mm/gup: remove vmas array from internal GUP functions

Now we have eliminated all callers to GUP APIs which use the vmas
parameter, eliminate it altogether.

This eliminates a class of bugs where vmas might have been kept around
longer than the mmap_lock and thus we need not be concerned about locks
being dropped during this operation leaving behind dangling pointers.

This simplifies the GUP API and makes it considerably clearer as to its
purpose - follow flags are applied and if pinning, an array of pages is
returned.

Link: https://lkml.kernel.org/r/6811b4b2b4b3baf3dd07f422bb18853bb2cd09fb.1684350871.git.lstoakes@gmail.com
Signed-off-by: Lorenzo Stoakes <lstoakes@gmail.com>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Janosch Frank <frankja@linux.ibm.com>
Cc: Jarkko Sakkinen <jarkko@kernel.org>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Sakari Ailus <sakari.ailus@linux.intel.com>
Cc: Sean Christopherson <seanjc@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 31 insertions, 52 deletions

diff --git a/mm/gup.c b/mm/gup.c
index 18e3bc2ee3f1..8db58305f4eb 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1024,8 +1024,6 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
  * @pages:	array that receives pointers to the pages pinned.
  *		Should be at least nr_pages long. Or NULL, if caller
  *		only intends to ensure the pages are faulted in.
- * @vmas:	array of pointers to vmas corresponding to each page.
- *		Or NULL if the caller does not require them.
  * @locked:     whether we're still with the mmap_lock held
  *
  * Returns either number of pages pinned (which may be less than the
@@ -1039,8 +1037,6 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
  *
  * The caller is responsible for releasing returned @pages, via put_page().
  *
- * @vmas are valid only as long as mmap_lock is held.
- *
  * Must be called with mmap_lock held.  It may be released.  See below.
  *
  * __get_user_pages walks a process's page tables and takes a reference to
@@ -1076,7 +1072,7 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
 static long __get_user_pages(struct mm_struct *mm,
 		unsigned long start, unsigned long nr_pages,
 		unsigned int gup_flags, struct page **pages,
-		struct vm_area_struct **vmas, int *locked)
+		int *locked)
 {
 	long ret = 0, i = 0;
 	struct vm_area_struct *vma = NULL;
@@ -1116,9 +1112,9 @@ static long __get_user_pages(struct mm_struct *mm,
 				goto out;
 
 			if (is_vm_hugetlb_page(vma)) {
-				i = follow_hugetlb_page(mm, vma, pages, vmas,
-						&start, &nr_pages, i,
-						gup_flags, locked);
+				i = follow_hugetlb_page(mm, vma, pages,
+							&start, &nr_pages, i,
+							gup_flags, locked);
 				if (!*locked) {
 					/*
 					 * We've got a VM_FAULT_RETRY
@@ -1183,10 +1179,6 @@ retry:
 			ctx.page_mask = 0;
 		}
 next_page:
-		if (vmas) {
-			vmas[i] = vma;
-			ctx.page_mask = 0;
-		}
 		page_increm = 1 + (~(start >> PAGE_SHIFT) & ctx.page_mask);
 		if (page_increm > nr_pages)
 			page_increm = nr_pages;
@@ -1341,7 +1333,6 @@ static __always_inline long __get_user_pages_locked(struct mm_struct *mm,
 						unsigned long start,
 						unsigned long nr_pages,
 						struct page **pages,
-						struct vm_area_struct **vmas,
 						int *locked,
 						unsigned int flags)
 {
@@ -1379,7 +1370,7 @@ static __always_inline long __get_user_pages_locked(struct mm_struct *mm,
 	pages_done = 0;
 	for (;;) {
 		ret = __get_user_pages(mm, start, nr_pages, flags, pages,
-				       vmas, locked);
+				       locked);
 		if (!(flags & FOLL_UNLOCKABLE)) {
 			/* VM_FAULT_RETRY couldn't trigger, bypass */
 			pages_done = ret;
@@ -1443,7 +1434,7 @@ retry:
 
 		*locked = 1;
 		ret = __get_user_pages(mm, start, 1, flags | FOLL_TRIED,
-				       pages, NULL, locked);
+				       pages, locked);
 		if (!*locked) {
 			/* Continue to retry until we succeeded */
 			BUG_ON(ret != 0);
@@ -1541,7 +1532,7 @@ long populate_vma_page_range(struct vm_area_struct *vma,
 	 * not result in a stack expansion that recurses back here.
 	 */
 	ret = __get_user_pages(mm, start, nr_pages, gup_flags,
-				NULL, NULL, locked ? locked : &local_locked);
+			       NULL, locked ? locked : &local_locked);
 	lru_add_drain();
 	return ret;
 }
@@ -1599,7 +1590,7 @@ long faultin_vma_page_range(struct vm_area_struct *vma, unsigned long start,
 		return -EINVAL;
 
 	ret = __get_user_pages(mm, start, nr_pages, gup_flags,
-				NULL, NULL, locked);
+			       NULL, locked);
 	lru_add_drain();
 	return ret;
 }
@@ -1667,8 +1658,7 @@ int __mm_populate(unsigned long start, unsigned long len, int ignore_errors)
 #else /* CONFIG_MMU */
 static long __get_user_pages_locked(struct mm_struct *mm, unsigned long start,
 		unsigned long nr_pages, struct page **pages,
-		struct vm_area_struct **vmas, int *locked,
-		unsigned int foll_flags)
+		int *locked, unsigned int foll_flags)
 {
 	struct vm_area_struct *vma;
 	bool must_unlock = false;
@@ -1712,8 +1702,7 @@ static long __get_user_pages_locked(struct mm_struct *mm, unsigned long start,
 			if (pages[i])
 				get_page(pages[i]);
 		}
-		if (vmas)
-			vmas[i] = vma;
+
 		start = (start + PAGE_SIZE) & PAGE_MASK;
 	}
 
@@ -1894,8 +1883,7 @@ struct page *get_dump_page(unsigned long addr)
 	int locked = 0;
 	int ret;
 
-	ret = __get_user_pages_locked(current->mm, addr, 1, &page, NULL,
-				      &locked,
+	ret = __get_user_pages_locked(current->mm, addr, 1, &page, &locked,
 				      FOLL_FORCE | FOLL_DUMP | FOLL_GET);
 	return (ret == 1) ? page : NULL;
 }
@@ -2068,7 +2056,6 @@ static long __gup_longterm_locked(struct mm_struct *mm,
 				  unsigned long start,
 				  unsigned long nr_pages,
 				  struct page **pages,
-				  struct vm_area_struct **vmas,
 				  int *locked,
 				  unsigned int gup_flags)
 {
@@ -2076,13 +2063,13 @@ static long __gup_longterm_locked(struct mm_struct *mm,
 	long rc, nr_pinned_pages;
 
 	if (!(gup_flags & FOLL_LONGTERM))
-		return __get_user_pages_locked(mm, start, nr_pages, pages, vmas,
+		return __get_user_pages_locked(mm, start, nr_pages, pages,
 					       locked, gup_flags);
 
 	flags = memalloc_pin_save();
 	do {
 		nr_pinned_pages = __get_user_pages_locked(mm, start, nr_pages,
-							  pages, vmas, locked,
+							  pages, locked,
 							  gup_flags);
 		if (nr_pinned_pages <= 0) {
 			rc = nr_pinned_pages;
@@ -2100,9 +2087,8 @@ static long __gup_longterm_locked(struct mm_struct *mm,
  * Check that the given flags are valid for the exported gup/pup interface, and
  * update them with the required flags that the caller must have set.
  */
-static bool is_valid_gup_args(struct page **pages, struct vm_area_struct **vmas,
-			      int *locked, unsigned int *gup_flags_p,
-			      unsigned int to_set)
+static bool is_valid_gup_args(struct page **pages, int *locked,
+			      unsigned int *gup_flags_p, unsigned int to_set)
 {
 	unsigned int gup_flags = *gup_flags_p;
 
@@ -2144,13 +2130,6 @@ static bool is_valid_gup_args(struct page **pages, struct vm_area_struct **vmas,
 			 (gup_flags & FOLL_PCI_P2PDMA)))
 		return false;
 
-	/*
-	 * Can't use VMAs with locked, as locked allows GUP to unlock
-	 * which invalidates the vmas array
-	 */
-	if (WARN_ON_ONCE(vmas && (gup_flags & FOLL_UNLOCKABLE)))
-		return false;
-
 	*gup_flags_p = gup_flags;
 	return true;
 }
@@ -2219,11 +2198,11 @@ long get_user_pages_remote(struct mm_struct *mm,
 {
 	int local_locked = 1;
 
-	if (!is_valid_gup_args(pages, NULL, locked, &gup_flags,
+	if (!is_valid_gup_args(pages, locked, &gup_flags,
 			       FOLL_TOUCH | FOLL_REMOTE))
 		return -EINVAL;
 
-	return __get_user_pages_locked(mm, start, nr_pages, pages, NULL,
+	return __get_user_pages_locked(mm, start, nr_pages, pages,
 				       locked ? locked : &local_locked,
 				       gup_flags);
 }
@@ -2258,11 +2237,11 @@ long get_user_pages(unsigned long start, unsigned long nr_pages,
 {
 	int locked = 1;
 
-	if (!is_valid_gup_args(pages, NULL, NULL, &gup_flags, FOLL_TOUCH))
+	if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_TOUCH))
 		return -EINVAL;
 
 	return __get_user_pages_locked(current->mm, start, nr_pages, pages,
-				       NULL, &locked, gup_flags);
+				       &locked, gup_flags);
 }
 EXPORT_SYMBOL(get_user_pages);
 
@@ -2286,12 +2265,12 @@ long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
 {
 	int locked = 0;
 
-	if (!is_valid_gup_args(pages, NULL, NULL, &gup_flags,
+	if (!is_valid_gup_args(pages, NULL, &gup_flags,
 			       FOLL_TOUCH | FOLL_UNLOCKABLE))
 		return -EINVAL;
 
 	return __get_user_pages_locked(current->mm, start, nr_pages, pages,
-				       NULL, &locked, gup_flags);
+				       &locked, gup_flags);
 }
 EXPORT_SYMBOL(get_user_pages_unlocked);
 
@@ -2981,7 +2960,7 @@ static int internal_get_user_pages_fast(unsigned long start,
 	start += nr_pinned << PAGE_SHIFT;
 	pages += nr_pinned;
 	ret = __gup_longterm_locked(current->mm, start, nr_pages - nr_pinned,
-				    pages, NULL, &locked,
+				    pages, &locked,
 				    gup_flags | FOLL_TOUCH | FOLL_UNLOCKABLE);
 	if (ret < 0) {
 		/*
@@ -3023,7 +3002,7 @@ int get_user_pages_fast_only(unsigned long start, int nr_pages,
 	 * FOLL_FAST_ONLY is required in order to match the API description of
 	 * this routine: no fall back to regular ("slow") GUP.
 	 */
-	if (!is_valid_gup_args(pages, NULL, NULL, &gup_flags,
+	if (!is_valid_gup_args(pages, NULL, &gup_flags,
 			       FOLL_GET | FOLL_FAST_ONLY))
 		return -EINVAL;
 
@@ -3056,7 +3035,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages,
 	 * FOLL_GET, because gup fast is always a "pin with a +1 page refcount"
 	 * request.
 	 */
-	if (!is_valid_gup_args(pages, NULL, NULL, &gup_flags, FOLL_GET))
+	if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_GET))
 		return -EINVAL;
 	return internal_get_user_pages_fast(start, nr_pages, gup_flags, pages);
 }
@@ -3081,7 +3060,7 @@ EXPORT_SYMBOL_GPL(get_user_pages_fast);
 int pin_user_pages_fast(unsigned long start, int nr_pages,
 			unsigned int gup_flags, struct page **pages)
 {
-	if (!is_valid_gup_args(pages, NULL, NULL, &gup_flags, FOLL_PIN))
+	if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_PIN))
 		return -EINVAL;
 	return internal_get_user_pages_fast(start, nr_pages, gup_flags, pages);
 }
@@ -3114,10 +3093,10 @@ long pin_user_pages_remote(struct mm_struct *mm,
 {
 	int local_locked = 1;
 
-	if (!is_valid_gup_args(pages, NULL, locked, &gup_flags,
+	if (!is_valid_gup_args(pages, locked, &gup_flags,
 			       FOLL_PIN | FOLL_TOUCH | FOLL_REMOTE))
 		return 0;
-	return __gup_longterm_locked(mm, start, nr_pages, pages, NULL,
+	return __gup_longterm_locked(mm, start, nr_pages, pages,
 				     locked ? locked : &local_locked,
 				     gup_flags);
 }
@@ -3143,10 +3122,10 @@ long pin_user_pages(unsigned long start, unsigned long nr_pages,
 {
 	int locked = 1;
 
-	if (!is_valid_gup_args(pages, NULL, NULL, &gup_flags, FOLL_PIN))
+	if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_PIN))
 		return 0;
 	return __gup_longterm_locked(current->mm, start, nr_pages,
-				     pages, NULL, &locked, gup_flags);
+				     pages, &locked, gup_flags);
 }
 EXPORT_SYMBOL(pin_user_pages);
 
@@ -3160,11 +3139,11 @@ long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
 {
 	int locked = 0;
 
-	if (!is_valid_gup_args(pages, NULL, NULL, &gup_flags,
+	if (!is_valid_gup_args(pages, NULL, &gup_flags,
 			       FOLL_PIN | FOLL_TOUCH | FOLL_UNLOCKABLE))
 		return 0;
 
-	return __gup_longterm_locked(current->mm, start, nr_pages, pages, NULL,
+	return __gup_longterm_locked(current->mm, start, nr_pages, pages,
 				     &locked, gup_flags);
 }
 EXPORT_SYMBOL(pin_user_pages_unlocked);