mm/gup: introduce pin_user_pages*() and FOLL_PIN

Introduce pin_user_pages*() variations of get_user_pages*() calls, and
also pin_longterm_pages*() variations.

For now, these are placeholder calls, until the various call sites are
converted to use the correct get_user_pages*() or pin_user_pages*() API.

These variants will eventually all set FOLL_PIN, which is also
introduced, and thoroughly documented.

    pin_user_pages()
    pin_user_pages_remote()
    pin_user_pages_fast()

All pages that are pinned via the above calls, must be unpinned via
put_user_page().

The underlying rules are:

* FOLL_PIN is a gup-internal flag, so the call sites should not directly
  set it.  That behavior is enforced with assertions.

* Call sites that want to indicate that they are going to do DirectIO
  ("DIO") or something with similar characteristics, should call a
  get_user_pages()-like wrapper call that sets FOLL_PIN.  These wrappers
  will:

    * Start with "pin_user_pages" instead of "get_user_pages".  That
      makes it easy to find and audit the call sites.

    * Set FOLL_PIN

* For pages that are received via FOLL_PIN, those pages must be returned
  via put_user_page().

Thanks to Jan Kara and Vlastimil Babka for explaining the 4 cases in
this documentation.  (I've reworded it and expanded upon it.)

Link: http://lkml.kernel.org/r/20200107224558.2362728-12-jhubbard@nvidia.comSigned-off-by: John Hubbard <jhubbard@nvidia.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>		[Documentation]
Reviewed-by: Jérôme Glisse <jglisse@redhat.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Alex Williamson <alex.williamson@redhat.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Björn Töpel <bjorn.topel@intel.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Leon Romanovsky <leonro@mellanox.com>
Cc: Mauro Carvalho Chehab <mchehab@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Documentation/core-api/index.rst

@@ -31,6 +31,7 @@ Core utilities
    generic-radix-tree
    memory-allocation
    mm-api
+   pin_user_pages
    gfp_mask-from-fs-io
    timekeeping
    boot-time-mm

include/linux/mm.h

@@ -1042,16 +1042,14 @@ static inline void put_page(struct page *page)
  * put_user_page() - release a gup-pinned page
  * @page:            pointer to page to be released
  *
- * Pages that were pinned via get_user_pages*() must be released via
- * either put_user_page(), or one of the put_user_pages*() routines
- * below. This is so that eventually, pages that are pinned via
- * get_user_pages*() can be separately tracked and uniquely handled. In
- * particular, interactions with RDMA and filesystems need special
- * handling.
+ * Pages that were pinned via pin_user_pages*() must be released via either
+ * put_user_page(), or one of the put_user_pages*() routines. This is so that
+ * eventually such pages can be separately tracked and uniquely handled. In
+ * particular, interactions with RDMA and filesystems need special handling.
  *
  * put_user_page() and put_page() are not interchangeable, despite this early
  * implementation that makes them look the same. put_user_page() calls must
- * be perfectly matched up with get_user_page() calls.
+ * be perfectly matched up with pin*() calls.
  */
 static inline void put_user_page(struct page *page)
 {
@@ -1509,9 +1507,16 @@ 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);
+long pin_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);
 long get_user_pages(unsigned long start, unsigned long nr_pages,
 			    unsigned int gup_flags, struct page **pages,
 			    struct vm_area_struct **vmas);
+long pin_user_pages(unsigned long start, unsigned long nr_pages,
+		    unsigned int gup_flags, struct page **pages,
+		    struct vm_area_struct **vmas);
 long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
 		    unsigned int gup_flags, struct page **pages, int *locked);
 long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
@@ -1519,6 +1524,8 @@ long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
 
 int get_user_pages_fast(unsigned long start, int nr_pages,
 			unsigned int gup_flags, struct page **pages);
+int pin_user_pages_fast(unsigned long start, int nr_pages,
+			unsigned int gup_flags, struct page **pages);
 
 int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc);
 int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc,
@@ -2583,13 +2590,15 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 #define FOLL_ANON	0x8000	/* don't do file mappings */
 #define FOLL_LONGTERM	0x10000	/* mapping lifetime is indefinite: see below */
 #define FOLL_SPLIT_PMD	0x20000	/* split huge pmd before returning */
+#define FOLL_PIN	0x40000	/* pages must be released via put_user_page() */
 
 /*
- * NOTE on FOLL_LONGTERM:
+ * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each
+ * other. Here is what they mean, and how to use them:
  *
  * FOLL_LONGTERM indicates that the page will be held for an indefinite time
- * period _often_ under userspace control.  This is contrasted with
- * iov_iter_get_pages() where usages which are transient.
+ * period _often_ under userspace control.  This is in contrast to
+ * iov_iter_get_pages(), whose usages are transient.
  *
  * FIXME: For pages which are part of a filesystem, mappings are subject to the
  * lifetime enforced by the filesystem and we need guarantees that longterm
@@ -2604,11 +2613,39 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
  * Currently only get_user_pages() and get_user_pages_fast() support this flag
  * and calls to get_user_pages_[un]locked are specifically not allowed.  This
  * is due to an incompatibility with the FS DAX check and
- * FAULT_FLAG_ALLOW_RETRY
+ * FAULT_FLAG_ALLOW_RETRY.
  *
- * In the CMA case: longterm pins in a CMA region would unnecessarily fragment
- * that region.  And so CMA attempts to migrate the page before pinning when
+ * In the CMA case: long term pins in a CMA region would unnecessarily fragment
+ * that region.  And so, CMA attempts to migrate the page before pinning, when
  * FOLL_LONGTERM is specified.
+ *
+ * FOLL_PIN indicates that a special kind of tracking (not just page->_refcount,
+ * but an additional pin counting system) will be invoked. This is intended for
+ * anything that gets a page reference and then touches page data (for example,
+ * Direct IO). This lets the filesystem know that some non-file-system entity is
+ * potentially changing the pages' data. In contrast to FOLL_GET (whose pages
+ * are released via put_page()), FOLL_PIN pages must be released, ultimately, by
+ * a call to put_user_page().
+ *
+ * FOLL_PIN is similar to FOLL_GET: both of these pin pages. They use different
+ * and separate refcounting mechanisms, however, and that means that each has
+ * its own acquire and release mechanisms:
+ *
+ *     FOLL_GET: get_user_pages*() to acquire, and put_page() to release.
+ *
+ *     FOLL_PIN: pin_user_pages*() to acquire, and put_user_pages to release.
+ *
+ * FOLL_PIN and FOLL_GET are mutually exclusive for a given function call.
+ * (The underlying pages may experience both FOLL_GET-based and FOLL_PIN-based
+ * calls applied to them, and that's perfectly OK. This is a constraint on the
+ * callers, not on the pages.)
+ *
+ * FOLL_PIN should be set internally by the pin_user_pages*() APIs, never
+ * directly by the caller. That's in order to help avoid mismatches when
+ * releasing pages: get_user_pages*() pages must be released via put_page(),
+ * while pin_user_pages*() pages must be released via put_user_page().
+ *
+ * Please see Documentation/vm/pin_user_pages.rst for more information.
  */
 
 static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags)

mm/gup.c

@@ -194,6 +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);
@@ -811,7 +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
@@ -1035,7 +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;
@@ -1606,11 +1619,19 @@ static __always_inline long __gup_longterm_locked(struct task_struct *tsk,
  * 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
@@ -1636,6 +1657,16 @@ long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
 }
 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
@@ -1647,6 +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);
 }
@@ -2389,30 +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 |
-				       FOLL_FORCE)))
+				       FOLL_FORCE | FOLL_PIN)))
 		return -EINVAL;
 
 	start = untagged_addr(start) & PAGE_MASK;
@@ -2452,4 +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);
+}
 EXPORT_SYMBOL_GPL(get_user_pages_fast);
+
+/**
+ * pin_user_pages_fast() - pin user pages in memory without taking locks
+ *
+ * For now, this is a placeholder function, until various call sites are
+ * converted to use the correct get_user_pages*() or pin_user_pages*() API. So,
+ * this is identical to get_user_pages_fast().
+ *
+ * This is intended for Case 1 (DIO) in Documentation/vm/pin_user_pages.rst. It
+ * is NOT intended for Case 2 (RDMA: long-term pins).
+ */
+int pin_user_pages_fast(unsigned long start, int nr_pages,
+			unsigned int gup_flags, struct page **pages)
+{
+	/*
+	 * This is a placeholder, until the pin functionality is activated.
+	 * Until then, just behave like the corresponding get_user_pages*()
+	 * routine.
+	 */
+	return get_user_pages_fast(start, nr_pages, gup_flags, pages);
+}
+EXPORT_SYMBOL_GPL(pin_user_pages_fast);
+
+/**
+ * pin_user_pages_remote() - pin pages of a remote process (task != current)
+ *
+ * For now, this is a placeholder function, until various call sites are
+ * converted to use the correct get_user_pages*() or pin_user_pages*() API. So,
+ * this is identical to get_user_pages_remote().
+ *
+ * This is intended for Case 1 (DIO) in Documentation/vm/pin_user_pages.rst. It
+ * is NOT intended for Case 2 (RDMA: long-term pins).
+ */
+long pin_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)
+{
+	/*
+	 * This is a placeholder, until the pin functionality is activated.
+	 * Until then, just behave like the corresponding get_user_pages*()
+	 * routine.
+	 */
+	return get_user_pages_remote(tsk, mm, start, nr_pages, gup_flags, pages,
+				     vmas, locked);
+}
+EXPORT_SYMBOL(pin_user_pages_remote);
+
+/**
+ * pin_user_pages() - pin user pages in memory for use by other devices
+ *
+ * For now, this is a placeholder function, until various call sites are
+ * converted to use the correct get_user_pages*() or pin_user_pages*() API. So,
+ * this is identical to get_user_pages().
+ *
+ * This is intended for Case 1 (DIO) in Documentation/vm/pin_user_pages.rst. It
+ * is NOT intended for Case 2 (RDMA: long-term pins).
+ */
+long pin_user_pages(unsigned long start, unsigned long nr_pages,
+		    unsigned int gup_flags, struct page **pages,
+		    struct vm_area_struct **vmas)
+{
+	/*
+	 * This is a placeholder, until the pin functionality is activated.
+	 * Until then, just behave like the corresponding get_user_pages*()
+	 * routine.
+	 */
+	return get_user_pages(start, nr_pages, gup_flags, pages, vmas);
+}
+EXPORT_SYMBOL(pin_user_pages);