On Mon, 23 Jan 2012 13:57:36 -0500
Nitin Gupta [off-list ref] wrote:

quoted

afacit this code should be added to core mm/.  Addition of code like
this to core mm/ will be fiercely resisted on principle!  Hence the
(currently missing) justifications for adding it had best be good ones.

I don't think this code should ever get into mm/ since its just a driver
specific allocator.

Like mm/mempool.c and mm/dmapool.c ;)

However its used by more than one driver (zcache and
zram) so it may be moved to lib/ or drivers/zsmalloc atmost?

I'd need to take another look at the code, but if the allocator is a
good and useful thing then we want other kernel code to use it where
possible and appropriate. Putting it in mm/ or lib/ says "hey, use this".

The code is extensively poking around in MM internals, especially the
pageframe fields.  So I'd say it's a part of MM (in mm/) rather than a
clean client of MM, which would place it in lib/.


btw, kmap_atomic() already returns void*, so casting its return value
is unneeded.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>