Newer firmware versions will support a new queue allocation
command, in order to deal with MLD where multiple stations
are used for a single queue. Add support for the new command.

This requires some refactoring of the queue allocation API,
which now gets
 - the station mask instead of the station ID
 - the flags without the "enable" flag, since that's no longer
   used in the new API

Additionally, this new API now requires that we remove queues
before removing a station, the firmware will no longer do that
internally. Also add support for that.
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20220210181930.acbf22ac2b66.I2bf38578c5ca1f7ffb2011a782f772db92fc4965@changeidSigned-off-by: NLuca Coelho <luciano.coelho@intel.com>

Sometimes RFIm can be deactivated in FW due to internal
errors. In this case, FW will send a notification to the
driver about that. Add a log message in this case since
FW logs are not always available.
Signed-off-by: NGregory Greenman <gregory.greenman@intel.com>
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20220205112029.48d0a1624fec.I8f9271959fc53223fa329ab097b12fd69b498b71@changeidSigned-off-by: NLuca Coelho <luciano.coelho@intel.com>

We haven't used this command for a long time, if ever, so we can
remove all related definitions.
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20220130115024.26c0044110cc.Ie0d215a22618e7a3ecc39eca349914981b608b4d@changeidSigned-off-by: NLuca Coelho <luciano.coelho@intel.com>

Nobody other than iwlwifi itself should be accessing the symbols
that it exports, so make that clear by moving them into a separate
new namespace ("IWLWIFI").
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20220130115024.67eba0b9867d.I6291815892746956c36489081f24f4f95b5160e4@changeidSigned-off-by: NLuca Coelho <luciano.coelho@intel.com>

We never return errors there, so just make it void.
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20220130115024.375b3a28d89e.Ia76e9bf13e26eb148abfebdaf859eab1b81d2af1@changeidSigned-off-by: NLuca Coelho <luciano.coelho@intel.com>

We may not have all the interfaces added to the driver when we get the
THERMAL_DUAL_CHAIN_REQUEST notification from the FW, so instead of
iterating all vifs to update SMPS, iterate only the ones that are
already assigned.  The interfaces that were not assigned yet, will be
updated accordingly when we start using them.
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>
Fixes: 2a7ce54c ("iwlwifi: mvm: honour firmware SMPS requests")
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20220129105618.9416aade2ba0.I0b71142f89e3f158aa058a1dfb2517c8c1fa3726@changeidSigned-off-by: NLuca Coelho <luciano.coelho@intel.com>

In order to de-const variables simply casting through (void *) is
not enough: "cast from 'const .. *' to 'void *' drops const qualifier".
Cast through (uintptr_t) as well [1] to make this compile on systems
with more strict requirements.
In addition passing const void *data to dma_map_single() also
drops the (const) qualifier.  De-constify on variable on assignment
which may be overwritten later.  In either case the (void *) cast
to dma_map_single() is not needed (anymore) either.

[1] See __DECONST() in sys/sys/cdefs.h in FreeBSD

Sponsored by:  The FreeBSD Foundation
Signed-off-by: NBjoern A. Zeeb <bz@FreeBSD.ORG>
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20220128153014.eb696eb56bf6.Ide1dd041f9b908c5154a600286a7453750b0704a@changeidSigned-off-by: NLuca Coelho <luciano.coelho@intel.com>

Since FW is now in charge of timing the channel switch, there is no need
to send the add/modify/remove time event command to fw with every (e)CSA
element.
However, the driver needs to cancel the channel switch if the CS start
notification arrives and it does not know about an ongoing channel switch.
Signed-off-by: NNathan Errera <nathan.errera@intel.com>
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20220128153013.ac3af0ff22c7.Ie87c62047b71b93b12aa80b5dc5391b4798dbe97@changeidSigned-off-by: NLuca Coelho <luciano.coelho@intel.com>

We add the fields for parsing extended ADDBA request/respond,
and new max 1K aggregation for limit ADDBA request/respond.

Adjust drivers to use the proper macro, IEEE80211_MAX_AMPDU_BUF ->
IEEE80211_MAX_AMPDU_BUF_HE.
Signed-off-by: NMordechay Goodstein <mordechay.goodstein@intel.com>
Link: https://lore.kernel.org/r/20220214173004.b8b447ce95b7.I0ee2554c94e89abc7a752b0f7cc7fd79c273efea@changeidSigned-off-by: NJohannes Berg <johannes.berg@intel.com>

Commit d068ca2a ("codel: split into multiple files") moved all
Qdisc-related code to codel_qdisc.h, move the include of pkt_sched.h
as well.

This is similar to the previous commit, although we don't care as
much about incremental builds after pkt_sched.h was touched itself
it is included by net/sch_generic.h which is modified ~20 times
a year.

This decreases the incremental build size after touching pkt_sched.h
from 1592 to 617 objects.

Fix unmasked missing includes in WiFi drivers.
Acked-by: NKalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20211221193941.3805147-2-kuba@kernel.orgSigned-off-by: NJakub Kicinski <kuba@kernel.org>

This notification ID was actually used for something else we
never implemented, but luckily we only had some debug code
here. Just remove it.
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20211219132536.a67b5b9db259.Ic55b306fcd2a3525b3993f4b7e00622dd95053ba@changeidSigned-off-by: NLuca Coelho <luciano.coelho@intel.com>

Currently we always return the op_mode with valid pointer in case
getting NVM failed, while it's only relevant for cases that CSME is the
owner of the nic.

Fix this by checking also who's the owner of the nic.
Signed-off-by: NMordechay Goodstein <mordechay.goodstein@intel.com>
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20211219132536.b1e96021b616.Id0164855f2dd01ecdecf79b239d6ee5974882245@changeidSigned-off-by: NLuca Coelho <luciano.coelho@intel.com>

Support resetting the firmware via TLV-based debugging.  When applied,
this will cause the driver to reset the firmware when the debugging
is triggered.
Signed-off-by: NMukesh Sisodiya <mukesh.sisodiya@intel.com>
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20211219121514.d59b29653a1e.I7b3be4a1ad1a9d5d0e86259740e89ac113c9348b@changeidSigned-off-by: NLuca Coelho <luciano.coelho@intel.com>

We don't really have much reason to mistrust the hardware
queue number, but if it gets mixed up we still don't want
to access some data out of bounds, so drop such frames.
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20211219121514.539aecb91247.I6e555a5185bad30d7d1a4659f9c0b99325425f18@changeidSigned-off-by: NLuca Coelho <luciano.coelho@intel.com>

If iwl_transt_start_hw() failed, we were returning without calling
wiphy_unlock() and rtnl_unlock(), causing a locking imbalance:

drivers/net/wireless/intel/iwlwifi/mvm/ops.c:686:12: warning: context imbalance in 'iwl_mvm_start_get_nvm' - wrong count at exit

Fix that by adding the unlock calls.
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>
Signed-off-by: NKalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20211219090128.42417-2-luca@coelho.fi

On struct iwl_rx_handlers we should document the min_size
member, do that.
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>
Signed-off-by: NKalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/iwlwifi.20211219110000.0c42c428bc6b.I8bfa49d534acc5f513f2fb3dff2d6f22f6c45071@changeid

Normally, when we hit an assert, we print out all the
assert data. However, in certain tests, when we trigger
it from debugfs intentionally, that can be useless and
confusing.

Allow writing the string "nolog\n" to the fw_nmi and
fw_restart files suppressing the assert dump as well
as - in the case of fw_restart - the

  iwlwifi 0000:00:00.0: FW error in SYNC CMD REPLY_ERROR

message.
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20211204174546.75e29a2ab68d.Id3064feda2ce7a77c116c6d6e71ce5ff447c6e86@changeidSigned-off-by: NLuca Coelho <luciano.coelho@intel.com>

Support reading the SAR Geographic Offset Mapping (SGOM) table from UEFI
to allow OEMs to override the values according to geographical regions.
Signed-off-by: NAyala Barazani <ayala.barazani@intel.com>
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20211204174546.e6dfd8b5dd40.Ibc9a8fe2bfde345f49df5d57ec56663da6a53dc4@changeidSigned-off-by: NLuca Coelho <luciano.coelho@intel.com>

When we use 2K RBs, we cannot receive all valid 802.11 frames,
including e.g. long beacons, since up to 2304 bytes are valid
(plus metadata and also encryption overhead etc.). Increase
the RB size to be always 4K to avoid that.
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20211204174545.675781ab0da5.I5c653f4c7dd726f8ad40077e4a109b85e7c0cdb1@changeidSigned-off-by: NLuca Coelho <luciano.coelho@intel.com>

The firmware is exposing a new system features control command,
define the necessary data structures etc. Rename "soc.h" to
"system.h" since the SoC command is also in the system group
and adding another file for just one more struct seemed like a
waste of files.
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20211204174545.94a120687887.I79acffcf0793ea9e4ddec24b06420961bfb4fe94@changeidSigned-off-by: NLuca Coelho <luciano.coelho@intel.com>

Some command strings in the system group weren't added
for debug, add them now.
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20211204130722.5bbda292908e.I53cefd74547a745fd29261a795c94611e7ee8d1d@changeidSigned-off-by: NLuca Coelho <luciano.coelho@intel.com>

There's an RLC configuration command in the firmware that's
going to replace the chain information in the PHY context.
Add support for this command, while leaving the PHY context
fields unset when we know the RLC command will be used.

Also add support to send only the RLC configuration command
if only the # of chains used on the PHY context changes.
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20211204083238.55faa3782bb0.I3f9d0071e680cab513c59b093d0827af99d41c51@changeidSigned-off-by: NLuca Coelho <luciano.coelho@intel.com>

We have a MAC component (which is inside the SoC) and it has several
different HW steps.  3 bits used to be enough but now we need 4-bits
to represent all the different steps.

Properly support 4-bits in the MAC step value by refactoring all the
current handling of the MAC step/dash.

Already from family 8000 and up the dash (bits 0-1) no longer exists
and the step (until 8000 bits 2-3) consists of the dash bits as well.

To do this remove the CSR_HW_REV_STEP and the CSR_HW_REV_DASH
macros, replace them with CSR_HW_REV_STEP_DASH and add hw_rev_step
into the trans struct.

In addition remove the CSR_HW_IF_CONFIG_REG_MSK_MAC_STEP and
CSR_HW_IF_CONFIG_REG_MSK_MAC_DASH macros and create a new macro
combining the 2 (this way we don't need shifting or anything else.)
Signed-off-by: NMatti Gottlieb <matti.gottlieb@intel.com>
Signed-off-by: NMike Golant <michael.golant@intel.com>
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20211207160459.2e81a14d1f80.Ia5287e37fb3439d805336837361f6491f958e465@changeidSigned-off-by: NLuca Coelho <luciano.coelho@intel.com>

Read the rfkill state upon boot, mac start and mac stop.
Reviewed-by: NLuciano Coelho <luciano.coelho@intel.com>
Signed-off-by: NEmmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: NKalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20211112062814.7502-6-emmanuel.grumbach@intel.com

iwlmei needs to know about the follwing events:

* Association
* De-association
* Country Code change
* SW Rfkill change
* SAR table changes

iwlmei can take the device away from us, so report the new
rfkill type when this happens.
Advertise the required data from the CSME firmware to the
usersapce: mostly, the AP that the CSME firmware is currently
associated to in case there is an active link protection
session.
Generate the HOST_ASSOC / HOST_DISSASSOC messages.

Don't support WPA1 (non-RSNA) for now.
Don't support shared wep either.
We can then determine the AUTH parameter by checking the AKM.
Feed the cipher from the key installation.

SW Rfkill will be implemented later when cfg80211 will
allow us to read the SW Rfkill state.
Co-Developed-by: NAyala Beker <ayala.beker@intel.com>
Signed-off-by: NAyala Beker <ayala.beker@intel.com>
Signed-off-by: NEmmanuel Grumbach <emmanuel.grumbach@intel.com>

v7: Ayala added her signed-off
    remove pointless function declaration
    fix a bug due to merge conflict in the HOST_ASSOC message
v8: leave a print if we have a SAP connection on a device we do
    not support (yet)
Signed-off-by: NKalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20211112062814.7502-4-emmanuel.grumbach@intel.com

Fix warnings produced by:
- lockdep_assert_wiphy() in function reg_process_self_managed_hint(),
- wiphy_dereference() in function iwl_mvm_init_fw_regd().
Both function are expected to be called in critical section.

The warnings were discovered when running v5.15 kernel
with debug options enabled:

1)
Hardware name: Google Delbin/Delbin
RIP: 0010:reg_process_self_managed_hint+0x254/0x347 [cfg80211]
...
Call Trace:
regulatory_set_wiphy_regd_sync+0x3d/0xb0
iwl_mvm_init_mcc+0x49d/0x5a2
iwl_op_mode_mvm_start+0x1b58/0x2507
? iwl_mvm_reprobe_wk+0x94/0x94
_iwl_op_mode_start+0x146/0x1a3
iwl_opmode_register+0xda/0x13d
init_module+0x28/0x1000

2)
drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c:263 suspicious rcu_dereference_protected() usage!
...
Hardware name: Google Delbin/Delbin, BIOS Google_Delbin
Call Trace:
dump_stack_lvl+0xb1/0xe6
iwl_mvm_init_fw_regd+0x2e7/0x379
iwl_mvm_init_mcc+0x2c6/0x5a2
iwl_op_mode_mvm_start+0x1b58/0x2507
? iwl_mvm_reprobe_wk+0x94/0x94
_iwl_op_mode_start+0x146/0x1a3
iwl_opmode_register+0xda/0x13d
init_module+0x28/0x100

Fixes: a05829a7 ("cfg80211: avoid holding the RTNL when calling the driver")
Signed-off-by: NŁukasz Bartosik <lb@semihalf.com>
Signed-off-by: NKalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20211110215744.5487-1-lukasz.bartosik@semihalf.com

In some very rare cases the init flow may fail.  In many cases, this is
recoverable, so we can retry.  Implement a loop to retry two more times
after the first attempt failed.

This can happen in two different situations, namely during probe and
during mac80211 start.  For the first case, a simple loop is enough.
For the second case, we need to add a flag to prevent mac80211 from
trying to restart it as well, leaving full control with the driver.

Cc: <stable@vger.kernel.org>
Signed-off-by: NMordechay Goodstein <mordechay.goodstein@intel.com>
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>
Signed-off-by: NKalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/iwlwifi.20211110150132.57514296ecab.I52a0411774b700bdc7dedb124d8b59bf99456eb2@changeid

There is no relation between the name and the purpose of the
notification. This notification is sent from FW when the channel switch
starts.
Signed-off-by: NNathan Errera <nathan.errera@intel.com>
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20211024181719.24b71b0cb741.I97deb70e18f259de51395a1e7c7e58c7b006c317@changeidSigned-off-by: NLuca Coelho <luciano.coelho@intel.com>

When this code was implemented, there was no official FW API
description yet, so a placeholder name was used (GEO_TX_POWER_LIMIT).
But then the command became actually called
PER_CHAIN_LIMIT_OFFSET_CMD.  Rename the command (and change related
comments) to PER_CHAIN_LIMIT_OFFSET_CMD to avoid confusion.
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20211024181719.672fa727ef75.I6572df5d1e3441a0214993a59985da9a9431f3e5@changeidSigned-off-by: NLuca Coelho <luciano.coelho@intel.com>

As part of the new rate_n_flags, FW added a new version for
LOCATION_RANGE_RSP_NTFY, and it's internal structure -
LOCATION_RANGE_RSP_AP_ETRY_NTFY. Add support for this.
Signed-off-by: NMiri Korenblit <miriam.rachel.korenblit@intel.com>
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20211017123741.c5c6c863631e.I4b493f4eeabbfa1dc965ae012b72fc57de7d5f4f@changeidSigned-off-by: NLuca Coelho <luciano.coelho@intel.com>

Use the previously added infrastructure to scrub key material
in firmware dumps:
 * in the TX FIFO data, just search for each key that we
   know about and override such data
 * scrub various commands that we sent to the firmware if
   they're present
 * in firmware memory, where advertised by firmware TLVs
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20211017123741.d1514964e6a7.I18f8c2ce8082952af7cfe5f8fe75fe51851b8853@changeidSigned-off-by: NLuca Coelho <luciano.coelho@intel.com>

In firmware dumps, currently all kinds of key material may be
included, e.g. in host commands (if firmware crashes during the
processing of a key-related command) or in the TX FIFO(s) if
we have been using in-TX-command key material.

Additionally, some firmware versions will advertise sections
of their internal data to not dump, due to them containing some
sensitive data.

Add some infrastructure to allow scrubbing this data out, as
dependent on the opmode's idea of what will need to be done.
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20211017123741.360cc8fe55b1.Ie3bd3ece38043969f7e116e61a6ec1197a58d78b@changeidSigned-off-by: NLuca Coelho <luciano.coelho@intel.com>

Consensus seems to be emerging that corporations or groups
shouldn't be listed as module authors, and we will not
maintain this email address any longer. Just remove it.
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20211017113927.32109514aad0.I91a7d745f4ab50ee8ef918ece00dda8251541595@changeidSigned-off-by: NLuca Coelho <luciano.coelho@intel.com>

Due to a rebase damage, we lost the rtnl_lock() when the patch was
sent out.  This causes an RTNL imbalance and failed assertions, due to
missing RTNL protection, for instance:

  RTNL: assertion failed at net/wireless/reg.c (4025)
  WARNING: CPU: 60 PID: 1720 at net/wireless/reg.c:4025 regulatory_set_wiphy_regd_sync+0x7f/0x90 [cfg80211]
  Call Trace:
   iwl_mvm_init_mcc+0x170/0x190 [iwlmvm]
   iwl_op_mode_mvm_start+0x824/0xa60 [iwlmvm]
   iwl_opmode_register+0xd0/0x130 [iwlwifi]
   init_module+0x23/0x1000 [iwlmvm]

Fix this by adding the missing rtnl_lock() back to the code.

Fixes: eb09ae93 ("iwlwifi: mvm: load regdomain at INIT stage")
Link: https://lore.kernel.org/lkml/CAHk-=wjB_zBwZ+WR9LOpvgjvaQn=cqryoKigod8QnZs=iYGEhA@mail.gmail.com/Reported-by: NLinus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>
Acked-by: NDavid S. Miller <davem@davemloft.net>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The new version sends station id in the notification. It's still not
used, but need to adjust the code since the offset of the data was
changed.
Signed-off-by: NGregory Greenman <gregory.greenman@intel.com>
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20210826224715.87bc9e45c40b.I770493dc4a293ed8bdf059518e94dccf5dd1b3a7@changeidSigned-off-by: NLuca Coelho <luciano.coelho@intel.com>

We used to load the regdomain only in the load stage,
this caused the 'iw phy phy0 reg get' command to fail if we
booted a machine with wifi off.
Therefor we should load it in INIT stage already.
Signed-off-by: NMiri Korenblit <miriam.rachel.korenblit@intel.com>
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20210805141826.a6077801d7d5.I7d8d5c895bc467efbf81ea055dde366ea01cced1@changeidSigned-off-by: NLuca Coelho <luciano.coelho@intel.com>

We used to read the PPAG, WRDS, EWRD, WGDS tables from ACPI
in the load stage only. This prevented vendor commands from
being executed before bringing the interface up. Move reading those tables
to INIT stage.
Signed-off-by: NMiri Korenblit <miriam.rachel.korenblit@intel.com>
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20210805141826.ce3b60f0b426.I3643bf00e714aae930880cc7d6cf390b142eaccb@changeidSigned-off-by: NLuca Coelho <luciano.coelho@intel.com>

With recent changes in the firmware SRAM debug during D3 is
enabled by default and need not be enabled by driver.
cleaning the code to align the same.
Signed-off-by: NMukesh Sisodiya <mukesh.sisodiya@intel.com>
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20210802215208.8535203d0ef7.Ib1695ce5de921b0472d0b1052e729e071573b863@changeidSigned-off-by: NLuca Coelho <luciano.coelho@intel.com>

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: NJohannes Berg <johannes.berg@intel.com>
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20210802172232.2e47e623f9e2.I9b0830dafbb68ef35b7b8f0f46160abec02ac7d0@changeidSigned-off-by: NLuca Coelho <luciano.coelho@intel.com>

The firmware SMPS request should only be honoured if the
connection is currently with HE and on 160 MHz, so check
that and then potentially reapply any request if the BW
changes.
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20210802172232.0cdcac5660da.I9ee7956fd4f48399855d1f97728bc58b36caf112@changeidSigned-off-by: NLuca Coelho <luciano.coelho@intel.com>