- 07 Dec, 2021 40 commits
-
-
Arnd Bergmann authored
If the iwlmei code is a loadable module, the main iwlwifi driver cannot be built-in: x86_64-linux-ld: drivers/net/wireless/intel/iwlwifi/pcie/trans.o: in function `iwl_pcie_prepare_card_hw': trans.c:(.text+0x4158): undefined reference to `iwl_mei_is_connected' Unfortunately, Kconfig enforces the opposite, forcing the MEI driver to not be built-in if iwlwifi is a module. To work around this, decouple iwlmei from iwlwifi and add the dependency in the other direction. Signed-off-by:
Arnd Bergmann <arnd@arndb.de> Link: https://lore.kernel.org/r/20211207151447.3338818-1-arnd@kernel.orgSigned-off-by:
Luca Coelho <luciano.coelho@intel.com>
-
Johannes Berg authored
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:
Johannes Berg <johannes.berg@intel.com> Signed-off-by:
-
Yaara Baruch authored
Add new Qu-Hr killer device id. Signed-off-by:
Yaara Baruch <yaara.baruch@intel.com> Signed-off-by:
-
Johannes Berg authored
This is part of the "device memory" type, but with the subtypes we can now detect it properly, rather than having to make assumptions on the ID. Signed-off-by:
-
Johannes Berg authored
On Bz devices, UREG_DOORBELL_TO_ISR6_NMI_BIT no longer actually triggers an NMI. So instead of setting BIT(0) | BIT(1) for the reset flow, we need to just set BIT(1) and then force the NMI in the new way. Signed-off-by:
-
Yaara Baruch authored
Add new Qu-Hr device ID. Signed-off-by:
-
Matti Gottlieb authored
Fix FW name for gl use the crf fm and not fm7, since the later no longer exists. Signed-off-by:
Matti Gottlieb <matti.gottlieb@intel.com> Signed-off-by:
-
Mukesh Sisodiya authored
Yoyo based debug is not applicable for 8000 and below old devices. The check added in code has 9000 and below familiy which is corrected. Signed-off-by:
Mukesh Sisodiya <mukesh.sisodiya@intel.com> Signed-off-by:
-
Ayala Barazani authored
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:
Ayala Barazani <ayala.barazani@intel.com> Signed-off-by:
-
Johannes Berg authored
In most cases, unless shutting down the NIC, we really need to retake ownership after doing a software reset of the NIC. Encode that into the API so we "automatically" do it, even in case of workarounds, and don't keep forgetting it like a few of the places we have did. Signed-off-by:
-
Johannes Berg authored
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:
-
Johannes Berg authored
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:
-
Luca Coelho authored
Start supporting API version 68 for AX devices. Signed-off-by:
-
Johannes Berg authored
Some command strings in the system group weren't added for debug, add them now. Signed-off-by:
-
Mordechay Goodstein authored
In next region tlv (3) region type is going to be split into bit mask without affecting the ops for handling region type, so we just mask the type independent of the version due to all versions having the same bits usage. Signed-off-by:
Mordechay Goodstein <mordechay.goodstein@intel.com> Signed-off-by:
-
Yaara Baruch authored
The names of the killer 1650i and 1650s devices weren't aligned. This patch swap the names in the structs. Signed-off-by:
-
Miri Korenblit authored
The exact size of WGDS revision 3 was calculated using the wrong parameters. Fix it. Signed-off-by:
Miri Korenblit <miriam.rachel.korenblit@intel.com> Signed-off-by:
-
Mukesh Sisodiya authored
Add DBGC4 memory for debug handling in driver which will be created, freed and collected from the FW in case of crash. Signed-off-by:
-
Mordechay Goodstein authored
In assoc state we only use narrow bandwidth, due to phy/radio not configured to max bandwidth. Signed-off-by:
-
Shaul Triebitz authored
When scheduling a session protection the id is saved but then it may be cleared when calling iwl_mvm_te_clear_data (if a previous session protection is currently active). Fix it by saving the id after calling iwl_mvm_te_clear_data. Signed-off-by:
Shaul Triebitz <shaul.triebitz@intel.com> Signed-off-by:
-
Mordechay Goodstein authored
The main changes are remove the respond from STATISTICS_CMD and sending it with STATISTICS_NOTIFICATION, and updating for all mac id's and phy id's in one notification. Signed-off-by:
-
Ilan Peer authored
The scan request command is identical in binary format to the previous scan request command and the only change is now a previously reserved octet is used to indicate new flags introduced in the command. Align the code to support the new version and the previous one. Later patches would add the specific handling for the new flags. Signed-off-by:
Ilan Peer <ilan.peer@intel.com> Signed-off-by:
-
Ilan Peer authored
Signed-off-by:
-
Luca Coelho authored
We need to support platforms with So and SoF together with Gf4 radio modules. The difference is that these devices support CDB, so add the entries accordingly. Signed-off-by:
-
Emmanuel Grumbach authored
When the station is removed we need to remove the session protection that may be still running. Note that we need also to remove the session protection upon unassoc in case the station is kept in the AUTH state. Signed-off-by:
Emmanuel Grumbach <emmanuel.grumbach@intel.com> Signed-off-by:
-
Luca Coelho authored
We don't use this structure anymore, except for a check that will never match, so we can remove this structure entirely. Signed-off-by:
-
Johannes Berg authored
A new version of this command deprecates the rxchain_info field but is otherwise the same, so treat it the same way. We already leave the rxchain_info zeroed since the RLC command is supported. Signed-off-by:
-
Johannes Berg authored
There are two possible versions of this command in use today, add a link to v1 as well in the documentation. Signed-off-by:
-
Johannes Berg authored
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:
-
Johannes Berg authored
Newer firmware versions are going to come with a new version of the wowlan status API, which gives us replay counters for both GTKs that might still be in use, as well as unifying the layout of the counters to just be 64-bit quantities. Extend our code to handle this case and be able to install replay counters for both keys, if they're sent up from the firmware. Signed-off-by:
-
Johannes Berg authored
There's a new version with some addition, we'll need to do something with the additional data later, but for now just parse it so we don't fail with the newer firmware. Signed-off-by:
-
Haim Dreyfuss authored
Instead of using two bits in the doorbell interrupt, the new Bz devices have a new CSR_IPC_SLEEP_CONTROL register to let drivers indicate the desired transition before triggering the doorbell interrupt. Signed-off-by:
Haim Dreyfuss <haim.dreyfuss@intel.com> Signed-off-by:
-
Johannes Berg authored
Move the GTK rekeying condition into iwl_mvm_set_key_rx_seq() so we can modify it in the next patch. In the next firmware API revision we'll properly get data for both active GTKs and will have to install it accordingly. Signed-off-by:
-
Mike Golant authored
Add support for Bz Z step HW with GF RF. Signed-off-by:
Mike Golant <michael.golant@intel.com> Signed-off-by:
-
Mike Golant authored
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:
-
Johannes Berg authored
If userspace installs a lot of multicast groups very quickly, then we may run out of command queue space as we send the updates in an asynchronous fashion (due to locking concerns), and the CPU can create them faster than the firmware can process them. This is true even when mac80211 has a work struct that gets scheduled. Fix this by synchronizing with the firmware after sending all those commands - outside of the iteration we can send a synchronous echo command that just has the effect of the CPU waiting for the prior asynchronous commands to finish. This also will cause fewer of the commands to be sent to the firmware overall, because the work will only run once when rescheduled multiple times while it's running. Link: https://bugzilla.kernel.org/show_bug.cgi?id=213649Suggested-by:
Maximilian Ernestus <maximilian@ernestus.de> Signed-off-by:
-
Johannes Berg authored
If we happen to decide an NSSN queue sync (IWL_MVM_RXQ_NSSN_SYNC) for some remaining packets that are still on the queue, but just after we've decided to do a delBA (which causes its own queues sync with IWL_MVM_RXQ_NOTIF_DEL_BA) we can end up with a sequence of events like this: CPU 1 CPU 2 remove BA session with baid N send IWL_MVM_RXQ_NOTIF_DEL_BA send IWL_MVM_RXQ_NSSN_SYNC get IWL_MVM_RXQ_NOTIF_DEL_BA get IWL_MVM_RXQ_NOTIF_DEL_BA get IWL_MVM_RXQ_NSSN_SYNC complete IWL_MVM_RXQ_NOTIF_DEL_BA remove N from baid_map[] get IWL_MVM_RXQ_NSSN_SYNC WARN_ON(!baid_map[N]) Thus, there's a race that leads in hitting the WARN_ON, but more importantly, it's a race that potentially even results in a new aggregation session getting assigned to baid N. To fix this, remove the WARN_ON() in the NSSN_SYNC case, we can't completely protect against hitting this case, so we shouldn't be warning. However, guard ourselves against BAID reuse by doing yet another round of queue synchronization after the entry is removed from the baid_map, so that it cannot be reused with any in-flight IWL_MVM_RXQ_NSSN_SYNC messages. Signed-off-by: -
Yang Shen authored
Fixes the following W=1 kernel build warning: drivers/net/wireless/intel/iwlwifi/mvm/rfi.c:11: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst Cc: Stanislav Yakovlev <stas.yakovlev@gmail.com> Signed-off-by:
Yang Shen <shenyang39@huawei.com> [removed the static const fix, since it's already done and updated the commit message accordingly.] Link: https://lore.kernel.org/r/20210517050141.61488-7-shenyang39@huawei.comSigned-off-by:
-
Lv Yunlong authored
In iwl_txq_dyn_alloc_dma, txq->tfds is freed at first time by: iwl_txq_alloc()->goto err_free_tfds->dma_free_coherent(). But it forgot to set txq->tfds to NULL. Then the txq->tfds is freed again in iwl_txq_dyn_alloc_dma by: goto error->iwl_txq_gen2_free_memory()->dma_free_coherent(). My patch sets txq->tfds to NULL after the first free to avoid the double free. Fixes: 0cd1ad2d ("iwlwifi: move all bus-independent TX functions to common code") Signed-off-by:
Lv Yunlong <lyl2019@mail.ustc.edu.cn> Link: https://lore.kernel.org/r/20210403054755.4781-1-lyl2019@mail.ustc.edu.cnSigned-off-by:
-
Emmanuel Grumbach authored
Smatch spot a possible NULL pointer dereference. Fix it. __iwl_mvm_mac_set_key can be called with sta = NULL Also add a NULL pointer check after memory allocation. Reported-by:
Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by:
-
