rsu: add TSF field into Rx radiotap.

Tested with Asus USB-N10.

Merge ^/head r309519 through r309757.

net80211 + drivers: convert to ieee80211_crypto_get_key_wepidx().

Proposed by: adrian

rsu: fix printf format specifiers.

rsu: add hardware crypto support (WEP, TKIP and CCMP).

This change includes firmware commands for key setup +
some additional checking via CAMREAD / CAMWRITE registers.
Nothing (except rsu_delete_ke

rsu: add hardware crypto support (WEP, TKIP and CCMP).

This change includes firmware commands for key setup +
some additional checking via CAMREAD / CAMWRITE registers.
Nothing (except rsu_delete_key() for pairwise keys) is deferred;
to ensure that things are done in order rsu_set_key() will wait
until key deletion task will be finished.

Tested with Asus USB-N10 (all ciphers).

Differences from initial (reviewed) patch:
- Pause AC queues before disassociation - since CMD_DISCONNECT clears
crypto state all pending frames must be processed / dropped before it.
- Check sc_running flag before trying to set static keys.
- Clear key index from bitmap even when firmware command fails
(it will be invalidated via CAMWRITE anyway).

Reviewed by: adrian, kevlo
Tested by: kevlo
Differential Revision: https://reviews.freebsd.org/D8706

show more ...

rsu: fix RSSI reporting, partially revert r288414.

- Append RCR_APP_PHYSTS bit after firmware loading - otherwise
firmware will reset the register and this modification will be lost.
(without it Rx

rsu: fix RSSI reporting, partially revert r288414.

- Append RCR_APP_PHYSTS bit after firmware loading - otherwise
firmware will reset the register and this modification will be lost.
(without it Rx PHY descriptor section will contain garbage).
- Check if R92S_RXDW0_PHYST bit is set (like it is done in rtwn(4)) -
even if infosz is non-zero the section may not contain anything useful.
- In case, if descriptor is absent (A-MPDU?) use last calibrated RSSI
(rtwn(4) uses RSSI from the previous (sub)frame; probably, this
approach should be used here too).

Tested with Asus USB-N10, STA mode.

show more ...

Merge ^/head r309263 through r309518.

rsu: fix frame processing in the Rx path (similar to r292207).

- Fill in Rx radiotap header correctly (for every packet in a chain;
not once per chain).
- Fix rate / flags fields in Rx radiotap.
- A

rsu: fix frame processing in the Rx path (similar to r292207).

- Fill in Rx radiotap header correctly (for every packet in a chain;
not once per chain).
- Fix rate / flags fields in Rx radiotap.
- Add debug messages for discarded frames.
- Pass received control (< sizeof(struct ieee80211_frame)) frames
to net80211 (if allowed by device filter; cannot happen yet).

Tested with Asus USB-N10.

Differential Revision: https://reviews.freebsd.org/D5723

show more ...

rsu: remove unused structures / variables.

Merge ^/head r309213 through r309262.

rsu: add support for hardware multicast filter setup.

The algorithm is the same as in rtwn(4).

Tested with Asus USB-N10 (STA) + RTL8188CUS (AP).

Merge ^/head r309170 through r309212.

rsu: various scanning fixes.

- Set IEEE80211_FEXT_SCAN_OFFLOAD flag; firmware can send null data
frames when associated.
- Check IEEE80211_SCAN_ACTIVE scan flag instead of IEEE80211_F_ASCAN
ic flag;

rsu: various scanning fixes.

- Set IEEE80211_FEXT_SCAN_OFFLOAD flag; firmware can send null data
frames when associated.
- Check IEEE80211_SCAN_ACTIVE scan flag instead of IEEE80211_F_ASCAN
ic flag; the last is never set since r170530.
- Eliminate software scan (net80211) <-> site_survey (driver) race:
* override ic_scan_curchan and ic_scan_mindwell pointers so net80211
will not try to finish scanning automatically;
* inform net80211 about current status via ieee80211_cancel_scan()
and ieee80211_scan_done();
* remove corresponding workaround from rsu_join_bss().

Now the driver can associate to an AP with hidden SSID.

Tested with Asus USB-N10.

show more ...

Merge ^/head r306906 through r307382.

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()
retur

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

show more ...

Merge ^/head r306412 through r306905.

[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 poin

[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.)

show more ...

Merge ^/head r306303 through 306411.

rsu: do not restart calibration task when going out of RUN state.

Clear 'sc_calibrating' flag and stop calibration task when interface
is not associated; this fixes possible panic after detach.

Rep

rsu: do not restart calibration task when going out of RUN state.

Clear 'sc_calibrating' flag and stop calibration task when interface
is not associated; this fixes possible panic after detach.

Reported and tested by: hselasky
Reviewed by: adrian
MFC after: 6 days

show more ...

urtwn, rtwn, rsu: switch to ieee80211_add_channel_list_2ghz().

- Use device's channel list instead of default one (from
ieee80211_init_channels()); adds 12 - 14 2GHz channels.
- Add ic_getradiocaps(

urtwn, rtwn, rsu: switch to ieee80211_add_channel_list_2ghz().

- Use device's channel list instead of default one (from
ieee80211_init_channels()); adds 12 - 14 2GHz channels.
- Add ic_getradiocaps() method.

show more ...

net80211 + drivers: hide size of 'bands' array behind a macro.

Auto-replace 'howmany(IEEE80211_MODE_MAX, 8)' with 'IEEE80211_MODE_BYTES'.
No functional changes.

MFH

Sponsored by: The FreeBSD Foundation

[rsu] We don't do A-MPDU transmit right now, so don't bother registering
for it.

Merge ^/head r294961 through r295350.

MfH @r295202

Expect to see panics in routing code at least now.