linux-stable.git/drivers/net/wireless/intel, branch v5.14.7

iwlwifi: pnvm: Fix a memory leak in 'iwl_pnvm_get_from_fs()'

2021-09-22T10:39:32+00:00

[ Upstream commit 45010c080e6e7434fcae73212b0087a03590049f ]

A firmware is requested but never released in this function. This leads to
a memory leak in the normal execution path.

Add the missing 'release_firmware()' call.
Also introduce a temp variable (new_len) in order to keep the value of
'pnvm->size' after the firmware has been released.

Fixes: cdda18fbbefa ("iwlwifi: pnvm: move file loading code to a separate function")
Signed-off-by: Christophe JAILLET 
Reviewed-by: Dan Carpenter 
Acked-by: Luca Coelho 
Signed-off-by: Kalle Valo 
Link: https://lore.kernel.org/r/1b5d80f54c1dbf85710fd285243932943b498fe7.1630614969.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Sasha Levin

iwlwifi: move get pnvm file name to a separate function

2021-09-22T10:39:32+00:00

[ Upstream commit b05c1d14a177eaffe3aa7fa18b39df3a3e1f3a47 ]

Move code that generates the pnvm file name to a separate function,
so that it can be reused.

Signed-off-by: Dror Moshe 
Signed-off-by: Luca Coelho 
Link: https://lore.kernel.org/r/iwlwifi.20210826224715.7d2dd18c75a2.I3652584755b9ab44909ddcd09ff4d80c6690a1ad@changeid
Signed-off-by: Luca Coelho 
Signed-off-by: Sasha Levin

iwlwifi: mvm: Fix scan channel flags settings

2021-09-18T11:43:58+00:00

[ Upstream commit 090f1be3abf3069ef856b29761f181808bf55917 ]

The iwl_mvm_scan_ch_n_aps_flag() is called with a variable
before the value of the variable is set. Fix it.

Signed-off-by: Ilan Peer 
Signed-off-by: Luca Coelho 
Link: https://lore.kernel.org/r/iwlwifi.20210826224715.f6f188980a5e.Ie7331a8b94004d308f6cbde44e519155a5be91dd@changeid
Signed-off-by: Luca Coelho 
Signed-off-by: Sasha Levin

iwlwifi: mvm: don't schedule the roc_done_wk if it is already running

2021-09-18T11:43:58+00:00

[ Upstream commit a76b57311b1a247e31b055872d021c38707dc3a8 ]

When P2P roc is removed, the IWL_MVM_STATUS_NEED_FLUSH_P2P bit is set
to indicate to iwl_mvm_roc_done_wk() that the removed roc is a P2P
one, so it will flush the broadcast station and not the aux station.

However, since setting this bit and scheduling the worker is done
in roc ended flow as well as in case the roc is removed, there is
a race where the worker has already started running (but did not
test this bit yet) and then it is scheduled again. In this case,
the first run of the worker will clear this bit, and thus the second
run will find it already cleared and will try to flush and remove
the aux station by mistake.

Fix it by scheduling the worker only if this bit is not yet set. In
case this bit is already set, the worker is either running or
scheduled, so there is no need to re-schedule it.

Signed-off-by: Avraham Stern 
Signed-off-by: Luca Coelho 
Link: https://lore.kernel.org/r/iwlwifi.20210819183728.8c147659b331.If5924375e9bfd46214ab8ab81cb9d0f5c82fbcbc@changeid
Signed-off-by: Luca Coelho 
Signed-off-by: Sasha Levin

iwlwifi: fw: correctly limit to monitor dump

2021-09-18T11:43:58+00:00

[ Upstream commit e6344c060209ef4e970cac18adeac1676a2a73cd ]

In commit 79f033f6f229 ("iwlwifi: dbg: don't limit dump decisions
to all or monitor") we changed the code to pass around a bitmap,
but in the monitor_only case, one place accidentally used the bit
number, not the bit mask, resulting in CSR and FW_INFO getting
dumped instead of monitor data. Fix that.

Signed-off-by: Johannes Berg 
Signed-off-by: Luca Coelho 
Link: https://lore.kernel.org/r/iwlwifi.20210805141826.774fd8729a33.Ic985a787071d1c0b127ef0ba8367da896ee11f57@changeid
Signed-off-by: Luca Coelho 
Signed-off-by: Sasha Levin

iwlwifi: mvm: fix access to BSS elements

2021-09-18T11:43:58+00:00

[ Upstream commit 6c608cd6962ebdf84fd3de6d42f88ed64d2f4e1b ]

BSS elements are protected using RCU, so we need to use
RCU properly to access them, fix that.

Signed-off-by: Johannes Berg 
Signed-off-by: Luca Coelho 
Link: https://lore.kernel.org/r/iwlwifi.20210805130823.fd8b5791ab44.Iba26800a6301078d3782fb249c476dd8ac2bf3c6@changeid
Signed-off-by: Luca Coelho 
Signed-off-by: Sasha Levin

iwlwifi: mvm: Fix umac scan request probe parameters

2021-09-18T11:43:58+00:00

[ Upstream commit 35fc5feca7b24b97e828e6e6a4243b4b9b0131f8 ]

Both 'iwl_scan_probe_params_v3' and 'iwl_scan_probe_params_v4'
wrongly addressed the 'bssid_array' field which should supposed
to be any array of BSSIDs each of size ETH_ALEN and not the
opposite. Fix it.

Signed-off-by: Ilan Peer 
Signed-off-by: Luca Coelho 
Link: https://lore.kernel.org/r/iwlwifi.20210802215208.04146f24794f.I90726440ddff75013e9fecbe9fa1a05c69e3f17b@changeid
Signed-off-by: Luca Coelho 
Signed-off-by: Sasha Levin

iwlwifi: mvm: avoid static queue number aliasing

2021-09-18T11:43:58+00:00

[ Upstream commit c6ce1c74ef2923b8ffd85f7f8b486f804f343b39 ]

When TVQM is enabled (iwl_mvm_has_new_tx_api() is true), then
queue numbers are just sequentially assigned 0, 1, 2, ...
Prior to TVQM, in DQA, there were some statically allocated
queue numbers:
* IWL_MVM_DQA_AUX_QUEUE == 1,
* both IWL_MVM_DQA_INJECT_MONITOR_QUEUE and
IWL_MVM_DQA_P2P_DEVICE_QUEUE == 2, and
* IWL_MVM_DQA_AP_PROBE_RESP_QUEUE == 9.

Now, these values are assigned to the members mvm->aux_queue,
mvm->snif_queue, mvm->probe_queue and mvm->p2p_dev_queue by
default. Normally, this doesn't really matter, and if TVQM is
in fact available we override them to the real values after
allocating a queue for use there.

However, this allocation doesn't always happen. For example,
for mvm->p2p_dev_queue (== 2) it only happens when the P2P
Device interface is started, if any. If it's not started, the
value in mvm->p2p_dev_queue remains 2. This wouldn't really
matter all that much if it weren't for iwl_mvm_is_static_queue()
which checks a queue number against one of those four static
numbers.

Now, if no P2P Device or monitor interface is added then queue
2 may be dynamically allocated, yet alias mvm->p2p_dev_queue or
mvm->snif_queue, and thus iwl_mvm_is_static_queue() erroneously
returns true for it. If it then gets full, all interface queues
are stopped, instead of just backpressuring against the one TXQ
that's really the only affected one.

This clearly can lead to issues, as everything is stopped even
if just a single TXQ filled its corresponding HW queue, if it
happens to have an appropriate number (2 or 9, AUX is always
reassigned.) Due to a mac80211 bug, this also led to a situation
in which the queues remained stopped across a deauthentication
and then attempts to connect to a new AP started failing, but
that's fixed separately.

Fix all of this by simply initializing the queue numbers to
the invalid value until they're used, if TVQM is enabled, and
also setting them back to that value when the queues are later
freed again.

Signed-off-by: Johannes Berg
Signed-off-by: Luca Coelho
Link: https://lore.kernel.org/r/iwlwifi.20210802172232.2e47e623f9e2.I9b0830dafbb68ef35b7b8f0f46160abec02ac7d0@changeid
Signed-off-by: Luca Coelho
Signed-off-by: Sasha Levin

iwlwifi: mvm: fix a memory leak in iwl_mvm_mac_ctxt_beacon_changed

2021-09-18T11:43:58+00:00

[ Upstream commit 0f5d44ac6e55551798dd3da0ff847c8df5990822 ]

If beacon_inject_active is true, we will return without freeing
beacon.  Fid that by freeing it before returning.

Signed-off-by: Zhang Qilong 
[reworded the commit message]
Signed-off-by: Luca Coelho 
Link: https://lore.kernel.org/r/iwlwifi.20210802172232.d16206ca60fc.I9984a9b442c84814c307cee3213044e24d26f38a@changeid
Signed-off-by: Luca Coelho 
Signed-off-by: Sasha Levin

iwlwifi: mvm: Do not use full SSIDs in 6GHz scan

2021-09-18T11:43:58+00:00

[ Upstream commit deedf9b97cd4ef45da476c9bdd2a5f3276053956 ]

The scan request processing populated the direct SSIDs
in the FW scan request command also for 6GHz scan, which is not
needed and might result in unexpected behavior.

Fix the code to add the direct SSIDs only in case the scan
is not a 6GHz scan.

Signed-off-by: Ilan Peer 
Signed-off-by: Luca Coelho 
Link: https://lore.kernel.org/r/iwlwifi.20210802170640.f465937c7bbf.Ic11a1659ddda850c3ec1b1afbe9e2b9577ac1800@changeid
Signed-off-by: Luca Coelho 
Signed-off-by: Sasha Levin