When processing an association response frame for a Multi-Link
connection, extract the per station profile for each additional
link, and use it for parsing the link elements.
As the Multi-Link element might be fragmented, add support for
reassembling a fragmented element. To simplify memory management
logic, extend 'struct ieee802_11_elems' to hold a scratch buffer,
which is used for the defragmentation. Once an element is
reconstructed in the scratch area, point the corresponding element
pointer to it. Currently only defragmentation of Multi-Link element
and the contained per-STA profile subelement is supported.
Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
The Multi-Link element can be fragmented, thus its size can exceed 254.
Thus, modify ieee80211_mle_size_ok() to use 'size_t len' instead of
'u8 len'.
Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
The common size is part of the length in the data
so don't add it again.
Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Add a function to validate EHT Multi-Link per station profile length.
Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
For assoc and connect result APIs, support reporting
failed links; they should still come with the BSS
pointer in the case of assoc, so they're released
correctly. In the case of connect result, this is
optional.
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
During link switching, the active links change, so we need to
recalculate the aggregate data in the stations.
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Add the link address to the per-link information, but only if we are
using MLO.
Signed-off-by: Benjamin Berg <benjamin.berg@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Create debugfs data per-link. For drivers, there is a new operation
link_sta_add_debugfs which will always be called.
For non-MLO, the station directory will be used directly rather than
creating a corresponding subdirectory. As such, non-MLO drivers can
simply continue to create the data from sta_debugfs_add.
Signed-off-by: Benjamin Berg <benjamin.berg@intel.com>
[add missing inlines if !CONFIG_MAC80211_DEBUGFS]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
While often not needed, this considerably simplifies going from a link
to the STA. This helps in cases such as debugfs where a single pointer
should allow accessing a specific link and the STA.
Signed-off-by: Benjamin Berg <benjamin.berg@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
When built with Control Flow Integrity, function prototypes between
caller and function declaration must match. These mismatches are visible
at compile time with the new -Wcast-function-type-strict in Clang[1].
Of the 1549 warnings found, 188 come from the atmel driver. For example:
drivers/net/wireless/atmel/atmel.c:2518:2: warning: cast from 'int (*)(struct net_device *, struct iw_request_info *, void *, char *)' to 'iw_handler' (aka 'int (*)(struct net_device *, struct iw_request_info *, union iwreq_data *, char *)') converts to incompatible function type [-Wcast-function-type-strict]
(iw_handler) atmel_config_commit, /* SIOCSIWCOMMIT */
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
The atmel Wireless Extension handler callbacks (iw_handler) use a union
for the data argument. Actually use the union and perform explicit
member selection in the function body instead of having a function
prototype mismatch. There are no resulting binary differences.
This patch is a cleanup based on Brad Spengler/PaX Team's modifications
to the atmel driver in their last public patch of grsecurity/PaX based
on my understanding of the code. Changes or omissions from the original
code are mine and don't reflect the original grsecurity/PaX code.
[1] https://reviews.llvm.org/D134831
Cc: Simon Kelley <simon@thekelleys.org.uk>
Cc: Kalle Valo <kvalo@kernel.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: linux-wireless@vger.kernel.org
Cc: netdev@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20221002032428.4091540-1-keescook@chromium.org
MAC maintains TX FIFO to transmit packets with meta data to BB layer. To
debug abnormal transmission, we need to dump the content to dig problem.
Since FIFO of 8852C locates on different address with different size and
need additional switch to enable read operation, this patch adds the
changes accordingly.
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20220930134417.10282-2-pkshih@realtek.com
8852CE is a combo chip, and WiFi driver controls pin MUX. To output BT
firmware log to specific hardware pin, set pin MUX to achieve.
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20220930134417.10282-1-pkshih@realtek.com
The new BB parameters add new cfg_tpe 4 to improve performance of eFEM
modules (rfe_type >= 50), but we are using iFEM modules for now, so this
warning can be ignored.
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20220930133659.7789-2-pkshih@realtek.com
Using mdelay() can work well, but calibration causes too much time. Use
proper udelay() to get shorter time and the same result.
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20220930133318.6335-2-pkshih@realtek.com
IQK can change the values of this register set, so need to backup and
restore the values. During we rewrite IQK, the policy is changed. Some
values are controlled and filled by IQK, and don't need to restore after
IQK. Therefore, remove this kind of registers from this array.
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20220930133318.6335-1-pkshih@realtek.com
Fixes the ap interface delete issue. Fix is to make sure interface
is created with supported version.
Patch has been verified by creating and deleting AP interface.
Signed-off-by: Prasanna Kerekoppa <prasanna.kerekoppa@infineon.com>
Signed-off-by: Ian Lin <ian.lin@infineon.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20220929050614.31518-4-ian.lin@infineon.com
To create virtual station interface for RSDB and VSDB, we add interface
creation version 1, 2 and 3 supports
The structures of each version are different and only version 3 and
later version are able to get interface creating version from firmware
side.
The patch has been verified two concurrent stations pings test with
interface create version 1:
89342(4359b1)-PCIE: 9.40.100
interface create version 2:
4373a0-sdio: 13.10.271
interface create version 3:
4373a0-sdio: 13.35.48
Signed-off-by: Wright Feng <wright.feng@cypress.com>
Signed-off-by: Chi-hsien Lin <chi-hsien.lin@infineon.com>
Signed-off-by: Ian Lin <ian.lin@infineon.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20220929050614.31518-3-ian.lin@infineon.com
With RSDB device, it is able to control two station interfaces
concurrently. So we add creating station interface support and
allow user to create it via cfg80211.
Signed-off-by: Wright Feng <wright.feng@cypress.com>
Signed-off-by: Chi-hsien Lin <chi-hsien.lin@infineon.com>
Signed-off-by: Ian Lin <ian.lin@infineon.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20220929050614.31518-2-ian.lin@infineon.com
To enhance FW debugging, we add dongle memory dump when hitting attaching
failure with PCIE bus. It can help developer to get more information
about dongle trap reason and root cause.
Signed-off-by: Wright Feng <wright.feng@cypress.com>
Signed-off-by: Chi-hsien Lin <chi-hsien.lin@cypress.com>
Signed-off-by: Ian Lin <ian.lin@infineon.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20220929031001.9962-4-ian.lin@infineon.com
When firmware hit trap at initialization, host will read abnormal
max_flowrings number from dongle, and it will cause kernel panic when
doing iowrite to initialize dongle ring.
To detect this error at early stage, we directly return error when getting
invalid max_flowrings(>256).
Signed-off-by: Wright Feng <wright.feng@cypress.com>
Signed-off-by: Chi-hsien Lin <chi-hsien.lin@cypress.com>
Signed-off-by: Ian Lin <ian.lin@infineon.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20220929031001.9962-3-ian.lin@infineon.com
Currently, host only reads console buffer when receiving mailbox data or
hit crash with PCIE bus. Therefore, we add timer in PCIE code to read
console buffer periodically to help developer and user check firmware
message when there is no data transmission between host and dongle.
Signed-off-by: Wright Feng <wright.feng@cypress.com>
Signed-off-by: Chi-hsien Lin <chi-hsien.lin@cypress.com>
Signed-off-by: Ian Lin <ian.lin@infineon.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20220929031001.9962-2-ian.lin@infineon.com
Auto Channel Select feature of HostAP uses dump_survey to fetch
OBSS statistics. When the device is in the middle of an authentication
sequence or just at the end of authentication completion, running
dump_survey would trigger a channel change. The channel change in-turn
can cause packet loss, resulting in authentication delay. With this change,
dump_survey won't be run when authentication or association is in progress,
hence resolving the issue.
Signed-off-by: Ramesh Rangavittal <ramesh.rangavittal@infineon.com>
Signed-off-by: Chung-Hsien Hsu <chung-hsien.hsu@infineon.com>
Signed-off-by: Chi-hsien Lin <chi-hsien.lin@infineon.com>
Signed-off-by: Ian Lin <ian.lin@infineon.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20220929012527.4152-5-ian.lin@infineon.com
This patch fix CERT-P2P:5.1.10 failure at step 18 Group formation failed
due to chip is under dump survey. Decrease the dump survery duration to
pass this certification case.
Signed-off-by: Double Lo <double.lo@cypress.com>
Signed-off-by: Chi-hsien Lin <chi-hsien.lin@infineon.com>
Signed-off-by: Ian Lin <ian.lin@infineon.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20220929012527.4152-4-ian.lin@infineon.com
When doing dump_survey, host will call "dump_obss" iovar to firmware
side. Host need to make sure the HW clock in dongle is on, or there is
high probability that firmware gets trap because register or shared
memory access failed. To fix this, we disable mpc when doing dump obss
and set it back after that.
[28350.512799] brcmfmac: brcmf_dump_obss: dump_obss error (-52)
[28743.402314] ieee80211 phy0: brcmf_fw_crashed: Firmware has halted or
crashed
[28745.869430] brcmfmac: brcmf_sdio_bus_rxctl: resumed on timeout
[28745.877546] brcmfmac: brcmf_sdio_checkdied: firmware trap in dongle
Signed-off-by: Wright Feng <wright.feng@cypress.com>
Signed-off-by: Chi-hsien Lin <chi-hsien.lin@infineon.com>
Signed-off-by: Ian Lin <ian.lin@infineon.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20220929012527.4152-3-ian.lin@infineon.com
To enable ACS feature in Hostap daemon, dump_survey cfg80211 ops and dump
obss survey command in firmware side are needed. This patch is for adding
dump_survey feature and adding DUMP_OBSS feature flag to check if
firmware supports dump_obss iovar.
Signed-off-by: Wright Feng <wright.feng@cypress.com>
Signed-off-by: Chi-hsien Lin <chi-hsien.lin@cypress.com>
Signed-off-by: Ian Lin <ian.lin@infineon.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20220929012527.4152-2-ian.lin@infineon.com
Re-enable the function rtl8xxxu_gen2_report_connect.
It informs the firmware when connecting to a network. This makes the
firmware enable the rate control, which makes the upload faster.
It also informs the firmware when disconnecting from a network. In the
past this made reconnecting impossible because it was sending the
auth on queue 0x7 (TXDESC_QUEUE_VO) instead of queue 0x12
(TXDESC_QUEUE_MGNT):
wlp0s20f0u3: send auth to 90:55:de:__:__:__ (try 1/3)
wlp0s20f0u3: send auth to 90:55:de:__:__:__ (try 2/3)
wlp0s20f0u3: send auth to 90:55:de:__:__:__ (try 3/3)
wlp0s20f0u3: authentication with 90:55:de:__:__:__ timed out
Probably the firmware disables the unnecessary TX queues when it
knows it's disconnected.
However, this was fixed in commit edd5747aa1 ("wifi: rtl8xxxu: Fix
skb misuse in TX queue selection").
Fixes: c59f13bbea ("rtl8xxxu: Work around issue with 8192eu and 8723bu devices not reconnecting")
Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/43200afc-0c65-ee72-48f8-231edd1df493@gmail.com
This chip is found in the cheapest USB adapters, e.g. 1.17 USD with
VAT and shipping from China included.
It's a gen 2 chip, similar to the RTL8723BU, but without Bluetooth.
Features: 2.4 GHz, b/g/n mode, 1T1R, 150 Mbps.
The vendor driver rtl8188fu version 4.3.23.6_20964.20170110 [0]
was used as reference. The CD shipped with the device includes a
newer driver, version 5.11.5-1-g12f7cde4b.20201102, but that one
couldn't complete the WPA2 key exchange thing for whatever reason.
[0] https://github.com/kelebek333/rtl8188fu
Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/b14f299d-3248-98fe-eee1-ba50d2e76c74@gmail.com
8852BE has two variants with different ID. One is 10ec:b852 that is a main
model with 2x2 antenna, and the other is 10ec:b85b that is a 1x1 model.
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20220928084336.34981-10-pkshih@realtek.com
This efuse region is to store PHY calibration, and it is a separated region
from the region that stores MAC address. Then, use these data to configure
via chip_ops::power_trim that is a calibration mechanism of TX power.
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20220928084336.34981-9-pkshih@realtek.com
efuse stores individual data about a chip itself, such as MAC address,
country code, RF and crystal calibration data, and so on. Define a struct
to help access efuse content, and copy them into a common struct.
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20220928084336.34981-8-pkshih@realtek.com
This chip_ops is to set TX power according to country, channel, rate and
so on. Since shared code is used to configure TX power, we only implement
specific part in this patch.
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20220928084336.34981-7-pkshih@realtek.com
Previously, value of each field is just shown as unsigned.
Now, we start to show them with sign to make things more intuitive
during debugging.
Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20220928084336.34981-6-pkshih@realtek.com
Previously, we thought control registers or setting things for TX power
series may change according to chip. So, setting functions are implemented
chip by chip. However, until now, the functions keep the same among chips,
at least 8852A, 8852C, and 8852B. There is a sufficient number of chips to
share generic setting functions. So, we now remake them including TX power
by rate, TX power offset, TX power limit, and TX power limit RU as generic
ones in phy.c.
Besides, there are some code refinements in the generic ones, but almost
all of the logic doesn't change.
Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20220928084336.34981-5-pkshih@realtek.com
These tables contain BB and RF parameters that driver will load them into
registers. It also contains TX power according to country, band, rate and
so on. Increasing thermal can cause TX power degraded, so power tracking
tables are defined to compensate TX power.
Internal version of these tables:
- HALRF_029_00_014 (R32)
- HALBB_027_046_05
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20220928084336.34981-3-pkshih@realtek.com
These tables contain BB and RF parameters that driver will load them into
registers. It also contains TX power according to country, band, rate and
so on. Increasing thermal can cause TX power degraded, so power tracking
tables are defined to compensate TX power.
Internal version of these tables:
- HALRF_029_00_014 (R32)
- HALBB_027_046_05
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20220928084336.34981-2-pkshih@realtek.com
Few stack changes and lots of driver changes in this round. brcmfmac
has more activity as usual and it gets new hardware support. ath11k
improves WCN6750 support and also other smaller features. And of
course changes all over.
Note: in early September wireless tree was merged to wireless-next to
avoid some conflicts with mac80211 patches, this shouldn't cause any
problems but wanted to mention anyway.
Major changes:
mac80211
* refactoring and preparation for Wi-Fi 7 Multi-Link Operation (MLO)
feature continues
brcmfmac
* support CYW43439 SDIO chipset
* support BCM4378 on Apple platforms
* support CYW89459 PCIe chipset
rtw89
* more work to get rtw8852c supported
* P2P support
* support for enabling and disabling MSDU aggregation via nl80211
mt76
* tx status reporting improvements
ath11k
* cold boot calibration support on WCN6750
* Target Wake Time (TWT) debugfs support for STA interface
* support to connect to a non-transmit MBSSID AP profile
* enable remain-on-channel support on WCN6750
* implement SRAM dump debugfs interface
* enable threaded NAPI on all hardware
* WoW support for WCN6750
* support to provide transmit power from firmware via nl80211
* support to get power save duration for each client
* spectral scan support for 160 MHz
wcn36xx
* add SNR from a received frame as a source of system entropy
-----BEGIN PGP SIGNATURE-----
iQFFBAABCgAvFiEEiBjanGPFTz4PRfLobhckVSbrbZsFAmM3BGYRHGt2YWxvQGtl
cm5lbC5vcmcACgkQbhckVSbrbZuR3Af/XiuMlnDB6flq+M/kQHLWWvHybLw5aCJ7
l3yXhNFWxpBl2hQXtj17JSjVCYQmxbfrgRqhbNhyACO25bpymCb5QctB9X+Y7TwL
250JmuKvQfFx5oJNRfJ67dKTf3raloQYbdEMJNqySgebL+eSfrDskc9vaCLVDmCK
I994fl0Q1wUbJ6fbuIFd07ti8ay6UlSS/iakv4+nEeimabtZWJWlXBWYRpKpikdP
h9z2kPtss6yz6seaQuw6ny+qysYLi11Tp+Cued9XR3dWOOhB2X1tLHH0H02xPw76
9OJZEJHycP2juxjMfAaktHY+VX36GPLsMLUTVusH0h/Fdy3VG8YSAw==
=emmG
-----END PGP SIGNATURE-----
Merge tag 'wireless-next-2022-09-30' of git://git.kernel.org/pub/scm/linux/kernel/git/wireless/wireless-next
Kalle Valo says:
====================
wireless-next patches for v6.1
Few stack changes and lots of driver changes in this round. brcmfmac
has more activity as usual and it gets new hardware support. ath11k
improves WCN6750 support and also other smaller features. And of
course changes all over.
Note: in early September wireless tree was merged to wireless-next to
avoid some conflicts with mac80211 patches, this shouldn't cause any
problems but wanted to mention anyway.
Major changes:
mac80211
- refactoring and preparation for Wi-Fi 7 Multi-Link Operation (MLO)
feature continues
brcmfmac
- support CYW43439 SDIO chipset
- support BCM4378 on Apple platforms
- support CYW89459 PCIe chipset
rtw89
- more work to get rtw8852c supported
- P2P support
- support for enabling and disabling MSDU aggregation via nl80211
mt76
- tx status reporting improvements
ath11k
- cold boot calibration support on WCN6750
- Target Wake Time (TWT) debugfs support for STA interface
- support to connect to a non-transmit MBSSID AP profile
- enable remain-on-channel support on WCN6750
- implement SRAM dump debugfs interface
- enable threaded NAPI on all hardware
- WoW support for WCN6750
- support to provide transmit power from firmware via nl80211
- support to get power save duration for each client
- spectral scan support for 160 MHz
wcn36xx
- add SNR from a received frame as a source of system entropy
* tag 'wireless-next-2022-09-30' of git://git.kernel.org/pub/scm/linux/kernel/git/wireless/wireless-next: (231 commits)
wifi: rtl8xxxu: Improve rtl8xxxu_queue_select
wifi: rtl8xxxu: Fix AIFS written to REG_EDCA_*_PARAM
wifi: rtl8xxxu: gen2: Enable 40 MHz channel width
wifi: rtw89: 8852b: configure DLE mem
wifi: rtw89: check DLE FIFO size with reserved size
wifi: rtw89: mac: correct register of report IMR
wifi: rtw89: pci: set power cut closed for 8852be
wifi: rtw89: pci: add to do PCI auto calibration
wifi: rtw89: 8852b: implement chip_ops::{enable,disable}_bb_rf
wifi: rtw89: add DMA busy checking bits to chip info
wifi: rtw89: mac: define DMA channel mask to avoid unsupported channels
wifi: rtw89: pci: mask out unsupported TX channels
iwlegacy: Replace zero-length arrays with DECLARE_FLEX_ARRAY() helper
ipw2x00: Replace zero-length array with DECLARE_FLEX_ARRAY() helper
wifi: iwlwifi: Track scan_cmd allocation size explicitly
brcmfmac: Remove the call to "dtim_assoc" IOVAR
brcmfmac: increase dcmd maximum buffer size
brcmfmac: Support 89459 pcie
brcmfmac: increase default max WOWL patterns to 16
cw1200: fix incorrect check to determine if no element is found in list
...
====================
Link: https://lore.kernel.org/r/20220930150413.A7984C433D6@smtp.kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Saeed Mahameed says:
====================
mlx5 xsk updates part2 2022-09-28
XSK buffer improvements, This is part #2 of 4 parts series.
1) Expose xsk min chunk size to drivers, to allow the driver to adjust to a
better buffer stride size
2) Adjust MTT page size to the XSK frame size, to avoid umem overrun in
certain situations.
3) Use xsk frame size as the striding RQ page size for XSK RQs
4) KSM for unaligned XSK, KSM allows arbitrary buffer chunk lengths
registration in HW, which makes more sense for unaligned XSK.
4) More cleanups and optimizations in preparation for next improvements
in part3
part 1: https://lore.kernel.org/netdev/20220927203611.244301-1-saeed@kernel.org/
====================
Link: https://lore.kernel.org/r/20220929072156.93299-1-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Although mlx5e_rq_free_shampo can be called unconditionally, it belongs
to case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ. Move it there to allow to
add more init/cleanup actions to the striding RQ case.
If xdp_rxq_info_reg_mem_model fails, don't forget to destroy the page
pool.
Signed-off-by: Maxim Mikityanskiy <maximmi@nvidia.com>
Reviewed-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The same clear_bit is called in both error and success flows. Move the
call to do it only once and remove the out label.
Signed-off-by: Maxim Mikityanskiy <maximmi@nvidia.com>
Reviewed-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
To decrease the nesting level and reduce duplication of code, create
functions to redirect direct RQTs to the actual RQs or drop_rq, which
are used in the activation and deactivation flows of channels.
Signed-off-by: Maxim Mikityanskiy <maximmi@nvidia.com>
Reviewed-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
mlx5e_xsk_page_alloc_pool became a thin wrapper around xsk_buff_alloc.
Drop it and call xsk_buff_alloc directly.
Signed-off-by: Maxim Mikityanskiy <maximmi@nvidia.com>
Reviewed-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
struct mlx5e_alloc_unit consists of a single union. Convert it to a
union itself to simplify casting it to struct xdp_buff *, which will be
used to implement XSK batching on striding RQ.
Signed-off-by: Maxim Mikityanskiy <maximmi@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
mlx5e_alloc_unit stores the DMA address and a pointer to either struct
page (regular RQ) or struct xdp_buff (XSK RQ). This DMA address is
redundant, because when a page or an XSK frame is allocated, the same
address is also stored there. Some flows take the address from struct
mlx5e_alloc_unit, and some take it from struct page or xdp_buff.
This commit removes the address from struct mlx5e_alloc_unit, which
makes it twice as small and improves locality (this struct is used in an
array), also saving on unnecessary stores to the addr field. Almost all
flows know unambiguously whether the DMA address should be taken from
page or from xdp_buff. The exception is the allocation flows, where a
new branch appeared, which will be optimized out in the next commits.
struct mlx5e_alloc_unit used to be called mlx5e_dma_info.
Signed-off-by: Maxim Mikityanskiy <maximmi@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The next commit will remove the DMA address from the struct currently
called mlx5e_dma_info, because the same value can be retrieved with
page_pool_get_dma_addr(page) in almost all cases, with the notable
exception of SHAMPO (HW GRO implementation) that modifies this address
on the fly, after the initial allocation.
To keep the SHAMPO logic intact, struct mlx5e_dma_info remains in the
SHAMPO code, consisting of addr and page (XSK is not compatible with
SHAMPO). The struct used in all other places is renamed to
mlx5e_alloc_unit, allowing the next commit to remove the addr field
without affecting SHAMPO.
The new name means "allocation unit", and it's more appropriate after
the field with the DMA address gets removed.
Signed-off-by: Maxim Mikityanskiy <maximmi@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
RX page cache stores dma_info structs, that consist of a pointer to
struct page and a DMA address. In fact, the DMA address is extracted
from struct page using page_pool_get_dma_addr when a page is pushed to
the cache. By moving this call to the point when a page is popped from
the cache, we can avoid storing the DMA address in the cache,
effectively reducing its size by two times without losing any
functionality.
Signed-off-by: Maxim Mikityanskiy <maximmi@nvidia.com>
Reviewed-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
WQEs must not cross page boundaries, they are padded with NOPs if they
don't fit the page. mlx5e_mpwrq_total_umr_wqebbs doesn't take into
account this padding, risking reserving not enough space.
The padding is not straightforward to add to this calculation, because
WQEs of different sizes may be mixed together in the queue. If each page
ends with a big WQE that doesn't fit and requires at most its size minus
1 WQEBB of padding, the total space can be much bigger than in case when
smaller WQEs take advantage of this padding.
Replace the wrong exact calculation by the following estimation. Each
padding can be at most the size of the maximum WQE used in the queue
minus one WQEBB. Let's call the rest of the page "useful space". If we
divide the total size of all needed WQEs by this useful space, rounding
up, we'll get the number of pages, which is enough to contain all these
WQEs. It's correct, because every WQE that appeared on the boundary
between two blocks of useful space would start in the useful space of
one page and end in the padding of the same page, while our estimation
reserved space for its tail in the next space, making the estimation not
smaller than the real space occupied in the queue.
The code actually uses a looser estimation: instead of taking the
maximum size of all used WQE types minus 1 WQEBB, it takes the maximum
hardware size of a WQE. It's made for simplicity and extensibility.
Signed-off-by: Maxim Mikityanskiy <maximmi@nvidia.com>
Reviewed-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The previous commit removed the last usage of xsk_buff_discard in mlx5e,
so the function that is no longer used can be removed.
Signed-off-by: Maxim Mikityanskiy <maximmi@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
CC: "Björn Töpel" <bjorn@kernel.org>
CC: Magnus Karlsson <magnus.karlsson@intel.com>
CC: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
UMR MTTs used in striding RQ have certain alignment requirements. While
it's guaranteed to work when UMR pages are aligned to the UMR page size,
in practice it works then UMR pages are aligned to 8 bytes. However,
it's still not enough flexibility for the unaligned mode of XSK. This
patch leverages KSM to map UMR pages without alignment requirements,
when unaligned XSK is active. The downside is that KSM entries are twice
as big as MTTs, which limits the maximum WQE size, so regular RQs and
aligned XSK continue using MTTs.
Signed-off-by: Maxim Mikityanskiy <maximmi@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Ilan Peer