linux-ext4.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: ira.weiny@intel.com
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Jason Gunthorpe <jgg@ziepe.ca>,
	Dan Williams <dan.j.williams@intel.com>,
	Matthew Wilcox <willy@infradead.org>, Jan Kara <jack@suse.cz>,
	"Theodore Ts'o" <tytso@mit.edu>,
	John Hubbard <jhubbard@nvidia.com>,
	Michal Hocko <mhocko@suse.com>,
	Dave Chinner <david@fromorbit.com>,
	linux-xfs@vger.kernel.org, linux-rdma@vger.kernel.org,
	linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	linux-nvdimm@lists.01.org, linux-ext4@vger.kernel.org,
	linux-mm@kvack.org, Ira Weiny <ira.weiny@intel.com>
Subject: [RFC PATCH v2 01/19] fs/locks: Export F_LAYOUT lease to user space
Date: Fri,  9 Aug 2019 15:58:15 -0700	[thread overview]
Message-ID: <20190809225833.6657-2-ira.weiny@intel.com> (raw)
In-Reply-To: <20190809225833.6657-1-ira.weiny@intel.com>

From: Ira Weiny <ira.weiny@intel.com>

In order to support an opt-in policy for users to allow long term pins
of FS DAX pages we need to export the LAYOUT lease to user space.

This is the first of 2 new lease flags which must be used to allow a
long term pin to be made on a file.

After the complete series:

0) Registrations to Device DAX char devs are not affected

1) The user has to opt in to allowing page pins on a file with an exclusive
   layout lease.  Both exclusive and layout lease flags are user visible now.

2) page pins will fail if the lease is not active when the file back page is
   encountered.

3) Any truncate or hole punch operation on a pinned DAX page will fail.

4) The user has the option of holding the lease or releasing it.  If they
   release it no other pin calls will work on the file.

5) Closing the file is ok.

6) Unmapping the file is ok

7) Pins against the files are tracked back to an owning file or an owning mm
   depending on the internal subsystem needs.  With RDMA there is an owning
   file which is related to the pined file.

8) Only RDMA is currently supported

9) Truncation of pages which are not actively pinned nor covered by a lease
   will succeed.

Signed-off-by: Ira Weiny <ira.weiny@intel.com>
---
 fs/locks.c                       | 36 +++++++++++++++++++++++++++-----
 include/linux/fs.h               |  2 +-
 include/uapi/asm-generic/fcntl.h |  3 +++
 3 files changed, 35 insertions(+), 6 deletions(-)

diff --git a/fs/locks.c b/fs/locks.c
index 24d1db632f6c..ad17c6ffca06 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -191,6 +191,8 @@ static int target_leasetype(struct file_lock *fl)
 		return F_UNLCK;
 	if (fl->fl_flags & FL_DOWNGRADE_PENDING)
 		return F_RDLCK;
+	if (fl->fl_flags & FL_LAYOUT)
+		return F_LAYOUT;
 	return fl->fl_type;
 }
 
@@ -611,7 +613,8 @@ static const struct lock_manager_operations lease_manager_ops = {
 /*
  * Initialize a lease, use the default lock manager operations
  */
-static int lease_init(struct file *filp, long type, struct file_lock *fl)
+static int lease_init(struct file *filp, long type, unsigned int flags,
+		      struct file_lock *fl)
 {
 	if (assign_type(fl, type) != 0)
 		return -EINVAL;
@@ -621,6 +624,8 @@ static int lease_init(struct file *filp, long type, struct file_lock *fl)
 
 	fl->fl_file = filp;
 	fl->fl_flags = FL_LEASE;
+	if (flags & FL_LAYOUT)
+		fl->fl_flags |= FL_LAYOUT;
 	fl->fl_start = 0;
 	fl->fl_end = OFFSET_MAX;
 	fl->fl_ops = NULL;
@@ -629,7 +634,8 @@ static int lease_init(struct file *filp, long type, struct file_lock *fl)
 }
 
 /* Allocate a file_lock initialised to this type of lease */
-static struct file_lock *lease_alloc(struct file *filp, long type)
+static struct file_lock *lease_alloc(struct file *filp, long type,
+				     unsigned int flags)
 {
 	struct file_lock *fl = locks_alloc_lock();
 	int error = -ENOMEM;
@@ -637,7 +643,7 @@ static struct file_lock *lease_alloc(struct file *filp, long type)
 	if (fl == NULL)
 		return ERR_PTR(error);
 
-	error = lease_init(filp, type, fl);
+	error = lease_init(filp, type, flags, fl);
 	if (error) {
 		locks_free_lock(fl);
 		return ERR_PTR(error);
@@ -1583,7 +1589,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 	int want_write = (mode & O_ACCMODE) != O_RDONLY;
 	LIST_HEAD(dispose);
 
-	new_fl = lease_alloc(NULL, want_write ? F_WRLCK : F_RDLCK);
+	new_fl = lease_alloc(NULL, want_write ? F_WRLCK : F_RDLCK, 0);
 	if (IS_ERR(new_fl))
 		return PTR_ERR(new_fl);
 	new_fl->fl_flags = type;
@@ -1720,6 +1726,8 @@ EXPORT_SYMBOL(lease_get_mtime);
  *
  *	%F_UNLCK to indicate no lease is held.
  *
+ *	%F_LAYOUT to indicate a layout lease is held.
+ *
  *	(if a lease break is pending):
  *
  *	%F_RDLCK to indicate an exclusive lease needs to be
@@ -2022,8 +2030,26 @@ static int do_fcntl_add_lease(unsigned int fd, struct file *filp, long arg)
 	struct file_lock *fl;
 	struct fasync_struct *new;
 	int error;
+	unsigned int flags = 0;
+
+	/*
+	 * NOTE on F_LAYOUT lease
+	 *
+	 * LAYOUT lease types are taken on files which the user knows that
+	 * they will be pinning in memory for some indeterminate amount of
+	 * time.  Such as for use with RDMA.  While we don't know what user
+	 * space is going to do with the file we still use a F_RDLOCK level of
+	 * lease.  This ensures that there are no conflicts between
+	 * 2 users.  The conflict should only come from the File system wanting
+	 * to revoke the lease in break_layout()  And this is done by using
+	 * F_WRLCK in the break code.
+	 */
+	if (arg == F_LAYOUT) {
+		arg = F_RDLCK;
+		flags = FL_LAYOUT;
+	}
 
-	fl = lease_alloc(filp, arg);
+	fl = lease_alloc(filp, arg, flags);
 	if (IS_ERR(fl))
 		return PTR_ERR(fl);
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 046108cd4ed9..dd60d5be9886 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1004,7 +1004,7 @@ static inline struct file *get_file(struct file *f)
 #define FL_DOWNGRADE_PENDING	256 /* Lease is being downgraded */
 #define FL_UNLOCK_PENDING	512 /* Lease is being broken */
 #define FL_OFDLCK	1024	/* lock is "owned" by struct file */
-#define FL_LAYOUT	2048	/* outstanding pNFS layout */
+#define FL_LAYOUT	2048	/* outstanding pNFS layout or user held pin */
 
 #define FL_CLOSE_POSIX (FL_POSIX | FL_CLOSE)
 
diff --git a/include/uapi/asm-generic/fcntl.h b/include/uapi/asm-generic/fcntl.h
index 9dc0bf0c5a6e..baddd54f3031 100644
--- a/include/uapi/asm-generic/fcntl.h
+++ b/include/uapi/asm-generic/fcntl.h
@@ -174,6 +174,9 @@ struct f_owner_ex {
 #define F_SHLCK		8	/* or 4 */
 #endif
 
+#define F_LAYOUT	16      /* layout lease to allow longterm pins such as
+				   RDMA */
+
 /* operations for bsd flock(), also used by the kernel implementation */
 #define LOCK_SH		1	/* shared lock */
 #define LOCK_EX		2	/* exclusive lock */
-- 
2.20.1


  reply	other threads:[~2019-08-09 23:00 UTC|newest]

Thread overview: 110+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-08-09 22:58 [RFC PATCH v2 00/19] RDMA/FS DAX truncate proposal V1,000,002 ;-) ira.weiny
2019-08-09 22:58 ` ira.weiny [this message]
2019-08-09 23:52   ` [RFC PATCH v2 01/19] fs/locks: Export F_LAYOUT lease to user space Dave Chinner
2019-08-12 17:36     ` Ira Weiny
2019-08-14  8:05       ` Dave Chinner
2019-08-14 11:21         ` Jeff Layton
2019-08-14 11:38           ` Dave Chinner
2019-08-09 22:58 ` [RFC PATCH v2 02/19] fs/locks: Add Exclusive flag to user Layout lease ira.weiny
2019-08-14 14:15   ` Jeff Layton
2019-08-14 21:56     ` Dave Chinner
2019-08-26 10:41       ` Jeff Layton
2019-08-29 23:34         ` Ira Weiny
2019-09-04 12:52           ` Jeff Layton
2019-09-04 23:12   ` John Hubbard
2019-08-09 22:58 ` [RFC PATCH v2 03/19] mm/gup: Pass flags down to __gup_device_huge* calls ira.weiny
2019-08-09 22:58 ` [RFC PATCH v2 04/19] mm/gup: Ensure F_LAYOUT lease is held prior to GUP'ing pages ira.weiny
2019-08-09 22:58 ` [RFC PATCH v2 05/19] fs/ext4: Teach ext4 to break layout leases ira.weiny
2019-08-09 22:58 ` [RFC PATCH v2 06/19] fs/ext4: Teach dax_layout_busy_page() to operate on a sub-range ira.weiny
2019-08-23 15:18   ` Vivek Goyal
2019-08-29 18:52     ` Ira Weiny
2019-08-09 22:58 ` [RFC PATCH v2 07/19] fs/xfs: Teach xfs to use new dax_layout_busy_page() ira.weiny
2019-08-09 23:30   ` Dave Chinner
2019-08-12 18:05     ` Ira Weiny
2019-08-14  8:04       ` Dave Chinner
2019-08-09 22:58 ` [RFC PATCH v2 08/19] fs/xfs: Fail truncate if page lease can't be broken ira.weiny
2019-08-09 23:22   ` Dave Chinner
2019-08-12 18:08     ` Ira Weiny
2019-08-09 22:58 ` [RFC PATCH v2 09/19] mm/gup: Introduce vaddr_pin structure ira.weiny
2019-08-10  0:06   ` John Hubbard
2019-08-09 22:58 ` [RFC PATCH v2 10/19] mm/gup: Pass a NULL vaddr_pin through GUP fast ira.weiny
2019-08-10  0:06   ` John Hubbard
2019-08-09 22:58 ` [RFC PATCH v2 11/19] mm/gup: Pass follow_page_context further down the call stack ira.weiny
2019-08-10  0:18   ` John Hubbard
2019-08-12 19:01     ` Ira Weiny
2019-08-09 22:58 ` [RFC PATCH v2 12/19] mm/gup: Prep put_user_pages() to take an vaddr_pin struct ira.weiny
2019-08-10  0:30   ` John Hubbard
2019-08-12 20:46     ` Ira Weiny
2019-08-09 22:58 ` [RFC PATCH v2 13/19] {mm,file}: Add file_pins objects ira.weiny
2019-08-09 22:58 ` [RFC PATCH v2 14/19] fs/locks: Associate file pins while performing GUP ira.weiny
2019-08-09 22:58 ` [RFC PATCH v2 15/19] mm/gup: Introduce vaddr_pin_pages() ira.weiny
2019-08-10  0:09   ` John Hubbard
2019-08-12 21:00     ` Ira Weiny
2019-08-12 21:20       ` John Hubbard
2019-08-11 23:07   ` John Hubbard
2019-08-12 21:01     ` Ira Weiny
2019-08-12 12:28   ` Jason Gunthorpe
2019-08-12 21:48     ` Ira Weiny
2019-08-13 11:47       ` Jason Gunthorpe
2019-08-13 17:46         ` Ira Weiny
2019-08-13 17:56           ` John Hubbard
2019-08-09 22:58 ` [RFC PATCH v2 16/19] RDMA/uverbs: Add back pointer to system file object ira.weiny
2019-08-12 13:00   ` Jason Gunthorpe
2019-08-12 17:28     ` Ira Weiny
2019-08-12 17:56       ` Jason Gunthorpe
2019-08-12 21:15         ` Ira Weiny
2019-08-13 11:48           ` Jason Gunthorpe
2019-08-13 17:41             ` Ira Weiny
2019-08-13 18:00               ` Jason Gunthorpe
2019-08-13 20:38                 ` Ira Weiny
2019-08-14 12:23                   ` Jason Gunthorpe
2019-08-14 17:50                     ` Ira Weiny
2019-08-14 18:15                       ` Jason Gunthorpe
2019-09-04 22:25                     ` Ira Weiny
2019-09-11  8:19                       ` Jason Gunthorpe
2019-08-09 22:58 ` [RFC PATCH v2 17/19] RDMA/umem: Convert to vaddr_[pin|unpin]* operations ira.weiny
2019-08-09 22:58 ` [RFC PATCH v2 18/19] {mm,procfs}: Add display file_pins proc ira.weiny
2019-08-09 22:58 ` [RFC PATCH v2 19/19] mm/gup: Remove FOLL_LONGTERM DAX exclusion ira.weiny
2019-08-14 10:17 ` [RFC PATCH v2 00/19] RDMA/FS DAX truncate proposal V1,000,002 ;-) Jan Kara
2019-08-14 18:08   ` Ira Weiny
2019-08-15 13:05     ` Jan Kara
2019-08-16 19:05       ` Ira Weiny
2019-08-16 23:20         ` [RFC PATCH v2 00/19] RDMA/FS DAX truncate proposal V1,000,002 ; -) Ira Weiny
2019-08-19  6:36           ` Jan Kara
2019-08-17  2:26         ` [RFC PATCH v2 00/19] RDMA/FS DAX truncate proposal V1,000,002 ;-) Dave Chinner
2019-08-19  6:34           ` Jan Kara
2019-08-19  9:24             ` Dave Chinner
2019-08-19 12:38               ` Jason Gunthorpe
2019-08-19 21:53                 ` Ira Weiny
2019-08-20  1:12                 ` Dave Chinner
2019-08-20 11:55                   ` Jason Gunthorpe
2019-08-21 18:02                     ` Ira Weiny
2019-08-21 18:13                       ` Jason Gunthorpe
2019-08-21 18:22                         ` John Hubbard
2019-08-21 18:57                         ` Ira Weiny
2019-08-21 19:06                           ` Ira Weiny
2019-08-21 19:48                           ` Jason Gunthorpe
2019-08-21 20:44                             ` Ira Weiny
2019-08-21 23:49                               ` Jason Gunthorpe
2019-08-23  3:23                               ` Dave Chinner
2019-08-23 12:04                                 ` Jason Gunthorpe
2019-08-24  0:11                                   ` Dave Chinner
2019-08-24  5:08                                     ` Ira Weiny
2019-08-26  5:55                                       ` Dave Chinner
2019-08-29  2:02                                         ` Ira Weiny
2019-08-29  3:27                                           ` John Hubbard
2019-08-29 16:16                                             ` Ira Weiny
2019-09-02 22:26                                           ` Dave Chinner
2019-09-04 16:54                                             ` Ira Weiny
2019-08-25 19:39                                     ` Jason Gunthorpe
2019-08-24  4:49                                 ` Ira Weiny
2019-08-25 19:40                                   ` Jason Gunthorpe
2019-08-23  0:59                       ` Dave Chinner
2019-08-23 17:15                         ` Ira Weiny
2019-08-24  0:18                           ` Dave Chinner
2019-08-20  0:05               ` John Hubbard
2019-08-20  1:20                 ` Dave Chinner
2019-08-20  3:09                   ` John Hubbard
2019-08-20  3:36                     ` Dave Chinner
2019-08-21 18:43                       ` John Hubbard
2019-08-21 19:09                         ` Ira Weiny

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190809225833.6657-2-ira.weiny@intel.com \
    --to=ira.weiny@intel.com \
    --cc=akpm@linux-foundation.org \
    --cc=dan.j.williams@intel.com \
    --cc=david@fromorbit.com \
    --cc=jack@suse.cz \
    --cc=jgg@ziepe.ca \
    --cc=jhubbard@nvidia.com \
    --cc=linux-ext4@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-nvdimm@lists.01.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=linux-xfs@vger.kernel.org \
    --cc=mhocko@suse.com \
    --cc=tytso@mit.edu \
    --cc=willy@infradead.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).