<wens>
looks like kernel breakage on my cortex-a8 sunxi devices is due to KASAN
lurchi_ is now known as lurchi__
shailangsa has quit []
mmarc__ has quit [Remote host closed the connection]
qCactus has joined #linux-sunxi
prefixcactus has quit [Ping timeout: 268 seconds]
mmarc__ has joined #linux-sunxi
mmarc__ has quit [Remote host closed the connection]
mmarc__ has joined #linux-sunxi
random_yanek has quit [Ping timeout: 252 seconds]
random_yanek has joined #linux-sunxi
victhor has joined #linux-sunxi
hlauer has joined #linux-sunxi
swiftgeek has quit [Ping timeout: 268 seconds]
elros1 has joined #linux-sunxi
Mangy_Dog has joined #linux-sunxi
Mangy_Dog has quit [Changing host]
Mangy_Dog has joined #linux-sunxi
tuxd3v has joined #linux-sunxi
tuxd3v has quit [Remote host closed the connection]
tuxd3v has joined #linux-sunxi
matthias_bgg has quit [Read error: Connection reset by peer]
matthias_bgg has joined #linux-sunxi
swiftgeek has joined #linux-sunxi
chewitt has quit [Read error: Connection reset by peer]
zhovner has quit [Quit: bye]
lurchi__ is now known as lurchi_
zhovner has joined #linux-sunxi
random_yanek has quit [Ping timeout: 246 seconds]
lennard has quit [Quit: hardware shuffle]
lurchi_ is now known as lurchi__
random_yanek has joined #linux-sunxi
<paulk-leonov>
Kwiboo: jernej: hi there, have you tried CPU-side access to cma-allocation vpu buffers with cedrus by any chance?
<paulk-leonov>
this is extremely slow here and I'm suspecting this is caused either by cache policy or memory bandwidth limits
<paulk-leonov>
cma-allocated*
elros1 has quit [Remote host closed the connection]
SdtElectronics has joined #linux-sunxi
lurchi__ is now known as lurchi_
<gediz0x539>
wens: i've had a kernel panic using A13 which had a stack trace like rcu_core -> __do_softirq -> run_ksoftirqd -> smpboot_thread_fn -> kthread
<gediz0x539>
is it relevant?
<SdtElectronics>
The USB Gadget/Ethernet page on wiki used legacy approach (precomposed configurations). I managed to make configfs-based gadget works on my A20 device. If I want to write about it, should I create a separate page or edit the original page?
bauen1_ is now known as bauen1
<apritzel>
SdtElectronics: Great, thanks for the offer! Please update the existing page, and put the configfs solution first.
<gediz0x539>
SdtElectronics: I would edit existing page and add explain new approach under a new title but if you do not want to, I think you can create a new page from scratch and link to it.
<SdtElectronics>
BTW, I noticed that option "Disable DMA (always use PIO)" is configured in the instructions of that page. I canceled that option in my configuration and everything seem to be just well. I wonder how does that option affect the gadget function, or it is merely due to the lack of support in older kernels?
chewitt has joined #linux-sunxi
<apritzel>
SdtElectronics: I thought the Allwinner gadget driver does not support DMA at all? So we always use PIO, regardless of that switch?
<SdtElectronics>
I'm not a kernel developer so I have no idea about the driver at all. Does that means configuring that option is unnecessary? If so I will just omit it in my edit
lurchi_ is now known as lurchi__
<mripard>
paulk-leonov: it's likely to be the caches, I'd expect CMA to access non-cacheable buffers
<paulk-leonov>
mripard: thanks!
<mripard>
possibly with write-combine, but it won't help if you access it
specing_ has joined #linux-sunxi
specing has quit [Ping timeout: 240 seconds]
specing_ is now known as specing
sunshavi has joined #linux-sunxi
<mripard>
paulk-leonov: yeah, vb2-dma-contig relies on dma_alloc_attrs, which works in the same way that dma_alloc_coherent for that case
<mripard>
and dma_alloc_coherent is supposed to return a coherent buffer
<mripard>
however we don't have any kind of hardware coherency afaik
<mripard>
so it just disables all the caches on that region
tnovotny has quit [Read error: Connection reset by peer]