niceplaces has quit [Read error: Connection reset by peer]
niceplace has joined #linux-sunxi
niceplace has quit [Read error: Connection reset by peer]
AneoX has quit [Ping timeout: 252 seconds]
niceplace has joined #linux-sunxi
AneoX has joined #linux-sunxi
niceplace has quit [Read error: Connection reset by peer]
Ke has quit [Ping timeout: 246 seconds]
Ke has joined #linux-sunxi
Ke has quit [Changing host]
Ke has joined #linux-sunxi
niceplace has joined #linux-sunxi
niceplace has quit [Read error: Connection reset by peer]
niceplace has joined #linux-sunxi
Mangy_Dog has quit [Remote host closed the connection]
Mangy_Dog has joined #linux-sunxi
nexgen has quit [Remote host closed the connection]
nexgen has joined #linux-sunxi
JohnDoe_71Rus has joined #linux-sunxi
gaston1980 has joined #linux-sunxi
cristian_c has joined #linux-sunxi
cristian__c has quit [Ping timeout: 264 seconds]
cristian__c has joined #linux-sunxi
cristian_c has quit [Ping timeout: 276 seconds]
niceplace has quit [Read error: Connection reset by peer]
niceplace has joined #linux-sunxi
Perlovka has joined #linux-sunxi
lurchi_ is now known as lurchi__
ldevulder_ is now known as ldevulder
<megi>
montjoie: is there any reason why sun4i-ss-cipher does not use DMA?
lurchi__ is now known as lurchi_
matthias_bgg has quit [Ping timeout: 250 seconds]
airwind has quit [Quit: airwind]
lurchi_ is now known as lurchi__
msevo has joined #linux-sunxi
matthias_bgg has joined #linux-sunxi
loki__ has joined #linux-sunxi
suprothunderbolt has quit [Ping timeout: 240 seconds]
afaerber has quit [Quit: Leaving]
niceplaces has joined #linux-sunxi
niceplace has quit [Ping timeout: 240 seconds]
niceplaces has quit [Ping timeout: 250 seconds]
niceplace has joined #linux-sunxi
tlwoerner has quit [Ping timeout: 276 seconds]
tlwoerner has joined #linux-sunxi
dddddd has joined #linux-sunxi
AneoX has quit [Ping timeout: 240 seconds]
tdebrouw has quit [Quit: Leaving.]
AneoX has joined #linux-sunxi
gsz has quit [Quit: Konversation terminated!]
msevo has quit [Quit: Leaving]
msevo has joined #linux-sunxi
msevo has quit [Client Quit]
popolon has joined #linux-sunxi
niceplace has quit [Read error: Connection reset by peer]
niceplace has joined #linux-sunxi
reinforce has quit [Quit: Leaving.]
cnxsoft has quit [Quit: cnxsoft]
<montjoie>
megi: TOO SLOW
<megi>
interesting
<megi>
one would guess otherwise
<montjoie>
speed is generic/10
<megi>
do you know why?
<montjoie>
using DMA needs dmamapping and some other checks
<montjoie>
this increase time of treatement
<megi>
so it's slow for small requests, because of setup costs?
<montjoie>
yes
<megi>
ok, thanks
<montjoie>
I could do a retry for a bench
<megi>
I was just looking for an example of DDMA use and figured I'd check the crypto driver, and was curious why it doesn't use it. I have no use for crypto.
<megi>
I'm trying to implement DRAM -> DMA -> TCON0 :)
<montjoie>
megi: I will try to refound my patch for it, and will give it to you as example
<megi>
I found some example in the NFC driver
<montjoie>
my far though was to add it as a kconfig option, but nobody asked for it and I forgot it
<megi>
yeah, maybe it can be faster for larger requests
<megi>
but who knows
<montjoie>
now dmcrypt accept 4096 sector size...
<megi>
I'm starting to get DMA on A13. It seems like a mess from afar - sometimes you have to use DMA controller, sometimes it's directly hooked into some module and you set buffer registers inside that module (like in display backend), etc.
<megi>
But it makes sense that display BE needs a bit more info for various planes, so DMA implementaion needs to be more complicated
<megi>
TCON0 is just "give me a bunch of data and I'll push it out all as is, in a linear fashion, thank you"
<megi>
so one DDMA channel is enough, and not much setup inside the module itself is necessary
tllim has joined #linux-sunxi
tllim has quit [Read error: Connection reset by peer]