On Wed, 2 Jul 2014, Oliver Neukum wrote:Stefan Klug
Leaving the zerocopy transfers out of this limit was intentional. I thought this is user-memory so we shouldn't add it to the overall limit as it is not allocated by usbfs.usbfs keeps track of the total amount of pinned memory and enforces an
Implementation details:It seems to me that the check is per call, so using
The patch only touches drivers/usb/core/devio.c.
In procy_do_submiturb(), it is checked if zerocopy is allowed. This is
currently a rough
check which compares the number of required pages to
ps->dev->bus->sg_tablesize.
multiple calls one could still pin unlimited amounts
of memory.
overall limit. It will be necessary to add the size of the transfer
buffer to that total.
So this one is fine, right?There is no way to do this. If the user program accesses memory whenI don't know if there is more to check there.How do you enforce the cache coherency rules?
Then the user memory provided inside the usbdevfs_urb structure is
pinned to
physical memory using get_user_pages_fast().
All the user pages are added to the scatter-gather list and the logic
continues as before.
it shouldn't, the transfer might not work right.
Good point. I'll add the fallback to the next iteration.Also you don't have a fall back if get_user_pages_fast()Agreed.
returns less than requested. It seems to me that than you
ought to fall back buffered IO.