Commit Graph

43 Commits

Author SHA1 Message Date
Nathan Whitehorn
f68992cf66 Performance improvements for octe(4):
- Distribute RX load across multiple cores, if present. This reverts
  r217212, which is no longer relevant (I think because of the newer
  SDK).
- Use newer APIs for pinning taskqueue entries to specific cores.
- Deepen RX buffers.

This more than doubles NAT forwarding throughput on my EdgeRouter Lite from,
with typical packet mixture, 90 Mbps to over 200 Mbps. The result matches
forwarding throughput in Linux without the UBNT hardware offload on the same
hardware, and thus likely reflects hardware limits.

Reviewed by:	jhibbits
2019-02-10 20:13:59 +00:00
Pedro F. Giffuni
19d3b47b92 sys/mips: further adoption of SPDX licensing ID tags.
Mainly focus on files that use BSD 2-Clause license, however the tool I
was using misidentified many licenses so this was mostly a manual - error
prone - task.

The Software Package Data Exchange (SPDX) group provides a specification
to make it easier for automated tools to detect and summarize well known
opensource licenses. We are gradually adopting the specification, noting
that the tags are considered only advisory and do not, in any way,
superceed or replace the license texts.
2017-11-27 15:07:26 +00:00
Pedro F. Giffuni
51369649b0 sys: further adoption of SPDX licensing ID tags.
Mainly focus on files that use BSD 3-Clause license.

The Software Package Data Exchange (SPDX) group provides a specification
to make it easier for automated tools to detect and summarize well known
opensource licenses. We are gradually adopting the specification, noting
that the tags are considered only advisory and do not, in any way,
superceed or replace the license texts.

Special thanks to Wind River for providing access to "The Duke of
Highlander" tool: an older (2014) run over FreeBSD tree was useful as a
starting point.
2017-11-20 19:43:44 +00:00
Jung-uk Kim
fd90e2ed54 CALLOUT_MPSAFE has lost its meaning since r141428, i.e., for more than ten
years for head.  However, it is continuously misused as the mpsafe argument
for callout_init(9).  Deprecate the flag and clean up callout_init() calls
to make them more consistent.

Differential Revision:	https://reviews.freebsd.org/D2613
Reviewed by:	jhb
MFC after:	2 weeks
2015-05-22 17:05:21 +00:00
Gleb Smirnoff
d8cc52c9a1 Mechanically convert to if_inc_counter(). 2014-09-19 09:19:49 +00:00
Alexander Kabaev
7cb7fbdee6 Add delay to Octeon MDIO access routines.
Prevent saturattion of the bus by constant polling which in
extreme cases can cause interface lockup. This makes FreeBSD
match similar case in the executive.
2014-09-14 00:02:37 +00:00
Gleb Smirnoff
1bffa9511f Use define from if_var.h to access a field inside struct if_data,
that resides in struct ifnet.

Sponsored by:	Nginx, Inc.
2014-08-30 19:55:54 +00:00
Juli Mallett
47281130c2 Add missing includes. 2013-12-10 09:38:18 +00:00
Gleb Smirnoff
66e01d73cd - Provide necessary includes.
- Remove unnecessary includes.

Sponsored by:	Netflix
Sponsored by:	Nginx, Inc.
2013-10-29 11:17:49 +00:00
Warner Losh
57f37a2584 Use cvmx_mgmt_port_num_ports() instead of the inlined copy of a
previous version of this function.
2013-05-02 19:47:36 +00:00
Gleb Smirnoff
eb1b1807af Mechanically substitute flags from historic mbuf allocator with
malloc(9) flags within sys.

Exceptions:

- sys/contrib not touched
- sys/mbuf.h edited manually
2012-12-05 08:04:20 +00:00
Juli Mallett
fcd5eed4f0 Prevent hang on ATCA-7220 when transmitting packets < 60 bytes. 2012-11-19 08:30:29 +00:00
Juli Mallett
d0ebf478da Remove redundant printf of SDK version which already appears earlier in boot. 2012-11-19 08:29:53 +00:00
Juli Mallett
ca765bc7ab Fix longstanding misprint. 2012-10-31 04:44:32 +00:00
Juli Mallett
3631682eab Actually check board type rather than using a specialized octeon_is_simulation
function.
2012-10-30 06:36:14 +00:00
Juli Mallett
dc4ee6ca91 Merge the Cavium Octeon SDK 2.3.0 Simple Executive code and update FreeBSD to
make use of it where possible.

This primarily brings in support for newer hardware, and FreeBSD is not yet
able to support the abundance of IRQs on new hardware and many features in the
Ethernet driver.

Because of the changes to IRQs in the Simple Executive, we have to maintain our
own list of Octeon IRQs now, which probably can be pared-down and be specific
to the CIU interrupt unit soon, and when other interrupt mechanisms are added
they can maintain their own definitions.

Remove unmasking of interrupts from within the UART device now that the
function used is no longer present in the Simple Executive.  The unmasking
seems to have been gratuitous as this is more properly handled by the buses
above the UART device, and seems to work on that basis.
2012-03-11 06:17:49 +00:00
Oleksandr Tymoshenko
f3318c38dc Revert part of old logic of assigning MAC addressess:
- Reserver respective number of addresses for managment port
- octm uses base address directly
- other drivers get MACs on "first come first served" basis

Reviewed by:	juli
2012-02-29 05:48:29 +00:00
Oleksandr Tymoshenko
57fa7d3101 Refctor address assignment for Octeon's ethernet ports:
- Centralize address assignment
- Make sure managment ports get first MAC address in pool
- Properly propagate fail if address allocation failed

Submitted by:	Andrew Duane <aduane@juniper.net>
2012-02-22 01:30:25 +00:00
Marcel Moolenaar
4699b5e472 Remove octeon_bootinfo from all files except octeon_machdep.c.
Use instead cvmx_sysinfo_get() consistently.

Reviewed by: jmallett, marcel
Obtained from: Juniper Networks, Inc
Author: Andrew Duane
2011-10-04 20:17:43 +00:00
Marius Strobl
3fcb7a5365 - Remove attempts to implement setting of BMCR_LOOP/MIIF_NOLOOP
(reporting IFM_LOOP based on BMCR_LOOP is left in place though as
  it might provide useful for debugging). For most mii(4) drivers it
  was unclear whether the PHYs driven by them actually support
  loopback or not. Moreover, typically loopback mode also needs to
  be activated on the MAC, which none of the Ethernet drivers using
  mii(4) implements. Given that loopback media has no real use (and
  obviously hardly had a chance to actually work) besides for driver
  development (which just loopback mode should be sufficient for
  though, i.e one doesn't necessary need support for loopback media)
  support for it is just dropped as both NetBSD and OpenBSD already
  did quite some time ago.
- Let mii_phy_add_media() also announce the support of IFM_NONE.
- Restructure the PHY entry points to use a structure of entry points
  instead of discrete function pointers, and extend this to include
  a "reset" entry point. Make sure any PHY-specific reset routine is
  always used, and provide one for lxtphy(4) which disables MII
  interrupts (as is done for a few other PHYs we have drivers for).
  This includes changing NIC drivers which previously just called the
  generic mii_phy_reset() to now actually call the PHY-specific reset
  routine, which might be crucial in some cases. While at it, the
  redundant checks in these NIC drivers for mii->mii_instance not being
  zero before calling the reset routines were removed because as soon
  as one PHY driver attaches mii->mii_instance is incremented and we
  hardly can end up in their media change callbacks etc if no PHY driver
  has attached as mii_attach() would have failed in that case and not
  attach a miibus(4) instance.
  Consequently, NIC drivers now no longer should call mii_phy_reset()
  directly, so it was removed from EXPORT_SYMS.
- Add a mii_phy_dev_attach() as a companion helper to mii_phy_dev_probe().
  The purpose of that function is to perform the common steps to attach
  a PHY driver instance and to hook it up to the miibus(4) instance and to
  optionally also handle the probing, addition and initialization of the
  supported media. So all a PHY driver without any special requirements
  has to do in its bus attach method is to call mii_phy_dev_attach()
  along with PHY-specific MIIF_* flags, a pointer to its PHY functions
  and the add_media set to one. All PHY drivers were updated to take
  advantage of mii_phy_dev_attach() as appropriate. Along with these
  changes the capability mask was added to the mii_softc structure so
  PHY drivers taking advantage of mii_phy_dev_attach() but still
  handling media on their own do not need to fiddle with the MII attach
  arguments anyway.
- Keep track of the PHY offset in the mii_softc structure. This is done
  for compatibility with NetBSD/OpenBSD.
- Keep track of the PHY's OUI, model and revision in the mii_softc
  structure. Several PHY drivers require this information also after
  attaching and previously had to wrap their own softc around mii_softc.
  NetBSD/OpenBSD also keep track of the model and revision on their
  mii_softc structure. All PHY drivers were updated to take advantage
  as appropriate.
- Convert the mebers of the MII data structure to unsigned where
  appropriate. This is partly inspired by NetBSD/OpenBSD.
- According to IEEE 802.3-2002 the bits actually have to be reversed
  when mapping an OUI to the MII ID registers. All PHY drivers and
  miidevs where changed as necessary. Actually this now again allows to
  largely share miidevs with NetBSD, which fixed this problem already
  9 years ago. Consequently miidevs was synced as far as possible.
- Add MIIF_NOMANPAUSE and mii_phy_flowstatus() calls to drivers that
  weren't explicitly converted to support flow control before. It's
  unclear whether flow control actually works with these but typically
  it should and their net behavior should be more correct with these
  changes in place than without if the MAC driver sets MIIF_DOPAUSE.

Obtained from:	NetBSD (partially)
Reviewed by:	yongari (earlier version), silence on arch@ and net@
2011-05-03 19:51:29 +00:00
Juli Mallett
e22b8a5a3b o) Set MAC addresses starting at the MAC base for all management ports, not
just the MR-730.
o) Start MAC addresses for the non-management ports after the management ports.

Submitted by:	Bhanu Prakash (with modifications)
2011-03-16 22:51:34 +00:00
Juli Mallett
26de5f20cc o) Tear down receive interrupt on detach.
Submitted by:	Bhanu Prakash
2011-03-16 08:56:22 +00:00
Juli Mallett
64974004ec o) Clean up FPA pools on module unload.
o) Allocate output buffer pool based on available output queues.

Submitted by:	Bhanu Prakash (with modifications)
2011-03-16 08:51:36 +00:00
Juli Mallett
cb2096acbf The Lanner MR-730 uses the first two MACs at its MAC base for the 10/100
management ports, and gigabit ports start at an offset of 2 from the MAC
base.
2011-02-12 02:41:33 +00:00
Juli Mallett
2e2b4ad457 If there is no WQE available for a packet that needs segmentation, drop it
and return.
2011-01-20 23:51:03 +00:00
Juli Mallett
3e46966ed3 Remove some compile-time options from the driver, particularly async IOBDMA
support which is unused on FreeBSD and which complicates working on the
code now, can easily be added back later by someone determined to use it.
2011-01-20 23:34:59 +00:00
Juli Mallett
449cf853ac Count output bytes and packets. 2011-01-10 22:14:30 +00:00
Juli Mallett
987da28eb7 Now that we correctly enable rx interrupts on all cores, performance has gotten
quite awful, because e.g. 4 packets will come in and get processed on 4
different cores at the same time, really battling with the TCP stack quite
painfully.  For now, just run one task at a time.

This gets performance up in most cases to where it was before the correctness
fixes that got interrupts to run on all cores (except in high-load TCP transmit
cases where all we're handling receive for is ACKs) and in some cases it's
better now.  What would be ideal would be to use a more advanced interrupt
mitigation strategy and possibly to use different workqueue groups per port for
multi-port systems, and so on, but this is a fine stopgap.
2011-01-09 23:46:24 +00:00
Juli Mallett
529fb1406b o) Remove some unused local definitions of IP protocol numbers.
o) Use CPU_FOREACH rather than a miscrafted for loop with an off-by-one to
   enable workq interrupts on all cores.
2011-01-09 23:05:46 +00:00
Juli Mallett
4a7b75273b o) Add support for the Lanner MR-321X/MR-325, which is just a modified MR-320.
o) On the Lanner MR-730, disable PCIe lane swap, per vendor.
2010-12-16 07:20:38 +00:00
Juli Mallett
074a0a8d57 Run all poll requests through a single function that can either do the generic
link state polling or media-specific ones, while avoidiing changing link state
on interfaces that use miibus; this substantially speeds up link time on
interface (re)initialization.
2010-11-30 07:14:05 +00:00
Juli Mallett
b8248487b3 Don't free the work queue entry that we're using to hold the scatter-gather
list on exit from the transmit path.  The scatter-gather list itself can be
asynchronously DMAed to the transmit hardware, and we could actually lock up
the transmitter if any of a number of races around this were lost.

Instead, let the PKO free the scatter-gather list when it is done with it, and
use the "i" bit in each segment of the packet to avoid having them go into the
FPA.

This fixes an unrecoverable transmit stall under transmit load.

MFC after:	3 days
2010-11-29 21:04:00 +00:00
Juli Mallett
04b6fa8330 Merge Cavium Octeon SDK 2.0 Simple Executive; this brings some fixes and new
facilities as well as support for the Octeon 2 family of SoCs.

XXX Note that with our antediluvian assembler, we can't support some Octeon 2
    instructions and fall back to using the old ones instead.
2010-11-28 08:18:16 +00:00
Juli Mallett
34e3f53b7c o) Remove some commented out or unimplemented code.
o) Remove some options that are configurable on Linux but not FreeBSD.
o) Centralize open/poll/stop routines for XAUI and SGMII and use the common
   uninit routine directly rather than providing a wrapper for it.  The init
   functions for these interfaces are now identical and the common init routine
   could merge in setting those function pointers except that some hardware
   seems to use no open/poll/stop method?
2010-11-28 05:57:24 +00:00
Juli Mallett
ed11b5abe1 Remove unused and broken code to implement POW send and POW-only devices; a
separate POW driver makes more sense, generally.
2010-11-28 00:26:08 +00:00
Juli Mallett
25b0900026 Use if_transmit to avoid ifq locking in transmit path. 2010-11-27 22:42:41 +00:00
Marius Strobl
8e5d93dbb4 Convert the PHY drivers to honor the mii_flags passed down and convert
the NIC drivers as well as the PHY drivers to take advantage of the
mii_attach() introduced in r213878 to get rid of certain hacks. For
the most part these were:
- Artificially limiting miibus_{read,write}reg methods to certain PHY
  addresses; we now let mii_attach() only probe the PHY at the desired
  address(es) instead.
- PHY drivers setting MIIF_* flags based on the NIC driver they hang
  off from, partly even based on grabbing and using the softc of the
  parent; we now pass these flags down from the NIC to the PHY drivers
  via mii_attach(). This got us rid of all such hacks except those of
  brgphy() in combination with bce(4) and bge(4), which is way beyond
  what can be expressed with simple flags.

While at it, I took the opportunity to change the NIC drivers to pass
up the error returned by mii_attach() (previously by mii_phy_probe())
and unify the error message used in this case where and as appropriate
as mii_attach() actually can fail for a number of reasons, not just
because of no PHY(s) being present at the expected address(es).

Reviewed by:	jhb, yongari
2010-10-15 14:52:11 +00:00
Juli Mallett
2bcbafd6be Keep polling at 50hz as long as link state is changing. 2010-10-13 21:45:56 +00:00
Juli Mallett
f05957f7c6 o) Make it possible to attach a PHY directly to an octe device rather than
using miibus, since for some devices that use multiple addresses on the bus,
   going through miibus may be unclear, and for devices that are not standard
   MII PHYs, miibus may throw a fit, necessitating complicated interfaces to
   fake the interface that it expects during probe/attach.
o) Make the mv88e61xx SMI interface in octe attach a PHY directly and fix some
   mistakes in the code that resulted from trying too hard to present a nice
   interface to miibus.
o) Add a PHY driver for the mv88e61xx.  If attached (it is optional in kernel
   compiles so the default behavior of having a dumb switch is preserved) it
   will place the switch in a VLAN-tagging mode such that each physical port
   has a VLAN associated with it and interfaces for the VLANs can be created to
   address or bridge between them.
   XXX It would be nice for this to be part of a single module including the
       SMI interface, and for it to fit into a generic switch configuration
       framework and for it to use DSA rather than VLANs, but this is a start
       and gives some sense of the parameters of such frameworks that are not
       currently present in FreeBSD.  In lieu of a switch configuration
       interface, per-port media status and VLAN settings are in a sysctl tree.
   XXX There may be some minor nits remaining in the handling of broadcast,
       multicast and unknown destination traffic.  It would also be nice to go
       through and replace the few remaining magic numbers with macros at some
       point in the future.
   XXX This has only been tested with the MV88E6161, but it should work with
       minimal or no modification on related switches, so support for probing
       them was included.

Thanks to Pat Saavedra of TELoIP and Rafal Jaworowski of Semihalf for their
assistance in understanding the switch chipset.
2010-10-13 09:17:44 +00:00
Juli Mallett
a22b69b772 o) Allow devices to override the MDIO read and write functions presented to
the miibus attached to octe interfaces.
o) Add an SMI/MDIO interface to the MV88E61XX and use it for the switch PHY on
   the Lanner MR-320.  An actual driver for the switch PHY will come later.
   Note that for now it intercepts and fakes MII_BMSR reads to prevent the
   miibus from talking to anything but the switch itself.
2010-10-02 05:43:17 +00:00
Juli Mallett
243ee7e777 o) Send mbufs to BPF listeners from within cvm_oct_xmit().
o) Pin receive threads when they're running since we do access some core-local
   resources.
2010-09-25 04:39:12 +00:00
Juli Mallett
1ea299ce0d Handle link updates in a task. 2010-09-25 01:18:01 +00:00
Juli Mallett
cea2b8b915 Update the port of FreeBSD to Cavium Octeon to use the Cavium Simple Executive
library:
o) Increase inline unit / large function growth limits for MIPS to accommodate
   the needs of the Simple Executive, which uses a shocking amount of inlining.
o) Remove TARGET_OCTEON and use CPU_CNMIPS to do things required by cnMIPS and
   the Octeon SoC.
o) Add OCTEON_VENDOR_LANNER to use Lanner's allocation of vendor-specific
   board numbers, specifically to support the MR320.
o) Add OCTEON_BOARD_CAPK_0100ND to hard-wire configuration for the CAPK-0100nd,
   which improperly uses an evaluation board's board number and breaks board
   detection at runtime.  This board is sold by Portwell as the CAM-0100.
o) Add support for the RTC available on some Octeon boards.
o) Add support for the Octeon PCI bus.  Note that rman_[sg]et_virtual for IO
   ports can not work unless building for n64.
o) Clean up the CompactFlash driver to use Simple Executive macros and
   structures where possible (it would be advisable to use the Simple Executive
   API to set the PIO mode, too, but that is not done presently.)  Also use
   structures from FreeBSD's ATA layer rather than structures copied from
   Linux.
o) Print available Octeon SoC features on boot.
o) Add support for the Octeon timecounter.
o) Use the Simple Executive's routines rather than local copies for doing reads
   and writes to 64-bit addresses and use its macros for various device
   addresses rather than using local copies.
o) Rename octeon_board_real to octeon_is_simulation to reduce differences with
   Cavium-provided code originally written for Linux.  Also make it use the
   same simplified test that the Simple Executive and Linux both use rather
   than our complex one.
o) Add support for the Octeon CIU, which is the main interrupt unit, as a bus
   to use normal interrupt allocation and setup routines.
o) Use the Simple Executive's bootmem facility to allocate physical memory for
   the kernel, rather than assuming we know which addresses we can steal.
   NB: This may reduce the amount of RAM the kernel reports you as having if
       you are leaving large temporary allocations made by U-Boot allocated
       when starting FreeBSD.
o) Add a port of the Cavium-provided Ethernet driver for Linux.  This changes
   Ethernet interface naming from rgmxN to octeN.  The new driver has vast
   improvements over the old one, both in performance and functionality, but
   does still have some features which have not been ported entirely and there
   may be unimplemented code that can be hit in everyday use.  I will make
   every effort to correct those as they are reported.
o) Support loading the kernel on non-contiguous cores.
o) Add very conservative support for harvesting randomness from the Octeon
   random number device.
o) Turn SMP on by default.
o) Clean up the style of the Octeon kernel configurations a little and make
   them compile with -march=octeon.
o) Add support for the Lanner MR320 and the CAPK-0100nd to the Simple
   Executive.
o) Modify the Simple Executive to build on FreeBSD and to build without
   executive-config.h or cvmx-config.h.  In the future we may want to
   revert part of these changes and supply executive-config.h and
   cvmx-config.h and access to the options contained in those files via
   kernel configuration files.
o) Modify the Simple Executive USB routines to support getting and setting
   of the USB PID.
2010-07-20 19:25:11 +00:00