[PATCH v3 0/8] Create 'old' ptes for faultaround mappings on arm64 with hardware access flag

@@ -980,7 +980,17 @@ static inline bool arch_faults_on_old_pte(void)
 
 	return !cpu_has_hw_af();
 }
-#define arch_faults_on_old_pte arch_faults_on_old_pte
+#define arch_faults_on_old_pte		arch_faults_on_old_pte
+
+/*
+ * Experimentally, it's cheap to set the access flag in hardware and we
+ * benefit from prefaulting mappings as 'old' to start with.
+ */
+static inline bool arch_wants_old_prefaulted_pte(void)
+{
+	return !arch_faults_on_old_pte();
+}
+#define arch_wants_old_prefaulted_pte	arch_wants_old_prefaulted_pte
 
 #endif /* !__ASSEMBLY__ */
 

@@ -434,6 +434,7 @@ extern pgprot_t protection_map[16];
  * @FAULT_FLAG_REMOTE: The fault is not for current task/mm.
  * @FAULT_FLAG_INSTRUCTION: The fault was during an instruction fetch.
  * @FAULT_FLAG_INTERRUPTIBLE: The fault can be interrupted by non-fatal signals.
+ * @FAULT_FLAG_PREFAULT: Fault was a prefault.
  *
  * About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify
  * whether we would allow page faults to retry by specifying these two

@@ -464,6 +465,7 @@ extern pgprot_t protection_map[16];
 #define FAULT_FLAG_REMOTE			0x80
 #define FAULT_FLAG_INSTRUCTION  		0x100
 #define FAULT_FLAG_INTERRUPTIBLE		0x200
+#define FAULT_FLAG_PREFAULT			0x400
 
 /*
  * The default fault flags that should be used by most of the

@@ -501,7 +503,8 @@ static inline bool fault_flag_allow_retry_first(unsigned int flags)
 	{ FAULT_FLAG_USER,		"USER" }, \
 	{ FAULT_FLAG_REMOTE,		"REMOTE" }, \
 	{ FAULT_FLAG_INSTRUCTION,	"INSTRUCTION" }, \
-	{ FAULT_FLAG_INTERRUPTIBLE,	"INTERRUPTIBLE" }
+	{ FAULT_FLAG_INTERRUPTIBLE,	"INTERRUPTIBLE" }, \
+	{ FAULT_FLAG_PREFAULT,		"PREFAULT" }
 
 /*
  * vm_fault is filled by the pagefault handler and passed to the vma's

@@ -3019,6 +3019,7 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf,
 	struct address_space *mapping = file->f_mapping;
 	pgoff_t last_pgoff = start_pgoff;
 	unsigned long address = vmf->address;
+	unsigned long flags = vmf->flags;
 	XA_STATE(xas, &mapping->i_pages, start_pgoff);
 	struct page *head, *page;
 	unsigned int mmap_miss = READ_ONCE(file->f_ra.mmap_miss);

@@ -3051,14 +3052,18 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf,
 		if (!pte_none(*vmf->pte))
 			goto unlock;
 
+		/* We're about to handle the fault */
+		if (vmf->address == address) {
+			vmf->flags &= ~FAULT_FLAG_PREFAULT;
+			ret = VM_FAULT_NOPAGE;
+		} else {
+			vmf->flags |= FAULT_FLAG_PREFAULT;
+		}
+
 		do_set_pte(vmf, page);
 		/* no need to invalidate: a not-present page won't be cached */
 		update_mmu_cache(vma, vmf->address, vmf->pte);
 		unlock_page(head);
-
-		/* The fault is handled */
-		if (vmf->address == address)
-			ret = VM_FAULT_NOPAGE;
 		continue;
 unlock:
 		unlock_page(head);

@@ -3067,6 +3072,7 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf,
 	pte_unmap_unlock(vmf->pte, vmf->ptl);
 out:
 	rcu_read_unlock();
+	vmf->flags = flags;
 	vmf->address = address;
 	WRITE_ONCE(file->f_ra.mmap_miss, mmap_miss);
 	return ret;

@@ -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;

@@ -3725,11 +3737,17 @@ void do_set_pte(struct vm_fault *vmf, struct page *page)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
+	bool prefault = vmf->flags & FAULT_FLAG_PREFAULT;
 	pte_t entry;
 
 	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);
+	else
+		entry = pte_sw_mkyoung(entry);
+
 	if (write)
 		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
 	/* copy-on-write page */

@@ -1319,17 +1319,19 @@ xfs_filemap_pfn_mkwrite(
 	return __xfs_filemap_fault(vmf, PE_SIZE_PTE, true);
 }
 
-static void
+static vm_fault_t
 xfs_filemap_map_pages(
 	struct vm_fault		*vmf,
 	pgoff_t			start_pgoff,
 	pgoff_t			end_pgoff)
 {
 	struct inode		*inode = file_inode(vmf->vma->vm_file);
+	vm_fault_t ret;
 
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
-	filemap_map_pages(vmf, start_pgoff, end_pgoff);
+	ret = filemap_map_pages(vmf, start_pgoff, end_pgoff);
 	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
+	return ret;
 }
 
 static const struct vm_operations_struct xfs_file_vm_ops = {

@@ -542,8 +542,8 @@ struct vm_fault {
 					 * is not NULL, otherwise pmd.
 					 */
 	pgtable_t prealloc_pte;		/* Pre-allocated pte page table.
-					 * vm_ops->map_pages() calls
-					 * alloc_set_pte() from atomic context.
+					 * vm_ops->map_pages() sets up a page
+					 * table from atomic context.
 					 * do_fault_around() pre-allocates
 					 * page table to avoid allocation from
 					 * atomic context.

@@ -578,7 +578,7 @@ struct vm_operations_struct {
 	vm_fault_t (*fault)(struct vm_fault *vmf);
 	vm_fault_t (*huge_fault)(struct vm_fault *vmf,
 			enum page_entry_size pe_size);
-	void (*map_pages)(struct vm_fault *vmf,
+	vm_fault_t (*map_pages)(struct vm_fault *vmf,
 			pgoff_t start_pgoff, pgoff_t end_pgoff);
 	unsigned long (*pagesize)(struct vm_area_struct * area);
 

@@ -988,7 +988,9 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
 	return pte;
 }
 
-vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct page *page);
+vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page);
+void do_set_pte(struct vm_fault *vmf, struct page *page);
+
 vm_fault_t finish_fault(struct vm_fault *vmf);
 vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf);
 #endif

@@ -2622,7 +2624,7 @@ extern void truncate_inode_pages_final(struct address_space *);
 
 /* generic vm_area_ops exported for stackable file systems */
 extern vm_fault_t filemap_fault(struct vm_fault *vmf);
-extern void filemap_map_pages(struct vm_fault *vmf,
+extern vm_fault_t filemap_map_pages(struct vm_fault *vmf,
 		pgoff_t start_pgoff, pgoff_t end_pgoff);
 extern vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf);
 

@@ -1314,6 +1314,17 @@ static inline int pmd_trans_unstable(pmd_t *pmd)
 #endif
 }
 
+/*
+ * 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 inline int pmd_devmap_trans_unstable(pmd_t *pmd)
+{
+	return pmd_devmap(*pmd) || pmd_trans_unstable(pmd);
+}
+
 #ifndef CONFIG_NUMA_BALANCING
 /*
  * Technically a PTE can be PROTNONE even when not doing NUMA balancing but

@@ -42,6 +42,7 @@
 #include <linux/psi.h>
 #include <linux/ramfs.h>
 #include <linux/page_idle.h>
+#include <asm/pgalloc.h>
 #include "internal.h"
 
 #define CREATE_TRACE_POINTS

@@ -2911,74 +2912,164 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
 }
 EXPORT_SYMBOL(filemap_fault);
 
-void filemap_map_pages(struct vm_fault *vmf,
-		pgoff_t start_pgoff, pgoff_t end_pgoff)
+static bool filemap_map_pmd(struct vm_fault *vmf, struct page *page)
 {
-	struct file *file = vmf->vma->vm_file;
+	struct mm_struct *mm = vmf->vma->vm_mm;
+
+	/* Huge page is mapped? No need to proceed. */
+	if (pmd_trans_huge(*vmf->pmd)) {
+		unlock_page(page);
+		put_page(page);
+		return true;
+	}
+
+	if (pmd_none(*vmf->pmd) && PageTransHuge(page)) {
+	    vm_fault_t ret = do_set_pmd(vmf, page);
+	    if (!ret) {
+		    /* The page is mapped successfully, reference consumed. */
+		    unlock_page(page);
+		    return true;
+	    }
+	}
+
+	if (pmd_none(*vmf->pmd)) {
+		vmf->ptl = pmd_lock(mm, vmf->pmd);
+		if (likely(pmd_none(*vmf->pmd))) {
+			mm_inc_nr_ptes(mm);
+			pmd_populate(mm, vmf->pmd, vmf->prealloc_pte);
+			vmf->prealloc_pte = NULL;
+		}
+		spin_unlock(vmf->ptl);
+	}
+
+	/* See comment in handle_pte_fault() */
+	if (pmd_devmap_trans_unstable(vmf->pmd)) {
+		unlock_page(page);
+		put_page(page);
+		return true;
+	}
+
+	return false;
+}
+
+static struct page *next_uptodate_page(struct page *page,
+				       struct address_space *mapping,
+				       struct xa_state *xas, pgoff_t end_pgoff)
+{
+	unsigned long max_idx;
+
+	do {
+		if (!page)
+			return NULL;
+		if (xas_retry(xas, page))
+			continue;
+		if (xa_is_value(page))
+			continue;
+		if (PageLocked(page))
+			continue;
+		if (!page_cache_get_speculative(page))
+			continue;
+		/* Has the page moved or been split? */
+		if (unlikely(page != xas_reload(xas)))
+			goto skip;
+		if (!PageUptodate(page) || PageReadahead(page))
+			goto skip;
+		if (PageHWPoison(page))
+			goto skip;
+		if (!trylock_page(page))
+			goto skip;
+		if (page->mapping != mapping)
+			goto unlock;
+		if (!PageUptodate(page))
+			goto unlock;
+		max_idx = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE);
+		if (xas->xa_index >= max_idx)
+			goto unlock;
+		return page;
+unlock:
+		unlock_page(page);
+skip:
+		put_page(page);
+	} while ((page = xas_next_entry(xas, end_pgoff)) != NULL);
+
+	return NULL;
+}
+
+static inline struct page *first_map_page(struct address_space *mapping,
+					  struct xa_state *xas,
+					  pgoff_t end_pgoff)
+{
+	return next_uptodate_page(xas_find(xas, end_pgoff),
+				  mapping, xas, end_pgoff);
+}
+
+static inline struct page *next_map_page(struct address_space *mapping,
+					 struct xa_state *xas,
+					 pgoff_t end_pgoff)
+{
+	return next_uptodate_page(xas_next_entry(xas, end_pgoff),
+				  mapping, xas, end_pgoff);
+}
+
+vm_fault_t filemap_map_pages(struct vm_fault *vmf,
+			     pgoff_t start_pgoff, pgoff_t end_pgoff)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	struct file *file = vma->vm_file;
 	struct address_space *mapping = file->f_mapping;
 	pgoff_t last_pgoff = start_pgoff;
-	unsigned long max_idx;
+	unsigned long address = vmf->address;
 	XA_STATE(xas, &mapping->i_pages, start_pgoff);
 	struct page *head, *page;
 	unsigned int mmap_miss = READ_ONCE(file->f_ra.mmap_miss);
+	vm_fault_t ret = 0;
 
 	rcu_read_lock();
-	xas_for_each(&xas, head, end_pgoff) {
-		if (xas_retry(&xas, head))
-			continue;
-		if (xa_is_value(head))
-			goto next;
+	head = first_map_page(mapping, &xas, end_pgoff);
+	if (!head)
+		goto out;
 
-		/*
-		 * Check for a locked page first, as a speculative
-		 * reference may adversely influence page migration.
-		 */
-		if (PageLocked(head))
-			goto next;
-		if (!page_cache_get_speculative(head))
-			goto next;
+	if (filemap_map_pmd(vmf, head)) {
+		ret = VM_FAULT_NOPAGE;
+		goto out;
+	}
 
-		/* Has the page moved or been split? */
-		if (unlikely(head != xas_reload(&xas)))
-			goto skip;
+	vmf->address = vma->vm_start + ((start_pgoff - vma->vm_pgoff) << PAGE_SHIFT);
+	vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl);
+	do {
 		page = find_subpage(head, xas.xa_index);
-
-		if (!PageUptodate(head) ||
-				PageReadahead(page) ||
-				PageHWPoison(page))
-			goto skip;
-		if (!trylock_page(head))
-			goto skip;
-
-		if (head->mapping != mapping || !PageUptodate(head))
-			goto unlock;
-
-		max_idx = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE);
-		if (xas.xa_index >= max_idx)
+		if (PageHWPoison(page))
 			goto unlock;
 
 		if (mmap_miss > 0)
 			mmap_miss--;
 
 		vmf->address += (xas.xa_index - last_pgoff) << PAGE_SHIFT;
-		if (vmf->pte)
-			vmf->pte += xas.xa_index - last_pgoff;
+		vmf->pte += xas.xa_index - last_pgoff;
 		last_pgoff = xas.xa_index;
-		if (alloc_set_pte(vmf, page))
+
+		if (!pte_none(*vmf->pte))
 			goto unlock;
+
+		do_set_pte(vmf, page);
+		/* no need to invalidate: a not-present page won't be cached */
+		update_mmu_cache(vma, vmf->address, vmf->pte);
 		unlock_page(head);
-		goto next;
+
+		/* The fault is handled */
+		if (vmf->address == address)
+			ret = VM_FAULT_NOPAGE;
+		continue;
 unlock:
 		unlock_page(head);
-skip:
 		put_page(head);
-next:
-		/* Huge page is mapped? No need to proceed. */
-		if (pmd_trans_huge(*vmf->pmd))
-			break;
-	}
+	} while ((head = next_map_page(mapping, &xas, end_pgoff)) != NULL);
+	pte_unmap_unlock(vmf->pte, vmf->ptl);
+out:
 	rcu_read_unlock();
+	vmf->address = address;
 	WRITE_ONCE(file->f_ra.mmap_miss, mmap_miss);
+	return ret;
 }
 EXPORT_SYMBOL(filemap_map_pages);
 

@@ -3503,7 +3503,7 @@ 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;
 

@@ -3643,66 +3643,6 @@ 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 +3657,7 @@ 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;

@@ -3775,52 +3715,17 @@ static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
 	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)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
 	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);

@@ -3837,14 +3742,8 @@ vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct page *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;
 }
 
-
 /**
  * finish_fault - finish page fault once we have prepared the page to fault
  *

@@ -3862,12 +3761,12 @@ 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 +3775,38 @@ 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);
+	else
+		ret = VM_FAULT_NOPAGE;
+
+	update_mmu_tlb(vma, vmf->address, vmf->pte);
+	pte_unmap_unlock(vmf->pte, vmf->ptl);
 	return ret;
 }
 

@@ -3951,13 +3876,12 @@ 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 +3889,7 @@ 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 +3897,11 @@ 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 +4257,18 @@ 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;
 		/*

@@ -1520,11 +1520,13 @@ static struct page *shmem_swapin(swp_entry_t swap, gfp_t gfp,
 {
 	struct vm_area_struct pvma;
 	struct page *page;
-	struct vm_fault vmf;
+	struct vm_fault vmf = {
+		.info = {
+			.vma = &pvma,
+		},
+	};
 
 	shmem_pseudo_vma_init(&pvma, info, index);
-	vmf.info.vma = &pvma;
-	vmf.info.address = 0;
 	page = swap_cluster_readahead(swap, gfp, &vmf);
 	shmem_pseudo_vma_destroy(&pvma);
 

@@ -1951,8 +1951,6 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 	si = swap_info[type];
 	pte = pte_offset_map(pmd, addr);
 	do {
-		struct vm_fault vmf;
-
 		if (!is_swap_pte(*pte))
 			continue;
 

@@ -1968,9 +1966,14 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 		swap_map = &si->swap_map[offset];
 		page = lookup_swap_cache(entry, vma, addr);
 		if (!page) {
-			vmf.info.vma = vma;
-			vmf.info.address = addr;
-			vmf.pmd = pmd;
+			struct vm_fault vmf = {
+				.info = {
+					.vma = vma,
+					.address = addr,
+				},
+				.pmd = pmd,
+			};
+
 			page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE,
 						&vmf);
 		}

@@ -521,7 +521,7 @@ struct vm_fault_info {
 };
 
 struct vm_fault {
-	struct vm_fault_info info;
+	const struct vm_fault_info info;
 	unsigned int flags;		/* FAULT_FLAG_xxx flags
 					 * XXX: should be in vm_fault_info */
 	pmd_t *pmd;			/* Pointer to pmd entry matching

@@ -434,7 +434,6 @@ extern pgprot_t protection_map[16];
  * @FAULT_FLAG_REMOTE: The fault is not for current task/mm.
  * @FAULT_FLAG_INSTRUCTION: The fault was during an instruction fetch.
  * @FAULT_FLAG_INTERRUPTIBLE: The fault can be interrupted by non-fatal signals.
- * @FAULT_FLAG_PREFAULT: Fault was a prefault.
  *
  * About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify
  * whether we would allow page faults to retry by specifying these two

@@ -465,7 +464,6 @@ extern pgprot_t protection_map[16];
 #define FAULT_FLAG_REMOTE			0x80
 #define FAULT_FLAG_INSTRUCTION  		0x100
 #define FAULT_FLAG_INTERRUPTIBLE		0x200
-#define FAULT_FLAG_PREFAULT			0x400
 
 /*
  * The default fault flags that should be used by most of the

@@ -503,8 +501,7 @@ static inline bool fault_flag_allow_retry_first(unsigned int flags)
 	{ FAULT_FLAG_USER,		"USER" }, \
 	{ FAULT_FLAG_REMOTE,		"REMOTE" }, \
 	{ FAULT_FLAG_INSTRUCTION,	"INSTRUCTION" }, \
-	{ FAULT_FLAG_INTERRUPTIBLE,	"INTERRUPTIBLE" }, \
-	{ FAULT_FLAG_PREFAULT,		"PREFAULT" }
+	{ FAULT_FLAG_INTERRUPTIBLE,	"INTERRUPTIBLE" }
 
 /*
  * vm_fault is filled by the pagefault handler and passed to the vma's

@@ -997,7 +994,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
 }
 
 vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page);
-void do_set_pte(struct vm_fault *vmf, struct page *page);
+void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr);
 
 vm_fault_t finish_fault(struct vm_fault *vmf);
 vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf);

@@ -3018,8 +3018,7 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf,
 	struct file *file = vma->vm_file;
 	struct address_space *mapping = file->f_mapping;
 	pgoff_t last_pgoff = start_pgoff;
-	unsigned long address = vmf->info.address;
-	unsigned long flags = vmf->flags;
+	unsigned long addr;
 	XA_STATE(xas, &mapping->i_pages, start_pgoff);
 	struct page *head, *page;
 	unsigned int mmap_miss = READ_ONCE(file->f_ra.mmap_miss);