Commit graph

106144 commits

Author SHA1 Message Date
Adrian Chadd
fa46d9db82 net80211: reduce code duplication in the ieee80211_ioctl_setwmeparam() + fix comments.
Submitted by:	<s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3701
2015-10-03 22:38:08 +00:00
Adrian Chadd
1354b52cfc rum(4): add WME support.
Tested:

* WUSB54GC, HOSTAP and STA modes.
* Me: rum0: MAC/BBP RT2573 (rev 0x2573a), RF RT2528

Submitted by:	<s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3700
2015-10-03 22:35:37 +00:00
Adrian Chadd
13072f8d84 run(4): fix WME support (untested).
Now run(4) fetches parameters from ic->ic_wme.wme_params array, which is never initialized
(and can be safely removed). This patch replaces &ic->ic_wme.wme_params with
&ic->ic_wme.wme_chanParams.cap_wmeParams (contains parameters for local station;
used by other drivers with WME support).

Tested:

* me: STA: run0: MAC/BBP RT5390 (rev 0x0502), RF RT5370 (MIMO 1T1R), address 38:83:45:11:78:ae
2015-10-03 22:33:45 +00:00
Mark Johnston
403ec61cbb Revert r288628 and instead fix a discrepancy between the posix_fadvise(2)
man page and POSIX: posix_fadvise(2) returns an error number on failure.

Reported by:	jilles
MFC after:	1 week
2015-10-03 22:27:14 +00:00
Adrian Chadd
f4ac78a284 rum(4): fix stats interpretation in rum_ratectl_task()
Testing:

* WUSB54GC, STA mode

Submitted by:	<s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3690
2015-10-03 22:26:59 +00:00
Adrian Chadd
342ced03e2 rum(4): set short/long retry limits
Now device will use retry limit, which is set via 'ifconfig <interface>
maxretry <number>'.

Tested:

* Tested on WUSB54GC, STA mode.

Submitted by:	<s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3689
2015-10-03 22:22:26 +00:00
Adrian Chadd
c42e124eca rum(4): fix sequence number generation.
* drop erroneous RT2573_TX_MORE_FRAG flag;
* provide RT2573_TX_HWSEQ where needed.

Submitted by:	<s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3672
2015-10-03 22:15:59 +00:00
Adrian Chadd
210ab3c258 net80211: drop ieee80211_beacon_offsets parameter from ieee80211_beacon_alloc() and ieee80211_beacon_update()
Submitted by:	<s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3659
2015-10-03 22:12:25 +00:00
Adrian Chadd
bc813c40bf net80211: drop redundant 3rd parameter from iv_key_set().
The MAC can be fetched from the key struct.

I added the ndis updates to make it compile.

Submitted by:	<s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3657
2015-10-03 21:48:27 +00:00
Adrian Chadd
ed5711a11b rum(4): drop unused 'node id' parameter.
Submitted by:	<s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3655
2015-10-03 20:53:10 +00:00
Adrian Chadd
2cb9ef8d38 rum(4): add support for hardware encryption (WEP, TKIP and CCMP).
This diff includes:

* Transmitter Addresses, Keys and TKIP MIC addition to the Security Key Table.
* Proper SEC Control Registers initialization and maintenance.
* Additional flags and values in TX descriptor, which are required for encryption support.
* Error checking in RX path.

Tested:

* Tested on WUSB54GC, STA (WEP, TKIP, CCMP), HOSTAP (CCMP) and IBSS (CCMP, WPA-None) modes.
* rum0: MAC/BBP RT2573 (rev 0x2573a), RF RT2528, STA mode (CCMP+TKIP)

Submitted by:	<s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3640
2015-10-03 20:49:08 +00:00
Adrian Chadd
0e3b4c60e4 rum(4): implement iv_update_beacon call (fixes client power save support).
Submitted by:	<s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3632
2015-10-03 20:45:43 +00:00
Adrian Chadd
a19dbd8d6f rum(4): attach rum_update_slot to ic_updateslot.
Submitted by:	<s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3631
2015-10-03 20:44:16 +00:00
Mark Johnston
a7713f7631 The return value of posix_fadvise(2) is just an error status, so
sys_posix_fadvise() should simply return the errno (or 0) to syscallenter()
rather than setting a return value.

MFC after:	1 week
2015-10-03 19:37:41 +00:00
Alan Cox
bc7275964c Reduce the scope of a variable to the only file where it is used. 2015-10-03 19:27:52 +00:00
Adrian Chadd
b780f86455 rum(4): split rum_prepare_beacon() into 'alloc' and 'set' stages
Note: I manually had to merge this; I merged in the "put beacon_offsets
into vap" commit before this.

Submitted by:	<s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3628
2015-10-03 17:49:11 +00:00
Adrian Chadd
50a31b4887 rum(4): add support for AHDEMO mode.
Submitted by:	<s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3627
2015-10-03 17:34:11 +00:00
Adrian Chadd
42769826d3 rum(4): simplify rum_set_bssid(), rum_set_macaddr() and rum_update_promisc()
Tested:

* rum0: MAC/BBP RT2573 (rev 0x2573a), RF RT2528, STA mode

Submitted by:	<s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3626
2015-10-03 17:30:57 +00:00
Adrian Chadd
1ba67b1130 rum(4): do not corrupt MAC address
Don't override the NIC MAC address with an overridden MAC address for
a VAP.

Submitted by:	<s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3625
2015-10-03 17:18:35 +00:00
Adrian Chadd
aa81f85365 rum(4): add error handling for rum_enable_tsf_sync() and rum_prepare_beacon()
Tested:

* rum0: MAC/BBP RT2573 (rev 0x2573a), RF RT2528, STA mode
  Note: haven't tested AP mode yet; will do once the rest of the
  AP mode / power save commits are in.

Submitted by:	<s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3624
2015-10-03 17:11:21 +00:00
Alan Cox
acada7aef0 Perform a single batched update to the object's paging-in-progress count
rather than updating it for each page.
2015-10-03 17:04:52 +00:00
Adrian Chadd
6095f7cad3 rum(4): move some code from rum_init() into separate function.
Tested:

* rum0: MAC/BBP RT2573 (rev 0x2573a), RF RT2528, STA mode

Submitted by:	<s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3623
2015-10-03 16:37:38 +00:00
Adrian Chadd
0698c0b3d1 rum(4): add error handling in initialization path
Tested:

* Tested on WUSB54GC, STA mode.
* rum0: MAC/BBP RT2573 (rev 0x2573a), RF RT2528, STA mode

Submitted by:	<s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3622
2015-10-03 16:21:06 +00:00
Adrian Chadd
b2a76342fd rum(4): simplify error handling rum_raw_xmit()
Move the mbuf free responsibility to the caller of the hardware xmit
function, not the hardware xmit function itself.

Submitted by:	<s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3621
2015-10-03 15:58:00 +00:00
Adrian Chadd
aca2cf3032 rum(4): check mbuf size before accessing its contents
Submitted by:	<s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3610
2015-10-03 15:52:58 +00:00
Adrian Chadd
a6ccd477ac rum(4): add TSF field into radiotap headers
Submitted by:	<s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3607
2015-10-03 15:49:55 +00:00
Adrian Chadd
99feb20233 run(4): Add initial support for IBSS merge.
Submitted by:	<s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3592
2015-10-03 15:48:21 +00:00
Hiroki Sato
6401c828ce - Schedule DAD for IN6_IFF_TENTATIVE addresses in nd6_timer(). This
catches cases that DAD probes cannot be sent because of
  IFF_UP && !IFF_DRV_RUNNING.

- nd6_dad_starttimer() now calls nd6_dad_ns_output(), instead of
  calling it before nd6_dad_starttimer().

- Do not release an entry in dadq when a duplicate entry is being
  added.
2015-10-03 12:09:12 +00:00
Alexander Motin
ec5a8cf7c0 Restore original array_rd_sz semantics.
Before r278702 prefetch was blocked for I/Os > 1MB, after -- >= 1MB.
1MB I/Os are used for bulk operations in CTL (XCOPY, VERIFY), and disabling
prefetch for them reduced the performance.

This is temporary local patch, that should be replaced when upstreamed.

Discussed with:	mahrens
MFC after:	3 days
2015-10-03 11:05:58 +00:00
Hiroki Sato
f1aaad0cd9 Add IFCAP_LINKSTATE support. 2015-10-03 09:15:23 +00:00
Adrian Chadd
30c00a2d89 Remove beacon offsets usage from if_rum.
Differential Revision: https://reviews.freebsd.org/D3658
2015-10-03 06:35:17 +00:00
Adrian Chadd
3eaa0cd531 urtwn(4): fix sequence numbering for QoS frames
Tested:

* urtwn0: MAC/BB RTL8188EU, RF 6052 1T1R, STA mode

Submitted by:	<s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3684
2015-10-03 06:07:01 +00:00
Adrian Chadd
1517a7ba0b ural(4): reduce copy-paste in ural_newstate().
Submitted by:	<s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3656
2015-10-03 05:55:16 +00:00
Adrian Chadd
f28c2f5e54 rum(4): add command queue for running sleepable tasks in non-sleepable contexts
Tested:

* Tested on WUSB54GC, STA mode.
* rum0: MAC/BBP RT2573 (rev 0x2573a), RF RT2528

Submitted by:	<s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3629
2015-10-03 05:46:35 +00:00
Adrian Chadd
e7b7db3d59 rum(4): some non-functional changes / cleanup
* Remove unused sc_txtap_len/sc_rxtap_len fields.
* Remove unused ackrate variable.
* Remove unneded warning in rum_update_mcast().
* Use nitems().
* Replace some hardcoded values for RT2573_MAC_CSR1 register.
* Remove second argument for RUM_LOCK_ASSERT() - it is always the same.

Submitted by:	<s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3605
2015-10-03 05:44:05 +00:00
Alexander V. Chernikov
c6fb65b1df Bump number of prefixes in O_IP_<SRC|DST> from 15 to 31 (max possible).
PR:		203459
Submitted by:	groos at xiplink.com
MFC after:	2 weeks
2015-10-03 05:42:25 +00:00
Andrey V. Elsukov
1a6fb597b0 Always detach encap handler when reconfiguring tunnel.
Reported by:	hrs
MFC after:	1 week
2015-10-03 03:57:58 +00:00
Adrian Chadd
15395998e9 net80211: add a possibility to retrieve current TX key without encapsulation.
Submitted by:	<s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3639
2015-10-03 00:57:33 +00:00
Adrian Chadd
c0cb93498d net80211: add new method for ieee80211_cipher (ic_setiv).
This can be used to update IV state for the caller without adding
information to the mbuf.  Some hardware (eg rum) apparently requires
bits of this.

Submitted by:	<s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3638
2015-10-03 00:50:13 +00:00
Adrian Chadd
483755be00 net80211: get rid of tx_phase1_done flag (ieee80211_crypto_tkip.c).
Submitted by:	<s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3596
2015-10-03 00:03:07 +00:00
Adrian Chadd
ef0d8f6351 net80211: separate ieee80211_crypto_get_keyid() from ieee80211_crypto_encap()
Tested:

* rum(4), STA mode
* rsu(4), STA mode
* urtwn(4), STA mode

Submitted by:	<s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3637
2015-10-02 21:25:48 +00:00
Adrian Chadd
d847071cf6 rum(4): sync rum_enable_tsf(_sync) with run(4).
Submitted by:	<s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3611
2015-10-02 15:30:37 +00:00
Adrian Chadd
a05022b22c rum(4): create few wrappers.
Tested:

rum0: <Belkin Belkin 54g USB Network Adapter, class 0/0, rev 2.00/0.01, addr 22> on usbus0
rum0: MAC/BBP RT2573 (rev 0x2573a), RF RT2528

Submitted by:	<s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3609
2015-10-02 15:28:44 +00:00
Adrian Chadd
cc9ae76160 rum(4): move common part of rum_bbp_write() and rum_bbp_read() into rum_bbp_busy().
Submitted by:	<s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3608
2015-10-02 15:26:33 +00:00
Adrian Chadd
6d8043213d rum(4): reduce code duplication.
Tested:

rum0: <Belkin Belkin 54g USB Network Adapter, class 0/0, rev 2.00/0.01, addr 21> on usbus0
rum0: MAC/BBP RT2573 (rev 0x2573a), RF RT2528

Submitted by:	<s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3606
2015-10-02 15:22:00 +00:00
Konstantin Belousov
7ecbae3523 Do not set 'flush to zero' VFPSCR_FZ bit by default. The correct
implementation of IEEE 754 arithmetic depends on denormals operating
correctly.  Both perl test suite and paranoia tripped over the
setting.

Reported by:	Stefan Parvu <sparvu@kronometrix.org>
Discussed with:	andrew
Sponsored by:	The FreeBSD Foundation
MFC after:	1 week
2015-10-02 13:25:59 +00:00
Konstantin Belousov
c39e422eed FreeBSD does not support SMP on ARMv5. Since processor is always
self-consistent, there is no need in anything but compiler barrier in
the implementation of atomic_thread_fence_*() on ARMv5.  Split
implementation of fences for ARMv4/5 and ARMv6; the former use
compiler barriers, the later also perform hardware barriers.

An issue which is fixed by the change is the faults from the CP15
coprocessor accesses in the user mode.  This was uncovered by the
pthread_once() changes in r287556.

Reported by:	Mattia Rossi <mattia.rossi.mailinglists@gmail.com>
Discussed with:	alc, cognet, jhb
Sponsored by:	The FreeBSD Foundation
MFC after:	1 week
2015-10-02 13:21:08 +00:00
Poul-Henning Kamp
d58b610faa Fail the sbuf if vsnprintf(3) fails. 2015-10-02 09:23:14 +00:00
Adrian Chadd
bf0b7b4527 Fix neeed -> neeeded.
Submitted by:	Andriy Voskoboinyk <s3erios@gmail.com>
Differential Revision:	https://reviews.freebsd.org/D3595
2015-10-02 02:21:36 +00:00
Alexander Motin
0952a19f7d More aggressively fill WUT read pipeline.
On some tests I've measured 5% copy speedup from this.
2015-10-01 19:07:15 +00:00