Re: [PATCH v1] mm/vmalloc: fix exact allocations with an alignment > 1

From: Uladzislau Rezki
Date: Wed Sep 29 2021 - 10:35:38 EST

> So the idea is that once we run into a dead end because we took a left
> subtree, we rollback to the next possible rigth subtree and try again.
> If we run into another dead end, we repeat ... thus, this can now happen
> more than once.
> I assume the only implication is that this can now be slower in some
> corner cases with larger alignment, because it might take longer to find
> something suitable. Fair enough.
Yep, your understanding is correct regarding the tree traversal. If no
suitable block
is found in left sub-tree we roll-back and check right one. So it can
be(the scanning)
more than one time.

I did some performance analyzing using vmalloc test suite to figure
out a performance
loss for allocations with specific alignment. On that syntactic test i
see approx. 30%
of degradation:

2.225 microseconds vs 1.496 microseconds. That time includes both
vmalloc() and vfree()
calls. I do not consider it as a big degrade, but from the other hand
we can still adjust the
search length for alignments > one page:

# add it on top of previous proposal and search length instead of size
length = align > PAGE_SIZE ? size + align:size;

in that case we solve a KASAN issue + do not introduce a degrade. For
alignment all free blocks are aligned to it anyway. As for users which
uses a fixed range
that is same as a requested size and at the same time want to apply a
special alignment
is not considered as a common case, also we do not have such users.


> >
> > Could you please help and test the KASAN use case?
> Just tried it, works just fine with KASAN and makes sense in general,
> thanks!

Sorry for the delay.

Uladzislau Rezki