github-mirror/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-11-06 21:58:01 +01:00
Code Issues Actions Packages Projects Releases Wiki Activity Graph

mm: mincore: use per-vma lock during page table walk

Browse Source 
do_mincore() performs a read-only, per-VMA residency query, making it a
good candidate for per-VMA locking.  Convert it to acquire the per-VMA
lock, thereby reducing contention on the per-MM mmap_lock.

Link: https://lore.kernel.org/20260916043153.2631696-1-wangkefeng.wang@huawei.com
Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Pedro Falcato <pfalcato@suse.de>
Acked-by: David Hildenbrand (Arm) <david@kernel.org>
Reviewed-by: Lorenzo Stoakes (ARM) <ljs@kernel.org>
Cc: Jann Horn <jannh@google.com>
Cc: Liam R. Howlett <liam@infradead.org>
Cc: Vlastimil Babka <vbabka@kernel.org>
Cc: Zi Yan <ziy@nvidia.com>
This commit is contained in:
Kefeng Wang 2026-09-16 12:31:52 +08:00 committed by Andrew Morton
parent 331f94007d
commit dba177ad78
1 changed files with 17 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
mm/mincore.c
View File

@ -235,24 +235,22 @@ static const struct mm_walk_ops mincore_walk_ops = {
.pmd_entry = mincore_pte_range,
.pte_hole = mincore_unmapped_range,
.hugetlb_entry = mincore_hugetlb,
.walk_lock = PGWALK_RDLOCK,
.walk_lock = PGWALK_VMA_RDLOCK_VERIFY,
};
/*
* Do a chunk of "sys_mincore()". We've already checked
* all the arguments, we hold the mmap semaphore: we should
* all the arguments, we hold the VMA read lock: we should
* just return the amount of info we're asked for.
*/
static long do_mincore(unsigned long addr, unsigned long pages, unsigned char *vec)
static long do_mincore(struct vm_area_struct *vma, unsigned long addr,
unsigned long pages, unsigned char *vec)
{
struct vm_area_struct *vma;
unsigned long end;
unsigned long end = min(vma->vm_end, addr + (pages << PAGE_SHIFT));
int err;
vma = vma_lookup(current->mm, addr);
if (!vma)
return -ENOMEM;
end = min(vma->vm_end, addr + (pages << PAGE_SHIFT));
vma_assert_locked(vma);
if (!can_do_mincore(vma)) {
unsigned long pages = DIV_ROUND_UP(end - addr, PAGE_SIZE);
memset(vec, 1, pages);
@ -319,13 +317,20 @@ SYSCALL_DEFINE3(mincore, unsigned long, start, size_t, len,
retval = 0;
while (pages) {
struct vm_area_struct *vma;
vma = vma_start_read_unlocked(current->mm, start);
if (!vma) {
retval = -ENOMEM;
break;
}
/*
* Do at most PAGE_SIZE entries per iteration, due to
* the temporary buffer size.
*/
mmap_read_lock(current->mm);
retval = do_mincore(start, min(pages, PAGE_SIZE), tmp);
mmap_read_unlock(current->mm);
retval = do_mincore(vma, start, min(pages, PAGE_SIZE), tmp);
vma_end_read(vma);
if (retval <= 0)
break;