Replacing all mmu_notifier_invalidate_page() by mmu_notifier_invalidat_range()
and making sure it is bracketed by call to mmu_notifier_invalidate_range_start/
end.
Note that because we can not presume the pmd value or pte value we have to
assume the worse and unconditionaly report an invalidation as happening.
Signed-off-by: Jérôme Glisse <jgli...@redhat.com>
Cc: Dan Williams <dan.j.willi...@intel.com>
Cc: Ross Zwisler <ross.zwis...@linux.intel.com>
Cc: Linus Torvalds <torva...@linux-foundation.org>
Cc: Bernhard Held <berny...@gmx.de>
Cc: Adam Borowski <kilob...@angband.pl>
Cc: Andrea Arcangeli <aarca...@redhat.com>
Cc: Radim Krčmář <rkrc...@redhat.com>
Cc: Wanpeng Li <kernel...@gmail.com>
Cc: Paolo Bonzini <pbonz...@redhat.com>
Cc: Takashi Iwai <ti...@suse.de>
Cc: Nadav Amit <nadav.a...@gmail.com>
Cc: Mike Galbraith <efa...@gmx.de>
Cc: Kirill A. Shutemov <kirill.shute...@linux.intel.com>
Cc: axie <a...@amd.com>
Cc: Andrew Morton <a...@linux-foundation.org>
---
mm/rmap.c | 44 +++++++++++++++++++++++++++++++++++++++++---
1 file changed, 41 insertions(+), 3 deletions(-)
diff --git a/mm/rmap.c b/mm/rmap.c
index c8993c63eb25..da97ed525088 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -887,11 +887,21 @@ static bool page_mkclean_one(struct page *page, struct
vm_area_struct *vma,
.address = address,
.flags = PVMW_SYNC,
};
+ unsigned long start = address, end;
int *cleaned = arg;
+ /*
+ * We have to assume the worse case ie pmd for invalidation. Note that
+ * the page can not be free from this function.
+ */
+ end = min(vma->vm_end, (start & PMD_MASK) + PMD_SIZE);
+ mmu_notifier_invalidate_range_start(vma->vm_mm, start, end);
+
while (page_vma_mapped_walk(&pvmw)) {
+ unsigned long cstart, cend;
int ret = 0;
- address = pvmw.address;
+
+ cstart = address = pvmw.address;
if (pvmw.pte) {
pte_t entry;
pte_t *pte = pvmw.pte;
@@ -904,6 +914,7 @@ static bool page_mkclean_one(struct page *page, struct
vm_area_struct *vma,
entry = pte_wrprotect(entry);
entry = pte_mkclean(entry);
set_pte_at(vma->vm_mm, address, pte, entry);
+ cend = cstart + PAGE_SIZE;
ret = 1;
} else {
#ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE
@@ -918,6 +929,8 @@ static bool page_mkclean_one(struct page *page, struct
vm_area_struct *vma,
entry = pmd_wrprotect(entry);
entry = pmd_mkclean(entry);
set_pmd_at(vma->vm_mm, address, pmd, entry);
+ cstart &= PMD_MASK;
+ cend = cstart + PMD_SIZE;
ret = 1;
#else
/* unexpected pmd-mapped page? */
@@ -926,11 +939,13 @@ static bool page_mkclean_one(struct page *page, struct
vm_area_struct *vma,
}
if (ret) {
- mmu_notifier_invalidate_page(vma->vm_mm, address);
+ mmu_notifier_invalidate_range(vma->vm_mm, cstart, cend);
(*cleaned)++;
}
}
+ mmu_notifier_invalidate_range_end(vma->vm_mm, start, end);
+
return true;
}
@@ -1324,6 +1339,7 @@ static bool try_to_unmap_one(struct page *page, struct
vm_area_struct *vma,
pte_t pteval;
struct page *subpage;
bool ret = true;
+ unsigned long start = address, end;
enum ttu_flags flags = (enum ttu_flags)arg;
/* munlock has nothing to gain from examining un-locked vmas */
@@ -1335,6 +1351,14 @@ static bool try_to_unmap_one(struct page *page, struct
vm_area_struct *vma,
flags & TTU_MIGRATION, page);
}
+ /*
+ * We have to assume the worse case ie pmd for invalidation. Note that
+ * the page can not be free in this function as call of try_to_unmap()
+ * must hold a reference on the page.
+ */
+ end = min(vma->vm_end, (start & PMD_MASK) + PMD_SIZE);
+ mmu_notifier_invalidate_range_start(vma->vm_mm, start, end);
+
while (page_vma_mapped_walk(&pvmw)) {
/*
* If the page is mlock()d, we cannot swap it out.
@@ -1408,6 +1432,8 @@ static bool try_to_unmap_one(struct page *page, struct
vm_area_struct *vma,
set_huge_swap_pte_at(mm, address,
pvmw.pte, pteval,
vma_mmu_pagesize(vma));
+ mmu_notifier_invalidate_range(mm, address,
+ address + vma_mmu_pagesize(vma));
} else {
dec_mm_counter(mm, mm_counter(page));
set_pte_at(mm, address, pvmw.pte, pteval);
@@ -1435,6 +1461,8 @@ static bool try_to_unmap_one(struct page *page, struct
vm_area_struct *vma,
if (pte_soft_dirty(pteval))
swp_pte = pte_swp_mksoft_dirty(swp_pte);
set_pte_at(mm, address, pvmw.pte, swp_pte);
+ mmu_notifier_invalidate_range(mm, address,
+ address + PAGE_SIZE);
} else if (PageAnon(page)) {
swp_entry_t entry = { .val = page_private(subpage) };
pte_t swp_pte;
@@ -1445,6 +1473,9 @@ static bool try_to_unmap_one(struct page *page, struct
vm_area_struct *vma,
if (unlikely(PageSwapBacked(page) !=
PageSwapCache(page))) {
WARN_ON_ONCE(1);
ret = false;
+ /* We have to invalidate as we cleared the pte
*/
+ mmu_notifier_invalidate_range(mm, address,
+ address + PAGE_SIZE);
page_vma_mapped_walk_done(&pvmw);
break;
}
@@ -1453,6 +1484,9 @@ static bool try_to_unmap_one(struct page *page, struct
vm_area_struct *vma,
if (!PageSwapBacked(page)) {
if (!PageDirty(page)) {
dec_mm_counter(mm, MM_ANONPAGES);
+ /* Invalidate as we cleared the pte */
+ mmu_notifier_invalidate_range(mm,
+ address, address + PAGE_SIZE);
goto discard;
}
@@ -1485,13 +1519,17 @@ static bool try_to_unmap_one(struct page *page, struct
vm_area_struct *vma,
if (pte_soft_dirty(pteval))
swp_pte = pte_swp_mksoft_dirty(swp_pte);
set_pte_at(mm, address, pvmw.pte, swp_pte);
+ mmu_notifier_invalidate_range(mm, address,
+ address + PAGE_SIZE);
} else
dec_mm_counter(mm, mm_counter_file(page));
discard:
page_remove_rmap(subpage, PageHuge(page));
put_page(page);
- mmu_notifier_invalidate_page(mm, address);
}
+
+ mmu_notifier_invalidate_range_end(vma->vm_mm, start, end);
+
return ret;
}
--
2.13.5
