc: multiple link support and LLC flow for smc_llc_do_confirm_rkey
Adapt smc_llc_do_confirm_rkey() to use the LLC flow and support the
rkeys of multiple links when the CONFIRM_RKEY LLC message is build.

Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Reviewed-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 12:44:33 -07:00
Karsten Graul
0fb0b02bd6 net/smc: adapt SMC client code to use the LLC flow
Change the code that processes the SMC client part of connection
establishment to use the LLC flow framework (CONFIRM_LINK request
messages).

Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Reviewed-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 12:44:33 -07:00
Karsten Graul
4667bb4aaa net/smc: adapt SMC server code to use the LLC flow
Change the code that processes the SMC server part of connection
establishment to use the LLC flow framework (CONFIRM_LINK response
messages).

Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Reviewed-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 12:44:33 -07:00
Karsten Graul
92334cfcb3 net/smc: add logic to evaluate CONFIRM_LINK messages to LLC layer
Introduce smc_llc_eval_conf_link() to evaluate the CONFIRM_LINK message
contents. This implements this logic at the LLC layer. The function will
be used by af_smc.c to process the received LLC layer messages.

Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Reviewed-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 12:44:33 -07:00
Karsten Graul
81e6e5e70d net/smc: introduce link group type
Add a type field to the link group which reflects the current link group
redundancy state.

Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Reviewed-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 12:44:33 -07:00
Karsten Graul
a6688d919b net/smc: enqueue all received LLC messages
Introduce smc_llc_enqueue() to enqueue LLC messages, and adapt
smc_llc_rx_handler() to enqueue all received LLC messages.
smc_llc_enqueue() also makes it possible to enqueue LLC messages from
local code.

Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Reviewed-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 12:44:33 -07:00
Karsten Graul
555da9af82 net/smc: add event-based llc_flow framework
The new framework allows to start specific types of LLC control flows,
protects active flows and makes it possible to wait for flows to finish
before starting a new flow.
This mechanism is used for the LLC control layer to model flows like
'add link' or 'delete link' which need to send/receive several LLC
messages and are not allowed to get interrupted by the wrong type of
messages.
'Add link' or 'Delete link' messages arriving in the middle of a flow
are delayed and processed when the current flow finished.

Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Reviewed-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 12:44:33 -07:00
Tang Bin
1569a3c443 net/faraday: Fix unnecessary check in ftmac100_probe()
The function ftmac100_probe() is only called with an openfirmware
platform device. Therefore there is no need to check that the passed
in device is NULL.

Signed-off-by: Zhang Shengju <zhangshengju@cmss.chinamobile.com>
Signed-off-by: Tang Bin <tangbin@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 12:20:54 -07:00
Yunjian Wang
51070a3627 rionet: Fix use correct return type for ndo_start_xmit()
The method ndo_start_xmit() returns a value of type netdev_tx_t. Fix
the ndo function to use the correct type.

Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 12:15:13 -07:00
Yunjian Wang
99b2292ba2 net: caif: Fix use correct return type for ndo_start_xmit()
The method ndo_start_xmit() returns a value of type netdev_tx_t. Fix
the ndo function to use the correct type.

Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 12:13:07 -07:00
David S. Miller
4b88de9f01 Merge branch 'net-phy-mdio-add-IPQ40xx-MDIO-support'
Robert Marko says:

====================
net: phy: mdio: add IPQ40xx MDIO support

This patch series provides support for the IPQ40xx built-in MDIO interface.
Included are driver, devicetree bindings for it and devicetree node.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 12:11:14 -07:00
Robert Marko
9c8c0f70ec ARM: dts: qcom: ipq4019: add MDIO node
This patch adds the necessary MDIO interface node
to the Qualcomm IPQ4019 DTSI.

Built-in QCA8337N switch is managed using it,
and since we have a driver for it lets add it.

Signed-off-by: Christian Lamparter <chunkeey@gmail.com>
Signed-off-by: Robert Marko <robert.marko@sartura.hr>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Cc: Luka Perkov <luka.perkov@sartura.hr>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 12:11:14 -07:00
Robert Marko
4972ecee06 dt-bindings: add Qualcomm IPQ4019 MDIO bindings
This patch adds the binding document for the IPQ40xx MDIO driver.

Signed-off-by: Robert Marko <robert.marko@sartura.hr>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Cc: Luka Perkov <luka.perkov@sartura.hr>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 12:11:14 -07:00
Robert Marko
466ed24fb2 net: phy: mdio: add IPQ4019 MDIO driver
This patch adds the driver for the MDIO interface
inside of Qualcomm IPQ40xx series SoC-s.

Signed-off-by: Christian Lamparter <chunkeey@gmail.com>
Signed-off-by: Robert Marko <robert.marko@sartura.hr>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Cc: Luka Perkov <luka.perkov@sartura.hr>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 12:11:14 -07:00
Zou Wei
40cf7fbe8a hinic: Use ARRAY_SIZE for nic_vf_cmd_msg_handler
fix coccinelle warning, use ARRAY_SIZE

drivers/net/ethernet/huawei/hinic/hinic_sriov.c:713:43-44: WARNING: Use ARRAY_SIZE

v1-->v2:
   remove cmd_number

v2-->v3:
   preserve the reverse christmas tree ordering of local variables

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Zou Wei <zou_wei@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 11:53:12 -07:00
YueHaibing
ddc2118ef0 hinic: make a bunch of functions static
These fucntions is used only in hinic_sriov.c,
so make them static to fix sparse warnings.

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 11:52:36 -07:00
Maxim Mikityanskiy
ec9cdca066 net/mlx5e: Unify reserving space for WQEs
In our fast-path design, a WQE (Work Queue Element) must not cross the
page boundary. To enforce that, for WQEs consisting of more than one BB
(Basic Block), the driver checks the available contiguous space in the
WQ in advance, and if it's not enough, it pads it with NOPs.

This patch modifies the code that calculates the position of next WQE,
considering the padding, and prepares the WQE. This code is common for
all SQ types. In this patch it's reorganized in a way that makes the
usage pattern unified for all SQ types, and makes the implementations
self-contained and look almost the same, preparing the repeating code to
further attempts to deduplicate it.

One place is left as is: mlx5e_sq_xmit and mlx5e_fill_sq_frag_edge call
inside, because it is special in a way that it may also copy WQE's cseg
and eseg when reserving space. This will be eliminated in one of the
following patches, and this place will be converted to the new approach,
too.

Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
2020-04-30 10:10:46 -07:00
Maxim Mikityanskiy
7d42c8e9ab net/mlx5e: Rename ICOSQ WQE info struct and field
Structs mlx5e_txqsq and mlx5e_xdpsq contain wqe_info arrays to store
supplementary information corresponding to WQEs in the queue. Struct
mlx5e_icosq also has such an array, but it's called differently -
ico_wqe. This patch renames it to unify with the other SQs.

In addition, rename the struct to emphasize its specific usage.

Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
2020-04-30 10:10:45 -07:00
Maxim Mikityanskiy
fed0c6cfcd net/mlx5e: Fetch WQE: reuse code and enforce typing
There are multiple functions mlx5{e,i}_*_fetch_wqe that contain the same
code, that is repeated, because they operate on different SQ struct
types. mlx5e_sq_fetch_wqe also returns void *, instead of the concrete
WQE type.

This commit generalizes the fetch WQE operation by putting this code
into a single function. To simplify calls of the generic function in
concrete use cases, macros are provided that substitute the right WQE
size and cast the return type.

Before this patch, fetch_wqe used to calculate pi itself, but the value
was often known to the caller. This calculation is moved outside to
eliminate this unnecessary step and prepare for the fill_frag_edge
refactoring in the next patch.

Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
2020-04-30 10:10:45 -07:00
Tariq Toukan
e2e11dbf36 net/mlx5e: XDP, Print the offending TX descriptor on error completion
Upon an error completion on an XDP SQ, print the offending WQE
to ease the debug process.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
2020-04-30 10:10:45 -07:00
Tariq Toukan
f1b95753ee net/mlx5e: TX, Generalise code and usage of error CQE dump
Error CQE was dumped only for TXQ SQs.
Generalise the function, and add usage for error completions
on ICO SQs and XDP SQs.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
2020-04-30 10:10:44 -07:00
Tariq Toukan
e658664c77 net/mlx5e: Use proper name field for the UMR key
Even though some of the WQE control segment's field share
the same memory bits (a union of fields), prefer having the
right field name for every different usage.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
2020-04-30 10:10:44 -07:00
Eran Ben Elisha
c6168161f6 net/mlx5: Add support for release all pages event
If FW sets release_all_pages bit in MLX5_EVENT_TYPE_PAGE_REQUEST,
driver shall release all pages of a given function id, with no further
pages reclaim negotiation with FW nor MANAGE_PAGES commands from driver
towards FW.

Upon receiving this bit as part of pages reclaim event, driver will
initiate release all flow, in which it will iterate and release all
function's pages.

As part of driver <-> FW capabilities handshake, FW will report
release_all_pages max HCA cap bit, and driver will set the
release_all_pages bit in HCA cap.

NIC: ConnectX-4 Lx
CPU: Intel(R) Xeon(R) CPU E5-2650 v2 @ 2.60GHz
Test case: Simulataniously FLR 4 VFs, and measure FW release pages by
driver.
Before: 3.18 Sec
After:  0.31 Sec

Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
2020-04-30 10:10:44 -07:00
Eran Ben Elisha
c7636942d2 net/mlx5: Rate limit page not found error messages
Thousands of pages are released with free_addr() function. In case of
buggy sync between FW and driver on released address, the log will be
flooded with error messages. Use mlx5_core_warn_rl() to limit it.

Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
2020-04-30 10:10:44 -07:00
Eran Ben Elisha
c655c1f469 net/mlx5: Add helper function to release fw page
Factor out the fwp address release page to an helper function, will be
used in the downstream patch.

Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
2020-04-30 10:10:44 -07:00
Tariq Toukan
51dde00b8f net/mlx5: Remove unused field in EQ
The size field in EQ is not in use.
Remove it.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Tal Gilboa <talgi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
2020-04-30 10:10:43 -07:00
Paul Blakey
d2658b4a1d net/mlx5: CT: Remove unused variables
Signed-off-by: Paul Blakey <paulb@mellanox.com>
Reviewed-by: Oz Shlomo <ozsh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
2020-04-30 10:10:43 -07:00
Roi Dayan
70a5698a56 net/mlx5e: CT: Avoid false warning about rule may be used uninitialized
Avoid gcc warning by preset rule to invalid ptr.

Fixes: 4c3844d9e9 ("net/mlx5e: CT: Introduce connection tracking")
Signed-off-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
2020-04-30 10:10:43 -07:00
Zheng Bin
e59b254cbe net/mlx5e: Remove unneeded semicolon
Fixes coccicheck warning:

drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c:690:2-3: Unneeded semicolon

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Zheng Bin <zhengbin13@huawei.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
2020-04-30 10:10:42 -07:00