@@ -241,6 +241,9 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw);
*/
unsigned long page_address_in_vma(struct page *, struct vm_area_struct *);
+int pfn_mkclean_range(unsigned long pfn, int npfn, pgoff_t pgoff,
+ struct vm_area_struct *vma);
+
/*
* Cleans the PTEs of shared mappings.
* (and since clean PTEs should also be readonly, write protects them too)
@@ -449,26 +449,22 @@ extern void clear_page_mlock(struct page *page);
extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma);
/*
- * At what user virtual address is page expected in vma?
- * Returns -EFAULT if all of the page is outside the range of vma.
- * If page is a compound head, the entire compound page is considered.
+ * Return the start of user virtual address at the specific offset within
+ * a vma.
*/
static inline unsigned long
-vma_address(struct page *page, struct vm_area_struct *vma)
+vma_pgoff_address(pgoff_t pgoff, unsigned long nr_pages,
+ struct vm_area_struct *vma)
{
- pgoff_t pgoff;
unsigned long address;
- VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */
- pgoff = page_to_pgoff(page);
if (pgoff >= vma->vm_pgoff) {
address = vma->vm_start +
((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
/* Check for address beyond vma (or wrapped through 0?) */
if (address < vma->vm_start || address >= vma->vm_end)
address = -EFAULT;
- } else if (PageHead(page) &&
- pgoff + compound_nr(page) - 1 >= vma->vm_pgoff) {
+ } else if (pgoff + nr_pages - 1 >= vma->vm_pgoff) {
/* Test above avoids possibility of wrap to 0 on 32-bit */
address = vma->vm_start;
} else {
@@ -478,6 +474,18 @@ vma_address(struct page *page, struct vm_area_struct *vma)
}
/*
+ * Return the start of user virtual address of a page within a vma.
+ * Returns -EFAULT if all of the page is outside the range of vma.
+ * If page is a compound head, the entire compound page is considered.
+ */
+static inline unsigned long
+vma_address(struct page *page, struct vm_area_struct *vma)
+{
+ VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */
+ return vma_pgoff_address(page_to_pgoff(page), compound_nr(page), vma);
+}
+
+/*
* Return the end of user virtual address at the specific offset within
* a vma.
*/
@@ -928,34 +928,33 @@ int page_referenced(struct page *page,
return pra.referenced;
}
-static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma,
- unsigned long address, void *arg)
+static int page_vma_mkclean_one(struct page_vma_mapped_walk *pvmw)
{
- struct page_vma_mapped_walk pvmw = {
- .page = page,
- .vma = vma,
- .address = address,
- .flags = PVMW_SYNC,
- };
+ int cleaned = 0;
+ struct vm_area_struct *vma = pvmw->vma;
struct mmu_notifier_range range;
- int *cleaned = arg;
+ unsigned long end;
+
+ if (pvmw->flags & PVMW_PFN_WALK)
+ end = vma_pgoff_address_end(pvmw->index, pvmw->nr, vma);
+ else
+ end = vma_address_end(pvmw->page, vma);
/*
* We have to assume the worse case ie pmd for invalidation. Note that
* the page can not be free from this function.
*/
- mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE,
- 0, vma, vma->vm_mm, address,
- vma_address_end(page, vma));
+ mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, 0, vma,
+ vma->vm_mm, pvmw->address, end);
mmu_notifier_invalidate_range_start(&range);
- while (page_vma_mapped_walk(&pvmw)) {
+ while (page_vma_mapped_walk(pvmw)) {
int ret = 0;
+ unsigned long address = pvmw->address;
- address = pvmw.address;
- if (pvmw.pte) {
+ if (pvmw->pte) {
pte_t entry;
- pte_t *pte = pvmw.pte;
+ pte_t *pte = pvmw->pte;
if (!pte_dirty(*pte) && !pte_write(*pte))
continue;
@@ -968,7 +967,7 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma,
ret = 1;
} else {
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- pmd_t *pmd = pvmw.pmd;
+ pmd_t *pmd = pvmw->pmd;
pmd_t entry;
if (!pmd_dirty(*pmd) && !pmd_write(*pmd))
@@ -995,11 +994,27 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma,
* See Documentation/vm/mmu_notifier.rst
*/
if (ret)
- (*cleaned)++;
+ cleaned++;
}
mmu_notifier_invalidate_range_end(&range);
+ return cleaned;
+}
+
+static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma,
+ unsigned long address, void *arg)
+{
+ struct page_vma_mapped_walk pvmw = {
+ .page = page,
+ .vma = vma,
+ .address = address,
+ .flags = PVMW_SYNC,
+ };
+ int *cleaned = arg;
+
+ *cleaned += page_vma_mkclean_one(&pvmw);
+
return true;
}
@@ -1037,6 +1052,39 @@ int folio_mkclean(struct folio *folio)
EXPORT_SYMBOL_GPL(folio_mkclean);
/**
+ * pfn_mkclean_range - Cleans the PTEs (including PMDs) mapped with range of
+ * [@pfn, @pfn + @npfn) at the specific offset (@pgoff)
+ * within the @vma of shared mappings. And since clean PTEs
+ * should also be readonly, write protects them too.
+ * @pfn: start pfn.
+ * @npfn: number of physically contiguous pfns srarting with @pfn.
+ * @pgoff: page offset that the @pfn mapped with.
+ * @vma: vma that @pfn mapped within.
+ *
+ * Returns the number of cleaned PTEs (including PMDs).
+ */
+int pfn_mkclean_range(unsigned long pfn, int npfn, pgoff_t pgoff,
+ struct vm_area_struct *vma)
+{
+ unsigned long address = vma_pgoff_address(pgoff, npfn, vma);
+ struct page_vma_mapped_walk pvmw = {
+ .pfn = pfn,
+ .nr = npfn,
+ .index = pgoff,
+ .vma = vma,
+ .address = address,
+ .flags = PVMW_SYNC | PVMW_PFN_WALK,
+ };
+
+ if (invalid_mkclean_vma(vma, NULL))
+ return 0;
+
+ VM_BUG_ON_VMA(address == -EFAULT, vma);
+
+ return page_vma_mkclean_one(&pvmw);
+}
+
+/**
* page_move_anon_rmap - move a page to our anon_vma
* @page: the page to move to our anon_vma
* @vma: the vma the page belongs to
The page_mkclean_one() is supposed to be used with the pfn that has a associated struct page, but not all the pfns (e.g. DAX) have a struct page. Introduce a new function pfn_mkclean_range() to cleans the PTEs (including PMDs) mapped with range of pfns which has no struct page associated with them. This helper will be used by DAX device in the next patch to make pfns clean. Signed-off-by: Muchun Song <songmuchun@bytedance.com> --- include/linux/rmap.h | 3 ++ mm/internal.h | 26 ++++++++++------ mm/rmap.c | 84 +++++++++++++++++++++++++++++++++++++++++----------- 3 files changed, 86 insertions(+), 27 deletions(-)