kernel/drivers/net/wireless/ath/ath11k/hal.h, branch linux-6.2.y

wifi: ath11k: Fix kernel-doc issues

2022-09-16T09:20:35Z

Fix documentation issues reported by kernel-doc: - Incorrect use of /** for non-kernel-doc comments - Mismatch between documented and actual identifiers - Incorrect identifier syntax Signed-off-by: Jeff Johnson Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20220909151246.22961-1-quic_jjohnson@quicinc.com

wifi: ath11k: Fix miscellaneous spelling errors

2022-09-16T09:19:14Z

Fix misspellings flagged by 'codespell'. Signed-off-by: Jeff Johnson Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20220909145535.20437-1-quic_jjohnson@quicinc.com

wifi: ath11k: Add multi TX ring support for WCN6750

2022-09-10T06:27:54Z

Currently in the case of WCN6750, only one TCL ring is used for TX, this is limiting the TX throughput in 160 MHz case, enabling multiple TCL rings on WCN6750 has shown an improvement of nearly 300 Mbps in the case of TCP TX, therefore add the support of multi TX ring for WCN6750. Currently TCL ring is selected based on CPU ID, this logic cannot be applied for WCN6750 as there is chance of out of order TX of packets and to avoid this, choose TCL ring based on flow hash so that packets of the same flow will end up on same TCL ring. For the same reason, TCL ring retry logic is also not applicable for WCN6750. Also the mapping of TCL, WBM & RBM IDs for WCN6750 is different from existing devices. Create a new TCM/WBM/RBM mapping for WCN6750. Change does not impact existing ath11k devices. Tested-on: WCN6750 hw1.0 AHB WLAN.MSL.1.0.1-00887-QCAMSLSWPLZ-1 Signed-off-by: Manikanta Pubbisetty Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20220905071805.31625-3-quic_mpubbise@quicinc.com

ath11k: Fix RX de-fragmentation issue on WCN6750

2022-05-06T06:20:12Z

The offset of REO register where the RX fragment destination ring is configured is different in WCN6750 as compared to WCN6855. Due to this differnce in offsets, on WCN6750, fragment destination ring will be configured incorrectly, leading to RX fragments not getting delivered to the driver. Fix this by defining HW specific offsets for the REO MISC CTL register. Tested-on: WCN6750 hw1.0 AHB WLAN.MSL.1.0.1-00887-QCAMSLSWPLZ-1 Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-01720.1-QCAHSPSWPL_V1_V2_SILICONZ_LITE-1 Tested-on: QCN9074 hw1.0 PCI WLAN.HK.2.5.0.1-01100-QCAHKSWPL_SILICONZ-1 Tested-on: IPQ8074 hw2.0 AHB WLAN.HK.2.4.0.1-00192-QCAHKSWPL_SILICONZ-1 Signed-off-by: Manikanta Pubbisetty Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20220504083900.31513-1-quic_mpubbise@quicinc.com

ath11k: HAL changes to support WCN6750

2022-05-02T13:59:07Z

Add HAL changes required to support WCN6750. Offsets of some registers for WCN6750 are different from other supported devices; move such register offsets to platform specific ath11k_hw_regs. Tested-on: WCN6750 hw1.0 AHB WLAN.MSL.1.0.1-00887-QCAMSLSWPLZ-1 Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-01720.1-QCAHSPSWPL_V1_V2_SILICONZ_LITE-1 Tested-on: QCN9074 hw1.0 PCI WLAN.HK.2.5.0.1-01100-QCAHKSWPL_SILICONZ-1 Tested-on: IPQ8074 hw2.0 AHB WLAN.HK.2.4.0.1-00192-QCAHKSWPL_SILICONZ-1 Signed-off-by: Manikanta Pubbisetty Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20220429170502.20080-8-quic_mpubbise@quicinc.com

ath11k: Avoid false DEADLOCK warning reported by lockdep

2021-12-13T09:49:22Z

With CONFIG_LOCKDEP=y and CONFIG_DEBUG_SPINLOCK=y, lockdep reports below warning: [ 166.059415] ============================================ [ 166.059416] WARNING: possible recursive locking detected [ 166.059418] 5.15.0-wt-ath+ #10 Tainted: G W O [ 166.059420] -------------------------------------------- [ 166.059421] kworker/0:2/116 is trying to acquire lock: [ 166.059423] ffff9905f2083160 (&srng->lock){+.-.}-{2:2}, at: ath11k_hal_reo_cmd_send+0x20/0x490 [ath11k] [ 166.059440] but task is already holding lock: [ 166.059442] ffff9905f2083230 (&srng->lock){+.-.}-{2:2}, at: ath11k_dp_process_reo_status+0x95/0x2d0 [ath11k] [ 166.059491] other info that might help us debug this: [ 166.059492] Possible unsafe locking scenario: [ 166.059493] CPU0 [ 166.059494] ---- [ 166.059495] lock(&srng->lock); [ 166.059498] lock(&srng->lock); [ 166.059500] *** DEADLOCK *** [ 166.059501] May be due to missing lock nesting notation [ 166.059502] 3 locks held by kworker/0:2/116: [ 166.059504] #0: ffff9905c0081548 ((wq_completion)events){+.+.}-{0:0}, at: process_one_work+0x1f6/0x660 [ 166.059511] #1: ffff9d2400a5fe68 ((debug_obj_work).work){+.+.}-{0:0}, at: process_one_work+0x1f6/0x660 [ 166.059517] #2: ffff9905f2083230 (&srng->lock){+.-.}-{2:2}, at: ath11k_dp_process_reo_status+0x95/0x2d0 [ath11k] [ 166.059532] stack backtrace: [ 166.059534] CPU: 0 PID: 116 Comm: kworker/0:2 Kdump: loaded Tainted: G W O 5.15.0-wt-ath+ #10 [ 166.059537] Hardware name: Intel(R) Client Systems NUC8i7HVK/NUC8i7HVB, BIOS HNKBLi70.86A.0059.2019.1112.1124 11/12/2019 [ 166.059539] Workqueue: events free_obj_work [ 166.059543] Call Trace: [ 166.059545] [ 166.059547] dump_stack_lvl+0x56/0x7b [ 166.059552] __lock_acquire+0xb9a/0x1a50 [ 166.059556] lock_acquire+0x1e2/0x330 [ 166.059560] ? ath11k_hal_reo_cmd_send+0x20/0x490 [ath11k] [ 166.059571] _raw_spin_lock_bh+0x33/0x70 [ 166.059574] ? ath11k_hal_reo_cmd_send+0x20/0x490 [ath11k] [ 166.059584] ath11k_hal_reo_cmd_send+0x20/0x490 [ath11k] [ 166.059594] ath11k_dp_tx_send_reo_cmd+0x3f/0x130 [ath11k] [ 166.059605] ath11k_dp_rx_tid_del_func+0x221/0x370 [ath11k] [ 166.059618] ath11k_dp_process_reo_status+0x22f/0x2d0 [ath11k] [ 166.059632] ? ath11k_dp_service_srng+0x2ea/0x2f0 [ath11k] [ 166.059643] ath11k_dp_service_srng+0x2ea/0x2f0 [ath11k] [ 166.059655] ath11k_pci_ext_grp_napi_poll+0x1c/0x70 [ath11k_pci] [ 166.059659] __napi_poll+0x28/0x230 [ 166.059664] net_rx_action+0x285/0x310 [ 166.059668] __do_softirq+0xe6/0x4d2 [ 166.059672] irq_exit_rcu+0xd2/0xf0 [ 166.059675] common_interrupt+0xa5/0xc0 [ 166.059678] [ 166.059679] [ 166.059680] asm_common_interrupt+0x1e/0x40 [ 166.059683] RIP: 0010:_raw_spin_unlock_irqrestore+0x38/0x70 [ 166.059686] Code: 83 c7 18 e8 2a 95 43 ff 48 89 ef e8 22 d2 43 ff 81 e3 00 02 00 00 75 25 9c 58 f6 c4 02 75 2d 48 85 db 74 01 fb bf 01 00 00 00 63 2e 40 ff 65 8b 05 8c 59 97 5c 85 c0 74 0a 5b 5d c3 e8 00 6a [ 166.059689] RSP: 0018:ffff9d2400a5fca0 EFLAGS: 00000206 [ 166.059692] RAX: 0000000000000002 RBX: 0000000000000200 RCX: 0000000000000006 [ 166.059694] RDX: 0000000000000000 RSI: ffffffffa404879b RDI: 0000000000000001 [ 166.059696] RBP: ffff9905c0053000 R08: 0000000000000001 R09: 0000000000000001 [ 166.059698] R10: ffff9d2400a5fc50 R11: 0000000000000001 R12: ffffe186c41e2840 [ 166.059700] R13: 0000000000000001 R14: ffff9905c78a1c68 R15: 0000000000000001 [ 166.059704] free_debug_processing+0x257/0x3d0 [ 166.059708] ? free_obj_work+0x1f5/0x250 [ 166.059712] __slab_free+0x374/0x5a0 [ 166.059718] ? kmem_cache_free+0x2e1/0x370 [ 166.059721] ? free_obj_work+0x1f5/0x250 [ 166.059724] kmem_cache_free+0x2e1/0x370 [ 166.059727] free_obj_work+0x1f5/0x250 [ 166.059731] process_one_work+0x28b/0x660 [ 166.059735] ? process_one_work+0x660/0x660 [ 166.059738] worker_thread+0x37/0x390 [ 166.059741] ? process_one_work+0x660/0x660 [ 166.059743] kthread+0x176/0x1a0 [ 166.059746] ? set_kthread_struct+0x40/0x40 [ 166.059749] ret_from_fork+0x22/0x30 [ 166.059754] Since these two lockes are both initialized in ath11k_hal_srng_setup, they are assigned with the same key. As a result lockdep suspects that the task is trying to acquire the same lock (due to same key) while already holding it, and thus reports the DEADLOCK warning. However as they are different spinlock instances, the warning is false positive. On the other hand, even no dead lock indeed, this is a major issue for upstream regression testing as it disables lockdep functionality. Fix it by assigning separate lock class key for each srng->lock. Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-01720.1-QCAHSPSWPL_V1_V2_SILICONZ_LITE-1 Signed-off-by: Baochen Qiang Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20211209011949.151472-1-quic_bqiang@quicinc.com

ath11k: allocate dst ring descriptors from cacheable memory

2021-11-15T09:21:49Z

tcl_data and reo_dst rings are currently being allocated using dma_allocate_coherent() which is non cacheable. Allocating ring memory from cacheable memory area allows cached descriptor access and prefetch next descriptors to optimize CPU usage during descriptor processing on NAPI. Based on the hardware param we can enable or disable this feature for the corresponding platform. Tested-on: QCN9074 hw1.0 PCI WLAN.HK.2.4.0.1.r2-00012-QCAHKSWPL_SILICONZ-1 Tested-on: IPQ8074 hw2.0 AHB WLAN.HK.2.4.0.1-01695-QCAHKSWPL_SILICONZ-1 Co-developed-by: Pradeep Kumar Chitrapu Signed-off-by: Pradeep Kumar Chitrapu Co-developed-by: Sriram R Signed-off-by: Sriram R Signed-off-by: Jouni Malinen Signed-off-by: P Praneesh Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/1630560820-21905-3-git-send-email-ppranees@codeaurora.org

ath11k: setup REO for WCN6855

2021-06-12T10:31:02Z

WCN6855 needs a different reo configuration, so add separate handling for this target in ath11k_hw_ops. Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-01720.1-QCAHSPSWPL_V1_V2_SILICONZ_LITE-1 Tested-on: QCA6390 hw2.0 PCI WLAN.HST.1.0.1-01740-QCAHSTSWPLZ_V2_TO_X86-1 Signed-off-by: Baochen Qiang Signed-off-by: Jouni Malinen Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20210511162214.29475-4-jouni@codeaurora.org

ath11k: add data path support for QCN9074

2021-02-17T09:32:51Z

hal rx descriptor is different for QCN9074 target type. since rx_msdu_end, rx_msdu_start, rx_mpdu_start elements are in different placement/alignment. In order to have generic data path, introduce platform specific hal rx descriptor access ops in ath11k_hw_ops. Tested-on: QCN9074 hw1.0 PCI WLAN.HK.2.4.0.1.r2-00012-QCAHKSWPL_SILICONZ-1 Signed-off-by: Karthikeyan Periyasamy Signed-off-by: Anilkumar Kolli Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/1612946530-28504-9-git-send-email-akolli@codeaurora.org

ath11k: add hal support for QCN9074

2021-02-17T09:32:48Z

Define the hal ring address and ring meta descriptor mask for QCN9074. Move the platform specific address to the ath11k_hw_regs. Define tx_mesh_enable ops in ath11k_hw_ops since its accessing platform specific TCL descriptor. Tested-on: QCN9074 hw1.0 PCI WLAN.HK.2.4.0.1.r2-00012-QCAHKSWPL_SILICONZ-1 Signed-off-by: Karthikeyan Periyasamy Signed-off-by: Anilkumar Kolli Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/1612946530-28504-8-git-send-email-akolli@codeaurora.org