Re: [PATCH] ath10k: use pre-allocated DMA buffer in Tx

[Peter Oh <poh@codeaurora.org>]

Does it happen after you applied copy engine patchset or even without 
the patchset?
I saw ath10k_pci_htt_tx_cb in backtrace which is not merged to master 
branch yet.
If it only happens after the patchset, I'll apply them and look into it 
if any possibilities are there.

On 10/08/2015 04:49 AM, Kalle Valo wrote:
> Peter Oh <poh@qca.qualcomm.com> writes:
>
>> ath10k driver is using dma_pool_alloc per packet and dma_pool_free
>> in coresponding at Tx completion.
>> Use of pre-allocated DMA buffer in Tx will improve saving CPU resource
>> by 5% while it consumes about 56KB memory more as trade off.
>>
>> Signed-off-by: Peter Oh <poh@qca.qualcomm.com>
> I see randomly the warning below with ath.git master branch commit
> 2e88ba7ebe8d1. Can this patch cause that?
>
> [   53.637883] ------------[ cut here ]------------
> [   53.637999] WARNING: CPU: 2 PID: 0 at lib/dma-debug.c:1090
> check_unmap+0x815/0x940()
> [   53.638070] ath10k_pci 0000:02:00.0: qca99x0 hw2.0 (0x01000000,
> 0x003801ff bmi 1:1) fw 10.4.1.00007 fwapi 5 bdapi 2 htt-ver 2.2 wmi-op 6
> htt-op 4 cal otp max-sta 512 raw 0 hwcrypto 1 features no-p2p
> [   53.638077] ath10k_pci 0000:02:00.0: debug 1 debugfs 1 tracing 1 dfs 1
> testmode 1
> [   53.638205] ath10k_pci 0000:02:00.0: DMA-API: device driver tries to
> free an invalid DMA memory address
> [   53.638270] Modules linked in: ath10k_pci ath10k_core ath mac80211
> cfg80211 [last unloaded: cfg80211]
> [   53.638800] CPU: 2 PID: 0 Comm: swapper/2 Not tainted 4.3.0-rc3-wl-ath+
> #1082
> [   53.638880] Hardware name: Hewlett-Packard HP ProBook 6540b/1722, BIOS
> 68CDD Ver. F.04 01/27/2010
> [   53.638951]  00000000 00000000 f4445de4 c133dd94 00000000 f4445e14
> c10562de c1b3e12c
> [   53.639551]  f4445e40 00000000 c1b3d3b9 00000442 c13693c5 c13693c5
> f422e840 f4445eb4
> [   53.640169]  00000000 f4445e2c c10563c3 00000009 f4445e24 c1b3e12c
> f4445e40 f4445ea4
> [   53.640802] Call Trace:
> [   53.640874]  [<c133dd94>] dump_stack+0x48/0x64
> [   53.640953]  [<c10562de>] warn_slowpath_common+0x8e/0xd0
> [   53.641031]  [<c13693c5>] ? check_unmap+0x815/0x940
> [   53.641115]  [<c13693c5>] ? check_unmap+0x815/0x940
> [   53.641201]  [<c10563c3>] warn_slowpath_fmt+0x33/0x40
> [   53.641277]  [<c13693c5>] check_unmap+0x815/0x940
> [   53.641356]  [<c1088e35>] ? local_clock+0x25/0x30
> [   53.641432]  [<c136974c>] debug_dma_unmap_page+0x8c/0xa0
> [   53.641511]  [<fa258aaf>] ath10k_pci_htt_tx_cb+0x8f/0xb0 [ath10k_pci]
> [   53.641589]  [<fa258af0>] ath10k_pci_htt_rx_cb+0x20/0x30 [ath10k_pci]
> [   53.641668]  [<fa25ca2c>] ath10k_ce_per_engine_service+0x5c/0xa0
> [ath10k_pci]
> [   53.641746]  [<fa25cae7>] ath10k_ce_per_engine_service_any+0x77/0x90
> [ath10k_pci]
> [   53.641825]  [<fa25aa4b>] ath10k_pci_tasklet+0x1b/0x50 [ath10k_pci]
> [   53.642064]  [<c105bc4e>] tasklet_action+0x9e/0xb0
> [   53.642142]  [<c105b17b>] __do_softirq+0xbb/0x3c0
> [   53.642222]  [<c105b0c0>] ?
> trace_event_raw_event_irq_handler_entry+0xa0/0xa0
> [   53.642300]  [<c10059b9>] do_softirq_own_stack+0x29/0x40
> [   53.642375]  <IRQ>  [<c105b716>] irq_exit+0x86/0xb0
> [   53.642526]  [<c18c2310>] do_IRQ+0x60/0x120
> [   53.642604]  [<c10a4deb>] ? trace_hardirqs_off+0xb/0x10
> [   53.642680]  [<c18c1931>] common_interrupt+0x31/0x38
> [   53.642760]  [<c1694fa9>] ? cpuidle_enter_state+0xc9/0x350
> [   53.642835]  [<c1696879>] ? menu_select+0x239/0x4b0
> [   53.642925]  [<c1695264>] cpuidle_enter+0x14/0x20
> [   53.643063]  [<c109becc>] call_cpuidle+0x3c/0x70
> [   53.643140]  [<c109c0a9>] cpu_startup_entry+0x1a9/0x390
> [   53.643218]  [<c1038b75>] start_secondary+0x105/0x150
> [   53.643294] ---[ end trace a5dc1d40148089eb ]---
>


_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k