redonkable
/
remarkable-linux
1
0
Fork 0
Code Releases Activity

[PATCH] mm: copy_pte_range progress fix 

My latency breaking in copy_pte_range didn't work as intended: instead of
checking at regularish intervals, after the first interval it checked every
time around the loop, too impatient to be preempted.  Fix that.

Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
wifi-calibration
Hugh Dickins 2005-10-29 18:15:53 -07:00 committed by Linus Torvalds
parent 09ad4bbc3a
commit e040f218bb
1 changed files with 8 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
mm/memory.c
View File

@ -410,7 +410,7 @@ static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
{ {
pte_t *src_pte, *dst_pte; pte_t *src_pte, *dst_pte;
unsigned long vm_flags = vma->vm_flags; unsigned long vm_flags = vma->vm_flags;
int progress; int progress = 0;
again: again:
dst_pte = pte_alloc_map(dst_mm, dst_pmd, addr); dst_pte = pte_alloc_map(dst_mm, dst_pmd, addr);
@ -418,17 +418,19 @@ again:
return -ENOMEM; return -ENOMEM;
src_pte = pte_offset_map_nested(src_pmd, addr); src_pte = pte_offset_map_nested(src_pmd, addr);
progress = 0;
spin_lock(&src_mm->page_table_lock); spin_lock(&src_mm->page_table_lock);
do { do {
/* /*
* We are holding two locks at this point - either of them * We are holding two locks at this point - either of them
* could generate latencies in another task on another CPU. * could generate latencies in another task on another CPU.
*/ */
if (progress >= 32 && (need_resched() || if (progress >= 32) {
need_lockbreak(&src_mm->page_table_lock) || progress = 0;
need_lockbreak(&dst_mm->page_table_lock))) if (need_resched() ||
break; need_lockbreak(&src_mm->page_table_lock) ||
need_lockbreak(&dst_mm->page_table_lock))
break;
}
if (pte_none(*src_pte)) { if (pte_none(*src_pte)) {
progress++; progress++;
continue; continue;