1 files changed, 66 insertions, 26 deletions

diff --git a/mm/memory.c b/mm/memory.c
index c32318dc11d4..550405fc3b5e 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -166,7 +166,7 @@ static int __init init_zero_pfn(void)
 	zero_pfn = page_to_pfn(ZERO_PAGE(0));
 	return 0;
 }
-core_initcall(init_zero_pfn);
+early_initcall(init_zero_pfn);
 
 void mm_trace_rss_stat(struct mm_struct *mm, int member, long count)
 {
@@ -809,12 +809,8 @@ copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma
 		  pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss,
 		  struct page **prealloc, pte_t pte, struct page *page)
 {
-	struct mm_struct *src_mm = src_vma->vm_mm;
 	struct page *new_page;
 
-	if (!is_cow_mapping(src_vma->vm_flags))
-		return 1;
-
 	/*
 	 * What we want to do is to check whether this page may
 	 * have been pinned by the parent process.  If so,
@@ -828,9 +824,7 @@ copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma
 	 * the page count. That might give false positives for
 	 * for pinning, but it will work correctly.
 	 */
-	if (likely(!atomic_read(&src_mm->has_pinned)))
-		return 1;
-	if (likely(!page_maybe_dma_pinned(page)))
+	if (likely(!page_needs_cow_for_dma(src_vma, page)))
 		return 1;
 
 	new_page = *prealloc;
@@ -2177,11 +2171,11 @@ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd,
 			unsigned long addr, unsigned long end,
 			unsigned long pfn, pgprot_t prot)
 {
-	pte_t *pte;
+	pte_t *pte, *mapped_pte;
 	spinlock_t *ptl;
 	int err = 0;
 
-	pte = pte_alloc_map_lock(mm, pmd, addr, &ptl);
+	mapped_pte = pte = pte_alloc_map_lock(mm, pmd, addr, &ptl);
 	if (!pte)
 		return -ENOMEM;
 	arch_enter_lazy_mmu_mode();
@@ -2195,7 +2189,7 @@ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd,
 		pfn++;
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 	arch_leave_lazy_mmu_mode();
-	pte_unmap_unlock(pte - 1, ptl);
+	pte_unmap_unlock(mapped_pte, ptl);
 	return err;
 }
 
@@ -2394,18 +2388,18 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
 				     pte_fn_t fn, void *data, bool create,
 				     pgtbl_mod_mask *mask)
 {
-	pte_t *pte;
+	pte_t *pte, *mapped_pte;
 	int err = 0;
 	spinlock_t *ptl;
 
 	if (create) {
-		pte = (mm == &init_mm) ?
+		mapped_pte = pte = (mm == &init_mm) ?
 			pte_alloc_kernel_track(pmd, addr, mask) :
 			pte_alloc_map_lock(mm, pmd, addr, &ptl);
 		if (!pte)
 			return -ENOMEM;
 	} else {
-		pte = (mm == &init_mm) ?
+		mapped_pte = pte = (mm == &init_mm) ?
 			pte_offset_kernel(pmd, addr) :
 			pte_offset_map_lock(mm, pmd, addr, &ptl);
 	}
@@ -2428,7 +2422,7 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
 	arch_leave_lazy_mmu_mode();
 
 	if (mm != &init_mm)
-		pte_unmap_unlock(pte-1, ptl);
+		pte_unmap_unlock(mapped_pte, ptl);
 	return err;
 }
 
@@ -2902,7 +2896,6 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 		}
 		flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte));
 		entry = mk_pte(new_page, vma->vm_page_prot);
-		entry = pte_sw_mkyoung(entry);
 		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
 
 		/*
@@ -3104,6 +3097,14 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf)
 		return handle_userfault(vmf, VM_UFFD_WP);
 	}
 
+	/*
+	 * Userfaultfd write-protect can defer flushes. Ensure the TLB
+	 * is flushed in this case before copying.
+	 */
+	if (unlikely(userfaultfd_wp(vmf->vma) &&
+		     mm_tlb_flush_pending(vmf->vma->vm_mm)))
+		flush_tlb_page(vmf->vma, vmf->address);
+
 	vmf->page = vm_normal_page(vma, vmf->address, vmf->orig_pte);
 	if (!vmf->page) {
 		/*
@@ -3560,7 +3561,6 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 	__SetPageUptodate(page);
 
 	entry = mk_pte(page, vma->vm_page_prot);
-	entry = pte_sw_mkyoung(entry);
 	if (vma->vm_flags & VM_WRITE)
 		entry = pte_mkwrite(pte_mkdirty(entry));
 
@@ -3745,8 +3745,6 @@ void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr)
 
 	if (prefault && arch_wants_old_prefaulted_pte())
 		entry = pte_mkold(entry);
-	else
-		entry = pte_sw_mkyoung(entry);
 
 	if (write)
 		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
@@ -4798,28 +4796,68 @@ out:
 	return ret;
 }
 
+/**
+ * generic_access_phys - generic implementation for iomem mmap access
+ * @vma: the vma to access
+ * @addr: userspace addres, not relative offset within @vma
+ * @buf: buffer to read/write
+ * @len: length of transfer
+ * @write: set to FOLL_WRITE when writing, otherwise reading
+ *
+ * This is a generic implementation for &vm_operations_struct.access for an
+ * iomem mapping. This callback is used by access_process_vm() when the @vma is
+ * not page based.
+ */
 int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
 			void *buf, int len, int write)
 {
 	resource_size_t phys_addr;
 	unsigned long prot = 0;
 	void __iomem *maddr;
-	int offset = addr & (PAGE_SIZE-1);
+	pte_t *ptep, pte;
+	spinlock_t *ptl;
+	int offset = offset_in_page(addr);
+	int ret = -EINVAL;
 
-	if (follow_phys(vma, addr, write, &prot, &phys_addr))
+	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
+		return -EINVAL;
+
+retry:
+	if (follow_pte(vma->vm_mm, addr, &ptep, &ptl))
+		return -EINVAL;
+	pte = *ptep;
+	pte_unmap_unlock(ptep, ptl);
+
+	prot = pgprot_val(pte_pgprot(pte));
+	phys_addr = (resource_size_t)pte_pfn(pte) << PAGE_SHIFT;
+
+	if ((write & FOLL_WRITE) && !pte_write(pte))
 		return -EINVAL;
 
 	maddr = ioremap_prot(phys_addr, PAGE_ALIGN(len + offset), prot);
 	if (!maddr)
 		return -ENOMEM;
 
+	if (follow_pte(vma->vm_mm, addr, &ptep, &ptl))
+		goto out_unmap;
+
+	if (!pte_same(pte, *ptep)) {
+		pte_unmap_unlock(ptep, ptl);
+		iounmap(maddr);
+
+		goto retry;
+	}
+
 	if (write)
 		memcpy_toio(maddr + offset, buf, len);
 	else
 		memcpy_fromio(buf, maddr + offset, len);
+	ret = len;
+	pte_unmap_unlock(ptep, ptl);
+out_unmap:
 	iounmap(maddr);
 
-	return len;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(generic_access_phys);
 #endif
@@ -5137,17 +5175,19 @@ long copy_huge_page_from_user(struct page *dst_page,
 	void *page_kaddr;
 	unsigned long i, rc = 0;
 	unsigned long ret_val = pages_per_huge_page * PAGE_SIZE;
+	struct page *subpage = dst_page;
 
-	for (i = 0; i < pages_per_huge_page; i++) {
+	for (i = 0; i < pages_per_huge_page;
+	     i++, subpage = mem_map_next(subpage, dst_page, i)) {
 		if (allow_pagefault)
-			page_kaddr = kmap(dst_page + i);
+			page_kaddr = kmap(subpage);
 		else
-			page_kaddr = kmap_atomic(dst_page + i);
+			page_kaddr = kmap_atomic(subpage);
 		rc = copy_from_user(page_kaddr,
 				(const void __user *)(src + i * PAGE_SIZE),
 				PAGE_SIZE);
 		if (allow_pagefault)
-			kunmap(dst_page + i);
+			kunmap(subpage);
 		else
 			kunmap_atomic(page_kaddr);