Just adding the upstream commit numbers and descriptions:
commit 41aacc1eea645c99edbe8fbcf78a97dc9b862adc
Author: Radu Caragea <email address hidden>
Date: Wed Aug 21 20:55:59 2013 +0300
x86 get_unmapped_area: Access mmap_legacy_base through mm_struct member
This is the updated version of df54d6fa5427 ("x86 get_unmapped_area():
use proper mmap base for bottom-up direction") that only randomizes the
mmap base address once.
Signed-off-by: Radu Caragea <email address hidden>
Reported-and-tested-by: Jeff Shorey <email address hidden>
Cc: Andrew Morton <email address hidden>
Cc: Michel Lespinasse <email address hidden>
Cc: Oleg Nesterov <email address hidden>
Cc: Rik van Riel <email address hidden>
Cc: Ingo Molnar <email address hidden>
Cc: Adrian Sendroiu <email address hidden>
Cc: Greg KH <email address hidden>
Cc: Kamal Mostafa <email address hidden>
Signed-off-by: Linus Torvalds <email address hidden>
Revert "x86 get_unmapped_area(): use proper mmap base for bottom-up direction"
This reverts commit df54d6fa54275ce59660453e29d1228c2b45a826.
The commit isn't necessarily wrong, but because it recalculates the
random mmap_base every time, it seems to confuse user memory allocators
that expect contiguous mmap allocations even when the mmap address isn't
specified.
In particular, the MATLAB Java runtime seems to be unhappy. See
Just adding the upstream commit numbers and descriptions:
commit 41aacc1eea645c9 9edbe8fbcf78a97 dc9b862adc
Author: Radu Caragea <email address hidden>
Date: Wed Aug 21 20:55:59 2013 +0300
x86 get_unmapped_area: Access mmap_legacy_base through mm_struct member
This is the updated version of df54d6fa5427 ("x86 get_unmapped_ area():
use proper mmap base for bottom-up direction") that only randomizes the
mmap base address once.
Signed-off-by: Radu Caragea <email address hidden> and-tested- by: Jeff Shorey <email address hidden>
Reported-
Cc: Andrew Morton <email address hidden>
Cc: Michel Lespinasse <email address hidden>
Cc: Oleg Nesterov <email address hidden>
Cc: Rik van Riel <email address hidden>
Cc: Ingo Molnar <email address hidden>
Cc: Adrian Sendroiu <email address hidden>
Cc: Greg KH <email address hidden>
Cc: Kamal Mostafa <email address hidden>
Signed-off-by: Linus Torvalds <email address hidden>
commit 5ea80f76a56605a 190a7ea16846c82 aa63dbd0aa
Author: Linus Torvalds <email address hidden>
Date: Thu Aug 22 09:13:06 2013 -0700
Revert "x86 get_unmapped_ area(): use proper mmap base for bottom-up direction"
This reverts commit df54d6fa54275ce 59660453e29d122 8c2b45a826.
The commit isn't necessarily wrong, but because it recalculates the
random mmap_base every time, it seems to confuse user memory allocators
that expect contiguous mmap allocations even when the mmap address isn't
specified.
In particular, the MATLAB Java runtime seems to be unhappy. See
https:/ /bugzilla. kernel. org/show_ bug.cgi? id=60774
So we'll want to apply the random offset only once, and Radu has a patch
for that. Revert this older commit in order to apply the other one.
Reported-by: Jeff Shorey <email address hidden>
Cc: Radu Caragea <email address hidden>
Cc: Andrew Morton <email address hidden>
Signed-off-by: Linus Torvalds <email address hidden>