Merge branch 'akpm' (patches from Andrew)

Pull updates from Andrew Morton:
 "Most of -mm and quite a number of other subsystems: hotfixes, scripts,
  ocfs2, misc, lib, binfmt, init, reiserfs, exec, dma-mapping, kcov.

  MM is fairly quiet this time.  Holidays, I assume"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (118 commits)
  kcov: ignore fault-inject and stacktrace
  include/linux/io-mapping.h-mapping: use PHYS_PFN() macro in io_mapping_map_atomic_wc()
  execve: warn if process starts with executable stack
  reiserfs: prevent NULL pointer dereference in reiserfs_insert_item()
  init/main.c: fix misleading "This architecture does not have kernel memory protection" message
  init/main.c: fix quoted value handling in unknown_bootoption
  init/main.c: remove unnecessary repair_env_string in do_initcall_level
  init/main.c: log arguments and environment passed to init
  fs/binfmt_elf.c: coredump: allow process with empty address space to coredump
  fs/binfmt_elf.c: coredump: delete duplicated overflow check
  fs/binfmt_elf.c: coredump: allocate core ELF header on stack
  fs/binfmt_elf.c: make BAD_ADDR() unlikely
  fs/binfmt_elf.c: better codegen around current->mm
  fs/binfmt_elf.c: don't copy ELF header around
  fs/binfmt_elf.c: fix ->start_code calculation
  fs/binfmt_elf.c: smaller code generation around auxv vector fill
  lib/find_bit.c: uninline helper _find_next_bit()
  lib/find_bit.c: join _find_next_bit{_le}
  uapi: rename ext2_swab() to swab() and share globally in swab.h
  lib/scatterlist.c: adjust indentation in __sg_alloc_table
  ...

27 files changed, 769 insertions, 621 deletions

diff --git a/mm/Makefile b/mm/Makefile
index 1937cc251883..32f08e22e824 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -20,6 +20,7 @@ KCOV_INSTRUMENT_kmemleak.o := n
 KCOV_INSTRUMENT_memcontrol.o := n
 KCOV_INSTRUMENT_mmzone.o := n
 KCOV_INSTRUMENT_vmstat.o := n
+KCOV_INSTRUMENT_failslab.o := n
 
 CFLAGS_init-mm.o += $(call cc-disable-warning, override-init)
 CFLAGS_init-mm.o += $(call cc-disable-warning, initializer-overrides)
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index c360f6a6c844..62f05f605fb5 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -21,6 +21,7 @@ struct backing_dev_info noop_backing_dev_info = {
 EXPORT_SYMBOL_GPL(noop_backing_dev_info);
 
 static struct class *bdi_class;
+const char *bdi_unknown_name = "(unknown)";
 
 /*
  * bdi_lock protects bdi_tree and updates to bdi_list. bdi_list has RCU
diff --git a/mm/debug.c b/mm/debug.c
index 74ee73cf7079..ecccd9f17801 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -46,7 +46,15 @@ void __dump_page(struct page *page, const char *reason)
 {
 	struct address_space *mapping;
 	bool page_poisoned = PagePoisoned(page);
+	/*
+	 * Accessing the pageblock without the zone lock. It could change to
+	 * "isolate" again in the meantime, but since we are just dumping the
+	 * state for debugging, it should be fine to accept a bit of
+	 * inaccuracy here due to racing.
+	 */
+	bool page_cma = is_migrate_cma_page(page);
 	int mapcount;
+	char *type = "";
 
 	/*
 	 * If struct page is poisoned don't access Page*() functions as that
@@ -78,9 +86,9 @@ void __dump_page(struct page *page, const char *reason)
 			page, page_ref_count(page), mapcount,
 			page->mapping, page_to_pgoff(page));
 	if (PageKsm(page))
-		pr_warn("ksm flags: %#lx(%pGp)\n", page->flags, &page->flags);
+		type = "ksm ";
 	else if (PageAnon(page))
-		pr_warn("anon flags: %#lx(%pGp)\n", page->flags, &page->flags);
+		type = "anon ";
 	else if (mapping) {
 		if (mapping->host && mapping->host->i_dentry.first) {
 			struct dentry *dentry;
@@ -88,10 +96,12 @@ void __dump_page(struct page *page, const char *reason)
 			pr_warn("%ps name:\"%pd\"\n", mapping->a_ops, dentry);
 		} else
 			pr_warn("%ps\n", mapping->a_ops);
-		pr_warn("flags: %#lx(%pGp)\n", page->flags, &page->flags);
 	}
 	BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS + 1);
 
+	pr_warn("%sflags: %#lx(%pGp)%s\n", type, page->flags, &page->flags,
+		page_cma ? " CMA" : "");
+
 hex_only:
 	print_hex_dump(KERN_WARNING, "raw: ", DUMP_PREFIX_NONE, 32,
 			sizeof(unsigned long), page,
diff --git a/mm/early_ioremap.c b/mm/early_ioremap.c
index 1826f191e72c..a0018ad1a1f6 100644
--- a/mm/early_ioremap.c
+++ b/mm/early_ioremap.c
@@ -121,8 +121,8 @@ __early_ioremap(resource_size_t phys_addr, unsigned long size, pgprot_t prot)
 		}
 	}
 
-	if (WARN(slot < 0, "%s(%08llx, %08lx) not found slot\n",
-		 __func__, (u64)phys_addr, size))
+	if (WARN(slot < 0, "%s(%pa, %08lx) not found slot\n",
+		 __func__, &phys_addr, size))
 		return NULL;
 
 	/* Don't allow wraparound or zero size */
@@ -158,8 +158,8 @@ __early_ioremap(resource_size_t phys_addr, unsigned long size, pgprot_t prot)
 		--idx;
 		--nrpages;
 	}
-	WARN(early_ioremap_debug, "%s(%08llx, %08lx) [%d] => %08lx + %08lx\n",
-	     __func__, (u64)phys_addr, size, slot, offset, slot_virt[slot]);
+	WARN(early_ioremap_debug, "%s(%pa, %08lx) [%d] => %08lx + %08lx\n",
+	     __func__, &phys_addr, size, slot, offset, slot_virt[slot]);
 
 	prev_map[slot] = (void __iomem *)(offset + slot_virt[slot]);
 	return prev_map[slot];
diff --git a/mm/filemap.c b/mm/filemap.c
index bf6aa30be58d..1784478270e1 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -632,33 +632,6 @@ static bool mapping_needs_writeback(struct address_space *mapping)
 	return mapping->nrpages;
 }
 
-int filemap_write_and_wait(struct address_space *mapping)
-{
-	int err = 0;
-
-	if (mapping_needs_writeback(mapping)) {
-		err = filemap_fdatawrite(mapping);
-		/*
-		 * Even if the above returned error, the pages may be
-		 * written partially (e.g. -ENOSPC), so we wait for it.
-		 * But the -EIO is special case, it may indicate the worst
-		 * thing (e.g. bug) happened, so we avoid waiting for it.
-		 */
-		if (err != -EIO) {
-			int err2 = filemap_fdatawait(mapping);
-			if (!err)
-				err = err2;
-		} else {
-			/* Clear any previously stored errors */
-			filemap_check_errors(mapping);
-		}
-	} else {
-		err = filemap_check_errors(mapping);
-	}
-	return err;
-}
-EXPORT_SYMBOL(filemap_write_and_wait);
-
 /**
  * filemap_write_and_wait_range - write out & wait on a file range
  * @mapping:	the address_space for the pages
@@ -680,7 +653,12 @@ int filemap_write_and_wait_range(struct address_space *mapping,
 	if (mapping_needs_writeback(mapping)) {
 		err = __filemap_fdatawrite_range(mapping, lstart, lend,
 						 WB_SYNC_ALL);
-		/* See comment of filemap_write_and_wait() */
+		/*
+		 * Even if the above returned error, the pages may be
+		 * written partially (e.g. -ENOSPC), so we wait for it.
+		 * But the -EIO is special case, it may indicate the worst
+		 * thing (e.g. bug) happened, so we avoid waiting for it.
+		 */
 		if (err != -EIO) {
 			int err2 = filemap_fdatawait_range(mapping,
 						lstart, lend);
diff --git a/mm/gup.c b/mm/gup.c
index 7646bf993b25..e13f4d211475 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -29,8 +29,23 @@ struct follow_page_context {
 	unsigned int page_mask;
 };
 
+/*
+ * Return the compound head page with ref appropriately incremented,
+ * or NULL if that failed.
+ */
+static inline struct page *try_get_compound_head(struct page *page, int refs)
+{
+	struct page *head = compound_head(page);
+
+	if (WARN_ON_ONCE(page_ref_count(head) < 0))
+		return NULL;
+	if (unlikely(!page_cache_add_speculative(head, refs)))
+		return NULL;
+	return head;
+}
+
 /**
- * put_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages
+ * unpin_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages
  * @pages:  array of pages to be maybe marked dirty, and definitely released.
  * @npages: number of pages in the @pages array.
  * @make_dirty: whether to mark the pages dirty
@@ -40,19 +55,19 @@ struct follow_page_context {
  *
  * For each page in the @pages array, make that page (or its head page, if a
  * compound page) dirty, if @make_dirty is true, and if the page was previously
- * listed as clean. In any case, releases all pages using put_user_page(),
- * possibly via put_user_pages(), for the non-dirty case.
+ * listed as clean. In any case, releases all pages using unpin_user_page(),
+ * possibly via unpin_user_pages(), for the non-dirty case.
  *
- * Please see the put_user_page() documentation for details.
+ * Please see the unpin_user_page() documentation for details.
  *
  * set_page_dirty_lock() is used internally. If instead, set_page_dirty() is
  * required, then the caller should a) verify that this is really correct,
  * because _lock() is usually required, and b) hand code it:
- * set_page_dirty_lock(), put_user_page().
+ * set_page_dirty_lock(), unpin_user_page().
  *
  */
-void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
-			       bool make_dirty)
+void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages,
+				 bool make_dirty)
 {
 	unsigned long index;
 
@@ -63,7 +78,7 @@ void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
 	 */
 
 	if (!make_dirty) {
-		put_user_pages(pages, npages);
+		unpin_user_pages(pages, npages);
 		return;
 	}
 
@@ -91,21 +106,21 @@ void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
 		 */
 		if (!PageDirty(page))
 			set_page_dirty_lock(page);
-		put_user_page(page);
+		unpin_user_page(page);
 	}
 }
-EXPORT_SYMBOL(put_user_pages_dirty_lock);
+EXPORT_SYMBOL(unpin_user_pages_dirty_lock);
 
 /**
- * put_user_pages() - release an array of gup-pinned pages.
+ * unpin_user_pages() - release an array of gup-pinned pages.
  * @pages:  array of pages to be marked dirty and released.
  * @npages: number of pages in the @pages array.
  *
- * For each page in the @pages array, release the page using put_user_page().
+ * For each page in the @pages array, release the page using unpin_user_page().
  *
- * Please see the put_user_page() documentation for details.
+ * Please see the unpin_user_page() documentation for details.
  */
-void put_user_pages(struct page **pages, unsigned long npages)
+void unpin_user_pages(struct page **pages, unsigned long npages)
 {
 	unsigned long index;
 
@@ -115,9 +130,9 @@ void put_user_pages(struct page **pages, unsigned long npages)
 	 * single operation to the head page should suffice.
 	 */
 	for (index = 0; index < npages; index++)
-		put_user_page(pages[index]);
+		unpin_user_page(pages[index]);
 }
-EXPORT_SYMBOL(put_user_pages);
+EXPORT_SYMBOL(unpin_user_pages);
 
 #ifdef CONFIG_MMU
 static struct page *no_page_table(struct vm_area_struct *vma,
@@ -179,6 +194,10 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
 	spinlock_t *ptl;
 	pte_t *ptep, pte;
 
+	/* FOLL_GET and FOLL_PIN are mutually exclusive. */
+	if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) ==
+			 (FOLL_PIN | FOLL_GET)))
+		return ERR_PTR(-EINVAL);
 retry:
 	if (unlikely(pmd_bad(*pmd)))
 		return no_page_table(vma, flags);
@@ -323,7 +342,7 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
 	pmdval = READ_ONCE(*pmd);
 	if (pmd_none(pmdval))
 		return no_page_table(vma, flags);
-	if (pmd_huge(pmdval) && vma->vm_flags & VM_HUGETLB) {
+	if (pmd_huge(pmdval) && is_vm_hugetlb_page(vma)) {
 		page = follow_huge_pmd(mm, address, pmd, flags);
 		if (page)
 			return page;
@@ -433,7 +452,7 @@ static struct page *follow_pud_mask(struct vm_area_struct *vma,
 	pud = pud_offset(p4dp, address);
 	if (pud_none(*pud))
 		return no_page_table(vma, flags);
-	if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) {
+	if (pud_huge(*pud) && is_vm_hugetlb_page(vma)) {
 		page = follow_huge_pud(mm, address, pud, flags);
 		if (page)
 			return page;
@@ -796,7 +815,7 @@ static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 
 	start = untagged_addr(start);
 
-	VM_BUG_ON(!!pages != !!(gup_flags & FOLL_GET));
+	VM_BUG_ON(!!pages != !!(gup_flags & (FOLL_GET | FOLL_PIN)));
 
 	/*
 	 * If FOLL_FORCE is set then do not force a full fault as the hinting
@@ -1020,7 +1039,16 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
 		BUG_ON(*locked != 1);
 	}
 
-	if (pages)
+	/*
+	 * FOLL_PIN and FOLL_GET are mutually exclusive. Traditional behavior
+	 * is to set FOLL_GET if the caller wants pages[] filled in (but has
+	 * carelessly failed to specify FOLL_GET), so keep doing that, but only
+	 * for FOLL_GET, not for the newer FOLL_PIN.
+	 *
+	 * FOLL_PIN always expects pages to be non-null, but no need to assert
+	 * that here, as any failures will be obvious enough.
+	 */
+	if (pages && !(flags & FOLL_PIN))
 		flags |= FOLL_GET;
 
 	pages_done = 0;
@@ -1096,88 +1124,6 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
 	return pages_done;
 }
 
-/*
- * get_user_pages_remote() - pin user pages in memory
- * @tsk:	the task_struct to use for page fault accounting, or
- *		NULL if faults are not to be recorded.
- * @mm:		mm_struct of target mm
- * @start:	starting user address
- * @nr_pages:	number of pages from start to pin
- * @gup_flags:	flags modifying lookup behaviour
- * @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:	pointer to lock flag indicating whether lock is held and
- *		subsequently whether VM_FAULT_RETRY functionality can be
- *		utilised. Lock must initially be held.
- *
- * Returns either number of pages pinned (which may be less than the
- * number requested), or an error. Details about the return value:
- *
- * -- If nr_pages is 0, returns 0.
- * -- If nr_pages is >0, but no pages were pinned, returns -errno.
- * -- If nr_pages is >0, and some pages were pinned, returns the number of
- *    pages pinned. Again, this may be less than nr_pages.
- *
- * The caller is responsible for releasing returned @pages, via put_page().
- *
- * @vmas are valid only as long as mmap_sem is held.
- *
- * Must be called with mmap_sem held for read or write.
- *
- * get_user_pages walks a process's page tables and takes a reference to
- * each struct page that each user address corresponds to at a given
- * instant. That is, it takes the page that would be accessed if a user
- * thread accesses the given user virtual address at that instant.
- *
- * This does not guarantee that the page exists in the user mappings when
- * get_user_pages returns, and there may even be a completely different
- * page there in some cases (eg. if mmapped pagecache has been invalidated
- * and subsequently re faulted). However it does guarantee that the page
- * won't be freed completely. And mostly callers simply care that the page
- * contains data that was valid *at some point in time*. Typically, an IO
- * or similar operation cannot guarantee anything stronger anyway because
- * locks can't be held over the syscall boundary.
- *
- * If gup_flags & FOLL_WRITE == 0, the page must not be written to. If the page
- * is written to, set_page_dirty (or set_page_dirty_lock, as appropriate) must
- * be called after the page is finished with, and before put_page is called.
- *
- * get_user_pages is typically used for fewer-copy IO operations, to get a
- * handle on the memory by some means other than accesses via the user virtual
- * addresses. The pages may be submitted for DMA to devices or accessed via
- * their kernel linear mapping (via the kmap APIs). Care should be taken to
- * use the correct cache flushing APIs.
- *
- * See also get_user_pages_fast, for performance critical applications.
- *
- * get_user_pages should be phased out in favor of
- * get_user_pages_locked|unlocked or get_user_pages_fast. Nothing
- * should use get_user_pages because it cannot pass
- * FAULT_FLAG_ALLOW_RETRY to handle_mm_fault.
- */
-long get_user_pages_remote(struct task_struct *tsk, 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)
-{
-	/*
-	 * FIXME: Current FOLL_LONGTERM behavior is incompatible with
-	 * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on
-	 * vmas.  As there are no users of this flag in this call we simply
-	 * disallow this option for now.
-	 */
-	if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM))
-		return -EINVAL;
-
-	return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas,
-				       locked,
-				       gup_flags | FOLL_TOUCH | FOLL_REMOTE);
-}
-EXPORT_SYMBOL(get_user_pages_remote);
-
 /**
  * populate_vma_page_range() -  populate a range of pages in the vma.
  * @vma:   target vma
@@ -1612,6 +1558,116 @@ static __always_inline long __gup_longterm_locked(struct task_struct *tsk,
 #endif /* CONFIG_FS_DAX || CONFIG_CMA */
 
 /*
+ * get_user_pages_remote() - pin user pages in memory
+ * @tsk:	the task_struct to use for page fault accounting, or
+ *		NULL if faults are not to be recorded.
+ * @mm:		mm_struct of target mm
+ * @start:	starting user address
+ * @nr_pages:	number of pages from start to pin
+ * @gup_flags:	flags modifying lookup behaviour
+ * @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:	pointer to lock flag indicating whether lock is held and
+ *		subsequently whether VM_FAULT_RETRY functionality can be
+ *		utilised. Lock must initially be held.
+ *
+ * Returns either number of pages pinned (which may be less than the
+ * number requested), or an error. Details about the return value:
+ *
+ * -- If nr_pages is 0, returns 0.
+ * -- If nr_pages is >0, but no pages were pinned, returns -errno.
+ * -- If nr_pages is >0, and some pages were pinned, returns the number of
+ *    pages pinned. Again, this may be less than nr_pages.
+ *
+ * The caller is responsible for releasing returned @pages, via put_page().
+ *
+ * @vmas are valid only as long as mmap_sem is held.
+ *
+ * Must be called with mmap_sem held for read or write.
+ *
+ * get_user_pages walks a process's page tables and takes a reference to
+ * each struct page that each user address corresponds to at a given
+ * instant. That is, it takes the page that would be accessed if a user
+ * thread accesses the given user virtual address at that instant.
+ *
+ * This does not guarantee that the page exists in the user mappings when
+ * get_user_pages returns, and there may even be a completely different
+ * page there in some cases (eg. if mmapped pagecache has been invalidated
+ * and subsequently re faulted). However it does guarantee that the page
+ * won't be freed completely. And mostly callers simply care that the page
+ * contains data that was valid *at some point in time*. Typically, an IO
+ * or similar operation cannot guarantee anything stronger anyway because
+ * locks can't be held over the syscall boundary.
+ *
+ * If gup_flags & FOLL_WRITE == 0, the page must not be written to. If the page
+ * is written to, set_page_dirty (or set_page_dirty_lock, as appropriate) must
+ * be called after the page is finished with, and before put_page is called.
+ *
+ * get_user_pages is typically used for fewer-copy IO operations, to get a
+ * handle on the memory by some means other than accesses via the user virtual
+ * addresses. The pages may be submitted for DMA to devices or accessed via
+ * their kernel linear mapping (via the kmap APIs). Care should be taken to
+ * use the correct cache flushing APIs.
+ *
+ * See also get_user_pages_fast, for performance critical applications.
+ *
+ * get_user_pages should be phased out in favor of
+ * get_user_pages_locked|unlocked or get_user_pages_fast. Nothing
+ * should use get_user_pages because it cannot pass
+ * FAULT_FLAG_ALLOW_RETRY to handle_mm_fault.
+ */
+#ifdef CONFIG_MMU
+long get_user_pages_remote(struct task_struct *tsk, 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)
+{
+	/*
+	 * FOLL_PIN must only be set internally by the pin_user_pages*() APIs,
+	 * never directly by the caller, so enforce that with an assertion:
+	 */
+	if (WARN_ON_ONCE(gup_flags & FOLL_PIN))
+		return -EINVAL;
+
+	/*
+	 * Parts of FOLL_LONGTERM behavior are incompatible with
+	 * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on
+	 * vmas. However, this only comes up if locked is set, and there are
+	 * callers that do request FOLL_LONGTERM, but do not set locked. So,
+	 * allow what we can.
+	 */
+	if (gup_flags & FOLL_LONGTERM) {
+		if (WARN_ON_ONCE(locked))
+			return -EINVAL;
+		/*
+		 * This will check the vmas (even if our vmas arg is NULL)
+		 * and return -ENOTSUPP if DAX isn't allowed in this case:
+		 */
+		return __gup_longterm_locked(tsk, mm, start, nr_pages, pages,
+					     vmas, gup_flags | FOLL_TOUCH |
+					     FOLL_REMOTE);
+	}
+
+	return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas,
+				       locked,
+				       gup_flags | FOLL_TOUCH | FOLL_REMOTE);
+}
+EXPORT_SYMBOL(get_user_pages_remote);
+
+#else /* CONFIG_MMU */
+long get_user_pages_remote(struct task_struct *tsk, 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)
+{
+	return 0;
+}
+#endif /* !CONFIG_MMU */
+
+/*
  * This is the same as get_user_pages_remote(), just with a
  * less-flexible calling convention where we assume that the task
  * and mm being operated on are the current task's and don't allow
@@ -1622,6 +1678,13 @@ long get_user_pages(unsigned long start, unsigned long nr_pages,
 		unsigned int gup_flags, struct page **pages,
 		struct vm_area_struct **vmas)
 {
+	/*
+	 * FOLL_PIN must only be set internally by the pin_user_pages*() APIs,
+	 * never directly by the caller, so enforce that with an assertion:
+	 */
+	if (WARN_ON_ONCE(gup_flags & FOLL_PIN))
+		return -EINVAL;
+
 	return __gup_longterm_locked(current, current->mm, start, nr_pages,
 				     pages, vmas, gup_flags | FOLL_TOUCH);
 }
@@ -1807,20 +1870,6 @@ static void __maybe_unused undo_dev_pagemap(int *nr, int nr_start,
 	}
 }
 
-/*
- * Return the compund head page with ref appropriately incremented,
- * or NULL if that failed.
- */
-static inline struct page *try_get_compound_head(struct page *page, int refs)
-{
-	struct page *head = compound_head(page);
-	if (WARN_ON_ONCE(page_ref_count(head) < 0))
-		return NULL;
-	if (unlikely(!page_cache_add_speculative(head, refs)))
-		return NULL;
-	return head;
-}
-
 #ifdef CONFIG_ARCH_HAS_PTE_SPECIAL
 static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 			 unsigned int flags, struct page **pages, int *nr)
@@ -1978,6 +2027,29 @@ static int __gup_device_huge_pud(pud_t pud, pud_t *pudp, unsigned long addr,
 }
 #endif
 
+static int record_subpages(struct page *page, unsigned long addr,
+			   unsigned long end, struct page **pages)
+{
+	int nr;
+
+	for (nr = 0; addr != end; addr += PAGE_SIZE)
+		pages[nr++] = page++;
+
+	return nr;
+}
+
+static void put_compound_head(struct page *page, int refs)
+{
+	VM_BUG_ON_PAGE(page_ref_count(page) < refs, page);
+	/*
+	 * Calling put_page() for each ref is unnecessarily slow. Only the last
+	 * ref needs a put_page().
+	 */
+	if (refs > 1)
+		page_ref_sub(page, refs - 1);
+	put_page(page);
+}
+
 #ifdef CONFIG_ARCH_HAS_HUGEPD
 static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
 				      unsigned long sz)
@@ -2007,32 +2079,20 @@ static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
 	/* hugepages are never "special" */
 	VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
 
-	refs = 0;
 	head = pte_page(pte);
-
 	page = head + ((addr & (sz-1)) >> PAGE_SHIFT);
-	do {
-		VM_BUG_ON(compound_head(page) != head);
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
+	refs = record_subpages(page, addr, end, pages + *nr);
 
 	head = try_get_compound_head(head, refs);
-	if (!head) {
-		*nr -= refs;
+	if (!head)
 		return 0;
-	}
 
 	if (unlikely(pte_val(pte) != pte_val(*ptep))) {
-		/* Could be optimized better */
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
+		put_compound_head(head, refs);
 		return 0;
 	}
 
+	*nr += refs;
 	SetPageReferenced(head);
 	return 1;
 }
@@ -2079,28 +2139,19 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 		return __gup_device_huge_pmd(orig, pmdp, addr, end, pages, nr);
 	}
 
-	refs = 0;
 	page = pmd_page(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
-	do {
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
+	refs = record_subpages(page, addr, end, pages + *nr);
 
 	head = try_get_compound_head(pmd_page(orig), refs);
-	if (!head) {
-		*nr -= refs;
+	if (!head)
 		return 0;
-	}
 
 	if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) {
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
+		put_compound_head(head, refs);
 		return 0;
 	}
 
+	*nr += refs;
 	SetPageReferenced(head);
 	return 1;
 }
@@ -2120,28 +2171,19 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 		return __gup_device_huge_pud(orig, pudp, addr, end, pages, nr);
 	}
 
-	refs = 0;
 	page = pud_page(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
-	do {
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
+	refs = record_subpages(page, addr, end, pages + *nr);
 
 	head = try_get_compound_head(pud_page(orig), refs);
-	if (!head) {
-		*nr -= refs;
+	if (!head)
 		return 0;
-	}
 
 	if (unlikely(pud_val(orig) != pud_val(*pudp))) {
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
+		put_compound_head(head, refs);
 		return 0;
 	}
 
+	*nr += refs;
 	SetPageReferenced(head);
 	return 1;
 }
@@ -2157,28 +2199,20 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
 		return 0;
 
 	BUILD_BUG_ON(pgd_devmap(orig));
-	refs = 0;
+
 	page = pgd_page(orig) + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT);
-	do {
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
+	refs = record_subpages(page, addr, end, pages + *nr);
 
 	head = try_get_compound_head(pgd_page(orig), refs);
-	if (!head) {
-		*nr -= refs;
+	if (!head)
 		return 0;
-	}
 
 	if (unlikely(pgd_val(orig) != pgd_val(*pgdp))) {
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
+		put_compound_head(head, refs);
 		return 0;
 	}
 
+	*nr += refs;
 	SetPageReferenced(head);
 	return 1;
 }
@@ -2237,7 +2271,7 @@ static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end,
 		pud_t pud = READ_ONCE(*pudp);
 
 		next = pud_addr_end(addr, end);
-		if (pud_none(pud))
+		if (unlikely(!pud_present(pud)))
 			return 0;
 		if (unlikely(pud_huge(pud))) {
 			if (!gup_huge_pud(pud, pudp, addr, next, flags,
@@ -2393,29 +2427,15 @@ static int __gup_longterm_unlocked(unsigned long start, int nr_pages,
 	return ret;
 }
 
-/**
- * get_user_pages_fast() - pin user pages in memory
- * @start:	starting user address
- * @nr_pages:	number of pages from start to pin
- * @gup_flags:	flags modifying pin behaviour
- * @pages:	array that receives pointers to the pages pinned.
- *		Should be at least nr_pages long.
- *
- * Attempt to pin user pages in memory without taking mm->mmap_sem.
- * If not successful, it will fall back to taking the lock and
- * calling get_user_pages().
- *
- * Returns number of pages pinned. This may be fewer than the number
- * requested. If nr_pages is 0 or negative, returns 0. If no pages
- * were pinned, returns -errno.
- */
-int get_user_pages_fast(unsigned long start, int nr_pages,
-			unsigned int gup_flags, struct page **pages)
+static int internal_get_user_pages_fast(unsigned long start, int nr_pages,
+					unsigned int gup_flags,
+					struct page **pages)
 {
 	unsigned long addr, len, end;
 	int nr = 0, ret = 0;
 
-	if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM)))
+	if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM |
+				       FOLL_FORCE | FOLL_PIN)))
 		return -EINVAL;
 
 	start = untagged_addr(start) & PAGE_MASK;
@@ -2455,4 +2475,103 @@ int get_user_pages_fast(unsigned long start, int nr_pages,
 
 	return ret;
 }
+
+/**
+ * get_user_pages_fast() - pin user pages in memory
+ * @start:	starting user address
+ * @nr_pages:	number of pages from start to pin
+ * @gup_flags:	flags modifying pin behaviour
+ * @pages:	array that receives pointers to the pages pinned.
+ *		Should be at least nr_pages long.
+ *
+ * Attempt to pin user pages in memory without taking mm->mmap_sem.
+ * If not successful, it will fall back to taking the lock and
+ * calling get_user_pages().
+ *
+ * Returns number of pages pinned. This may be fewer than the number requested.
+ * If nr_pages is 0 or negative, returns 0. If no pages were pinned, returns
+ * -errno.
+ */
+int get_user_pages_fast(unsigned long start, int nr_pages,
+			unsigned int gup_flags, struct page **pages)
+{
+	/*
+	 * FOLL_PIN must only be set internally by the pin_user_pages*() APIs,
+	 * never directly by the caller, so enforce that:
+	 */
+	if (WARN_ON_ONCE(gup_flags & FOLL_PIN))
+		return -EINVAL;
+
+	return internal_get_user_pages_fast(start, nr_pages, gup_flags, pages);
+}