Commit Graph

73 Commits

Author SHA1 Message Date
Imre Vadász
b22fe30db1 [iwm] Sync iwm_nvm_read_chunk() function with Linux iwlwifi.
This fixes an error handling detail in iwm_nvm_read_chunk(), where an
error response from the firmware for an NVM read shouldn't be fatal if
the offset was non-zero.

Approved by:	adrian (mentor)
Obtained from:	DragonFlyBSD git 250a1c33fca1725121fe499f9cebc90267d209f9
Differential Revision:	https://reviews.freebsd.org/D8542
2016-11-17 20:00:20 +00:00
Gavin Atkinson
bfcd23a946 iwm: If firmware load fails during init via iwm_preinit() we bail out
before calling ieee80211_ifattach() so the taskqueue hasn't been
initialized. Don't try to drain it, we'll panic.
Looks like this issue was introduced in r303326.

Reviewed by:	avos, sbruno, adrian
Differential Revision:	https://reviews.freebsd.org/D8499
2016-11-12 18:33:56 +00:00
Imre Vadász
06d706238b [iwm] Set full-offload scan flag. Fixes fw panic when already associated.
* Starting a scan from wpa_supplicant or via ifconfig while associated,
  should no longer cause firmware panics or abort early.

Tested:

* AC7260, STA mode

Approved by:	adrian (mentor)
Differential Revision:	https://reviews.freebsd.org/D8412
2016-11-01 22:47:58 +00:00
Imre Vadász
6dc2f84316 [iwm] Get rid of SYNC_RESP_STRUCT and SYNC_RESP_PTR macros.
* SYNC_RESP_STRUCT and SYNC_RESP_PTR originate from the OpenBSD version of
  iwm, and they weren't serving any real purpose in the FreeBSD port.

* We just do a single bus_dmamap_sync for syncing the complete received frame,
  instead of explicitly bus_dmamap_sync-ing subranges of the frame like in
  the OpenBSD iwm code.

Approved by:	adrian (mentor)
Differential Revision:	https://reviews.freebsd.org/D7939
2016-11-01 22:38:26 +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
Andriy Voskoboinyk
4623c73135 iwm: add missing 'Rx errors' counter incrementation. 2016-10-09 10:21:28 +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
Adrian Chadd
6f87599bdf [iwm] fix default antenna selection a bit; fix 5GHz rate control handling.
* Don't do the antenna switching when setting up the rate table - we don't
  take into account whether it's an active antenna or not (eg shared with BT.)
  I'll look into this a bit more later.

* The default antenna is still 1, I'll look into that a bit more later.
  (So no, this doesn't fix it for Larry who needs ANT_B to be active, not
  ANT_A.)

* My changes to the rate control setup used the wrong method for finding
  a suitable rate, which led to 1M CCK frames being queued for 11a operation.
  This is .. sub-optimal.  Change the rate control lookup path to use
  the global table instead of the per-node table, which won't be setup
  until the node rate table is setup (which happens way too late in this
  game.)

Tested:

* Intel 7260, 2G and 5G operation.
2016-09-24 01:21:42 +00:00
Adrian Chadd
cf4f71f1e5 [iwm] use rate control info from the node txrates; use mgmtrate for EAPOL frames
This changes the transmit rate control code to do a few things:

* use fixed rates (mcast, ucast, mgmt) where required.
* Don't use a hard-coded 11a or 11bg rate for non-data frames -
  use what net80211 says we should use.
* use mgmtrate for EAPOL frames.

Reviewed by:	avos
Differential Revision:	https://reviews.freebsd.org/D7994
2016-09-21 20:56:10 +00:00
Imre Vadász
bff11ce594 [iwm] Improve reliability of iwm_release on disassociation a bit.
* We need to first call ivp->iv_newstate(), to enqueue the deauth/deassoc
  mgmt frame, then flush the tx queue, before actually calling
  iwm_release().

* cycling a wlan connection via wpa_cli frontend to wpa_supplicant, by
  issuing disconnect and reconnect commandos works quite well.
  (There is still an issue when disconnecting/reconnecting too quickly)

* Reassociating or roaming via wpa_supplicant is still broken.

Approved by:	adrian (mentor)
Differential Revision:	https://reviews.freebsd.org/D7943
2016-09-19 22:36:30 +00:00
Imre Vadász
e4dc86e060 [iwm] Remove dead fw_totlen from struct iwm_fw_sects; clean up struct iwm_nvm_data.
* No functional change, none of these values were ever read.

* The values removed from struct iwm_nvm_data are only used for old dvm
  devices in Linux iwlwifi, and irrelevant to iwm hence.

Approved by:	adrian (mentor)
Differential Revision:	https://reviews.freebsd.org/D7945
2016-09-19 22:26:37 +00:00
Imre Vadász
0ba35431ee [iwm] Use IWM_DEFAULT_SCAN_CHANNELS define as default for sc_capa_n_scan_channels.
Approved by:	adrian (mentor)
Obtained from:	Linux iwlwifi
Differential Revision:	https://reviews.freebsd.org/D7938
2016-09-19 22:23:46 +00:00
Imre Vadász
22359652af [iwm] Remove deprecated scan API definitions.
* This removes deprecated scan API definitions, which have been unused
  since the upgrade to version 16 firmware in change r303327.

* Part of this change matches the header-file changes in Linux git commit
  1f9403863c080478ad78247c89b018e95bdfb027.

* No functional change.

Approved by:	adrian (mentor)
Differential Revision:	https://reviews.freebsd.org/D7937
2016-09-19 22:20:46 +00:00
Imre Vadász
fbb27a30bf [iwm] Remove wrappers around iwm_dma_contig_free() calls.
No functional changes.

Inspired by:	OpenBSD
Approved by:	adrian (mentor)
Differential Revision:	https://reviews.freebsd.org/D7933
2016-09-19 22:16:03 +00:00
Imre Vadász
0cd7fa558e [iwm] Fix iwm_poll_bit() error value check in iwm_attach().
The iwm(4) iwm_poll_bit() function returns 1 on success, and 0 on failure,
whereas the iwl_poll_bit() in Linux iwlwifi returns < 0 on failure.

So the (ret < 0) check ended up ignoring any error returned by
iwm_poll_bit().

Approved by:	adrian (mentor)
Differential Revision:	https://reviews.freebsd.org/D7932
2016-09-19 22:13:08 +00:00
Imre Vadász
739e99ba69 [iwm] Fix off-by-one check in iwm_read_firmware().
This fixes a potential buffer overrun in the firmware parsing code.

Reported by:	Coverity
Approved by:	adrian (mentor)
Differential Revision:	https://reviews.freebsd.org/D7931
2016-09-19 22:11:34 +00:00
Imre Vadász
ef81578c9f [iwm] Remove unused field from iwm_rx_data. Use uint32_t instead of enum type.
The wantresp field in struct iwm_rx_data has never been used for anything,
so we can just delete it.

Apparently struct iwm_sf_cfg_cmd was compiled correctly (using a 32bit
value to represent the enum), but it still seems like a very bad idea to use
an enum type in a __packed struct.

Approved by:	adrian (mentor)
Differential Revision:	https://reviews.freebsd.org/D7930
2016-09-19 22:08:47 +00:00
Imre Vadász
b47237ce60 [iwm] Use htole16 for policy field in struct iwm_time_event_cmd_v2.
The htole32 was working fine for little-endian machines, but would have
been broken on big-endian.

Approved by:	adrian (mentor)
Differential Revision:	https://reviews.freebsd.org/D7929
2016-09-19 22:06:00 +00:00
Adrian Chadd
4083793433 [iwm] fix up RSSI calculations for both scan results and normal RX operations.
* hard code a noise floor of -96 for now. The noise floor update code returns
  some "interesting" values that I can't map to anything useful right now.
* Ensure a default noise floor is set - otherwise the initial scan results
  have a noise floor of '0'.
* Fix up the RSSI calculation to be correctly relative to the noise floor.
  The RSSI routines return an absolute value in dBm - so fix this up.
* Cap RSSI values appropriately.
* Ensure we pass in a 1/2 dB unit value in to net80211.

Tested:

* Intel 7260, STA mode

iwm0: <Intel Dual Band Wireless AC 7260> mem 0xf1400000-0xf1401fff irq 17 at device 0.0 on pci2
iwm0: hw rev 0x140, fw ver 16.242414.0, address xx:xx:xx:xx:xx:xx
2016-09-18 05:07:18 +00:00
Andriy Voskoboinyk
9afea60f98 iwm: fix scanning for hidden SSIDs.
Setup SSIDs in scan command so firmware will send direct probe request(s)
while scanning.

Tested by:	dbkirk@gmail.com

PR:		211519
MFC after:	1 week
2016-09-06 10:08:32 +00:00
Andriy Voskoboinyk
e796f68455 iwm: fix few comment typos. 2016-08-27 10:04:48 +00:00
Andriy Voskoboinyk
d845f44fb1 iwm: add 'command accepted' debug notification (copied from wpi(4)).
Now it should be easier to find out which command causes firmware
panics when few commands are sent in a short period of time.
2016-08-27 08:34:20 +00:00
Imre Vadász
a3c0e7f2fb [iwm] Fix iwm_poll_bit() usage in iwm_stop_device(), fixup r303418.
* iwm_poll_bit() returns 1 on success and 0 on failure, whereas
  iwl_poll_bit() in Linux's iwlwifi returns >= 0 on success and < 0 on
  failure.

* Because of the wrong iwm_poll_bit return code check, no warning was
  printed if tx DMA stopping failed.

Approved by:	adrian (mentor)
Differential Revision:	https://reviews.freebsd.org/D7371
2016-07-30 19:03:32 +00:00
Imre Vadász
34938c3085 [iwm] When stopping TX DMA, wait for all channels at once.
* Makes the TX DMA stopping more similar to Linux code, and potentially
      a bit faster. Also, output an error message when TX DMA idling fails.

    Taken-From: Linux iwlwifi

Tested:

* AC3165, STA mode

Approved by:	adrian (mentor)
Obtained from:	DragonFlyBSD git 2ee486ddff973ac552ff787c17e8d83e8ae0f24c
Differential Revision:	https://reviews.freebsd.org/D7325
2016-07-27 20:51:31 +00:00
Imre Vadász
2b8cf46a68 [iwm] Set different pm_timeout for action frames.
When building a Tx Command for management frames, we are lacking
    a check for action frames, for which we should set a different
    pm_timeout.  This cause the fw to stay awake for 100TU after each
    such frame is transmitted, resulting an excessive power consumption.

    Taken-From: Linux iwlwifi (git b084a35663c3f1f7)

Approved by:	adrian (mentor)
Obtained from:	Linux git b084a35663c3f1f7de1c45c4ae3006864c940fe7
Obtained from:	DragonFlyBSD git ba00f0e3ae873d6f0d5743e22c3ebc49c44dfdac
Differential Revision:	https://reviews.freebsd.org/D7324
2016-07-27 20:46:51 +00:00
Imre Vadász
74adf80539 [iwm] Fix inverted logic in iwm_tx().
The PROT_REQUIRE flag in should be set for data frames above a certain
    length, but we were setting it for !data frames above a certain length,
    which makes no sense at all.

    Taken-From: OpenBSD, Linux iwlwifi

Approved by:	adrian (mentor)
Obtained from:	DragonFlyBSD git 8cc03924a36c572c2908e659e624f44636dc2b33
Differential Revision:	https://reviews.freebsd.org/D7323
2016-07-27 20:43:08 +00:00
Sean Bruno
6a5bc1d1ee iwm(4) synchronize driver to DragonFlyBSD version and recent f/w update.
Submitted by:	Kevin Bowling (kevin.bowling@kev009.com)
MFC after:	2 weeks
Differential Revision:	https://reviews.freebsd.org/D6967
2016-07-26 00:02:17 +00:00
Sean Bruno
33c7715f9b iwm(4): switch to ieee80211_runtask()
Submitted by:	Andiry Voskoboinyk (s3erios@gmail.com)
MFC after:	2 weeks
Differential Revision:	https://reviews.freebsd.org/D5054
2016-07-25 23:44:44 +00:00
Adrian Chadd
1eccf20376 [iwm] Use mbuf for large firmware commands, like OpenBSD does.
We also need to consider the size of large firmware commands in iwm_alloc_tx_ring(),
in the dma tag creation, when qid == IWM_MVM_CMD_QUEUE. The old code apparently
only allocated a 2KB (MCLBYTES) sized buffer when it actually expected 4KB.

Submitted by:	Imre Vadasz <imre@vdsz.com>
Approved by:	re (gjb)
Differential Revision:	https://reviews.freebsd.org/D6824
2016-06-23 01:13:30 +00:00
Adrian Chadd
8a1660e16a [iwm] Add and use iwm_phy_db_free(), to plug phy_db memory leak.
(Together with other iwm(4) memory leak fixes) Memory leakage in M_DEVBUF
is now at ca. 2KB for each iwm(4) module load/unload cycle.

Submitted by:	Imre Vadasz <imre@vdsz.com>
Approved by:	re (gjb)
Obtained from:	DragonflyBSD git eaf551a1d464c643e98ce5781971dd32124e9af1
Differential Revision:	https://reviews.freebsd.org/D6819
2016-06-23 01:11:52 +00:00
Adrian Chadd
f6ea76fb7e [iwm] Fix iwm_dma_contig_free(). dma->map is always NULL here.
* When bus_dmamem_alloc is used, the bus_dmamap_t is usually set to NULL, so
  we were never actually freeing any dma memory allocations done via
  iwm_dma_contig_alloc(). So we should check dma->vaddr instead of dma->map here.

* Also, the dmamap is actually supposed to be invalidated as part of
  bus_dmamem_free(), so bus_dmamap_destroy() is never needed here.

Submitted by:	Imre Vadasz <imre@vdsz.com>
Approved by:	re (gjb)
Obtained from:	DragonflyBSD git ef2b29a7ba6ca8a9d2c82ab591c0622227ff84cb
2016-06-23 01:00:13 +00:00
Adrian Chadd
bc6cd01d38 [iwm] Use vap->iv_myaddr instead of ic->ic_macaddr when vap != NULL.
ic_macaddr is only used for the initial mac address provided by NVM. We should
rather use vap->iv_myaddr when vap != NULL, to allow the MAC address
to be changed later with ifconfig(8).

Submitted by:	Imre Vadasz <imre@vdsz.com>
Reviewed by:	avos
Approved by:	re (gjb)
Obtained from:	DragonflyBSD git 4aee7a78275676d22d14c04177bd0c9377d91478
Differential Revision:	https://reviews.freebsd.org/D6743
2016-06-23 00:56:54 +00:00
Adrian Chadd
5b4dc397af [iwm] free RX ring / NVM memory after they're used.
* Free RX ring during detach
* Free NVM memory after parsing

Tested:

* 7260, STA mode

Submitted by:	Imre Vadasz <imre@vdsz.com>
Approved by:	re (gjb)
Obtained from:	dragonflybsd
Differential Revision:	https://reviews.freebsd.org/D6817
2016-06-16 17:59:15 +00:00
Adrian Chadd
5799c2bce7 [iwm] Fix up busdma use in the RX path
When allocating a new mbuf or bus_dmamap_load()-ing it fails,
we can just keep the old mbuf since we are dropping that packet anyway.
Instead of doing bus_dmamap_create() and bus_dmamap_destroy() all the time,
create an extra bus_dmamap_t which we can use to safely try
bus_dmamap_load()-ing the new mbuf. On success we just swap the spare
bus_dmamap_t with the data->map of that ring entry.

Tested:

Tested with Intel AC7260, verified with vmstat -m that new kernel no
longer visibly leaks memory from the M_DEVBUF malloc type.
Before, leakage was 1KB every few seconds while ping(8)-ing over the wlan
connection.

Submitted by:	Imre Vadasz <imre@vdsz.com>
Approved by:	re@
Obtained from:	DragonflyBSD.git cc440b26818b5dfdd9af504d71c1b0e6522b53ef
Differential Revision:	https://reviews.freebsd.org/D6742
2016-06-13 00:13:20 +00:00
Adrian Chadd
0e92cf939f [iwm] valid_{tx,rx}_ant from radio_cfg is only needed for 8000 family.
* The "if (!data->valid_tx_ant || !data->valid_rx_ant) {" check was getting
  triggered with a 3165 chipset.

Submitted by:	Imre Vadasz <imre@vdsz.com>
Obtained from:	DragonflyBSD 3655dfb6fc311fc83e5ce8370dd91b4cd4a37991
2016-06-02 06:22:59 +00:00
Adrian Chadd
88b6e4f33a [iwm] Fix several nitpicks in iwm(4).
Move some declarations to if_iwmreg.h.
    Remove iwm_fw_alive(); just call iwm_post_alive() directly.
    Simplify iwm_mvm_add_sta().
    Return timeout error from iwm_apm_init().
    Print a message when init (i.e. boot) firmware fails to load.
    Remove some commented-out code which wouldn't compile anyway.
    Move iwm_mvm_tx_fifo to if_iwmreg.h to match better where Linux puts it.

    Taken-From: OpenBSD (if_iwm.c r1.80 and if_iwmreg.h r1.11)

Submitted by:	 Imre Vadasz <imre@vdsz.com>
Obtained from:	DragonflyBSD 29fcb331e5620ae145a6ab9cdda830e22fff626a
2016-06-02 05:43:16 +00:00
Adrian Chadd
3028d11c3e [iwm] Add bit-polling in Rx-DMA init code path.
Taken-From: OpenBSD (if_iwm.c r1.80)

Submitted by:	Imre Vadasz <imre@vdsz.com>
Obtained from:	DragonflyBSD ed35558754288911048cb607e57c688273ebd8d4
2016-06-02 05:00:52 +00:00
Adrian Chadd
ebb6ea5662 [iwm] Clean up iwm(4) scanning logic a bit.
Submitted by:	Imre Vadasz <imre@vdsz.com>
Obtained from:	DragonflyBSD 8f3ffab9136e33263d424275ec28f57ad2096437
2016-06-02 04:54:56 +00:00
Adrian Chadd
7a8b94e1d2 [iwm] Use IWM_MAX_CMD_PAYLOAD_SIZE to improve command length checks.
Taken-From: OpenBSD (parts of if_iwm.c r1.57 and if_iwmreg.h r1.10)

Obtained from:	DragonflyBSD b70c1eaad06257c5c7f4d8110d21642ebec14f42
2016-06-02 04:53:28 +00:00
Adrian Chadd
ee55925e29 [iwm] add LED blinking for iwm hardware that supports it.
Submitted by:	Imre Vadasz <imre@vdsz.com>
Obtained from:	DragonflyBSD, Linux iwlwifi/mvm
2016-06-02 04:42:28 +00:00
Adrian Chadd
63b3f62ab3 [iwm] remove dead code.
if_iwm - GC some dead code, left by a partially applied OpenBSD change.

Taken-From: OpenBSD (if_iwm.c r1.69)

Submitted by:	Imre Vadasz <imre@vdsz.com>
Obtained from:	DragonflyBSD git 07dfed32ea39b980b0b80d27ff938e7c3ca4c0b5
2016-05-27 07:10:11 +00:00
Andriy Voskoboinyk
b789292fd8 iwm: add 'opt_wlan.h' include into source files.
Include net80211 options file, so IEEE80211_DEBUG_REFCNT option will be
handled correctly.
2016-05-19 23:31:00 +00:00
Andriy Voskoboinyk
ace1dfdd0b iwm: restart device after watchdog timeouts. 2016-05-19 22:43:21 +00:00
Eitan Adler
cef367e6a1 Don't repeat the the word 'the'
(one manual change to fix grammar)

Confirmed With: db
Approved by: secteam (not really, but this is a comment typo fix)
2016-05-17 12:52:31 +00:00
Kevin Lo
cbb62fa6aa Follow-up r298818: hide size of 'bands' array behind a macro. 2016-05-16 02:27:28 +00:00
Pedro F. Giffuni
453130d9bf sys/dev: minor spelling fixes.
Most affect comments, very few have user-visible effects.
2016-05-03 03:41:25 +00:00
Andriy Voskoboinyk
d35192e513 iwm: fix parameters for iwm_add_channel_band()
It accepts <first index, max index + 1>, not
<first index, number of entries>.

Reported by:	adrian
2016-05-02 19:07:44 +00:00
Andriy Voskoboinyk
5c1f6e21a5 iwm: switch to ieee80211_add_channel()
- Switch to ieee80211_add_channel().
- Parse/set more channel flags (DFS, NOADHOC).
- Add ic_getradiocaps() method.

Reviewed by:	adrian
Differential Revision:	https://reviews.freebsd.org/D6150
2016-05-01 14:27:27 +00:00
Adrian Chadd
82f860283c [iwn] fill in the TX command rate info flags consistently.
The Linux driver sets the rate_n_flags regardless of whether it's being
sent using firmware rate control or local rate control.  This includes
the antenna configuration.

Thanks to Kyle Evans <kevans91@ksu.edu> for pointing this out to me
and doing some investigation/testing on his end.

Tested:

* Intel 7260 STA, 2G and 5G networks
2016-05-01 05:01:10 +00:00