1 files changed, 168 insertions, 166 deletions

diff --git a/mm/memory.c b/mm/memory.c
index 9e8576a83147..c8e357627318 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -134,6 +134,18 @@ static inline bool arch_faults_on_old_pte(void)
 }
 #endif
 
+#ifndef arch_wants_old_prefaulted_pte
+static inline bool arch_wants_old_prefaulted_pte(void)
+{
+	/*
+	 * Transitioning a PTE from 'old' to 'young' can be expensive on
+	 * some architectures, even if it's performed in hardware. By
+	 * default, "false" means prefaulted entries will be 'young'.
+	 */
+	return false;
+}
+#endif
+
 static int __init disable_randmaps(char *s)
 {
 	randomize_va_space = 0;
@@ -2165,11 +2177,11 @@ 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();
@@ -2183,7 +2195,7 @@ 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;
 }
 
@@ -2382,18 +2394,18 @@ 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);
 	}
@@ -2416,7 +2428,7 @@ 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;
 }
 
@@ -2890,7 +2902,6 @@ 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);
 
 		/*
@@ -3503,7 +3514,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 	if (pte_alloc(vma->vm_mm, vmf->pmd))
 		return VM_FAULT_OOM;
 
-	/* See the comment in pte_alloc_one_map() */
+	/* See comment in handle_pte_fault() */
 	if (unlikely(pmd_trans_unstable(vmf->pmd)))
 		return 0;
 
@@ -3548,7 +3559,6 @@ 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));
 
@@ -3643,66 +3653,6 @@ static vm_fault_t __do_fault(struct vm_fault *vmf)
 	return ret;
 }
 
-/*
- * The ordering of these checks is important for pmds with _PAGE_DEVMAP set.
- * If we check pmd_trans_unstable() first we will trip the bad_pmd() check
- * inside of pmd_none_or_trans_huge_or_clear_bad(). This will end up correctly
- * returning 1 but not before it spams dmesg with the pmd_clear_bad() output.
- */
-static int pmd_devmap_trans_unstable(pmd_t *pmd)
-{
-	return pmd_devmap(*pmd) || pmd_trans_unstable(pmd);
-}
-
-static vm_fault_t pte_alloc_one_map(struct vm_fault *vmf)
-{
-	struct vm_area_struct *vma = vmf->vma;
-
-	if (!pmd_none(*vmf->pmd))
-		goto map_pte;
-	if (vmf->prealloc_pte) {
-		vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
-		if (unlikely(!pmd_none(*vmf->pmd))) {
-			spin_unlock(vmf->ptl);
-			goto map_pte;
-		}
-
-		mm_inc_nr_ptes(vma->vm_mm);
-		pmd_populate(vma->vm_mm, vmf->pmd, vmf->prealloc_pte);
-		spin_unlock(vmf->ptl);
-		vmf->prealloc_pte = NULL;
-	} else if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd))) {
-		return VM_FAULT_OOM;
-	}
-map_pte:
-	/*
-	 * If a huge pmd materialized under us just retry later.  Use
-	 * pmd_trans_unstable() via pmd_devmap_trans_unstable() instead of
-	 * pmd_trans_huge() to ensure the pmd didn't become pmd_trans_huge
-	 * under us and then back to pmd_none, as a result of MADV_DONTNEED
-	 * running immediately after a huge pmd fault in a different thread of
-	 * this mm, in turn leading to a misleading pmd_trans_huge() retval.
-	 * All we have to ensure is that it is a regular pmd that we can walk
-	 * with pte_offset_map() and we can do that through an atomic read in
-	 * C, which is what pmd_trans_unstable() provides.
-	 */
-	if (pmd_devmap_trans_unstable(vmf->pmd))
-		return VM_FAULT_NOPAGE;
-
-	/*
-	 * At this point we know that our vmf->pmd points to a page of ptes
-	 * and it cannot become pmd_none(), pmd_devmap() or pmd_trans_huge()
-	 * for the duration of the fault.  If a racing MADV_DONTNEED runs and
-	 * we zap the ptes pointed to by our vmf->pmd, the vmf->ptl will still
-	 * be valid and we will re-check to make sure the vmf->pte isn't
-	 * pte_none() under vmf->ptl protection when we return to
-	 * alloc_set_pte().
-	 */
-	vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
-			&vmf->ptl);
-	return 0;
-}
-
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 static void deposit_prealloc_pte(struct vm_fault *vmf)
 {
@@ -3717,7 +3667,7 @@ static void deposit_prealloc_pte(struct vm_fault *vmf)
 	vmf->prealloc_pte = NULL;
 }
 
-static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
+vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
@@ -3775,76 +3725,39 @@ out:
 	return ret;
 }
 #else
-static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
+vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
 {
-	BUILD_BUG();
-	return 0;
+	return VM_FAULT_FALLBACK;
 }
 #endif
 
-/**
- * alloc_set_pte - setup new PTE entry for given page and add reverse page
- * mapping. If needed, the function allocates page table or use pre-allocated.
- *
- * @vmf: fault environment
- * @page: page to map
- *
- * Caller must take care of unlocking vmf->ptl, if vmf->pte is non-NULL on
- * return.
- *
- * Target users are page handler itself and implementations of
- * vm_ops->map_pages.
- *
- * Return: %0 on success, %VM_FAULT_ code in case of error.
- */
-vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct page *page)
+void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
+	bool prefault = vmf->address != addr;
 	pte_t entry;
-	vm_fault_t ret;
-
-	if (pmd_none(*vmf->pmd) && PageTransCompound(page)) {
-		ret = do_set_pmd(vmf, page);
-		if (ret != VM_FAULT_FALLBACK)
-			return ret;
-	}
-
-	if (!vmf->pte) {
-		ret = pte_alloc_one_map(vmf);
-		if (ret)
-			return ret;
-	}
-
-	/* Re-check under ptl */
-	if (unlikely(!pte_none(*vmf->pte))) {
-		update_mmu_tlb(vma, vmf->address, vmf->pte);
-		return VM_FAULT_NOPAGE;
-	}
 
 	flush_icache_page(vma, page);
 	entry = mk_pte(page, vma->vm_page_prot);
-	entry = pte_sw_mkyoung(entry);
+
+	if (prefault && arch_wants_old_prefaulted_pte())
+		entry = pte_mkold(entry);
+
 	if (write)
 		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
 	/* copy-on-write page */
 	if (write && !(vma->vm_flags & VM_SHARED)) {
 		inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
-		page_add_new_anon_rmap(page, vma, vmf->address, false);
+		page_add_new_anon_rmap(page, vma, addr, false);
 		lru_cache_add_inactive_or_unevictable(page, vma);
 	} else {
 		inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page));
 		page_add_file_rmap(page, false);
 	}
-	set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry);
-
-	/* no need to invalidate: a not-present page won't be cached */
-	update_mmu_cache(vma, vmf->address, vmf->pte);
-
-	return 0;
+	set_pte_at(vma->vm_mm, addr, vmf->pte, entry);
 }
 
-
 /**
  * finish_fault - finish page fault once we have prepared the page to fault
  *
@@ -3862,12 +3775,12 @@ vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct page *page)
  */
 vm_fault_t finish_fault(struct vm_fault *vmf)
 {
+	struct vm_area_struct *vma = vmf->vma;
 	struct page *page;
-	vm_fault_t ret = 0;
+	vm_fault_t ret;
 
 	/* Did we COW the page? */
-	if ((vmf->flags & FAULT_FLAG_WRITE) &&
-	    !(vmf->vma->vm_flags & VM_SHARED))
+	if ((vmf->flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED))
 		page = vmf->cow_page;
 	else
 		page = vmf->page;
@@ -3876,12 +3789,38 @@ vm_fault_t finish_fault(struct vm_fault *vmf)
 	 * check even for read faults because we might have lost our CoWed
 	 * page
 	 */
-	if (!(vmf->vma->vm_flags & VM_SHARED))
-		ret = check_stable_address_space(vmf->vma->vm_mm);
-	if (!ret)
-		ret = alloc_set_pte(vmf, page);
-	if (vmf->pte)
-		pte_unmap_unlock(vmf->pte, vmf->ptl);
+	if (!(vma->vm_flags & VM_SHARED)) {
+		ret = check_stable_address_space(vma->vm_mm);
+		if (ret)
+			return ret;
+	}
+
+	if (pmd_none(*vmf->pmd)) {
+		if (PageTransCompound(page)) {
+			ret = do_set_pmd(vmf, page);
+			if (ret != VM_FAULT_FALLBACK)
+				return ret;
+		}
+
+		if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd)))
+			return VM_FAULT_OOM;
+	}
+
+	/* See comment in handle_pte_fault() */
+	if (pmd_devmap_trans_unstable(vmf->pmd))
+		return 0;
+
+	vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
+				      vmf->address, &vmf->ptl);
+	ret = 0;
+	/* Re-check under ptl */
+	if (likely(pte_none(*vmf->pte)))
+		do_set_pte(vmf, page, vmf->address);
+	else
+		ret = VM_FAULT_NOPAGE;
+
+	update_mmu_tlb(vma, vmf->address, vmf->pte);
+	pte_unmap_unlock(vmf->pte, vmf->ptl);
 	return ret;
 }
 
@@ -3951,13 +3890,12 @@ static vm_fault_t do_fault_around(struct vm_fault *vmf)
 	pgoff_t start_pgoff = vmf->pgoff;
 	pgoff_t end_pgoff;
 	int off;
-	vm_fault_t ret = 0;
 
 	nr_pages = READ_ONCE(fault_around_bytes) >> PAGE_SHIFT;
 	mask = ~(nr_pages * PAGE_SIZE - 1) & PAGE_MASK;
 
-	vmf->address = max(address & mask, vmf->vma->vm_start);
-	off = ((address - vmf->address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1);
+	address = max(address & mask, vmf->vma->vm_start);
+	off = ((vmf->address - address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1);
 	start_pgoff -= off;
 
 	/*
@@ -3965,7 +3903,7 @@ static vm_fault_t do_fault_around(struct vm_fault *vmf)
 	 *  the vma or nr_pages from start_pgoff, depending what is nearest.
 	 */
 	end_pgoff = start_pgoff -
-		((vmf->address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) +
+		((address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) +
 		PTRS_PER_PTE - 1;
 	end_pgoff = min3(end_pgoff, vma_pages(vmf->vma) + vmf->vma->vm_pgoff - 1,
 			start_pgoff + nr_pages - 1);
@@ -3973,31 +3911,11 @@ static vm_fault_t do_fault_around(struct vm_fault *vmf)
 	if (pmd_none(*vmf->pmd)) {
 		vmf->prealloc_pte = pte_alloc_one(vmf->vma->vm_mm);
 		if (!vmf->prealloc_pte)
-			goto out;
+			return VM_FAULT_OOM;
 		smp_wmb(); /* See comment in __pte_alloc() */
 	}
 
-	vmf->vma->vm_ops->map_pages(vmf, start_pgoff, end_pgoff);
-
-	/* Huge page is mapped? Page fault is solved */
-	if (pmd_trans_huge(*vmf->pmd)) {
-		ret = VM_FAULT_NOPAGE;
-		goto out;
-	}
-
-	/* ->map_pages() haven't done anything useful. Cold page cache? */
-	if (!vmf->pte)
-		goto out;
-
-	/* check if the page fault is solved */
-	vmf->pte -= (vmf->address >> PAGE_SHIFT) - (address >> PAGE_SHIFT);
-	if (!pte_none(*vmf->pte))
-		ret = VM_FAULT_NOPAGE;
-	pte_unmap_unlock(vmf->pte, vmf->ptl);
-out:
-	vmf->address = address;
-	vmf->pte = NULL;
-	return ret;
+	return vmf->vma->vm_ops->map_pages(vmf, start_pgoff, end_pgoff);
 }
 
 static vm_fault_t do_read_fault(struct vm_fault *vmf)
@@ -4353,7 +4271,18 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf)
 		 */
 		vmf->pte = NULL;
 	} else {
-		/* See comment in pte_alloc_one_map() */
+		/*
+		 * If a huge pmd materialized under us just retry later.  Use
+		 * pmd_trans_unstable() via pmd_devmap_trans_unstable() instead
+		 * of pmd_trans_huge() to ensure the pmd didn't become
+		 * pmd_trans_huge under us and then back to pmd_none, as a
+		 * result of MADV_DONTNEED running immediately after a huge pmd
+		 * fault in a different thread of this mm, in turn leading to a
+		 * misleading pmd_trans_huge() retval. All we have to ensure is
+		 * that it is a regular pmd that we can walk with
+		 * pte_offset_map() and we can do that through an atomic read
+		 * in C, which is what pmd_trans_unstable() provides.
+		 */
 		if (pmd_devmap_trans_unstable(vmf->pmd))
 			return 0;
 		/*
@@ -4709,9 +4638,9 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
 }
 #endif /* __PAGETABLE_PMD_FOLDED */
 
-int follow_pte(struct mm_struct *mm, unsigned long address,
-	       struct mmu_notifier_range *range, pte_t **ptepp, pmd_t **pmdpp,
-	       spinlock_t **ptlp)
+int follow_invalidate_pte(struct mm_struct *mm, unsigned long address,
+			  struct mmu_notifier_range *range, pte_t **ptepp,
+			  pmd_t **pmdpp, spinlock_t **ptlp)
 {
 	pgd_t *pgd;
 	p4d_t *p4d;
@@ -4777,6 +4706,34 @@ out:
 }
 
 /**
+ * follow_pte - look up PTE at a user virtual address
+ * @mm: the mm_struct of the target address space
+ * @address: user virtual address
+ * @ptepp: location to store found PTE
+ * @ptlp: location to store the lock for the PTE
+ *
+ * On a successful return, the pointer to the PTE is stored in @ptepp;
+ * the corresponding lock is taken and its location is stored in @ptlp.
+ * The contents of the PTE are only stable until @ptlp is released;
+ * any further use, if any, must be protected against invalidation
+ * with MMU notifiers.
+ *
+ * Only IO mappings and raw PFN mappings are allowed.  The mmap semaphore
+ * should be taken for read.
+ *
+ * KVM uses this function.  While it is arguably less bad than ``follow_pfn``,
+ * it is not a good general-purpose API.
+ *
+ * Return: zero on success, -ve otherwise.
+ */
+int follow_pte(struct mm_struct *mm, unsigned long address,
+	       pte_t **ptepp, spinlock_t **ptlp)
+{
+	return follow_invalidate_pte(mm, address, NULL, ptepp, NULL, ptlp);
+}
+EXPORT_SYMBOL_GPL(follow_pte);
+
+/**
  * follow_pfn - look up PFN at a user virtual address
  * @vma: memory mapping
  * @address: user virtual address
@@ -4784,6 +4741,9 @@ out:
  *
  * Only IO mappings and raw PFN mappings are allowed.
  *
+ * This function does not allow the caller to read the permissions
+ * of the PTE.  Do not use it.
+ *
  * Return: zero and the pfn at @pfn on success, -ve otherwise.
  */
 int follow_pfn(struct vm_area_struct *vma, unsigned long address,
@@ -4796,7 +4756,7 @@ int follow_pfn(struct vm_area_struct *vma, unsigned long address,
 	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
 		return ret;
 
-	ret = follow_pte(vma->vm_mm, address, NULL, &ptep, NULL, &ptl);
+	ret = follow_pte(vma->vm_mm, address, &ptep, &ptl);
 	if (ret)
 		return ret;
 	*pfn = pte_pfn(*ptep);
@@ -4817,7 +4777,7 @@ int follow_phys(struct vm_area_struct *vma,
 	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
 		goto out;
 
-	if (follow_pte(vma->vm_mm, address, NULL, &ptep, NULL, &ptl))
+	if (follow_pte(vma->vm_mm, address, &ptep, &ptl))
 		goto out;
 	pte = *ptep;
 
@@ -4834,28 +4794,68 @@ 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
@@ -5173,17 +5173,19 @@ 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);