+ block-add-dio_w_-wrappers-for-pin-unpin-user-pages.patch added to mm-unstable branch

+ block-add-dio_w_-wrappers-for-pin-unpin-user-pages.patch added to mm-unstable branch

[Andrew Morton]

The patch titled
     Subject: block: add dio_w_*() wrappers for pin, unpin user pages
has been added to the -mm mm-unstable branch.  Its filename is
     block-add-dio_w_-wrappers-for-pin-unpin-user-pages.patch

This patch will shortly appear at
     https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/block-add-dio_w_-wrappers-for-pin-unpin-user-pages.patch

This patch will later appear in the mm-unstable branch at
    git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***

The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days

------------------------------------------------------
From: John Hubbard <jhubbard@nvidia.com>
Subject: block: add dio_w_*() wrappers for pin, unpin user pages
Date: Sat, 27 Aug 2022 01:36:03 -0700

Background: The Direct IO part of the block infrastructure is being
changed to use pin_user_page*() and unpin_user_page*() calls, in place of
a mix of get_user_pages_fast(), get_page(), and put_page().  These have to
be changed over all at the same time, for block, bio, and all filesystems.
However, most filesystems can be changed via iomap and core filesystem
routines, so let's get that in place, and then continue on with converting
the remaining filesystems (9P, CIFS) and anything else that feeds pages
into bio that ultimately get released via bio_release_pages().

Add a new config parameter, CONFIG_BLK_USE_PIN_USER_PAGES_FOR_DIO, and
dio_w_*() wrapper functions.  The dio_w_ prefix was chosen for uniqueness,
so as to ease a subsequent kernel-wide rename via search-and-replace. 
Together, these allow the developer to choose between these sets of
routines, for Direct IO code paths:

a) pin_user_pages_fast()
    pin_user_page()
    unpin_user_page()

b) get_user_pages_fast()
    get_page()
    put_page()

CONFIG_BLK_USE_PIN_USER_PAGES_FOR_DIO is a temporary setting, and may be
deleted once the conversion is complete.  In the meantime, developers can
enable this in order to try out each filesystem.

Please remember that these /proc/vmstat items (below) should normally
contain the same values as each other, except during the middle of
pin/unpin operations.  As such, they can be helpful when monitoring test
runs:

    nr_foll_pin_acquired
    nr_foll_pin_released

Link: https://lkml.kernel.org/r/20220827083607.2345453-3-jhubbard@nvidia.com
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Anna Schumaker <anna@kernel.org>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: "Darrick J. Wong" <djwong@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Logan Gunthorpe <logang@deltatee.com>
Cc: Miklos Szeredi <miklos@szeredi.hu>
Cc: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 block/Kconfig        |   24 ++++++++++++++++++++++++
 include/linux/bvec.h |   40 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 64 insertions(+)

--- a/block/Kconfig~block-add-dio_w_-wrappers-for-pin-unpin-user-pages
+++ a/block/Kconfig
@@ -48,6 +48,30 @@ config BLK_DEV_BSG_COMMON
 config BLK_ICQ
 	bool
 
+config BLK_USE_PIN_USER_PAGES_FOR_DIO
+	bool "DEVELOPERS ONLY: Enable pin_user_pages() for Direct IO" if EXPERT
+	default n
+
+	help
+	  For Direct IO code, retain the pages via calls to
+	  pin_user_pages_fast(), instead of via get_user_pages_fast().
+	  Likewise, use pin_user_page() instead of get_page(). And then
+	  release such pages via unpin_user_page(), instead of
+	  put_page().
+
+	  This is a temporary setting, which will be deleted once the
+	  conversion is completed, reviewed, and tested. In the meantime,
+	  developers can enable this in order to try out each filesystem.
+	  For that, it's best to monitor these /proc/vmstat items:
+
+		nr_foll_pin_acquired
+		nr_foll_pin_released
+
+	  ...to ensure that they remain equal, when "at rest".
+
+	  Say yes here ONLY if are actively developing or testing the
+	  block layer or filesystems with pin_user_pages_fast().
+
 config BLK_DEV_BSGLIB
 	bool "Block layer SG support v4 helper lib"
 	select BLK_DEV_BSG_COMMON
--- a/include/linux/bvec.h~block-add-dio_w_-wrappers-for-pin-unpin-user-pages
+++ a/include/linux/bvec.h
@@ -241,4 +241,44 @@ static inline void *bvec_virt(struct bio
 	return page_address(bvec->bv_page) + bvec->bv_offset;
 }
 
+#ifdef CONFIG_BLK_USE_PIN_USER_PAGES_FOR_DIO
+#define dio_w_pin_user_pages_fast(s, n, p, f)	pin_user_pages_fast(s, n, p, f)
+#define dio_w_pin_user_page(p)			pin_user_page(p)
+#define dio_w_iov_iter_pin_pages(i, p, m, n, s) iov_iter_pin_pages(i, p, m, n, s)
+#define dio_w_iov_iter_pin_pages_alloc(i, p, m, s) iov_iter_pin_pages_alloc(i, p, m, s)
+#define dio_w_unpin_user_page(p)		unpin_user_page(p)
+#define dio_w_unpin_user_pages(p, n)		unpin_user_pages(p, n)
+#define dio_w_unpin_user_pages_dirty_lock(p, n, d) unpin_user_pages_dirty_lock(p, n, d)
+
+#else
+#define dio_w_pin_user_pages_fast(s, n, p, f)	get_user_pages_fast(s, n, p, f)
+#define dio_w_pin_user_page(p)			get_page(p)
+#define dio_w_iov_iter_pin_pages(i, p, m, n, s) iov_iter_get_pages2(i, p, m, n, s)
+#define dio_w_iov_iter_pin_pages_alloc(i, p, m, s) iov_iter_get_pages_alloc2(i, p, m, s)
+#define dio_w_unpin_user_page(p)		put_page(p)
+
+static inline void dio_w_unpin_user_pages(struct page **pages,
+					  unsigned long npages)
+{
+	unsigned long i;
+
+	for (i = 0; i < npages; i++)
+		put_page(pages[i]);
+}
+
+static inline void dio_w_unpin_user_pages_dirty_lock(struct page **pages,
+						     unsigned long npages,
+						     bool make_dirty)
+{
+	unsigned long i;
+
+	for (i = 0; i < npages; i++) {
+		if (make_dirty)
+			set_page_dirty_lock(pages[i]);
+		put_page(pages[i]);
+	}
+}
+
+#endif
+
 #endif /* __LINUX_BVEC_H */
_

Patches currently in -mm which might be from jhubbard@nvidia.com are

mm-gup-introduce-pin_user_page.patch
block-add-dio_w_-wrappers-for-pin-unpin-user-pages.patch
iov_iter-new-iov_iter_pin_pages-routines.patch
block-bio-fs-convert-most-filesystems-to-pin_user_pages_fast.patch
nfs-direct-io-convert-to-foll_pin-pages.patch
fuse-convert-direct-io-paths-to-use-foll_pin.patch

+ block-add-dio_w_-wrappers-for-pin-unpin-user-pages.patch added to mm-unstable branch

[Andrew Morton]

The patch titled
     Subject: block: add dio_w_*() wrappers for pin, unpin user pages
has been added to the -mm mm-unstable branch.  Its filename is
     block-add-dio_w_-wrappers-for-pin-unpin-user-pages.patch

This patch will shortly appear at
     https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/block-add-dio_w_-wrappers-for-pin-unpin-user-pages.patch

This patch will later appear in the mm-unstable branch at
    git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***

The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days

------------------------------------------------------
From: John Hubbard <jhubbard@nvidia.com>
Subject: block: add dio_w_*() wrappers for pin, unpin user pages
Date: Tue, 30 Aug 2022 21:18:39 -0700

Background: The Direct IO part of the block infrastructure is being
changed to use pin_user_page*() and unpin_user_page*() calls, in place
of a mix of get_user_pages_fast(), get_page(), and put_page(). These
have to be changed over all at the same time, for block, bio, and all
filesystems. However, most filesystems can be changed via iomap and core
filesystem routines, so let's get that in place, and then continue on
with converting the remaining filesystems (9P, CIFS) and anything else
that feeds pages into bio that ultimately get released via
bio_release_pages().

Add a new config parameter, CONFIG_BLK_USE_PIN_USER_PAGES_FOR_DIO, and
dio_w_*() wrapper functions. The dio_w_ prefix was chosen for
uniqueness, so as to ease a subsequent kernel-wide rename via
search-and-replace. Together, these allow the developer to choose
between these sets of routines, for Direct IO code paths:

a) pin_user_pages_fast()
    pin_user_page()
    unpin_user_page()

b) get_user_pages_fast()
    get_page()
    put_page()

CONFIG_BLK_USE_PIN_USER_PAGES_FOR_DIO is a temporary setting, and may
be deleted once the conversion is complete. In the meantime, developers
can enable this in order to try out each filesystem.

Please remember that these /proc/vmstat items (below) should normally
contain the same values as each other, except during the middle of
pin/unpin operations. As such, they can be helpful when monitoring test
runs:

    nr_foll_pin_acquired
    nr_foll_pin_released

Link: https://lkml.kernel.org/r/20220831041843.973026-4-jhubbard@nvidia.com
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Anna Schumaker <anna@kernel.org>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Darrick J. Wong <djwong@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Logan Gunthorpe <logang@deltatee.com>
Cc: Miklos Szeredi <miklos@szeredi.hu>
Cc: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 block/Kconfig        |   24 ++++++++++++++++++++++++
 include/linux/bvec.h |   37 +++++++++++++++++++++++++++++++++++++
 2 files changed, 61 insertions(+)

--- a/block/Kconfig~block-add-dio_w_-wrappers-for-pin-unpin-user-pages
+++ a/block/Kconfig
@@ -48,6 +48,30 @@ config BLK_DEV_BSG_COMMON
 config BLK_ICQ
 	bool
 
+config BLK_USE_PIN_USER_PAGES_FOR_DIO
+	bool "DEVELOPERS ONLY: Enable pin_user_pages() for Direct IO" if EXPERT
+	default n
+
+	help
+	  For Direct IO code, retain the pages via calls to
+	  pin_user_pages_fast(), instead of via get_user_pages_fast().
+	  Likewise, use pin_user_page() instead of get_page(). And then
+	  release such pages via unpin_user_page(), instead of
+	  put_page().
+
+	  This is a temporary setting, which will be deleted once the
+	  conversion is completed, reviewed, and tested. In the meantime,
+	  developers can enable this in order to try out each filesystem.
+	  For that, it's best to monitor these /proc/vmstat items:
+
+		nr_foll_pin_acquired
+		nr_foll_pin_released
+
+	  ...to ensure that they remain equal, when "at rest".
+
+	  Say yes here ONLY if are actively developing or testing the
+	  block layer or filesystems with pin_user_pages_fast().
+
 config BLK_DEV_BSGLIB
 	bool "Block layer SG support v4 helper lib"
 	select BLK_DEV_BSG_COMMON
--- a/include/linux/bvec.h~block-add-dio_w_-wrappers-for-pin-unpin-user-pages
+++ a/include/linux/bvec.h
@@ -241,4 +241,41 @@ static inline void *bvec_virt(struct bio
 	return page_address(bvec->bv_page) + bvec->bv_offset;
 }
 
+#ifdef CONFIG_BLK_USE_PIN_USER_PAGES_FOR_DIO
+#define dio_w_pin_user_pages_fast(s, n, p, f)	pin_user_pages_fast(s, n, p, f)
+#define dio_w_pin_user_page(p)			pin_user_page(p)
+#define dio_w_iov_iter_pin_pages(i, p, m, n, s) iov_iter_pin_pages(i, p, m, n, s)
+#define dio_w_iov_iter_pin_pages_alloc(i, p, m, s) iov_iter_pin_pages_alloc(i, p, m, s)
+#define dio_w_unpin_user_page(p)		unpin_user_page(p)
+#define dio_w_unpin_user_pages(p, n)		unpin_user_pages(p, n)
+#define dio_w_unpin_user_pages_dirty_lock(p, n, d) unpin_user_pages_dirty_lock(p, n, d)
+
+#else
+#define dio_w_pin_user_pages_fast(s, n, p, f)	get_user_pages_fast(s, n, p, f)
+#define dio_w_pin_user_page(p)			get_page(p)
+#define dio_w_iov_iter_pin_pages(i, p, m, n, s) iov_iter_get_pages2(i, p, m, n, s)
+#define dio_w_iov_iter_pin_pages_alloc(i, p, m, s) iov_iter_get_pages_alloc2(i, p, m, s)
+#define dio_w_unpin_user_page(p)		put_page(p)
+
+static inline void dio_w_unpin_user_pages(struct page **pages,
+					  unsigned long npages)
+{
+	release_pages(pages, npages);
+}
+
+static inline void dio_w_unpin_user_pages_dirty_lock(struct page **pages,
+						     unsigned long npages,
+						     bool make_dirty)
+{
+	unsigned long i;
+
+	for (i = 0; i < npages; i++) {
+		if (make_dirty)
+			set_page_dirty_lock(pages[i]);
+		put_page(pages[i]);
+	}
+}
+
+#endif
+
 #endif /* __LINUX_BVEC_H */
_

Patches currently in -mm which might be from jhubbard@nvidia.com are

mm-change-release_pages-to-use-unsigned-long-for-npages.patch
mm-gup-introduce-pin_user_page.patch
block-add-dio_w_-wrappers-for-pin-unpin-user-pages.patch
iov_iter-new-iov_iter_pin_pages-routines.patch
block-bio-fs-convert-most-filesystems-to-pin_user_pages_fast.patch
nfs-direct-io-convert-to-foll_pin-pages.patch
fuse-convert-direct-io-paths-to-use-foll_pin.patch