- 20 Oct, 2021 40 commits
-
-
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 <greearb@candelatech.com> Signed-off-by:
Felix Fietkau <nbd@nbd.name>
-
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 <sean.wang@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 <lorenzo@kernel.org> 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:
-
Lorenzo Bianconi authored
mt7921_sta_stats is no longer needed Signed-off-by:
-
Lorenzo Bianconi authored
Remove unused tx rate reporting through mcu tx done event since now tx status is fully supported Signed-off-by:
-
Lorenzo Bianconi authored
Report tx rate from tx status packets instead of receiving periodic mcu event. This improves flexibility, accuracy and AQL performance, and simplifies code flow for better readability. Signed-off-by:
-
Lorenzo Bianconi authored
Introduce infrastructure support for tx status reporting Signed-off-by:
-
Lorenzo Bianconi authored
Similar to mt7915, introduce mt7921_txwi_free to report tx rate to mac80211. This is a preliminary patch to add proper tx status report. Signed-off-by:
-
Ryder Lee authored
Without this change, garbage is seen in the hwmon name and sensors output for mt7615 is garbled. Fixes: 109e505a ("mt76: mt7615: add thermal sensor device support") Signed-off-by:
Ryder Lee <ryder.lee@mediatek.com> Signed-off-by:
-
Ben Greear authored
Without this change, garbage is seen in the hwmon name and sensors output for mt7915 is garbled. It appears that the hwmon logic does not make a copy of the incoming string, but instead just copies a char* and expects it to never go away. Fixes: 33fe9c63 ("mt76: mt7915: add thermal sensor device support") Signed-off-by:
-
Ryder Lee authored
The user is allowed to change beacon tx rate (HT/VHT/HE) from hostapd. Signed-off-by:
-
Felix Fietkau authored
napi_schedule() can call __raise_softirq_irqoff(), which can perform softirq handling, so it must not be called in a pure process context with BH enabled. Signed-off-by: -
Ryder Lee authored
Give a proper boottime_ns value for netlink RX to avoid scan issues with Android. Signed-off-by:
-
Christophe JAILLET authored
The wrappers in include/linux/pci-dma-compat.h should go away. The patch has been generated with the coccinelle script below. It has been compile tested. @@ @@ - PCI_DMA_BIDIRECTIONAL + DMA_BIDIRECTIONAL @@ @@ - PCI_DMA_TODEVICE + DMA_TO_DEVICE @@ @@ - PCI_DMA_FROMDEVICE + DMA_FROM_DEVICE @@ @@ - PCI_DMA_NONE + DMA_NONE @@ expression e1, e2, e3; @@ - pci_alloc_consistent(e1, e2, e3) + dma_alloc_coherent(&e1->dev, e2, e3, GFP_) @@ expression e1, e2, e3; @@ - pci_zalloc_consistent(e1, e2, e3) + dma_alloc_coherent(&e1->dev, e2, e3, GFP_) @@ expression e1, e2, e3, e4; @@ - pci_free_consistent(e1, e2, e3, e4) + dma_free_coherent(&e1->dev, e2, e3, e4) @@ expression e1, e2, e3, e4; @@ - pci_map_single(e1, e2, e3, e4) + dma_map_single(&e1->dev, e2, e3, e4) @@ expression e1, e2, e3, e4; @@ - pci_unmap_single(e1, e2, e3, e4) + dma_unmap_single(&e1->dev, e2, e3, e4) @@ expression e1, e2, e3, e4, e5; @@ - pci_map_page(e1, e2, e3, e4, e5) + dma_map_page(&e1->dev, e2, e3, e4, e5) @@ expression e1, e2, e3, e4; @@ - pci_unmap_page(e1, e2, e3, e4) + dma_unmap_page(&e1->dev, e2, e3, e4) @@ expression e1, e2, e3, e4; @@ - pci_map_sg(e1, e2, e3, e4) + dma_map_sg(&e1->dev, e2, e3, e4) @@ expression e1, e2, e3, e4; @@ - pci_unmap_sg(e1, e2, e3, e4) + dma_unmap_sg(&e1->dev, e2, e3, e4) @@ expression e1, e2, e3, e4; @@ - pci_dma_sync_single_for_cpu(e1, e2, e3, e4) + dma_sync_single_for_cpu(&e1->dev, e2, e3, e4) @@ expression e1, e2, e3, e4; @@ - pci_dma_sync_single_for_device(e1, e2, e3, e4) + dma_sync_single_for_device(&e1->dev, e2, e3, e4) @@ expression e1, e2, e3, e4; @@ - pci_dma_sync_sg_for_cpu(e1, e2, e3, e4) + dma_sync_sg_for_cpu(&e1->dev, e2, e3, e4) @@ expression e1, e2, e3, e4; @@ - pci_dma_sync_sg_for_device(e1, e2, e3, e4) + dma_sync_sg_for_device(&e1->dev, e2, e3, e4) @@ expression e1, e2; @@ - pci_dma_mapping_error(e1, e2) + dma_mapping_error(&e1->dev, e2) @@ expression e1, e2; @@ - pci_set_dma_mask(e1, e2) + dma_set_mask(&e1->dev, e2) @@ expression e1, e2; @@ - pci_set_consistent_dma_mask(e1, e2) + dma_set_coherent_mask(&e1->dev, e2) Signed-off-by:
Christophe JAILLET <christophe.jaillet@wanadoo.fr> Signed-off-by:
-
jing yangyang authored
./drivers/net/wireless/mediatek/mt76/mt7615/usb_sdio.c:172:8-9:WARNING: return of 0/1 in function 'mt7663_usb_sdio_tx_status_data' with return type bool Return statements in functions returning bool should use true/false instead of 1/0. Generated by: scripts/coccinelle/misc/boolreturn.cocci Reported-by:
Zeal Robot <zealci@zte.com.cn> Signed-off-by:
jing yangyang <jing.yangyang@zte.com.cn> Signed-off-by:
-
Lorenzo Bianconi authored
mt7921 mac work can be idle for a long time due to runtime-pm so update mib counters dumping phy stats Signed-off-by:
-
Lorenzo Bianconi authored
Add missing device wakeup in debugfs code if we are accessing chip registers. Fixes: 1d8efc74 ("mt76: mt7921: introduce Runtime PM support") Signed-off-by:
-
Ryder Lee authored
Rename "queues" to "tx-queues" to reflect its meaning. Signed-off-by:
-
Ryder Lee authored
Complete PSE/PLE queue statistics, including per-sta AC queue information. Co-developed-by:
Sujuan Chen <sujuan.chen@mediatek.com> Signed-off-by:
-
Lorenzo Bianconi authored
As for 7915 moving mt7921_queue_rx_skb makes it possible to make some functions in mac.c static Signed-off-by:
-
Felix Fietkau authored
WMM index range needs to be split between both PHYs if a second PHY exists. The condition for that was accidentally written as checking if the vif PHY is the secondary one Signed-off-by: -
Lorenzo Bianconi authored
Even if it is a not real issue, add missing brackets in mt7915_mcu_sta_bfer_ht routine in order to improve code readability Signed-off-by:
-
Lorenzo Bianconi authored
Introduce mcu APIs to configure bss coloring and to report bss coloring collisions. Add support to report coloring countdown in beacon sent by the device. Co-developed-by:
-
MeiChia Chiu authored
Initialize brightness_set and blink_set callbacks to enable LED support. The base 0x7c000000 is MCU space so driver can't touch it, and should map the LED base to 0x18000000 host's view. Signed-off-by:
MeiChia Chiu <meichia.chiu@mediatek.com> Signed-off-by:
Money Wang <money.wang@mediatek.com> Signed-off-by:
-
Ben Greear authored
If skb is null, then don't try to dereference it. Signed-off-by:
-
Ben Greear authored
At 160, this chip can only do 2x2 NSS. Fix the features accordingly, verified it shows up properly in iw phy foo info now. Signed-off-by:
-
Ryder Lee authored
Drop MT_DRV_AMSDU_OFFLOAD after introducing IEEE80211_OFFLOAD_ENCAP_ENABLED flag in mac80211. Driver now checks vif->offload_flags to know encap offload status of each interface. Signed-off-by:
-
Ryder Lee authored
1. EIFS has been divided into OFDM/CCK fields after 11ax generation. 2. For 5G/6G SIFS setting, hardware counts extra 6us for OFDM. Signed-off-by:
-
Lorenzo Bianconi authored
Fix the following sparse endianness warnings drivers/net/wireless/mediatek/mt76/mt7921/mac.c:212:28: warning: cast from restricted __le32 drivers/net/wireless/mediatek/mt76/mt7921/mac.c:212:28: warning: cast to restricted __le32 drivers/net/wireless/mediatek/mt76/mt7921/mac.c:212:28: warning: restricted __le32 degrades to integer drivers/net/wireless/mediatek/mt76/mt7921/mac.c:212:28: warning: cast from restricted __le32 drivers/net/wireless/mediatek/mt76/mt7921/mac.c:212:28: warning: restricted __le32 degrades to integer drivers/net/wireless/mediatek/mt76/mt7921/mac.c:217:25: warning: cast from restricted __le32 drivers/net/wireless/mediatek/mt76/mt7921/mac.c:217:25: warning: restricted __le32 degrades to integer drivers/net/wireless/mediatek/mt76/mt7921/mac.c:217:25: warning: cast from restricted __le32 drivers/net/wireless/mediatek/mt76/mt7921/mac.c:217:25: warning: restricted __le32 degrades to integer drivers/net/wireless/mediatek/mt76/mt7921/mac.c:222:25: warning: cast from restricted __le32 drivers/net/wireless/mediatek/mt76/mt7921/mac.c:222:25: warning: cast to restricted __le32 drivers/net/wireless/mediatek/mt76/mt7921/mac.c:222:25: warning: restricted __le32 degrades to integer drivers/net/wireless/mediatek/mt76/mt7921/mac.c:222:25: warning: cast from restricted __le32 drivers/net/wireless/mediatek/mt76/mt7921/mac.c:222:25: warning: restricted __le32 degrades to integer drivers/net/wireless/mediatek/mt76/mt7921/mac.c:224:25: warning: cast from restricted __le32 drivers/net/wireless/mediatek/mt76/mt7921/mac.c:224:25: warning: cast to restricted __le32 drivers/net/wireless/mediatek/mt76/mt7921/mac.c:224:25: warning: restricted __le32 degrades to integer drivers/net/wireless/mediatek/mt76/mt7921/mac.c:224:25: warning: cast from restricted __le32 drivers/net/wireless/mediatek/mt76/mt7921/mac.c:224:25: warning: restricted __le32 degrades to integer drivers/net/wireless/mediatek/mt76/mt7921/mac.c:259:13: warning: cast from restricted __le32 drivers/net/wireless/mediatek/mt76/mt7921/mac.c:259:13: warning: restricted __le32 degrades to integer Signed-off-by:
-
Sean Wang authored
Fix the kernel warning from cfg80211_calculate_bitrate due to the legacy rate is not parsed well in the current driver. Also, zeros struct rate_info before we fill it out to avoid the old value is kept such as rate->legacy. [ 790.921560] WARNING: CPU: 7 PID: 970 at net/wireless/util.c:1298 cfg80211_calculate_bitrate+0x354/0x35c [cfg80211] [ 790.987738] Hardware name: MediaTek Asurada rev1 board (DT) [ 790.993298] pstate: a0400009 (NzCv daif +PAN -UAO) [ 790.998104] pc : cfg80211_calculate_bitrate+0x354/0x35c [cfg80211] [ 791.004295] lr : cfg80211_calculate_bitrate+0x180/0x35c [cfg80211] [ 791.010462] sp : ffffffc0129c3880 [ 791.013765] x29: ffffffc0129c3880 x28: ffffffd38305bea8 [ 791.019065] x27: ffffffc0129c3970 x26: 0000000000000013 [ 791.024364] x25: 00000000000003ca x24: 000000000000002f [ 791.029664] x23: 00000000000000d0 x22: ffffff8d108bc000 [ 791.034964] x21: ffffff8d108bc0d0 x20: ffffffc0129c39a8 [ 791.040264] x19: ffffffc0129c39a8 x18: 00000000ffff0a10 [ 791.045563] x17: 0000000000000050 x16: 00000000000000ec [ 791.050910] x15: ffffffd3f9ebed9c x14: 0000000000000006 [ 791.056211] x13: 00000000000b2eea x12: 0000000000000000 [ 791.061511] x11: 00000000ffffffff x10: 0000000000000000 [ 791.066811] x9 : 0000000000000000 x8 : 0000000000000000 [ 791.072110] x7 : 0000000000000000 x6 : ffffffd3fafa5a7b [ 791.077409] x5 : 0000000000000000 x4 : 0000000000000000 [ 791.082708] x3 : 0000000000000000 x2 : 0000000000000000 [ 791.088008] x1 : ffffff8d3f79c918 x0 : 0000000000000000 [ 791.093308] Call trace: [ 791.095770] cfg80211_calculate_bitrate+0x354/0x35c [cfg80211] [ 791.101615] nl80211_put_sta_rate+0x6c/0x2c0 [cfg80211] [ 791.106853] nl80211_send_station+0x980/0xaa4 [cfg80211] [ 791.112178] nl80211_get_station+0xb4/0x134 [cfg80211] [ 791.117308] genl_rcv_msg+0x3a0/0x440 [ 791.120960] netlink_rcv_skb+0xcc/0x118 [ 791.124785] genl_rcv+0x34/0x48 [ 791.127916] netlink_unicast+0x144/0x1dc Fixes: 1c099ab4 ("mt76: mt7921: add MCU support") Signed-off-by:
-
Sean Wang authored
According to the firmware usage, OFDM rates should fill out bit 6 - 13 while CCK rates should fill out bit 0 - 3 in legacy field of RA info to make the rate adaption runs propertly. Otherwise, a unicast frame might be picking up the unsupported rate to send out. Fixes: 1c099ab4 ("mt76: mt7921: add MCU support") Reported-by:
Joshua Emele <jemele@chromium.org> Co-developed-by:
-
Ryder Lee authored
Add HE-LTF control. Signed-off-by:
Shayne Chen <shayne.chen@mediatek.com> Signed-off-by:
-
Sean Wang authored
Report HE MU/BF radiotap. That fixed HE MU packets dropped by mac80211 because they are missing the ieee80211_radiotap_he_mu header. Fixes: 163f4d22 ("mt76: mt7921: add MAC support") Co-developed-by:
Eric-SY Chang <Eric-SY.Chang@mediatek.com> Signed-off-by:
-
