Commit Graph

30 Commits

Author SHA1 Message Date
Matt Macy
d7c5a620e2 ifnet: Replace if_addr_lock rwlock with epoch + mutex
Run on LLNW canaries and tested by pho@

gallatin:
Using a 14-core, 28-HTT single socket E5-2697 v3 with a 40GbE MLX5
based ConnectX 4-LX NIC, I see an almost 12% improvement in received
packet rate, and a larger improvement in bytes delivered all the way
to userspace.

When the host receiving 64 streams of netperf -H $DUT -t UDP_STREAM -- -m 1,
I see, using nstat -I mce0 1 before the patch:

InMpps OMpps  InGbs  OGbs err TCP Est %CPU syscalls csw     irq GBfree
4.98   0.00   4.42   0.00 4235592     33   83.80 4720653 2149771   1235 247.32
4.73   0.00   4.20   0.00 4025260     33   82.99 4724900 2139833   1204 247.32
4.72   0.00   4.20   0.00 4035252     33   82.14 4719162 2132023   1264 247.32
4.71   0.00   4.21   0.00 4073206     33   83.68 4744973 2123317   1347 247.32
4.72   0.00   4.21   0.00 4061118     33   80.82 4713615 2188091   1490 247.32
4.72   0.00   4.21   0.00 4051675     33   85.29 4727399 2109011   1205 247.32
4.73   0.00   4.21   0.00 4039056     33   84.65 4724735 2102603   1053 247.32

After the patch

InMpps OMpps  InGbs  OGbs err TCP Est %CPU syscalls csw     irq GBfree
5.43   0.00   4.20   0.00 3313143     33   84.96 5434214 1900162   2656 245.51
5.43   0.00   4.20   0.00 3308527     33   85.24 5439695 1809382   2521 245.51
5.42   0.00   4.19   0.00 3316778     33   87.54 5416028 1805835   2256 245.51
5.42   0.00   4.19   0.00 3317673     33   90.44 5426044 1763056   2332 245.51
5.42   0.00   4.19   0.00 3314839     33   88.11 5435732 1792218   2499 245.52
5.44   0.00   4.19   0.00 3293228     33   91.84 5426301 1668597   2121 245.52

Similarly, netperf reports 230Mb/s before the patch, and 270Mb/s after the patch

Reviewed by:	gallatin
Sponsored by:	Limelight Networks
Differential Revision:	https://reviews.freebsd.org/D15366
2018-05-18 20:13:34 +00:00
Andriy Voskoboinyk
cf268a8302 otus(4): check mcast / mgt / ucast rates during Tx descriptor setup
These parameters may be changed via ifconfig(8); by default,
mgt / mcast rates are lowest possible and ucast rate is not set
(matches previous configuration).

While here, store some variables locally for better readability.
2018-03-11 00:38:08 +00:00
Adrian Chadd
9fbe631a1a [net80211] convert all of the WME use over to a temporary copy of WME info.
This removes the direct WME info access in the ieee80211com struct and instead
provides a method of fetching the data.  Right now it's a no-op but eventually
it'll turn into a per-VAP method for drivers that support it (eg iwn, iwm,
upcoming ath10k work) as things like p2p support require this kind of behaviour.

Tested:

* ath(4), STA and AP mode

TODO:

* yes, this is slightly stack size-y, but it is an important first step
  to get drivers migrated over to a sensible WME API.  A lot of per-phy things
  need to be converted to per-VAP before P2P, 11ac firmware, etc stuff shows up.
2018-01-02 00:07:28 +00:00
Andriy Voskoboinyk
f631357540 net80211 drivers: fix rate setup for EAPOL frames, obtain Tx parameters
directly from the node.

- Use ni_txparms directly instead of calculating them manually every time
- Move M_EAPOL flag check upper; otherwise it may be skipped due to
'ucastrate' / 'mcastrate' check
- Use 'mgtrate' for control frames too (see ifconfig(8), mgtrate parameter)
- Add few more M_EAPOL checks where it was missing (zyd(4), ural(4),
urtw(4))
- Few unrelated cleanups

Tested with:
 - Intel 6205 (iwn(4)), STA mode;
 - WUSB54GC (rum(4)), HOSTAP mode + RTL8188EU (rtwn(4)), STA mode.

Reviewed by:	adrian
Differential Revision:	https://reviews.freebsd.org/D9811
2017-02-26 20:49:35 +00:00
Andriy Voskoboinyk
bdc7291ec9 net80211: convert all ieee80211_input_mimo*() consumers
to ieee80211_add_rx_params() + drop last (ieee80211_rx_stats) parameter

Note: there is an additional check for ieee80211_get_rx_params()
return value (which does not exist in the original diff).

Reviewed by:	adrian
Differential Revision:	https://reviews.freebsd.org/D8207
2016-10-12 20:50:13 +00:00
Adrian Chadd
e97796e2b6 [net80211] extend the ieee80211_rx_stats struct to include more information.
There are a variety of more interesting RX statistics that we should
keep track of but we don't.  This is a starting point for adding more
information.

Specifically:

* now the RX rate information and some of the packet status is
  passed up;
* The 32 bit or 64 bit TSF is passed up;
* the PHY mode is passed up;
* the "I'm decap'ed AMSDU!" state is passed up;
* number of RX chains is bumped to 4.

This is all mostly a placeholder for getting the data into the RX status
before we pass it up to net80211 - unfortunately we don't yet enforce
that drivers provide it, nor do we pass the provided info back up the
stack so anyone can use the data.

We're going to need to use some of this data moving forward.
Notably, now that some hardware can do AMSDU decap for us (the intel iwm
driver can do it when we flip it on; the ath10k port I'm doing does
it for us) then we need to pass it up through the stack so the duplicate
RX sequence numbers and crypto/IV details don't cause the packet to
be dropped and/or counted against a replay counter.

It's also the beginning of being able to do more interesting node
accounting in net80211.  Specifically, once drivers start populating
per-packet rate information, AMPDU information, timestamps, etc,
we can start providing histograms of rate-versus-RSSI, account
for receive time spent per node and other such interesting things.

(Note: I'm also hoping to include ranging and RTT information for
future chipset support; and it's likely going to include it in
this kind of fashion.)
2016-10-08 01:12:29 +00:00
Andriy Voskoboinyk
f6930bec33 net80211: ieee80211_ratectl*: switch to reusable KPI
Replace various void * / int argument combinations with common structures:
- ieee80211_ratectl_tx_status for *_tx_complete();
- ieee80211_ratectl_tx_stats for *_tx_update();

While here, improve amrr_tx_update() for a bit:
1. In case, if receiver is not known (typical for Ralink USB drivers),
refresh Tx rate for all nodes on the interface.
2. There was a misuse:
- otus(4) sends non-decreasing counters (as originally intended);
- but ural(4), rum(4) and run(4) are using 'read & clear' registers
to obtain statistics for some period of time (and those 'last period'
values are used as arguments for tx_update()). If arguments are not big
enough, they are just discarded after the next call.

Fix: move counting into *_tx_update()
(now otus(4) will zero out all node counters after every tx_update() call)

Tested with:
- Intel 3945BG (wpi(4)), STA mode.
- WUSB54GC (rum(4)), STA / HOSTAP mode.
- RTL8188EU (urtwn(4)), STA mode.

Reviewed by:	adrian
Differential Revision:	https://reviews.freebsd.org/D8037
2016-10-02 20:35:55 +00:00
Pedro F. Giffuni
9be4c8d056 otus: minor catchup with OpenBSD.
Bump the OpenBSD revision tag since the corresponding changes don't
apply to us and drop an unnecessary header.

No functional change.
2016-05-09 19:28:22 +00:00
Adrian Chadd
b35978d0da [otus] implement monitor mode.
* break out the operating mode and rx filter into new functions, rather
  than them being hard-coded
* if we're in sniffer mode or not associated, set the BSS MAC to all zero,
  rather than relying on a chip reset to do it for us
* add comments about .. how interestingly buggy the chip is.

Tested:

* AR9170 + AR9102, STA+monitor mode

Obtained from:	linux carl9170 (general chip workings, constant definitions)
2016-05-02 05:43:46 +00:00
Andriy Voskoboinyk
7f145aba97 otus: switch to ieee80211_add_channel_list_*()
- Use device's channel list instead of default one
(from ieee80211_init_channels()).
- Sort channels (ieee80211_add_channel_list_* requirement).
- Add ic_getradiocaps() method.

Added channels:
2GHz band: 12, 13 and 14.
5GHz band: 34, 38, 42, 46 and 165.

Reviewed by:	adrian
Differential Revision:	https://reviews.freebsd.org/D6145
2016-05-01 18:15:40 +00:00
Andriy Voskoboinyk
a061fea6ee net80211 + drivers: hide size of 'bands' array behind a macro.
Auto-replace 'howmany(IEEE80211_MODE_MAX, 8)' with 'IEEE80211_MODE_BYTES'.
No functional changes.
2016-04-29 22:14:11 +00:00
Andriy Voskoboinyk
31021a2b4e net80211: replace internal LE_READ_*/LE_WRITE_* macro with system
le*dec / le*enc functions.

Replace net80211 specific macros with system-wide bytestream
encoding/decoding functions:
- LE_READ_2 ->  le16dec
- LE_READ_4 ->  le32dec
- LE_WRITE_2 -> le16enc
- LE_WRITE_4 -> le32enc

+ drop ieee80211_input.h include, where it was included for these
operations only.

Reviewed by:	adrian
Differential Revision:	https://reviews.freebsd.org/D6030
2016-04-20 18:29:30 +00:00
Gleb Smirnoff
8ec07310fa These files were getting sys/malloc.h and vm/uma.h with header pollution
via sys/mbuf.h
2016-02-01 17:41:21 +00:00
Andriy Voskoboinyk
0046e1868f net80211 drivers: fix ieee80211_init_channels() usage
Fix out-of-bounds read (all) / write (11n capable) for drivers
that are using ieee80211_init_channels() to initialize channel list.

Tested with:
 * RTL8188EU, STA mode.
 * RTL8188CUS, STA mode.
 * WUSB54GC, HOSTAP mode.

Approved by:	adrian (mentor)
MFC after:	2 weeks
Differential Revision:	https://reviews.freebsd.org/D4818
2016-01-07 18:41:03 +00:00
Andriy Voskoboinyk
bdfff33ff6 net80211: remove hardcoded slot time durations from drivers
- Add IEEE80211_GET_SLOTTIME(ic) macro.
- Use predefined macroses to set slot time.

Approved by:	adrian (mentor)
Differential Revision:	https://reviews.freebsd.org/D4044
2015-12-13 20:48:24 +00:00
Adrian Chadd
6933fefb10 otus(4) - add flags for RX filter, configuration and sniffer.
Obtained from:	Linux carl9170
2015-11-06 03:09:26 +00:00
Andriy Voskoboinyk
a14954c5d6 net80211: WME callback cleanup in various drivers
Since r288350, ic_wme_task() is called via ieee80211_runtask(),
so, any additional deferring from the driver side is not needed.

Approved by:	adrian (mentor)
Differential Revision:	https://reviews.freebsd.org/D4072
2015-11-05 17:58:18 +00:00
Adrian Chadd
a181f63f0d otus(4) - monitor mode fixes, large-mbuf crash fix
* refactor out the rx filter and operating mode code into a separate
  method.
* add some comments about what's left with setting the operating mode
  based on what carl9170 does.
* comment out some init from otus_init_mac() - it's no longer needed as
  it's always init'ed now.
* add debugging and a missing return around a failure to call m_get2() -
  during monitor mode operation I found RXing of frames > 2k, which
  fails allocation.  I'm sure they're valid (it's configuring 11n RX and
  receiving 11n frames even though the driver doesn't "do" 11n)
  and may be A-MSDU; but allocations fail and we should handle that
  gracefully.

Tested:

* UB82 reference NIC (AR9170 + AR9104 2x2 dual band NIC); STA and
  monitor mode operation.
2015-10-27 00:57:06 +00:00
Adrian Chadd
8f335b62c1 otus(4) - add missing ieee80211_free_node() call. 2015-10-23 02:09:23 +00:00
Adrian Chadd
b0f4d8f05a otus(4) - demagicify register names.
Obtained from:	Linux carl9170 hw.h
2015-10-23 02:08:47 +00:00
Adrian Chadd
5433f3578a otus(4): begin supporting raw transmit parameters in otus_tx()
* Add a comment about the parameters I should support, stolen shamelessly
  from iwn(4);
* Implement the rate bit for the raw transmit path;
* Print out the host-order versions of each of the transmit bits, so
  I have a hope in heck of debugging why things are going wrong.

This still doesn't fix 5GHz in the office but that's likely due to a lot
of other configuration parameters being 2GHz-specific.  That'll come next.

Tested:

* AR9170 + AR9103 (2/5GHz) 2x2, 5GHz association
2015-10-23 00:48:00 +00:00
Adrian Chadd
02b3773ac4 otus(4) - use the local node alloc function so there's space for statistics.
* Use the correct malloc type for node allocation - M_80211_NODE - so
  the default node free method in net80211 will work correctly.
* Fix otus_node_alloc() to suit FreeBSD's net80211.
* .. and actually call otus_node_alloc() so there's space for the
  per-node tx statistics.  Otherwise, well, it will be scribbling over
  random memory.

Tested:

* AR9170, STA mode
2015-10-19 01:21:29 +00:00
Adrian Chadd
fd7b55de48 otus(4) - add initial monitor mode; use lowest rate for EAPOL
The monitor mode stuff is from the openbsd driver, but it doesn't
100% work.  It doesn't seem to get all frames for all BSSes.
However, it's enough to at start debugging things.  That 0xffffffff
write is /I think/ the RX filter, but I am still not 100% sure about
it all.

Then, whilst here, use the lowest rate for EAPOL frames.  This is just
generally a good thing to do.
2015-10-19 01:14:26 +00:00
Adrian Chadd
4f4a7a03ce net80211 drivers: eliminate any references to sc_rxtap_len/sc_txtap_len (never used here)
Submitted by:	<s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3776
2015-10-12 05:21:51 +00:00
Adrian Chadd
d957a93abe net80211: move ieee80211_free_node() call on error from ic_raw_xmit() to ieee80211_raw_output().
This doesn't free the mbuf upon error; the driver ic_raw_xmit method is still
doing that.

Submitted by:	<s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3774
2015-10-12 04:55:20 +00:00
Kevin Lo
c99a4e8a47 Declare odata as a pointer type instead of a pointer to pointer.
Reviewed by:	adrian
2015-10-07 03:33:25 +00:00
Adrian Chadd
c74d474720 if_otus fixes; add fast-frames support.
Fast-frames:

* include opt_wlan.h ; tsk to not doing it earlier;
* add a tx pending tracking counter for seeing how deep
  the hardware TX queue is;
* add the frame aging code from if_ath;
* add fast-frames capability to the driver setup.

Bugs:

* free the buffers (and node references) before
  detaching net80211 state.  This prevents a use-after-free in
  the node free path where we've destroyed net80211 underneath it.
2015-09-28 01:09:48 +00:00
Adrian Chadd
c4dabdf78a Track the command response code buffer size and verify it in the
receive path.
2015-09-27 03:46:55 +00:00
Adrian Chadd
436ed6b50d Fix a bug in the TX command handling - log when a too-large payload is
sent, and fix a bug I found when doing so.
2015-09-26 07:14:00 +00:00
Adrian Chadd
a9fcb51fbb Add an initial driver for the AR9170 series draft-11n hardware from
Atheros.

Thanks to OpenBSD for providing a driver based on the original
Atheros open source driver circa 2008.  This uses the early, pre-carl9170
atheros provided firmware.

It only supports 11bg at the moment.  I've not tested it with 11a
(and so the TX rate control logic may be slightly wrong!) so if
you do have the dual-band version of this hardware please do let me know.

Tested:

* AR9170, TP-Link WN821N 2GHz.

TODO:

* Hook this up to a non-module build.
2015-09-26 07:08:35 +00:00