mm: introduce fault_env

The idea borrowed from Peter's patch from patchset on speculative page
faults[1]:

Instead of passing around the endless list of function arguments,
replace the lot with a single structure so we can change context without
endless function signature changes.

The changes are mostly mechanical with exception of faultaround code:
filemap_map_pages() got reworked a bit.

This patch is preparation for the next one.

[1] http://lkml.kernel.org/r/20141020222841.302891540@infradead.org

Link: http://lkml.kernel.org/r/1466021202-61880-9-git-send-email-kirill.shutemov@linux.intel.com
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Documentation/filesystems/Locking

@@ -548,13 +548,13 @@ subsequent truncate), and then return with VM_FAULT_LOCKED, and the page
 locked. The VM will unlock the page.
 
 	->map_pages() is called when VM asks to map easy accessible pages.
-Filesystem should find and map pages associated with offsets from "pgoff"
-till "max_pgoff". ->map_pages() is called with page table locked and must
+Filesystem should find and map pages associated with offsets from "start_pgoff"
+till "end_pgoff". ->map_pages() is called with page table locked and must
 not block.  If it's not possible to reach a page without blocking,
 filesystem should skip it. Filesystem should use do_set_pte() to setup
-page table entry. Pointer to entry associated with offset "pgoff" is
-passed in "pte" field in vm_fault structure. Pointers to entries for other
-offsets should be calculated relative to "pte".
+page table entry. Pointer to entry associated with the page is passed in
+"pte" field in fault_env structure. Pointers to entries for other offsets
+should be calculated relative to "pte".
 
 	->page_mkwrite() is called when a previously read-only pte is
 about to become writeable. The filesystem again must ensure that there are

fs/userfaultfd.c

@@ -257,10 +257,9 @@ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx,
  * fatal_signal_pending()s, and the mmap_sem must be released before
  * returning it.
  */
-int handle_userfault(struct vm_area_struct *vma, unsigned long address,
-		     unsigned int flags, unsigned long reason)
+int handle_userfault(struct fault_env *fe, unsigned long reason)
 {
-	struct mm_struct *mm = vma->vm_mm;
+	struct mm_struct *mm = fe->vma->vm_mm;
 	struct userfaultfd_ctx *ctx;
 	struct userfaultfd_wait_queue uwq;
 	int ret;
@@ -269,7 +268,7 @@ int handle_userfault(struct vm_area_struct *vma, unsigned long address,
 	BUG_ON(!rwsem_is_locked(&mm->mmap_sem));
 
 	ret = VM_FAULT_SIGBUS;
-	ctx = vma->vm_userfaultfd_ctx.ctx;
+	ctx = fe->vma->vm_userfaultfd_ctx.ctx;
 	if (!ctx)
 		goto out;
 
@@ -302,17 +301,17 @@ int handle_userfault(struct vm_area_struct *vma, unsigned long address,
 	 * without first stopping userland access to the memory. For
 	 * VM_UFFD_MISSING userfaults this is enough for now.
 	 */
-	if (unlikely(!(flags & FAULT_FLAG_ALLOW_RETRY))) {
+	if (unlikely(!(fe->flags & FAULT_FLAG_ALLOW_RETRY))) {
 		/*
 		 * Validate the invariant that nowait must allow retry
 		 * to be sure not to return SIGBUS erroneously on
 		 * nowait invocations.
 		 */
-		BUG_ON(flags & FAULT_FLAG_RETRY_NOWAIT);
+		BUG_ON(fe->flags & FAULT_FLAG_RETRY_NOWAIT);
 #ifdef CONFIG_DEBUG_VM
 		if (printk_ratelimit()) {
 			printk(KERN_WARNING
-			       "FAULT_FLAG_ALLOW_RETRY missing %x\n", flags);
+			       "FAULT_FLAG_ALLOW_RETRY missing %x\n", fe->flags);
 			dump_stack();
 		}
 #endif
@@ -324,18 +323,19 @@ int handle_userfault(struct vm_area_struct *vma, unsigned long address,
 	 * and wait.
 	 */
 	ret = VM_FAULT_RETRY;
-	if (flags & FAULT_FLAG_RETRY_NOWAIT)
+	if (fe->flags & FAULT_FLAG_RETRY_NOWAIT)
 		goto out;
 
 	/* take the reference before dropping the mmap_sem */
 	userfaultfd_ctx_get(ctx);
 
 	init_waitqueue_func_entry(&uwq.wq, userfaultfd_wake_function);
 	uwq.wq.private = current;
-	uwq.msg = userfault_msg(address, flags, reason);
+	uwq.msg = userfault_msg(fe->address, fe->flags, reason);
 	uwq.ctx = ctx;
 
-	return_to_userland = (flags & (FAULT_FLAG_USER|FAULT_FLAG_KILLABLE)) ==
+	return_to_userland =
+		(fe->flags & (FAULT_FLAG_USER|FAULT_FLAG_KILLABLE)) ==
 		(FAULT_FLAG_USER|FAULT_FLAG_KILLABLE);
 
 	spin_lock(&ctx->fault_pending_wqh.lock);
@@ -353,7 +353,7 @@ int handle_userfault(struct vm_area_struct *vma, unsigned long address,
 			  TASK_KILLABLE);
 	spin_unlock(&ctx->fault_pending_wqh.lock);
 
-	must_wait = userfaultfd_must_wait(ctx, address, flags, reason);
+	must_wait = userfaultfd_must_wait(ctx, fe->address, fe->flags, reason);
 	up_read(&mm->mmap_sem);
 
 	if (likely(must_wait && !ACCESS_ONCE(ctx->released) &&

include/linux/huge_mm.h

@@ -1,20 +1,12 @@
 #ifndef _LINUX_HUGE_MM_H
 #define _LINUX_HUGE_MM_H
 
-extern int do_huge_pmd_anonymous_page(struct mm_struct *mm,
-				      struct vm_area_struct *vma,
-				      unsigned long address, pmd_t *pmd,
-				      unsigned int flags);
+extern int do_huge_pmd_anonymous_page(struct fault_env *fe);
 extern int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 			 pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
 			 struct vm_area_struct *vma);
-extern void huge_pmd_set_accessed(struct mm_struct *mm,
-				  struct vm_area_struct *vma,
-				  unsigned long address, pmd_t *pmd,
-				  pmd_t orig_pmd, int dirty);
-extern int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
-			       unsigned long address, pmd_t *pmd,
-			       pmd_t orig_pmd);
+extern void huge_pmd_set_accessed(struct fault_env *fe, pmd_t orig_pmd);
+extern int do_huge_pmd_wp_page(struct fault_env *fe, pmd_t orig_pmd);
 extern struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 					  unsigned long addr,
 					  pmd_t *pmd,
@@ -134,8 +126,7 @@ static inline int hpage_nr_pages(struct page *page)
 	return 1;
 }
 
-extern int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
-				unsigned long addr, pmd_t pmd, pmd_t *pmdp);
+extern int do_huge_pmd_numa_page(struct fault_env *fe, pmd_t orig_pmd);
 
 extern struct page *huge_zero_page;
 
@@ -196,8 +187,7 @@ static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd,
 	return NULL;
 }
 
-static inline int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
-					unsigned long addr, pmd_t pmd, pmd_t *pmdp)
+static inline int do_huge_pmd_numa_page(struct fault_env *fe, pmd_t orig_pmd)
 {
 	return 0;
 }

include/linux/mm.h

@@ -309,10 +309,27 @@ struct vm_fault {
 					 * VM_FAULT_DAX_LOCKED and fill in
 					 * entry here.
 					 */
-	/* for ->map_pages() only */
-	pgoff_t max_pgoff;		/* map pages for offset from pgoff till
-					 * max_pgoff inclusive */
-	pte_t *pte;			/* pte entry associated with ->pgoff */
+};
+
+/*
+ * Page fault context: passes though page fault handler instead of endless list
+ * of function arguments.
+ */
+struct fault_env {
+	struct vm_area_struct *vma;	/* Target VMA */
+	unsigned long address;		/* Faulting virtual address */
+	unsigned int flags;		/* FAULT_FLAG_xxx flags */
+	pmd_t *pmd;			/* Pointer to pmd entry matching
+					 * the 'address'
+					 */
+	pte_t *pte;			/* Pointer to pte entry matching
+					 * the 'address'. NULL if the page
+					 * table hasn't been allocated.
+					 */
+	spinlock_t *ptl;		/* Page table lock.
+					 * Protects pte page table if 'pte'
+					 * is not NULL, otherwise pmd.
+					 */
 };
 
 /*
@@ -327,7 +344,8 @@ struct vm_operations_struct {
 	int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf);
 	int (*pmd_fault)(struct vm_area_struct *, unsigned long address,
 						pmd_t *, unsigned int flags);
-	void (*map_pages)(struct vm_area_struct *vma, struct vm_fault *vmf);
+	void (*map_pages)(struct fault_env *fe,
+			pgoff_t start_pgoff, pgoff_t end_pgoff);
 
 	/* notification that a previously read-only page is about to become
 	 * writable, if an error is returned it will cause a SIGBUS */
@@ -600,8 +618,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
 	return pte;
 }
 
-void do_set_pte(struct vm_area_struct *vma, unsigned long address,
-		struct page *page, pte_t *pte, bool write, bool anon);
+void do_set_pte(struct fault_env *fe, struct page *page);
 #endif
 
 /*
@@ -2062,7 +2079,8 @@ extern void truncate_inode_pages_final(struct address_space *);
 
 /* generic vm_area_ops exported for stackable file systems */
 extern int filemap_fault(struct vm_area_struct *, struct vm_fault *);
-extern void filemap_map_pages(struct vm_area_struct *vma, struct vm_fault *vmf);
+extern void filemap_map_pages(struct fault_env *fe,
+		pgoff_t start_pgoff, pgoff_t end_pgoff);
 extern int filemap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
 
 /* mm/page-writeback.c */

include/linux/userfaultfd_k.h

@@ -27,8 +27,7 @@
 #define UFFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK)
 #define UFFD_FLAGS_SET (EFD_SHARED_FCNTL_FLAGS)
 
-extern int handle_userfault(struct vm_area_struct *vma, unsigned long address,
-			    unsigned int flags, unsigned long reason);
+extern int handle_userfault(struct fault_env *fe, unsigned long reason);
 
 extern ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start,
 			    unsigned long src_start, unsigned long len);
@@ -56,10 +55,7 @@ static inline bool userfaultfd_armed(struct vm_area_struct *vma)
 #else /* CONFIG_USERFAULTFD */
 
 /* mm helpers */
-static inline int handle_userfault(struct vm_area_struct *vma,
-				   unsigned long address,
-				   unsigned int flags,
-				   unsigned long reason)
+static inline int handle_userfault(struct fault_env *fe, unsigned long reason)
 {
 	return VM_FAULT_SIGBUS;
 }

mm/filemap.c

@@ -2128,22 +2128,27 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 }
 EXPORT_SYMBOL(filemap_fault);
 
-void filemap_map_pages(struct vm_area_struct *vma, struct vm_fault *vmf)
+void filemap_map_pages(struct fault_env *fe,
+		pgoff_t start_pgoff, pgoff_t end_pgoff)
 {
 	struct radix_tree_iter iter;
 	void **slot;
-	struct file *file = vma->vm_file;
+	struct file *file = fe->vma->vm_file;
 	struct address_space *mapping = file->f_mapping;
+	pgoff_t last_pgoff = start_pgoff;
 	loff_t size;
 	struct page *page;
-	unsigned long address = (unsigned long) vmf->virtual_address;
-	unsigned long addr;
-	pte_t *pte;
 
 	rcu_read_lock();
-	radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, vmf->pgoff) {
-		if (iter.index > vmf->max_pgoff)
+	radix_tree_for_each_slot(slot, &mapping->page_tree, &iter,
+			start_pgoff) {
+		if (iter.index > end_pgoff)
 			break;
+		fe->pte += iter.index - last_pgoff;
+		fe->address += (iter.index - last_pgoff) << PAGE_SHIFT;
+		last_pgoff = iter.index;
+		if (!pte_none(*fe->pte))
+			goto next;
 repeat:
 		page = radix_tree_deref_slot(slot);
 		if (unlikely(!page))
@@ -2179,22 +2184,17 @@ void filemap_map_pages(struct vm_area_struct *vma, struct vm_fault *vmf)
 		if (page->index >= size >> PAGE_SHIFT)
 			goto unlock;
 
-		pte = vmf->pte + page->index - vmf->pgoff;
-		if (!pte_none(*pte))
-			goto unlock;
-
 		if (file->f_ra.mmap_miss > 0)
 			file->f_ra.mmap_miss--;
-		addr = address + (page->index - vmf->pgoff) * PAGE_SIZE;
-		do_set_pte(vma, addr, page, pte, false, false);
+		do_set_pte(fe, page);
 		unlock_page(page);
 		goto next;
 unlock:
 		unlock_page(page);
 skip:
 		put_page(page);
 next:
-		if (iter.index == vmf->max_pgoff)
+		if (iter.index == end_pgoff)
 			break;
 	}
 	rcu_read_unlock();