summaryrefslogtreecommitdiff
path: root/scripts
diff options
context:
space:
mode:
authorMartin Fuzzey <martin.fuzzey@flowbird.group>2021-08-30 18:26:45 +0300
committerKalle Valo <kvalo@codeaurora.org>2021-09-21 08:42:37 +0300
commit99ac6018821253ec67f466086afb63fc18ea48e2 (patch)
tree404b89edb556cd54a9a9abe1d04b35019ce0904e /scripts
parent9b14ed6e11b72dd4806535449ca6c6962cb2369d (diff)
downloadlinux-99ac6018821253ec67f466086afb63fc18ea48e2.tar.xz
rsi: fix key enabled check causing unwanted encryption for vap_id > 0
My previous patch checked if encryption should be enabled by directly checking info->control.hw_key (like the downstream driver). However that missed that the control and driver_info members of struct ieee80211_tx_info are union fields. Due to this when rsi_core_xmit() updates fields in "tx_params" (driver_info) it can overwrite the control.hw_key, causing the result of the later test to be incorrect. With the current structure layout the first byte of control.hw_key is overlayed with the vap_id so, since we only test if control.hw_key is NULL / non NULL, a non zero vap_id will incorrectly enable encryption. In basic STA and AP modes the vap_id is always zero so it works but in P2P client mode a second VIF is created causing vap_id to be non zero and hence encryption to be enabled before keys have been set. Fix this by extracting the key presence flag to a new field in the driver private tx_params structure and populating it first. Fixes: 314538041b56 ("rsi: fix AP mode with WPA failure due to encrypted EAPOL") Signed-off-by: Martin Fuzzey <martin.fuzzey@flowbird.group> CC: stable@vger.kernel.org Signed-off-by: Kalle Valo <kvalo@codeaurora.org> Link: https://lore.kernel.org/r/1630337206-12410-3-git-send-email-martin.fuzzey@flowbird.group
Diffstat (limited to 'scripts')
0 files changed, 0 insertions, 0 deletions