- 20 Oct, 2021 40 commits
-
-
Ryder Lee authored
Beacon elements might be changed by hostapd configuraion, so driver should compare both IEs and PHY capabilities to get the least common denominator before association. Co-developed-by:
Evelyn Tsai <evelyn.tsai@mediatek.com> Signed-off-by:
Ryder Lee <ryder.lee@mediatek.com> Signed-off-by:
Shayne Chen <shayne.chen@mediatek.com> Signed-off-by:
Felix Fietkau <nbd@nbd.name>
-
Lorenzo Bianconi authored
Fix the following NULL pointer dereference in mt76_connac_get_phy_mode_v2 routine triggered on mt7663s device when sta is NULL [ 5.490700] mt7663s mmc0:0001:1: N9 Firmware Version: 3.1.1, Build Time: 20200604161656 [ 5.490815] mt7663s mmc0:0001:1: Region number: 0x4 [ 5.490868] mt7663s mmc0:0001:1: Parsing tailer Region: 0 [ 5.496251] mt7663s mmc0:0001:1: Region 0, override_addr = 0x00118000 [ 5.496419] mt7663s mmc0:0001:1: Parsing tailer Region: 1 [ 5.624027] mt7663s mmc0:0001:1: Parsing tailer Region: 2 [ 5.656999] mt7663s mmc0:0001:1: Parsing tailer Region: 3 [ 5.671876] mt7663s mmc0:0001:1: override_addr = 0x00118000, option = 3 [ 9.358658] BUG: kernel NULL pointer dereference, address: 0000000000000000 [ 9.358775] #PF: supervisor read access in kernel mode [ 9.358831] #PF: error_code(0x0000) - not-present page [ 9.358886] PGD 0 P4D 0 [ 9.358917] Oops: 0000 [#1] SMP [ 9.358960] CPU: 0 PID: 235 Comm: NetworkManager Not tainted 5.15.0-rc4-kvm-02151-g39e333d657f4-dirty #769 [ 9.359057] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.14.0-4.fc34 04/01/2014 [ 9.359150] RIP: 0010:mt76_connac_get_phy_mode_v2+0xc9/0x11c [ 9.359473] RAX: 0000000000000013 RBX: 0000000000000000 RCX: 0000000000000027 [ 9.359546] RDX: ffff8881f9c17358 RSI: 0000000000000001 RDI: ffff8881f9c17350 [ 9.359624] RBP: ffff88810bac1ed4 R08: ffffffff822a4a48 R09: 0000000000000003 [ 9.359697] R10: ffffffff82234a60 R11: ffffffff82234a60 R12: ffff88810bac1eec [ 9.359779] R13: 0000000000000000 R14: ffff88810bad1648 R15: ffff88810bac1eb8 [ 9.359859] FS: 00007f5f1e45bbc0(0000) GS:ffff8881f9c00000(0000) knlGS:0000000000000000 [ 9.359939] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 9.360003] CR2: 0000000000000000 CR3: 0000000105d5d000 CR4: 00000000000006b0 [ 9.360083] Call Trace: [ 9.360116] mt76_connac_mcu_uni_add_bss.cold+0x21/0x250 [ 9.360175] ? schedule_preempt_disabled+0xa/0x10 [ 9.360232] ? __mutex_lock.constprop.0+0x2ab/0x460 [ 9.360286] mt7615_remove_interface+0x63/0x1d0 [ 9.360342] drv_remove_interface+0x32/0xe0 [ 9.360385] ieee80211_do_stop+0x5da/0x800 [ 9.360428] ? dev_reset_queue+0x30/0x90 [ 9.360472] ieee80211_stop+0x3b/0xb0 [ 9.360516] __dev_close_many+0x7a/0xd0 [ 9.360559] __dev_change_flags+0xd6/0x1f0 [ 9.360604] dev_change_flags+0x21/0x60 [ 9.360648] do_setlink+0x259/0xfb0 [ 9.360686] ? __nla_validate_parse+0x51/0xb80 [ 9.360742] __rtnl_newlink+0x5b3/0x960 [ 9.360785] ? inet6_fill_ifla6_attrs+0x41d/0x470 [ 9.360841] ? __kmalloc_track_caller+0x57/0x3c0 [ 9.360905] ? netlink_trim+0x8a/0xb0 [ 9.360949] ? skb_queue_tail+0x1b/0x50 Fixes: 67aa2743 ("mt76: mt7921: rely on mt76_connac_mcu common library") Signed-off-by:
Lorenzo Bianconi <lorenzo@kernel.org> Signed-off-by:
-
Felix Fietkau authored
Avoids false positive on detecting frags or encrypted mgmt frames Signed-off-by: -
Xing Song authored
When received frame is decryped by hardware, CCMP PN is checked by mt76. When management frame protection (IEEE 802.11w) is used, we must use a separate counter for tracking received CCMP packet number for the management frames. The previously used counter was shared with data frames and that can cause problems in detecting replays incorrectly for robust management frames. Add a new counter just for robust management frames to avoid this issue. Signed-off-by:
Xing Song <xing.song@mediatek.com> Signed-off-by:
-
Deren Wu authored
Add a delay parameter for firmware to support delay scheduled scan. Signed-off-by:
Deren Wu <deren.wu@mediatek.com> Signed-off-by:
-
Ryder Lee authored
[ 103.451600] CPU 3 Unable to handle kernel paging request at virtual address 00000003, epc == 8576591c, ra == 857659f0 [ 103.462226] Oops[#1]: [ 103.464499] CPU: 3 PID: 9247 Comm: ifconfig Tainted: G W 5.4.143 #0 [ 103.472031] $ 0 : 00000000 00000001 83be3854 00000000 [ 103.477239] $ 4 : 8102a374 8102a374 8102f0b0 00000200 [ 103.482444] $ 8 : 0000002d 000001e4 64373765 5d206337 [ 103.487647] $12 : 00000000 00000005 00000000 0006d1df [ 103.492853] $16 : 83be3848 853838a8 8743d600 00010000 [ 103.498059] $20 : 00000000 00000000 8553dec0 0000007f [ 103.503266] $24 : 00000003 80382084 [ 103.508472] $28 : 831d4000 831d5bc0 00000001 857659f0 [ 103.513678] Hi : 00000122 [ 103.516543] Lo : d1768000 [ 103.519452] epc : 8576591c mt7615_mcu_add_bss+0xd0/0x3c0 [mt7615_common] [ 103.526306] ra : 857659f0 mt7615_mcu_add_bss+0x1a4/0x3c0 [mt7615_common] [ 103.533232] Status: 11007c03 KERNEL EXL IE [ 103.537402] Cause : 40800008 (ExcCode 02) [ 103.541389] BadVA : 00000003 [ 103.544253] PrId : 0001992f (MIPS 1004Kc) [ 103.797086] Call Trace: [ 103.799562] [<8576591c>] mt7615_mcu_add_bss+0xd0/0x3c0 [mt7615_common] [ 103.806082] [<85760a14>] mt7615_remove_interface+0x74/0x1e0 [mt7615_common] [ 103.813280] [<85603fcc>] drv_remove_interface+0x2c/0xa0 [mac80211] [ 103.819612] [<8561a8e4>] ieee80211_del_virtual_monitor.part.22+0x74/0xe8 [mac80211] [ 103.827410] [<8561b7f0>] ieee80211_do_stop+0x4a4/0x8a0 [mac80211] [ 103.833671] [<8561bc00>] ieee80211_stop+0x14/0x24 [mac80211] [ 103.839405] [<8045a328>] __dev_close_many+0x9c/0x10c [ 103.844364] [<80463de4>] __dev_change_flags+0x16c/0x1e4 [ 103.849569] [<80463e84>] dev_change_flags+0x28/0x70 [ 103.854440] [<80521e54>] devinet_ioctl+0x280/0x774 [ 103.859222] [<80526248>] inet_ioctl+0xa4/0x1c8 [ 103.863674] [<80436830>] sock_ioctl+0x2d8/0x4bc [ 103.868201] [<801adbb4>] do_vfs_ioctl+0xb8/0x7c0 [ 103.872804] [<801ae30c>] ksys_ioctl+0x50/0xb4 [ 103.877156] [<80014598>] syscall_common+0x34/0x58 Fixes: 04b8e659 ("mt76: add mac80211 driver for MT7615 PCIe-based chipsets") Signed-off-by:
-
Lorenzo Bianconi authored
Improve {xmit,rx}-queue debugfs node readability Signed-off-by: -
Lorenzo Bianconi authored
Introduce twt_stats knob in debugfs in order to dump established agreements Tested-by:
Peter Chiu <chui-hao.chiu@mediatek.com> Tested-by:
-
Lorenzo Bianconi authored
Enable TWT support in AP mode Tested-by:
-
Lorenzo Bianconi authored
Introduce individual TWT support to mt7915 in AP mode. Implement the two following mac80211 callbacks: - add_twt_setup - twt_teardown_request Tested-by:
-
Lorenzo Bianconi authored
This is a preliminary patch to add TWT support to mt7915 Tested-by:
-
Lorenzo Bianconi authored
Introduce an unlocked verion of mt7915_get_tsf routine. This is a preliminary patch to add TWT support to mt7915. Tested-by:
-
Sean Wang authored
Each firmware piece with mt7915 and mt7921 do not have the MCU header to reroute the packet to the internal RAM. So we do not need to consider the MCU header size in __mt76_mcu_send_firmware. Move the MCU header overhead calculation to mt76_mcu_send_firmware (for older chipsets) Fixes: e57b7901 ("mt76: add mac80211 driver for MT7915 PCIe-based chipsets") Fixes: 1c099ab4 ("mt76: mt7921: add MCU support") Signed-off-by:
Sean Wang <sean.wang@mediatek.com> Signed-off-by:
-
Lorenzo Bianconi authored
Introduce __mt76_mcu_send_firmware routine to specify mcu message max length. This is a preliminary patch to support mt7921s driver. Co-developed-by:
-
Daniel Golle authored
EEPROM data for mt76 can be embedded into device-tree as an array. Signed-off-by:
Daniel Golle <daniel@makrotopia.org> Acked-by:
Rob Herring <robh@kernel.org> Signed-off-by:
-
Daniel Golle authored
Some platforms boot from SD card and don't come with calibration data stored anywhere on the board. As EEPROM data is rather small it can be embedded into the device tree to be loaded from there by the mt76. Signed-off-by:
-
Lorenzo Bianconi authored
Reduce MT_TX_STATUS_SKB_TIMEOUT to 250ms Tested-by: mrkiko.rs@gmail.com Co-developed-by:
Ben Greear <greearb@candelatech.com> Signed-off-by:
-
Lorenzo Bianconi authored
Substitute sk_buff_head status_list with spinlock_t status_lock since we just need it for locking Tested-by: mrkiko.rs@gmail.com Signed-off-by:
-
Lorenzo Bianconi authored
Remove mt76_wcid pointer from mt76_tx_status_check signature since it is always set to NULL Tested-by: mrkiko.rs@gmail.com Signed-off-by:
-
Lorenzo Bianconi authored
Introduce per-wcid idr to manage packet id for txs. This allow fast idr lookup and skb queueing at the same time. Tested-by: mrkiko.rs@gmail.com Signed-off-by:
-
Lorenzo Bianconi authored
Unlock 6GHz band if supported by the device. Configure HE 6G capabilities. Tested-by:
-
Lorenzo Bianconi authored
Introduce 6GHz channel list in mt76 module. This is a preliminary patch to unlock 6GHz band for mt7921 devices. Tested-by:
-
Lorenzo Bianconi authored
This is a preliminary patch to enable 6GHz band for mt7921 devices. Tested-by:
-
Lorenzo Bianconi authored
This is a preliminary patch to enable 6GHz band for mt7921 devices. Tested-by:
-
Lorenzo Bianconi authored
Introduce sta_rec_he_6g_capa tlv in order configure the mcu with 6GHz capabilities. This is a preliminary patch to enable 6GHz band for mt7921 devices. Tested-by:
-
Lorenzo Bianconi authored
Configure tx rate power for 6GHz channels. This is a preliminary patch to enable 6GHz band for mt7921 devices. Tested-by:
-
Lorenzo Bianconi authored
Configure 6GHz channels defining mcu channel domain. This is a preliminary patch to enable 6GHz band on mt7921 devices. Tested-by:
-
Lorenzo Bianconi authored
This is a preliminary patch to support 6GHz band on mt7921 devices. Tested-by:
-
Lorenzo Bianconi authored
This is a preliminary patch to support 6GHz band on mt7921 devices. Tested-by:
-
Ben Greear authored
This adds the new mib counters from last patch into ethtool stats. Signed-off-by:
-
Ben Greear authored
Add register definitions and read & accumulate them in the mib polling logic. Note that some registers should not be read since firmware is already reading them. If driver reads those, they will be cleared-on-read, and so the firmware stats will be incorrect. For these 'do-not-read' stats, add them to the registers definition so that other developers can be aware of these constraints, but do not actually read them in the driver. Signed-off-by:
-
Ben Greear authored
These counters are clear-on-read, so we need to accumulate them in the update_stats poll logic, and read the accumulated values instead of directly doing register reads when reporting to debugfs and ethtool stats. Signed-off-by:
-
Ben Greear authored
The tx status callback is not called for every frame, so those specific counters under-count, but at least they give some idea of what is going on. Signed-off-by:
-
Ben Greear authored
Add tx-mode (ofdma, ht, vht, HE) histogram, tx-ru-idx histogram, and tx-bandwidth histogram. Also add tx attempts and tx success counters. All of this is per-station. Signed-off-by:
-
Ben Greear authored
This exposes some tx-path stats to the ethtool API, so that ethtool -S wlanX provides some more useful info. Signed-off-by:
-
Sean Wang authored
We should pass the error code to the caller immediately to avoid the possible infinite retry to release the semaphore. Fixes: 1c099ab4 ("mt76: mt7921: add MCU support") Co-developed-by:
YN Chen <YN.Chen@mediatek.com> Signed-off-by:
-
Sean Wang authored
Robustify hardware initialization in the current driver probing flow to get rid of the device is possibly lost after the machine boot due to possible firmware abnormal state by trying to recover the failure with more chances. Tested-by:
Leon Yen <Leon.Yen@mediatek.com> Tested-by:
-
Lorenzo Bianconi authored
Fix possible infinite loop in mt7915_load_patch if mt7915_mcu_patch_sem_ctrl always returns an error. Fixes: e57b7901 ("mt76: add mac80211 driver for MT7915 PCIe-based chipsets") Signed-off-by:
-
Lorenzo Bianconi authored
Check all possible errors returned in mt7915_mcu_init routine. Signed-off-by:
-
Xingbang Liu authored
as you are already in a tasklet, it is unnecessary to call spin_lock_bh. Signed-off-by:
Xingbang Liu <liu.airalert@gmail.com> Signed-off-by:
-
