Ahmad Fatoum [Tue, 17 Aug 2021 06:35:22 +0000 (08:35 +0200)]
brcmfmac: pcie: fix oops on failure to resume and reprobe
When resuming from suspend, brcmf_pcie_pm_leave_D3 will first attempt a
hot resume and then fall back to removing the PCI device and then
reprobing. If this probe fails, the kernel will oops, because brcmf_err,
which is called to report the failure will dereference the stale bus
pointer. Open code and use the default bus-less brcmf_err to avoid this.
bcma: Fix memory leak for internally-handled cores
kmemleak reported that dev_name() of internally-handled cores were leaked
on driver unbinding. Let's use device_initialize() to take refcounts for
them and put_device() to properly free the related stuff.
While looking at it, there's another potential issue for those which should
be *registered* into driver core. If device_register() failed, we put
device once and freed bcma_device structures. In bcma_unregister_cores(),
they're treated as unregistered and we hit both UAF and double-free. That
smells not good and has also been fixed now.
I think last commits in tag iwlwifi-next-for-kalle-2021-08-26 are not
ready yet so I'm skipping those and pulling an earlier commit. I
modified Luca's description below to not include the skipped commits.
iwlwifi patches for v5.15
* Support scanning hidden 6GHz networks;
* Some improvements in the FW error dumps;
* Add some HE capability flags
* A bunch of janitorial clean-ups;
* Clean-ups in the TX code;
* Small fix for SMPS;
* Support for a new hardware family (Bz);
* Small fix in the scan code;
* A bunch of changes in the D3 code, including new FW API;
* Finalize the refactoring of 6GHz scan;
* Initial changes in the SAR profile code;
* Fix reading one of our ACPI tables (WTAS);
* Support some new ACPI table revisions;
* Support new API of the WoWlan status FW notification;
* Fixes in SAR ACPI tables handling;
* Some debugging improvements;
* Fix in ROC;
* Support for new FW API versions;
* Support new FW command versions;
* Some other small fixes, clean-ups and improvements.
Paweł Drewniak [Tue, 24 Aug 2021 22:13:30 +0000 (23:13 +0100)]
brcmfmac: Add WPA3 Personal with FT to supported cipher suites
This allows the driver to connect to BSSIDs supporting SAE with 802.11r.
Tested on Raspberry Pi 4 Model B (STA) and UniFi 6LR/OpenWRT 21.02.0-rc2.
AP was set to 'sae-mixed' (WPA2/3 Personal).
Linus Walleij [Sat, 21 Aug 2021 23:58:00 +0000 (01:58 +0200)]
ssb: Drop legacy header include
The SSB header only uses the legacy <linux/gpio.h> header to get
struct gpio_chip so inluce <linux/gpio/driver.h> which is the right
include to deal with gpio_chip.
Nathan Chancellor [Mon, 23 Aug 2021 22:20:14 +0000 (15:20 -0700)]
rtlwifi: rtl8192de: Fix initialization of place in _rtl92c_phy_get_rightchnlplace()
Clang warns:
drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c:901:6: warning:
variable 'place' is used uninitialized whenever 'if' condition is false
[-Wsometimes-uninitialized]
if (chnl > 14) {
^~~~~~~~~
drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c:909:9: note:
uninitialized use occurs here
return place;
^~~~~
drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c:901:2: note: remove
the 'if' if its condition is always true
if (chnl > 14) {
^~~~~~~~~~~~~~~
drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c:899:10: note:
initialize the variable 'place' to silence this warning
u8 place;
^
= '\0'
1 warning generated.
Commit 369956ae5720 ("rtlwifi: rtl8192de: Remove redundant variable
initializations") removed the initialization of place but it appears
that this removal was in the wrong function.
_rtl92c_phy_get_rightchnlplace() returns place's value at the end of the
function so now if the if statement is false, place never gets
initialized. Add that initialization back to address the warning.
place's initialization is not necessary in
rtl92d_get_rightchnlplace_for_iqk() as place is only used within the if
statement so it can be removed, which is likely what was intended in the
first place.
Dan Carpenter [Fri, 13 Aug 2021 11:34:38 +0000 (14:34 +0300)]
ath6kl: wmi: fix an error code in ath6kl_wmi_sync_point()
This error path is unlikely because of it checked for NULL and
returned -ENOMEM earlier in the function. But it should return
an error code here as well if we ever do hit it because of a
race condition or something.
Fixes: bdcd81707973 ("Add ath6kl cleaned up driver") Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Kalle Valo <kvalo@codeaurora.org> Link: https://lore.kernel.org/r/20210813113438.GB30697@kili
Bad header can have large length field which can cause OOB.
cptr is the last bytes for read, and the eeprom is parsed
from high to low address. The OOB, triggered by the condition
length > cptr could cause memory error with a read on
negative index.
There are some sanity check around length, but it is not
compared with cptr (the remaining bytes). Here, the
corrupted/bad EEPROM can cause panic.
I was able to reproduce the crash, but I cannot find the
log and the reproducer now. After I applied the patch, the
bug is no longer reproducible.
Loic Poulain [Thu, 26 Aug 2021 15:46:08 +0000 (17:46 +0200)]
wcn36xx: Fix missing frame timestamp for beacon/probe-resp
When receiving a beacon or probe response, we should update the
boottime_ns field which is the timestamp the frame was received at.
(cf mac80211.h)
This fixes a scanning issue with Android since it relies on this
timestamp to determine when the AP has been seen for the last time
(via the nl80211 BSS_LAST_SEEN_BOOTTIME parameter).
Bjorn Andersson [Tue, 24 Aug 2021 17:12:25 +0000 (10:12 -0700)]
wcn36xx: Allow firmware name to be overridden by DT
The WLAN NV firmware blob differs between platforms, and possibly
devices, so add support in the wcn36xx driver for reading the path of
this file from DT in order to allow these files to live in a generic
file system (or linux-firmware).
For some reason the parent (wcnss_ctrl) also needs to upload this blob,
so rather than specifying the same information in both nodes wcn36xx
reads the string from the parent's of_node.
Joseph Gates [Wed, 18 Aug 2021 11:31:43 +0000 (13:31 +0200)]
wcn36xx: Ensure finish scan is not requested before start scan
If the operating channel is the first in the scan list, it was seen that
a finish scan request would be sent before a start scan request was
sent, causing the firmware to fail all future scans. Track the current
channel being scanned to avoid requesting the scan finish before it
starts.
Johannes Berg [Thu, 26 Aug 2021 19:47:43 +0000 (22:47 +0300)]
iwlwifi: mvm: don't use FW key ID in beacon protection
To check beacon protection had a mismatch of the key ID we
currently use the key ID from the firmware, but firmware
side we want to clean up the API to stop reporting this.
Instead, check the IWL_RX_MPDU_STATUS_KEY_VALID bit that
indicates that the firmware used the correct key, and if
that's set but we get invalid MIC/replay use the key ID
from the frame to look up the key and notify mac80211 of
MIC error or replay. Since both keys must have the same
cipher and thus MIC length, we can use either of them to
look up the MIC length.
Shaul Triebitz [Thu, 26 Aug 2021 19:47:41 +0000 (22:47 +0300)]
iwlwifi: mvm: support broadcast TWT alone
Tell the firmware about broadcast TWT support
even if individual TWT is not supported.
In that case the firmware will negotiate only
a broadcast TWT session.
Avraham Stern [Thu, 26 Aug 2021 19:47:38 +0000 (22:47 +0300)]
iwlwifi: mvm: add support for responder config command version 9
This version adds the following configuration options:
1. Enable/disable setting the session id in the FTM frame
2. Set the BSS color for the responder
3. Set the minimum and maximum time between measurements for
non trigger based NDP ranging.
Avraham Stern [Thu, 26 Aug 2021 19:47:37 +0000 (22:47 +0300)]
iwlwifi: mvm: add support for range request command version 13
This version adds the following configuration options:
1. Set the BSS color for NDP ranging
2. Set the minimum and maximum time between measurements for
non trigger based NDP ranging.
3. Terminate the session in case the responder requests LMR feedback.
Johannes Berg [Thu, 19 Aug 2021 15:40:35 +0000 (18:40 +0300)]
iwlwifi: allow debug init in RF-kill
We can send this even if initializing in RF-kill, thus
suppressing a bunch of error messages about it. In fact,
we _want_ to, since we might still want to debug the
firmware even if in RF-kill.
Avraham Stern [Thu, 19 Aug 2021 15:40:34 +0000 (18:40 +0300)]
iwlwifi: mvm: don't schedule the roc_done_wk if it is already running
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.
Johannes Berg [Thu, 19 Aug 2021 15:40:31 +0000 (18:40 +0300)]
iwlwifi: fw: fix debug dump data declarations
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.
Johannes Berg [Thu, 19 Aug 2021 15:40:30 +0000 (18:40 +0300)]
iwlwifi: api: remove datamember from struct
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.
Johannes Berg [Thu, 19 Aug 2021 15:40:28 +0000 (18:40 +0300)]
iwlwifi: pcie: avoid dma unmap/remap in crash dump
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.
Luca Coelho [Thu, 19 Aug 2021 15:40:27 +0000 (18:40 +0300)]
iwlwifi: acpi: fill in SAR tables with defaults
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.
Miri Korenblit [Thu, 5 Aug 2021 11:21:57 +0000 (14:21 +0300)]
iwlwifi: mvm: load regdomain at INIT stage
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.
Miri Korenblit [Thu, 5 Aug 2021 11:21:56 +0000 (14:21 +0300)]
iwlwifi: mvm: Read the PPAG and SAR tables at INIT stage
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.
Johannes Berg [Thu, 5 Aug 2021 11:21:54 +0000 (14:21 +0300)]
iwlwifi: fw: correctly limit to monitor dump
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.
Abhishek Naik [Thu, 5 Aug 2021 11:21:53 +0000 (14:21 +0300)]
iwlwifi: skip first element in the WTAS ACPI table
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.
Gregory Greenman [Thu, 5 Aug 2021 11:21:52 +0000 (14:21 +0300)]
iwlwifi: mvm: support version 11 of wowlan statuses notification
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.
Luca Coelho [Thu, 5 Aug 2021 11:21:51 +0000 (14:21 +0300)]
iwlwifi: convert flat GEO profile table to a struct version
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.
Luca Coelho [Thu, 5 Aug 2021 11:21:49 +0000 (14:21 +0300)]
iwlwifi: support reading and storing EWRD revisions 1 and 2
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.
Luca Coelho [Thu, 5 Aug 2021 11:21:48 +0000 (14:21 +0300)]
iwlwifi: acpi: support reading and storing WRDS revision 1 and 2
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.
Luca Coelho [Thu, 5 Aug 2021 11:21:47 +0000 (14:21 +0300)]
iwlwifi: pass number of chains and sub-bands to iwl_sar_set_profile()
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.
Luca Coelho [Thu, 5 Aug 2021 10:19:34 +0000 (13:19 +0300)]
iwlwifi: remove ACPI_SAR_NUM_TABLES definition
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.
Luca Coelho [Thu, 5 Aug 2021 10:19:33 +0000 (13:19 +0300)]
iwlwifi: convert flat SAR profile table to a struct version
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.
Luca Coelho [Thu, 5 Aug 2021 10:19:32 +0000 (13:19 +0300)]
iwlwifi: rename ACPI_SAR_NUM_CHAIN_LIMITS to ACPI_SAR_NUM_CHAINS
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.
Ilan Peer [Thu, 5 Aug 2021 10:19:30 +0000 (13:19 +0300)]
iwlwifi: mvm: Refactor setting of SSIDs for 6GHz scan
- 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.
Avraham Stern [Thu, 5 Aug 2021 10:19:29 +0000 (13:19 +0300)]
iwlwifi: mvm: silently drop encrypted frames for unknown station
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.
Johannes Berg [Thu, 5 Aug 2021 10:19:28 +0000 (13:19 +0300)]
iwlwifi: mvm: d3: implement RSC command version 5
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.
Johannes Berg [Thu, 5 Aug 2021 10:19:27 +0000 (13:19 +0300)]
iwlwifi: mvm: d3: make key reprogramming iteration optional
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.
Johannes Berg [Thu, 5 Aug 2021 10:19:26 +0000 (13:19 +0300)]
iwlwifi: mvm: d3: add separate key iteration for GTK type
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.
Johannes Berg [Thu, 5 Aug 2021 10:19:25 +0000 (13:19 +0300)]
iwlwifi: mvm: d3: refactor TSC/RSC configuration
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.
Johannes Berg [Thu, 5 Aug 2021 10:19:23 +0000 (13:19 +0300)]
iwlwifi: mvm: d3: separate TKIP data from key iteration
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.
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.
Johannes Berg [Mon, 2 Aug 2021 18:58:50 +0000 (21:58 +0300)]
iwlwifi: read MAC address from correct place on Bz
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.
Johannes Berg [Mon, 2 Aug 2021 14:28:29 +0000 (17:28 +0300)]
iwlwifi: mvm: treat MMPDUs in iwl_mvm_mac_tx() as bcast
There's no need for all the complicated conditions here, any
bufferable MMPDUs or MMPDUs for client interfaces are already
coming through the TXQ interface, not iwl_mvm_mac_tx().
Johannes Berg [Mon, 2 Aug 2021 14:28:28 +0000 (17:28 +0300)]
iwlwifi: mvm: clean up number of HW queues
Since switching to mac80211 TXQs, we no longer need to
advertise more hardware queues than ACs, since we don't
even set QUEUE_CONTROL anyway, so the vif->hw_queue[]
mapping array won't be used.
All we need (at least for now) is for hw->queues to
indicate that we have enough queues to handle QoS.
Johannes Berg [Mon, 2 Aug 2021 14:28:27 +0000 (17:28 +0300)]
iwlwifi: mvm: avoid static queue number aliasing
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.
Luca Coelho [Mon, 2 Aug 2021 14:28:22 +0000 (17:28 +0300)]
iwlwifi: mvm: remove check for vif in iwl_mvm_vif_from_mac80211()
This check is useless, because we would return NULL in that case and
none of the callers actually check that the return value was not NULL
before accessing it.
Johannes Berg [Mon, 2 Aug 2021 14:28:20 +0000 (17:28 +0300)]
iwlwifi: mvm: restrict FW SMPS request
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.
Johannes Berg [Mon, 2 Aug 2021 14:28:19 +0000 (17:28 +0300)]
iwlwifi: mvm: set replay counter on key install
When installing a (new) key, set the replay counter so that
after FW restart the firmware has the correct value of the
replay counters.
This doesn't have a large effect - for frames that reach
the driver, it will do a replay check, and when installing
a new key, the counter is normally zero to start with (not
for GTK though, if joining the BSS for the first time).
Since this only affects frames handled entirely by the FW,
and that's restricted to a few unicast management frames,
the only affect here is for those after a firmware restart.
Mordechay Goodstein [Mon, 2 Aug 2021 14:28:18 +0000 (17:28 +0300)]
iwlwifi: mvm: remove trigger EAPOL time event
EAPOL failure results in deauthentication with various reasons, not
related to AUTH failure specifically, so we just merge AUTH failure
with failed to assoc to AP.
Ilan Peer [Mon, 2 Aug 2021 14:09:43 +0000 (17:09 +0300)]
iwlwifi: mvm: Add support for hidden network scan on 6GHz band
Add support for discovery of hidden networks on the 6GHz band,
by including the scan request direct SSIDs in the FW scan request
command:
- In case a short SSID matches one of the direct SSIDs in the scan
request command, add the matching SSID in the same offset in the
'direct_ssids' array.
- Otherwise, add the SSID in one of the available slots.
Additionally, as a preparation to handle hidden APs, refactor
iwl_mvm_umac_scan_cfg_channels_v6_6g() the function.
Ilan Peer [Mon, 2 Aug 2021 14:09:42 +0000 (17:09 +0300)]
iwlwifi: mvm: Do not use full SSIDs in 6GHz scan
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.
Luca Coelho [Mon, 2 Aug 2021 14:09:41 +0000 (17:09 +0300)]
iwlwifi: print PNVM complete notification status in hexadecimal
This value is not a simple incrementing integer, it contains some
flags as well, so reading it in hexadecimal is easier. Change the
print to do it in hex instead of decimal.
Johannes Berg [Mon, 2 Aug 2021 14:09:40 +0000 (17:09 +0300)]
iwlwifi: pcie: dump error on FW reset handshake failures
If the firmware crashes while we're waiting for the reset
handshake then it cannot possibly make progress anymore,
and we will just time out the wait. That's pointless, so
just stop waiting at that point.
Additionally, if it never acknowledges the reset handshake,
something went wrong.
Dump an error in both of these cases, but we need to do it
synchronously here since the device will be turned off.
Johannes Berg [Mon, 2 Aug 2021 14:09:38 +0000 (17:09 +0300)]
iwlwifi: pcie: free RBs during configure
When switching op-modes, or more generally when reconfiguring,
we might switch the RB size. In _iwl_pcie_rx_init() we have a
comment saying we must free all RBs since we might switch the
size, but this is actually too late: the switch has been done
and we'll free the buffers with the wrong size.
Fix this by always freeing the buffers, if any, at the start
of configure, instead of only after the size may have changed.
On 64-bit machines, struct iwl_rx_mem_buffer has a lot of
padding due to the use of pointers after the small items.
Move the list entry before them, and while at it also add
documentation for it.
Johannes Berg [Mon, 2 Aug 2021 14:09:36 +0000 (17:09 +0300)]
iwlwifi: mvm: avoid FW restart while shutting down
If the firmware crashes while we're already shutting down
the system, there isn't much we can do since the shutdown
process is continuing and we wanted to do that. Don't do
a FW restart, with the implied debug collection, in this
case.
David S. Miller [Wed, 25 Aug 2021 12:44:30 +0000 (13:44 +0100)]
Merge branch 'pktgen-samples-next'
Juhee Kang says:
====================
samples: pktgen: enhance the ability to print the execution results of samples
This patch series improves the ability to print the execution result of pktgen
samples by adding a line which calls the function before termination and adding
trap SIGINT. Also, this series documents the latest pktgen usage options.
Currently, pktgen samples print the execution result when terminated usually.
However, sample03 is not working properly.
Because sample03 doesn't call the function which prints the execution result
when terminated normally, unlike other samples. So the first commit solves
this issue by adding a line which calls the function before termination.
Also, all pktgen samples are able to send infinite messages per thread by
setting the count option to 0, and pktgen is stopped by Ctrl-C. However,
the sample besides sample{3...5} don't work appropriately because Ctrl-C stops
the script, not just pktgen.
So the second commit solves this issue by adding trap SIGINT. Also, changes
control_c function to print_results to maintain consistency with other samples
on the first commit and second commit.
And current pktgen.rst documentation doesn't add the latest pktgen sample
usage options such as count and IPv6, and so on. Also, the old pktgen
sample scripts are still included in the document. The old scripts were removed
by the commit a4b6ade8359f ("samples/pktgen: remove remaining old pktgen
sample scripts").
Thus, the last commit documents the latest pktgen sample usage and removes
old sample scripts. And fixes a minor typo.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Juhee Kang [Wed, 25 Aug 2021 10:57:17 +0000 (19:57 +0900)]
pktgen: document the latest pktgen usage options
Currently, the pktgen.rst documentation doesn't cover the latest pktgen
sample usage options such as count and IPv6, and so on. Also, this
documentation includes the old sample scripts which are no longer use
because it was removed by the commit a4b6ade8359f ("samples/pktgen :
remove remaining old pktgen sample scripts")
Thus, this commit documents pktgen sample usage using the latest options
and removes old sample scripts, and fixes a minor typo.
Signed-off-by: Juhee Kang <claudiajkang@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Juhee Kang [Wed, 25 Aug 2021 10:57:16 +0000 (19:57 +0900)]
samples: pktgen: add trap SIGINT for printing execution result
All pktgen samples can send indefinitely num messages per thread by
setting the count option to 0(-n 0). If running sample with setting
count 0 and press Ctrl-C to stop this program, the program prints the
result of the execution so far. Currently, the samples besides
sample{3...5} don't work properly. Because Ctrl-C stops the script, not
just pktgen.
In order to solve this, this commit adds trap SIGINT. Also, this commit
changes control_c function to print_result to maintain consistency with
other samples.
Signed-off-by: Juhee Kang <claudiajkang@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
The reason why it doesn't print the execution result when the program is
terminated usually is that sample03 doesn't call the function which
prints the result, unlike other samples.
So, this commit solves this issue by calling the function before
termination. Also, this commit changes control_c function to
print_result to maintain consistency with other samples.
Signed-off-by: Juhee Kang <claudiajkang@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Wed, 25 Aug 2021 12:39:02 +0000 (13:39 +0100)]
Merge branch 'octeontx2-traffic-shaping'
Sunil Goutham says:
====================
Octeontx2: Traffic shaping and SDP link config support
This patch series adds support for traffic shaping configuration
on all silicons available after 96xx C0. And also adds SDP link
related configuration needed when Octeon is connected as an end-point
and traffic needs to flow from end-point to host and vice versa.
Series also has other changes like
- New mbox messages in admin function driver for PF/VF drivers
to retrieve available HW resource count. HW resources like block LFs,
bandwidth profiles etc are covered.
- Added PTP device ID for new CN10K and 95O silicons.
- etc
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Sunil Goutham [Wed, 25 Aug 2021 12:18:46 +0000 (17:48 +0530)]
octeontx2-af: Add mbox to retrieve bandwidth profile free count
Added mbox for PF/VF drivers to retrieve current ingress bandwidth
profile free count. Also added current policer timeunit
configuration info based on which ratelimiting decisions can be
taken by PF/VF drivers.
Signed-off-by: Sunil Goutham <sgoutham@marvell.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Sunil Goutham [Wed, 25 Aug 2021 12:18:45 +0000 (17:48 +0530)]
octeontx2-af: Remove channel verification while installing MCAM rules
New usecases are popping up where in user wants to install common MCAM
filters for all interfaces. Having channel verification will result in
duplicating such MCAM filters for each of the ingress interface. Hence
removed channel verification.
Signed-off-by: Sunil Goutham <sgoutham@marvell.com> Signed-off-by: David S. Miller <davem@davemloft.net>
projects / users / willy / xarray.git / log