Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>

Even out Rx performance across MTU sizes by changing from full
skb allocations to page-based frag allocations.  The device
supports a form of scatter-gather in the Rx path, so we can
set up a number of pages for each descriptor, all of which are
easier to alloc and pass around than the standard kzalloc'd
buffer.  An skb is wrapped around the pages while processing
the received packets, and pages are recycled as needed, or
left alone if they weren't used in the Rx.
Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>

Add a watchdog to periodically monitor the NIC heartbeat.
Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>

Most of our firmware has a heartbeat feature that the driver
can watch for to see if the FW is still alive and likely to
answer a dev_cmd or AdminQ request.
Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>

Fix the initial interrupt coalesce usec-to-hw setting
to actually be usec-to-hw.

Fixes: 780eded3 ("ionic: report users coalesce request")
Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>

Fix up struct names in the ionic_if.h comments
Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>

We have only one user of the error path, so we can inline it.
In addition the call to rtl8169_make_unusable_by_asic() can be removed
because rtl8169_alloc_rx_data() didn't call rtl8169_mark_to_asic() yet
for the respective index if returning NULL.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This patch aligns the fix_features callback with the vendor driver and
also disables IPv6 HW checksumming and TSO if jumbo packets are used
on RTL8101/RTL8168/RTL8125.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Merge branch 'for-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/bluetooth/bluetooth-next

Johan Hedberg says:

====================
pull request: bluetooth-next 2019-10-23

Here's the main bluetooth-next pull request for the 5.5 kernel:

 - Multiple fixes to hci_qca driver
 - Fix for HCI_USER_CHANNEL initialization
 - btwlink: drop superseded driver
 - Add support for Intel FW download error recovery
 - Various other smaller fixes & improvements

Please let me know if there are any issues pulling. Thanks.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

The TCPI_OPT_SYN_DATA bit as part of tcpi_options currently reports whether
or not data-in-SYN was ack'd on both the client and server side. We'd like
to gather more information on the client-side in the failure case in order
to indicate the reason for the failure. This can be useful for not only
debugging TFO, but also for creating TFO socket policies. For example, if
a middle box removes the TFO option or drops a data-in-SYN, we can
can detect this case, and turn off TFO for these connections saving the
extra retransmits.

The newly added tcpi_fastopen_client_fail status is 2 bits and has the
following 4 states:

1) TFO_STATUS_UNSPEC

Catch-all state which includes when TFO is disabled via black hole
detection, which is indicated via LINUX_MIB_TCPFASTOPENBLACKHOLE.

2) TFO_COOKIE_UNAVAILABLE

If TFO_CLIENT_NO_COOKIE mode is off, this state indicates that no cookie
is available in the cache.

3) TFO_DATA_NOT_ACKED

Data was sent with SYN, we received a SYN/ACK but it did not cover the data
portion. Cookie is not accepted by server because the cookie may be invalid
or the server may be overloaded.

4) TFO_SYN_RETRANSMITTED

Data was sent with SYN, we received a SYN/ACK which did not cover the data
after at least 1 additional SYN was sent (without data). It may be the case
that a middle-box is dropping data-in-SYN packets. Thus, it would be more
efficient to not use TFO on this connection to avoid extra retransmits
during connection establishment.

These new fields do not cover all the cases where TFO may fail, but other
failures, such as SYN/ACK + data being dropped, will result in the
connection not becoming established. And a connection blackhole after
session establishment shows up as a stalled connection.
Signed-off-by: Jason Baron <jbaron@akamai.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Christoph Paasch <cpaasch@apple.com>
Cc: Yuchung Cheng <ycheng@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Grygorii Strashko says:

====================
net: phy: dp83867: enable robust auto-mdix

Patch 1 - improves link detection when dp83867 PHY is configured in manual mode
by enabling CFG3[9] Robust Auto-MDIX option.

Patch 2 - is minor optimization.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Move DT parsing code to probe dp83867_probe() as it's one time operation.
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The link detection timeouts can be observed (or link might not be detected
at all) when dp83867 PHY is configured in manual mode (speed/duplex).

CFG3[9] Robust Auto-MDIX option allows to significantly improve link detection
in case dp83867 is configured in manual mode and reduce link detection
time.
As per DM: "If link partners are configured to operational modes that are
not supported by normal Auto MDI/MDIX mode (like Auto-Neg versus Force
100Base-TX or Force 100Base-TX versus Force 100Base-TX), this Robust Auto
MDI/MDIX mode allows MDI/MDIX resolution and prevents deadlock."

Hence, enable this option by default as there are no known reasons
not to do so.
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

There is networking hardware that isn't based on Ethernet for layers 1 and 2.

For example CAN.

CAN is a multi-master serial bus standard for connecting Electronic Control
Units [ECUs] also known as nodes. A frame on the CAN bus carries up to 8 bytes
of payload. Frame corruption is detected by a CRC. However frame loss due to
corruption is possible, but a quite unusual phenomenon.

While fq_codel works great for TCP/IP, it doesn't for CAN. There are a lot of
legacy protocols on top of CAN, which are not build with flow control or high
CAN frame drop rates in mind.

When using fq_codel, as soon as the queue reaches a certain delay based length,
skbs from the head of the queue are silently dropped. Silently meaning that the
user space using a send() or similar syscall doesn't get an error. However
TCP's flow control algorithm will detect dropped packages and adjust the
bandwidth accordingly.

When using fq_codel and sending raw frames over CAN, which is the common use
case, the user space thinks the package has been sent without problems, because
send() returned without an error. pfifo_fast will drop skbs, if the queue
length exceeds the maximum. But with this scheduler the skbs at the tail are
dropped, an error (-ENOBUFS) is propagated to user space. So that the user
space can slow down the package generation.

On distributions, where fq_codel is made default via CONFIG_DEFAULT_NET_SCH
during compile time, or set default during runtime with sysctl
net.core.default_qdisc (see [1]), we get a bad user experience. In my test case
with pfifo_fast, I can transfer thousands of million CAN frames without a frame
drop. On the other hand with fq_codel there is more then one lost CAN frame per
thousand frames.

As pointed out fq_codel is not suited for CAN hardware, so this patch changes
attach_one_default_qdisc() to use pfifo_fast for "ARPHRD_CAN" network devices.

During transition of a netdev from down to up state the default queuing
discipline is attached by attach_default_qdiscs() with the help of
attach_one_default_qdisc(). This patch modifies attach_one_default_qdisc() to
attach the pfifo_fast (pfifo_fast_ops) if the network device type is
"ARPHRD_CAN".

[1] https://github.com/systemd/systemd/issues/9194Suggested-by: Marc Kleine-Budde <mkl@pengutronix.de>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Signed-off-by: Vincent Prince <vincent.prince.fr@gmail.com>
Acked-by: Dave Taht <dave.taht@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Fix the pointer rtl_fw->fw would be used before checking in
rtl8152_apply_firmware() that causes the following kernel oops.

Unable to handle kernel NULL pointer dereference at virtual address 00000002
pgd = (ptrval)
[00000002] *pgd=00000000
Internal error: Oops: 5 [#1] PREEMPT SMP ARM
Modules linked in:
CPU: 0 PID: 131 Comm: kworker/0:2 Not tainted
5.4.0-rc1-00539-g9370f2d0 #6788
Hardware name: SAMSUNG EXYNOS (Flattened Device Tree)
Workqueue: events_long rtl_hw_phy_work_func_t
PC is at rtl8152_apply_firmware+0x14/0x464
LR is at r8153_hw_phy_cfg+0x24/0x17c
pc : [<c064f4e4>]    lr : [<c064fa18>]    psr: a0000013
sp : e75c9e60  ip : 60000013  fp : c11b7614
r10: e883b91c  r9 : 00000000  r8 : fffffffe
r7 : e883b640  r6 : fffffffe  r5 : fffffffe  r4 : e883b640
r3 : 736cfe7c  r2 : 736cfe7c  r1 : 000052f8  r0 : e883b640
Flags: NzCv  IRQs on  FIQs on  Mode SVC_32  ISA ARM  Segment none
Control: 10c5387d  Table: 6640006a  DAC: 00000051
Process kworker/0:2 (pid: 131, stack limit = 0x(ptrval))
Stack: (0xe75c9e60 to 0xe75ca000)
...
[<c064f4e4>] (rtl8152_apply_firmware) from [<c064fa18>]
(r8153_hw_phy_cfg+0x24/0x17c)
[<c064fa18>] (r8153_hw_phy_cfg) from [<c064e784>]
(rtl_hw_phy_work_func_t+0x220/0x3e4)
[<c064e784>] (rtl_hw_phy_work_func_t) from [<c0148a74>]
(process_one_work+0x22c/0x7c8)
[<c0148a74>] (process_one_work) from [<c0149054>] (worker_thread+0x44/0x520)
[<c0149054>] (worker_thread) from [<c0150548>] (kthread+0x130/0x164)
[<c0150548>] (kthread) from [<c01010b4>] (ret_from_fork+0x14/0x20)
Exception stack(0xe75c9fb0 to 0xe75c9ff8)
...

Fixes: 9370f2d0 ("r8152: support request_firmware for RTL8153")
Reported-by: Marek Szyprowski <m.szyprowski@samsung.com>
Tested-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Madalin Bucur says:

====================
DPAA Ethernet changes

v3: add newline at the end of error messages
v2: resending with From: field matching signed-off-by

Here's a series of changes for the DPAA Ethernet, addressing minor
or unapparent issues in the codebase, adding probe ordering based on
a recently added DPAA QMan API, removing some redundant code.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Newline was missing at the end of the error message.
Signed-off-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Remove unused struct member second_largest_buf_size. Also, an out of
bounds access would have occurred in the removed code if there was only
one buffer pool in use.
Signed-off-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The DPAA Ethernet driver is using the FMan MAC as the device for DMA
mapping. This is not actually correct, as the real DMA device is the
FMan port (the FMan Rx port for reception and the FMan Tx port for
transmission). Changing the device used for DMA mapping to the Fman
Rx and Tx port devices.
Signed-off-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Add an API that retrieves the 'struct device' that the specified FMan
port probed against. The new API will be used in a subsequent patch
that corrects the DMA devices used by the dpaa_eth driver.
Signed-off-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Signed-off-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Condition was previously checked, removing duplicate code.
Signed-off-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

If the DPAA 1 Ethernet driver gets probed before the QBMan driver it will
cause a boot crash. Add predictability in the probing order by deferring
the Ethernet driver probe after QBMan and portals by using the recently
introduced QBMan APIs.
Signed-off-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Signed-off-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The liodn base registers are specific to PAMU based NXP systems and are
reserved on SMMU based ones. Don't access them unless PAMU is compiled in.
Signed-off-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Signed-off-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Igor Russkikh says:

====================
net: aquantia: PTP support for AQC devices

This patchset introduces PTP feature support in Aquantia AQC atlantic driver.

This implementation is a joined effort of aquantia developers:
Egor is the main designer and driver/firmware architect on PTP,
Sergey and Dmitry are included as co-developers.
Dmitry also helped me in the overall patchset preparations.

Feature was verified on AQC hardware with testptp tool, linuxptp,
gptp and with Motu hardware unit.

version3 updates:
- Review comments applied: error handling, various fixes

version2 updates:
- Fixing issues from Andrew's review: replacing self with
  ptp var name, making ptp_clk_offset a field in the ptp instance.
  devm_kzalloc advice is actually non applicable, because ptp object gets
  created/destroyed on each network device close/open and it should not be
  linked with dev lifecycle.
- Rearranging commit authorship, adding Egor as a ptp module main maintainer
- Fixing kbuild 32bit division issues
====================
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

PTP implementation is designed and maintained by Egor Pomozov, adding
him as this module maintainer. Egor is the author of the core
functionality and the architect, and is to be contacted for
all Aquantia PTP/AVB functionality.
Signed-off-by: Egor Pomozov <epomozov@marvell.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Depending on FW configuration we can manage from 0 to 3 PINs for periodic output
and from 0 to 1 ext ts PIN for getting TS for external event.

Ext TS PIN functionality is implemented via periodic timestamps polling
directly from PHY, because right now there is now way to receive the
PIN trigger interrupt from phy.

The polling interval is 15 milliseconds.
Co-developed-by: Egor Pomozov <epomozov@marvell.com>
Signed-off-by: Egor Pomozov <epomozov@marvell.com>
Co-developed-by: Pavel Belous <pavel.belous@aquantia.com>
Signed-off-by: Pavel Belous <pavel.belous@aquantia.com>
Signed-off-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

GPIO PIN control and access is done by direct phy manipulation.
Here we add an aq_phy module which is able to access phy registers
via MDIO access mailbox.

Access is controlled via HW semaphore.
Co-developed-by: Nikita Danilov <nikita.danilov@aquantia.com>
Signed-off-by: Nikita Danilov <nikita.danilov@aquantia.com>
Signed-off-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>

Ethtool callback with basic information on what PTP features are supported
by the device.
Signed-off-by: Egor Pomozov <epomozov@marvell.com>
Co-developed-by: Sergey Samoilenko <sergey.samoilenko@aquantia.com>
Signed-off-by: Sergey Samoilenko <sergey.samoilenko@aquantia.com>
Co-developed-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Here we add support for PTP specific IOCTLs of HW timestamp get/set.

These will use filters to configure flows onto the required queue ids.
Co-developed-by: Sergey Samoilenko <sergey.samoilenko@aquantia.com>
Signed-off-by: Sergey Samoilenko <sergey.samoilenko@aquantia.com>
Signed-off-by: Egor Pomozov <epomozov@marvell.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

We implement HW filter reservation for PTP traffic. Special location
in filters table is marked as reserved, because incoming ptp traffic
should be directed only to PTP designated queue. This way HW will do PTP
timestamping and proper processing.
Co-developed-by: Egor Pomozov <epomozov@marvell.com>
Signed-off-by: Egor Pomozov <epomozov@marvell.com>
Co-developed-by: Sergey Samoilenko <sergey.samoilenko@aquantia.com>
Signed-off-by: Sergey Samoilenko <sergey.samoilenko@aquantia.com>
Signed-off-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Here we do alloc/free IRQs for PTP rings.
We also implement processing of PTP packets on TX and RX sides.
Signed-off-by: Egor Pomozov <epomozov@marvell.com>
Co-developed-by: Sergey Samoilenko <sergey.samoilenko@aquantia.com>
Signed-off-by: Sergey Samoilenko <sergey.samoilenko@aquantia.com>
Co-developed-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Checkpatch and styling fixes on parts of code touched by ptp
Signed-off-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>

Add implementations of PTP rings alloc/free.

PTP desing on this device uses two separate rings on a separate traffic
class for traffic rx/tx.

Third ring (hwts) is not a traffic ring, but is used only to receive timestamps
of the transmitted packets.
Signed-off-by: Egor Pomozov <epomozov@marvell.com>
Co-developed-by: Sergey Samoilenko <sergey.samoilenko@aquantia.com>
Signed-off-by: Sergey Samoilenko <sergey.samoilenko@aquantia.com>
Co-developed-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Basic HW functions implemented for adjusting frequency,
adjusting time, getting and setting time.
With these callbacks we now do register ptp clock in the system.

Firmware interface parts are defined for PTP requests and interactions.
Enable/disable PTP counters in HW on clock register/unregister.
Signed-off-by: Egor Pomozov <epomozov@marvell.com>
Co-developed-by: Sergey Samoilenko <sergey.samoilenko@aquantia.com>
Signed-off-by: Sergey Samoilenko <sergey.samoilenko@aquantia.com>
Co-developed-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Make some other bit-enums more clear about positioning,
this helps on debugging and development
Signed-off-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>

Here we add basic function for PTP clock register/unregister.
We also declare FW/HW capability bits used to control PTP feature on device.

PTP device is created if network card has appropriate FW that has PTP
enabled in config. HW supports timestamping for PTPv2 802.AS1 and
PTPv2 IPv4 UDP packets.

It also supports basic PTP callbacks for getting/setting time, adjusting
frequency and time as well.
Signed-off-by: Egor Pomozov <epomozov@marvell.com>
Co-developed-by: Sergey Samoilenko <sergey.samoilenko@aquantia.com>
Signed-off-by: Sergey Samoilenko <sergey.samoilenko@aquantia.com>
Co-developed-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Fixes gcc '-Wunused-but-set-variable' warning:

drivers/net/usb/lan78xx.c:3995:6: warning:
 variable event set but not used [-Wunused-but-set-variable]

It is never used, so can be removed.
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Ido Schimmel says:

====================
mlxsw: Update main pool computation and pool size limits

Petr says:

In Spectrum ASICs, the shared buffer is an area of memory where packets are
kept until they can be transmitted. There are two resources associated with
shared buffer size: cap_total_buffer_size and cap_guaranteed_shared_buffer.
So far, mlxsw has been using the former as a limit when validating shared
buffer pool size configuration. However, the total size also includes
headrooms and reserved space, which really cannot be used for shared buffer
pools. Patch #1 mends this and has mlxsw use the guaranteed size.

To configure default pool sizes, mlxsw has historically hard-coded one or
two smallish pools, and one "main" pool that took most of the shared buffer
(that would be pool 0 on ingress and pool 4 on egress). During the
development of Spectrum-2, it became clear that the shared buffer size
keeps shrinking as bugs are identified and worked around. In order to
prevent having to tweak the size of pools 0 and 4 to catch up with updates
to values reported by the FW, patch #2 changes the way these pools are set.
Instead of hard-coding a fixed value, the main pool now takes whatever is
left from the guaranteed size after the smaller pool(s) are taken into
account.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Instead of hard-coding the size of the largest pool, calculate it from the
reported guaranteed shared buffer size and sizes of other pools (currently
only the CPU port pool).
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

There are two resources associated with shared buffer size:
cap_total_buffer_size, and cap_guaranteed_shared_buffer. So far, mlxsw has
been using the former as a limit to determine how large a pool size is
allowed to be. However, the total size also includes headrooms and reserved
space, which really cannot be used for shared buffer pools.

Therefore convert mlxsw to use the latter resource as a limit. Adjust
hard-coded pool sizes to be the guaranteed size minus 256000 bytes for CPU
port pool. On Spectrum-1 that actually leads to an increase. A follow-up
patch will have this size calculated automatically.
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>