The patch titled
Subject: mm: modify the method to search addr in unmapped_area_topdown
has been added to the -mm tree. Its filename is
mm-modify-the-method-to-search-addr-in-unmapped_area_topdown.patch
This patch should soon appear at
https://ozlabs.org/~akpm/mmots/broken-out/mm-modify-the-method-to-search-addr-in-unmapped_area_topdown.patch
and later at
https://ozlabs.org/~akpm/mmotm/broken-out/mm-modify-the-method-to-search-addr-in-unmapped_area_topdown.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: lipeifeng <lipeifeng@xxxxxxxx>
Subject: mm: modify the method to search addr in unmapped_area_topdown
The old method will firstly find the space in len(info->length +
info->align_mask), and get address at the desired alignment.
Sometime, addr would be failed if there are enough addr space in kernel by
above method, e.g., you can't get a addr sized in 1Mbytes, align_mask
1Mbytes successfully although there are still (2M-1)bytes space in kernel.
This patch would fix thr problem above by the new method: find the space
in info->length and judge if at the desired info->align_mask at the same
time.
Do a simple test in TIF_32BIT:
- Try to malloc (size:1M align:2M) until allocation fails;
- Try to malloc (size:1M align:1M) and account how to space can be
alloced successfully.
Before optimization: alloced 1.9G+ bytes.
After optimization: alloced 0 bytes.
Link: https://lkml.kernel.org/r/20220402094550.129-1-lipeifeng@xxxxxxxx
Signed-off-by: lipeifeng <lipeifeng@xxxxxxxx>
Cc: Michel Lespinasse <michel@xxxxxxxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: <zhangshiming@xxxxxxxx>
Cc: Barry Song <21cnbao@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/mmap.c | 20 +++++++++++++++-----
1 file changed, 15 insertions(+), 5 deletions(-)
--- a/mm/mmap.c~mm-modify-the-method-to-search-addr-in-unmapped_area_topdown
+++ a/mm/mmap.c
@@ -2014,13 +2014,14 @@ static unsigned long unmapped_area_topdo
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
- unsigned long length, low_limit, high_limit, gap_start, gap_end;
+ unsigned long length, low_limit, high_limit, gap_start, gap_end, gap_end_tmp;
/* Adjust search length to account for worst case alignment overhead */
length = info->length + info->align_mask;
if (length < info->length)
return -ENOMEM;
+ length = info->length;
/*
* Adjust search limits by the desired length.
* See implementation comment at top of unmapped_area().
@@ -2036,8 +2037,12 @@ static unsigned long unmapped_area_topdo
/* Check highest gap, which does not precede any rbtree node */
gap_start = mm->highest_vm_end;
- if (gap_start <= high_limit)
- goto found_highest;
+ if (gap_start <= high_limit) {
+ gap_end_tmp = gap_end - info->length;
+ gap_end_tmp -= (gap_end_tmp - info->align_offset) & info->align_mask;
+ if (gap_end_tmp >= gap_start)
+ goto found_highest;
+ }
/* Check if rbtree root looks promising */
if (RB_EMPTY_ROOT(&mm->mm_rb))
@@ -2065,8 +2070,13 @@ check_current:
if (gap_end < low_limit)
return -ENOMEM;
if (gap_start <= high_limit &&
- gap_end > gap_start && gap_end - gap_start >= length)
- goto found;
+ gap_end > gap_start && gap_end - gap_start >= length) {
+ gap_end_tmp = gap_end - info->length;
+ gap_end_tmp -= (gap_end_tmp - info->align_offset) & info->align_mask;
+ if (gap_end_tmp >= gap_start)
+ goto found;
+
+ }
/* Visit left subtree if it looks promising */
if (vma->vm_rb.rb_left) {
_
Patches currently in -mm which might be from lipeifeng@xxxxxxxx are
mm-modify-the-method-to-search-addr-in-unmapped_area_topdown.patch
