Permalink
Switch branches/tags
r8.a3.09-build_51 r8.a3.09-build_50 r8.a3.09-build_49 r8.a3.09-build_48 r8.a3.09-build_47 r8.a3.09-build_45 r8.a3.09-build_44 r8.a3.09-build_43 r8.a3.09-build_42 r8.a3.09-build_41 r8.a3.09-build_39 r8.a3.09-build_38 r8.a3.09-build_37 r8.a3.09-build_36 r8.a3.09-build_35 r8.a3.09-build_30 r8.a3.09-build_29 r8.a3.09-build_28 r8.a3.09-build_27 r8.a3.09-build_25 r8.a3.09-build_24 r8.a3.09-build_23 r8.a3.09-build_22 r8.a3.09-build_21 r8.a3.09-build_20 r8.a3.09-build_19 r8.a3.08-build_18 r8.a3.08-build_14 r8.a3.08-build_13 r8.a3.08-build_12 r8.a3.08-build_11 r8.a3.08-build_10 r8.a3.05-build_8 r8.a3.05-build_7 r8.a3.05-build_6 r8.a3.05-build_5 r8.a3.05-build_4 r8.a3.05-build_3 r8.a3.05-build_1 r8.a2.09 r8.a2.08 r8.a2.08-candidate r8.a2.07 r8.a2.07-build_146 r8.a2.07-build_141 r8.a2.07-build_140 r8.a2.07-build_139 r8.a2.07-build_136 r8.a2.06 r8.a2.05 r8.a2.04 r8.a2.03 r8.a2.03-build_132 r8.a2.03-build_131 r8.a2.03-build_130 r8.a2.03-build_129 r8.a2.03-build_128 r8.a2.03-build_127 r8.a2.01 r8.a2.01-build_126 r8.a2.01-build_124 r8.a2.01-build_123 r8.a2.01-build_122 r8.a2.01-build_121 r8.a2.01-build_120 r8.a2.01-build_119 r8.a2.01-build_118 r8.a1.06-build_117 r8.a1.06-build_116 r8.a1.06-build_113 r8.a1.06-build_111 r8.a1.06-build_110 r8.a1.06-build_109 r8.a1.06-build_108 r8.a1.06-build_107 r8.a1.06-build_105 r8.a1.06-build_104 r8.a1.06-build_103 r8.a1.06-build_102 r8.a1.06-build_101 r8.a1.06-build_100 r8.a1.06-build_99 r8.a1.06-build_98 r8.a1.05 r8.a1.05-build_97 r8.a1.05-build_96 r8.a1.05-build_95 r8.a1.05-build_94 r8.a1.05-build_93 r8.a1.05-build_92 r8.a1.05-build_91 r8.a1.05-build_90 r8.a1.05-build_89 r8.a1.05-build_88 r8.a1.05-build_87 r8.a1.05-build_86 r8.a1.04-build_84 r8.a1.04-build_83 r8.a1.04-build_82 r8.a1.04-build_81
Nothing to show
Commits on Mar 6, 2012
  1. hostapd: only updated already-set beacons when processing OLBC

    When hostapd is about to start an AP using HT40, it starts a scan to
    check whether it is allowed or not.  If OLBC is detected before the
    scan has completed, it sets the beacons prematurely.
    
    To fix this, instead of setting all beacons when OLBC is detected,
    only update the ones that have already been started.
    
    Signed-off-by: Luciano Coelho <coelho@ti.com>
    Luciano Coelho committed Mar 6, 2012
Commits on Feb 15, 2012
  1. config: enable NL80211

    Just enable it in both hostapd and wpa_s.
    
    Signed-off-by: Luciano Coelho <coelho@ti.com>
    Luciano Coelho committed Feb 15, 2012
Commits on Feb 12, 2012
  1. wpa_s: add API to disable or enable roaming

    If bgscan is configured then it will be disabled and enabled
    as well as roaming. This allows wpa_s users to disable roaming
    and bgscan when they wish (e.g. device screen is turned off/on)
    To disable send "SET roaming_disabled 1" and to enable replace with 0.
    eyalsh committed Feb 12, 2012
Commits on Feb 10, 2012
  1. wpa_supplicant: update config file to support bgscan

    Change-Id: Iec36d01c34e53c6e503d1078f5a43277b78c7378
    Signed-off-by: Ido Reis <idor@ti.com>
    Ido Reis committed with eyalsh Dec 29, 2011
  2. hostapd: enable N rates in .config

    Change-Id: I945161d57a1c7c326bbc1f172eae2d7c3211a733
    Signed-off-by: Ido Reis <idor@ti.com>
    Ido Reis committed with eyalsh Dec 29, 2011
  3. wpa_s: Disable bgscan and roaming when driver support is limited

    Some drivers are limited in certain conditions (e.g. wl12xx
    on multi role with a single channel) and would like wpa_s
    to disable bgscan and roaming attempts in these situations.
    
    Signed-off-by: Eyal Shapira <eyal@wizery.com>
    eyalsh committed Jan 24, 2012
Commits on Feb 9, 2012
  1. nl80211: Handle ROAMING_SUPPORT event

    Some drivers may notify us that roaming support changed.
    This is passed on to wpa_s in order to take that into
    account regarding bgscan and roaming.
    
    Signed-off-by: Eyal Shapira <eyal@wizery.com>
    eyalsh committed Jan 24, 2012
  2. sched scan: add support for short and long intervals

    Configure sched scan to use short and long intervals
    if the driver supports it
    eyalsh committed Jan 18, 2012
  3. sched scan: Add config parameters for short and long intervals

    Part of support for short and long intervals
    eyalsh committed Jan 16, 2012
  4. sched scan: read driver support for sched scan intervals

    Use the feature flag reported by NL80211 to know
    if the driver supports short and long intervals in
    the sched scan API. This is a prep patch for the
    actual handling of this flag.
    eyalsh committed Jan 17, 2012
  5. Fix wpa_supplicant and hostapd native linux compilation

    Android related stuff weren't ifdef'd properly
    which broke down native linux compilation
    eyalsh committed Jan 4, 2012
  6. Fix deauth with reason 7 due to multiple assoc_req received

    Additional assoc_reqs received after an initial assoc_req (due to a timeout
    in the STA) was already being handled caused the handle_assoc flow to
    run again and in the process delete the station added to the driver
    (in add_pre_assoc_sta). A race would occur where assoc_resp
    was already sent to the STA (as part of the handling of the initial
    assoc_req) and it sent a null data packet which arrived
    while the station was deleted. This caused the packet to be classified
    as a class 3 frame coming from an unknown STA and a deauth
    would occur. Fix this by discarding additional assoc_req between
    receiving the 1st assoc_req and getting a tx callback for the assoc_resp.
    
    Signed-off-by: Eyal Shapira <eyal@wizery.com>
    eyalsh committed Feb 8, 2012
  7. save eapol for later use (EAPOL Start race)

    [ Includes null check missing from the original patch - Arik ]
    
    Signed-off-by: Arik Nemtsov <arik@wizery.com>
    elp committed with eyalsh Dec 7, 2011
  8. add station before getting assoc resp tx completion

    Add the station before sending the association
    response (rather than after tx completion), in
    order to handle EAPOL-Start before tx completion
    race.
    
    Signed-off-by: Arik Nemtsov <arik@wizery.com>
    elp committed with eyalsh Dec 29, 2011
  9. AP: use uapsd if go_apsd was set

    don't set params.uapsd to -1, as it's a valid value.
    
    set conf->bss->wmm_enabled and conf->bss->wmm_uapsd
    to enable (and advertise) wmm.
    
    This is currently only a workaround, until we'll have
    a more generic way to set GO params.
    
    Signed-off-by: Arik Nemtsov <arik@wizery.com>
    elp committed with eyalsh Jul 24, 2011
  10. P2P: use GO channel for Operating Channel IE

    [ To be upstreamed - Arik ]
    
    Change-Id: I5285126515b47cd3b4cdce717310835f23a78f0a
    Signed-off-by: Eliad Peller <eliad@wizery.com>
    elp committed with eyalsh Aug 22, 2011
  11. nl80211: Do not send HANGED event on private command failure

    Upstream implementation sends the HANGED state event on
    private command failure. Unimplemented commands were
    sent to the driver as-is, causing the HANGED event to be sent
    and cause a recovery. Private command handling was modified so
    that only implemented commands are sent to the driver and
    the sending of the HANGED event was removed
    Yotam Rubin committed with eyalsh Dec 26, 2011
  12. Enable wpa_dbg on Android

    Only wpa_printf was enabled which caused a lot
    of logs to be missed on Android
    
    Signed-off-by: Eyal Shapira <eyal@wizery.com>
    eyalsh committed Dec 18, 2011
  13. sched scan: Continue to scan even if previous scan cancel fails

    cancel_sched_scan might fail if there wasn't any scan going
    on before. This shouldn't stop a new sched scan attempt.
    
    Signed-off-by: Eyal Shapira <eyal@wizery.com>
    eyalsh committed Dec 18, 2011
  14. sched scan: Avoid changing state to SCANNING

    sched scan was indicating to the supplicant that scanning was in progress
    which prevented broadcast scan attempts from cli (or in Android from the
    framework).
    
    Signed-off-by: Eyal Shapira <eyal@wizery.com>
    eyalsh committed Dec 26, 2011
  15. sched scan: Logic changes

    Scan up to 16 network of the top priority in the configuration using
    sched scan. If there are more than 16 use normal scan as well.
    Stop using the timeout mechanism and interval/timeout backoffs.
    
    Signed-off-by: Eyal Shapira <eyal@wizery.com>
    eyalsh committed Dec 26, 2011
  16. sched scan: Avoid scan if no enabled networks

    There's no point to sched scan when there's no enabled networks.
    This also fixes a bug where the supplicant would reset
    its scan results in case such a sched scan was initiated
    and therefore would cause a "flickering" network list effect on Android.
    (For a moment you see the network list and the next it's empty)
    
    Signed-off-by: Eyal Shapira <eyal@wizery.com>
    eyalsh committed Dec 26, 2011
  17. sched scan: Continue to scan even if previous scan cancel fails

    cancel_sched_scan might fail if there wasn't any scan going
    on before. This shouldn't stop a new sched scan attempt.
    
    Signed-off-by: Eyal Shapira <eyal@wizery.com>
    eyalsh committed Dec 26, 2011
  18. sched scan: Update scan according to changes in network list

    sched scan wasn't updated according to changes in the network list
    (enable/disable/remove). This caused the FW to continue scanning
    with the wrong list configured which triggered problems.
    
    Signed-off-by: Eyal Shapira <eyal@wizery.com>
    eyalsh committed Dec 26, 2011
  19. sched scan: Turn passive scan into active

    In case there are no scan_ssid networks in the conf
    passive scan was done. Better do an active scan using
    broadcast probe request as it's shorter
    eyalsh committed Dec 26, 2011
  20. sched scan: Fallback to normal scan during WPS

    This is a fix for the WPS problem where WPS
    session wasn't initiated until an manual scan was triggered.
    During WPS session we need a periodic broadcast scan
    to occur so that APs will see that we're in WPS session.
    
    Signed-off-by: Eyal Shapira <eyal@wizery.com>
    eyalsh committed Dec 26, 2011
  21. Always set RXFILTER 0 and 1

    In ginger these filters where always set but they where removed
    completely in ICS. They need to be active for unicast and bcast
    to work. Make sure they are always set.
    
    Signed-off-by: Pontus Fuchs <pontus.fuchs@gmail.com>
    pof2 committed with eyalsh Dec 30, 2011
  22. Remove ARP wowlan wakeup pattern

    As FW now includes Auto ARP response there's no
    need to wakeup on ARPs
    
    Signed-off-by: Eyal Shapira <eyal@wizery.com>
    eyalsh committed Dec 18, 2011
  23. driver_nl80211: rx filters - add support for longer patterns

    - Add support for long patterns (longer than 8 bytes)
    - Separate Rx filters static configuration from code
    - Add DHCP and ARP Rx filters
    
    Signed-off-by: Eyal Shapira <eyal@wizery.com>
    Signed-off-by: Assaf Azulay <assaf@ti.com>
    eyalsh committed Jan 3, 2012
  24. driver_nl8011: Add support for DRIVER RXFILTER command

    Add support for this Android specific feature using WoWLAN packet
    pattern triggers.
    
    Signed-off-by: Pontus Fuchs <pontus.fuchs@tactel.se>
    Pontus Fuchs committed with eyalsh Dec 26, 2011
  25. wpa_supplicant: change config - enable ROAMING, 11n and remove rand-pool

    CONFIG_ROAMING flag was added in Android for roaming and it is
    turned off by default.
    
    Also turn on 11N in wpa_supplicant and disable the random-pool (to speed
    up connection operations)
    
    Change-Id: I3eb21cc5da656e7686e2f1f8d20df2e86696e788
    Signed-off-by: Vishal Mahaveer <a0271468@ti.com>
    Yotam Rubin committed with eyalsh Dec 25, 2011
  26. nl80211: Add missing code in wpa_driver_nl80211_probe_req_report

    Commit "6e933c1e09094a8972ef1e782c57f8b3c55c91d0" removed piece of code from
    wpa_driver_nl80211_probe_req_report API.
    
    Adding it back.
    
    Change-Id: I51bab24d5a84244c462539d0cd0b625e4281e92f
    Signed-off-by: Vishal Mahaveer <a0271468@ti.com>
    Vishal Mahaveer committed with eyalsh Oct 24, 2011
  27. hostapd: add support for android created sockets (/dev/socket/)

    Add the same support that wpa_supplicant has with sockets created
    by the Android system using the init.rc services options
    Just as the supplicant, if the ctrl_iface is a name and not a path
    (i.e. doesn't start with '/') the hostapd will assume that this is
    an Android created socket named wpa_$(ctrl_iface) which is opened
    in /dev/socket/
    hostapd_cli sockets will be created in /data/misc/wifi/sockets
    The hardcoded configuration is set in the Android.mk of hostapd
    just like it is with the supplicant.
    
    In addition, the hostapd_cli needs an Android property by the name
    ap.interface to hold the ctrl_iface name to connect to the hostapd's
    socket.
    Yotam Rubin committed with eyalsh Dec 25, 2011
Commits on Feb 8, 2012
  1. nl80211: Add get_noa() support for WFD certification (BRCM)

    BUG: b/5367351
    
    Change-Id: I14ed79e10ade205c5dd4cdc0d2e888ed1279d1bb
    Signed-off-by: Dmitry Shmidt <dimitrysh@google.com>
    Dmitry Shmidt committed with jmalinen Sep 28, 2011