- 26 Aug, 2021 40 commits
-
-
Johannes Berg authored
The debug dump ranges aren't just an array of such ranges since each range has a variable size. Therefore, the use of a struct array is misleading at best. Change it to be a u8 data[] instead of the struct array, the code doesn't significantly change since it's actually doing things correctly now. Signed-off-by:
Johannes Berg <johannes.berg@intel.com> Signed-off-by:
Luca Coelho <luciano.coelho@intel.com> Link: https://lore.kernel.org/r/iwlwifi.20210819183728.693c9891097d.Idcaab1fd659e8be2f56be647b2534befd61a4460@changeidSigned-off-by:
-
Johannes Berg authored
We don't use this, but we embed this struct elsewhere and having structs with flexible arrays embedded isn't quite right, with sparse (for example) complaining. Remove the data[] member in this case. Signed-off-by:
-
Johannes Berg authored
Sparse warns about some type mismatches, which really is just because of the strangely placed __percpu annotation. Put it into the correct place. Signed-off-by:
-
Johannes Berg authored
DMA-API debug code pointed out that in this code path we never check the return value of dma_map_page(), which could fail. However, we don't really even want to unmap/remap, we just want to ensure that we can actually access the last version of the data that the (now-dead) device may have written, so only need to dma_sync_single_for_cpu() instead. Signed-off-by:
-
Luca Coelho authored
If the tables we get in the iwl_sar_set_profile() is smaller than the revision we support, we need to fill the values with 0. Make sure that's the case. Signed-off-by:
-
Luca Coelho authored
The tables we store are the larger of all the revisions, so we need to fill in the values that we don't get from ACPI when using older revisions. Signed-off-by:
-
Luca Coelho authored
Start supporting API version 65 for AX devices. Signed-off-by:
-
Luca Coelho authored
Revisions 0 and 1 are identical, so we were already supporting that. But revision 2 has a different size, so we have to try to read them separately. Add support for this new revision. Signed-off-by:
-
Miri Korenblit authored
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:
Miri Korenblit <miriam.rachel.korenblit@intel.com> Signed-off-by:
-
Miri Korenblit authored
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:
-
Shaul Triebitz authored
If the session protection ends but no beacon was heard, the driver triggers a disconnection. Trigger WRT in that case so it can be debugged. Signed-off-by:
Shaul Triebitz <shaul.triebitz@intel.com> Signed-off-by:
-
Johannes Berg authored
In commit 79f033f6 ("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:
-
Abhishek Naik authored
By mistake we were considering the first element of the WTAS wifi package as part of the data we want to rid, but that element is the wifi package signature (always 0x07), so it should be skipped. Change the code to read the data starting from element 1 instead. Signed-off-by:
Abhishek Naik <abhishek.naik@intel.com> Fixes: 28dd7ccd ("iwlwifi: acpi: read TAS table from ACPI and send it to the FW") Signed-off-by:
-
Gregory Greenman authored
The new version of the command has same size and layout as version 10. It just sends corresponding station id in one of the reserved fields. It's not used in the driver, so just be ready to accept version 11. Signed-off-by:
Gregory Greenman <gregory.greenman@intel.com> Signed-off-by:
-
Luca Coelho authored
The GEO profiles have been stored in single-dimension arrays and the access has been done via a single index. We will soon need to support different revisions of this table, which will make the flat array even harder to handle. To prepare for that, convert the single-dimension array to a struct with substructures. Signed-off-by:
-
Luca Coelho authored
When we started supporting the new FW API for the geo profiles, we stopped using this definition, but left it there. Remove it now. Signed-off-by:
-
Luca Coelho authored
As an extension to the WRDS support for revisions 1 and 2, do the same for the EWRD tables. These tables have a very similar format to the WRDS table, so most of the code is similar. Signed-off-by:
-
Luca Coelho authored
Change the SAR profile tables storage to revision 2 regardless of the revision we read from ACPI. Revision 2 is a superset of revision 1, which is in turn a superset of revision 0, so they can all be stored inside revision 2. Add support for reading and storing also revisions 1 and 2, whose only difference is the number of chains and number of sub-bands. So most of the code revolves around passing different chain and sub-band sizes. With this patch we still pass only revision 0 to the firmware, but that will be changed in a separate patch. Signed-off-by:
-
Luca Coelho authored
The number of chains and sub-bands read from the ACPI tables varies depending on the revision. Pass these numbers to the iwl_sar_set_profile() function in order to make using different revisions easier. Signed-off-by:
-
Luca Coelho authored
This definition was only used to pass the size of the tables in the FW API to the iwl_sar_select_profile() function, but we should actually pass the definition from the FW API file. We don't have the concept of tables in the ACPI definition, so we can remove it. Signed-off-by:
-
Luca Coelho authored
The SAR profiles have been stored in single-dimension arrays and the access has been done via a single index. We will soon need to support different revisions of this table, which will make the flat array even harder to handle. To prepare for that, convert the single-dimension array to a struct with substructures. Signed-off-by:
-
Luca Coelho authored
The "LIMITS" in the macro name don't have much meaning, so remove it to make the macro shorter and better reflect that this is the number of chains that we have limits for. Signed-off-by:
-
Johannes Berg authored
BSS elements are protected using RCU, so we need to use RCU properly to access them, fix that. Signed-off-by:
-
Ilan Peer authored
- Short SSIDs should always be added for direct SSIDs included in the scan request. However, this was not done in case that information for collocated APs was included. Fix this. - With the above fix, if the FW also supports discovery of hidden APs over the 6GHz band, also set the corresponding full SSID information. Signed-off-by:
Ilan Peer <ilan.peer@intel.com> Signed-off-by:
-
Avraham Stern authored
When a station is removed, the driver-mac80211 station mapping is removed before the station is actually deleted from the FW. As a result, it is reasonable that the FW will continue to pass frames although the driver doesn't have a station for them anymore. Thus change the message severity level from ERR to DEBUG_DROP. Signed-off-by:
Avraham Stern <avraham.stern@intel.com> Signed-off-by:
-
Johannes Berg authored
In later firmware we haven't needed the TSC anyway since we have it already (and firmware image doesn't change), but the new version adds the ability to send down replay counters for more than one GTK. Implement that. Signed-off-by:
-
Johannes Berg authored
Now that only reprogramming is left in the initial key iteration, skip it entirely on unified firmware images instead of skipping only the command sending inside of it. Signed-off-by:
-
Johannes Berg authored
If we're sending the KEK/KCK data we also need the GTK and IGTK type, add a separate key iteration for that so we can make the configure_key iteration optional later. Signed-off-by:
-
Johannes Berg authored
Refactor the TSC/RSC configuration out from the normal wowlan key iteration so we can replace it later with a different one adapted to a different firmware API. Signed-off-by:
-
Johannes Berg authored
We only ever pass cmd_flags == CMD_ASYNC, so might as well not have the argument. Remove it. Signed-off-by:
-
Johannes Berg authored
We do a key iteration to program the keys, and while at it we also collect the data necessary for TKIP. This code has all kinds of dependencies on the firmware API though, so take out the TKIP phase 1 key generation and do that in a separate key iteration only if necessary. Signed-off-by:
-
Johannes Berg authored
There's no need to differentiate identical default and cipher type cases, nor do we really need to have a 'ret' variable. Signed-off-by:
-
Johannes Berg authored
The new version 3 of the station key API has gotten rid of the strange hole in the sequence counter values, support that. Signed-off-by:
-
Ilan Peer authored
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:
-
Johannes Berg authored
Bz device reset flow changed, now the hardware (instead of firmware) will reset the PCI bus etc., this can take up to 100ms. Signed-off-by:
-
Johannes Berg authored
The method to NMI the firmware also changed in Bz devices, implement the new logic. Signed-off-by:
-
Johannes Berg authored
Device startup changed in Bz, some register bits moved around. Change the code accordingly. The new Bz hardware changes also the way we wake it (grab NIC access) and the way we disable bus mastering, update the driver code accordingly. Signed-off-by:
-
Johannes Berg authored
On Bz devices, the MAC address CSRs changed from 0x380 to 0x30. Change the boolean configuration "mac_addr_from_csr" to hold the base address instead, and set it correctly for the different devices using this feature. Signed-off-by:
-
Johannes Berg authored
The real name isn't determined yet, but give them a new name that isn't clashing with older devices. Signed-off-by:
-
Johannes Berg authored
These devices have some places with different behaviour required, so split them off into their own family as they should be. Signed-off-by:
-
