On 04/23/2015 11:03 PM, Kirill A. Shutemov wrote:
We need to prepare kernel to allow transhuge pages to be mapped with
ptes too. We need to handle FOLL_SPLIT in follow_page_pte().
Also we use split_huge_page() directly instead of split_huge_page_pmd().
split_huge_page_pmd() will gone.
You still call split_huge_page_pmd() for the is_huge_zero_page(page)
case. Also, of the code around split_huge_page() you basically took from
split_huge_page_pmd() and open-coded into follow_page_mask(), you didn't
include the mmu notifier calls. Why are they needed in
split_huge_page_pmd() but not here?
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Tested-by: Sasha Levin <sasha.levin@xxxxxxxxxx>
---
mm/gup.c | 67 +++++++++++++++++++++++++++++++++++++++++++++++-----------------
1 file changed, 49 insertions(+), 18 deletions(-)
diff --git a/mm/gup.c b/mm/gup.c
index 203781fa96a5..ebdb39b3e820 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -79,6 +79,19 @@ retry:
page = pte_page(pte);
}
+ if (flags & FOLL_SPLIT && PageTransCompound(page)) {
+ int ret;
+ get_page(page);
+ pte_unmap_unlock(ptep, ptl);
+ lock_page(page);
+ ret = split_huge_page(page);
+ unlock_page(page);
+ put_page(page);
+ if (ret)
+ return ERR_PTR(ret);
+ goto retry;
+ }
+
if (flags & FOLL_GET)
get_page_foll(page);
if (flags & FOLL_TOUCH) {
@@ -186,27 +199,45 @@ struct page *follow_page_mask(struct vm_area_struct *vma,
}
if ((flags & FOLL_NUMA) && pmd_protnone(*pmd))
return no_page_table(vma, flags);
- if (pmd_trans_huge(*pmd)) {
- if (flags & FOLL_SPLIT) {
+ if (likely(!pmd_trans_huge(*pmd)))
+ return follow_page_pte(vma, address, pmd, flags);
+
+ ptl = pmd_lock(mm, pmd);
+ if (unlikely(!pmd_trans_huge(*pmd))) {
+ spin_unlock(ptl);
+ return follow_page_pte(vma, address, pmd, flags);
+ }
+
+ if (unlikely(pmd_trans_splitting(*pmd))) {
+ spin_unlock(ptl);
+ wait_split_huge_page(vma->anon_vma, pmd);
+ return follow_page_pte(vma, address, pmd, flags);
+ }
+
+ if (flags & FOLL_SPLIT) {
+ int ret;
+ page = pmd_page(*pmd);
+ if (is_huge_zero_page(page)) {
+ spin_unlock(ptl);
+ ret = 0;
split_huge_page_pmd(vma, address, pmd);
- return follow_page_pte(vma, address, pmd, flags);
- }
- ptl = pmd_lock(mm, pmd);
- if (likely(pmd_trans_huge(*pmd))) {
- if (unlikely(pmd_trans_splitting(*pmd))) {
- spin_unlock(ptl);
- wait_split_huge_page(vma->anon_vma, pmd);
- } else {
- page = follow_trans_huge_pmd(vma, address,
- pmd, flags);
- spin_unlock(ptl);
- *page_mask = HPAGE_PMD_NR - 1;
- return page;
- }
- } else
+ } else {
+ get_page(page);
spin_unlock(ptl);
+ lock_page(page);
+ ret = split_huge_page(page);
+ unlock_page(page);
+ put_page(page);
+ }
+
+ return ret ? ERR_PTR(ret) :
+ follow_page_pte(vma, address, pmd, flags);
}
- return follow_page_pte(vma, address, pmd, flags);
+
+ page = follow_trans_huge_pmd(vma, address, pmd, flags);
+ spin_unlock(ptl);
+ *page_mask = HPAGE_PMD_NR - 1;
+ return page;
}
static int get_gate_page(struct mm_struct *mm, unsigned long address,
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>