All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jan Kara <jack@suse.cz>
To: <linux-fsdevel@vger.kernel.org>
Cc: Christoph Hellwig <hch@infradead.org>,
	Amir Goldstein <amir73il@gmail.com>,
	Dave Chinner <david@fromorbit.com>, Ted Tso <tytso@mit.edu>,
	Jan Kara <jack@suse.cz>, Christoph Hellwig <hch@lst.de>,
	linux-xfs@vger.kernel.org,
	"Darrick J. Wong" <darrick.wong@oracle.com>
Subject: [PATCH 05/12] xfs: Convert to use invalidate_lock
Date: Fri, 23 Apr 2021 19:29:34 +0200	[thread overview]
Message-ID: <20210423173018.23133-5-jack@suse.cz> (raw)
In-Reply-To: <20210423171010.12-1-jack@suse.cz>

Use invalidate_lock instead of XFS internal i_mmap_lock. The intended
purpose of invalidate_lock is exactly the same. Note that the locking in
__xfs_filemap_fault() slightly changes as filemap_fault() already takes
invalidate_lock.

Reviewed-by: Christoph Hellwig <hch@lst.de>
CC: <linux-xfs@vger.kernel.org>
CC: "Darrick J. Wong" <darrick.wong@oracle.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/xfs/xfs_file.c  | 12 ++++++-----
 fs/xfs/xfs_inode.c | 52 ++++++++++++++++++++++++++--------------------
 fs/xfs/xfs_inode.h |  1 -
 fs/xfs/xfs_super.c |  2 --
 4 files changed, 36 insertions(+), 31 deletions(-)

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index a007ca0711d9..2fc04ce0e9f9 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1282,7 +1282,7 @@ xfs_file_llseek(
  *
  * mmap_lock (MM)
  *   sb_start_pagefault(vfs, freeze)
- *     i_mmaplock (XFS - truncate serialisation)
+ *     invalidate_lock (vfs - truncate serialisation)
  *       page_lock (MM)
  *         i_lock (XFS - extent map serialisation)
  */
@@ -1303,24 +1303,26 @@ __xfs_filemap_fault(
 		file_update_time(vmf->vma->vm_file);
 	}
 
-	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 	if (IS_DAX(inode)) {
 		pfn_t pfn;
 
+		xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 		ret = dax_iomap_fault(vmf, pe_size, &pfn, NULL,
 				(write_fault && !vmf->cow_page) ?
 				 &xfs_direct_write_iomap_ops :
 				 &xfs_read_iomap_ops);
 		if (ret & VM_FAULT_NEEDDSYNC)
 			ret = dax_finish_sync_fault(vmf, pe_size, pfn);
+		xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 	} else {
-		if (write_fault)
+		if (write_fault) {
+			xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 			ret = iomap_page_mkwrite(vmf,
 					&xfs_buffered_write_iomap_ops);
-		else
+			xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
+		} else
 			ret = filemap_fault(vmf);
 	}
-	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
 	if (write_fault)
 		sb_end_pagefault(inode->i_sb);
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index f93370bd7b1e..ac83409d0bf3 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -134,7 +134,7 @@ xfs_ilock_attr_map_shared(
 
 /*
  * In addition to i_rwsem in the VFS inode, the xfs inode contains 2
- * multi-reader locks: i_mmap_lock and the i_lock.  This routine allows
+ * multi-reader locks: invalidate_lock and the i_lock.  This routine allows
  * various combinations of the locks to be obtained.
  *
  * The 3 locks should always be ordered so that the IO lock is obtained first,
@@ -142,23 +142,23 @@ xfs_ilock_attr_map_shared(
  *
  * Basic locking order:
  *
- * i_rwsem -> i_mmap_lock -> page_lock -> i_ilock
+ * i_rwsem -> invalidate_lock -> page_lock -> i_ilock
  *
  * mmap_lock locking order:
  *
  * i_rwsem -> page lock -> mmap_lock
- * mmap_lock -> i_mmap_lock -> page_lock
+ * mmap_lock -> invalidate_lock -> page_lock
  *
  * The difference in mmap_lock locking order mean that we cannot hold the
- * i_mmap_lock over syscall based read(2)/write(2) based IO. These IO paths can
- * fault in pages during copy in/out (for buffered IO) or require the mmap_lock
- * in get_user_pages() to map the user pages into the kernel address space for
- * direct IO. Similarly the i_rwsem cannot be taken inside a page fault because
- * page faults already hold the mmap_lock.
+ * invalidate_lock over syscall based read(2)/write(2) based IO. These IO paths
+ * can fault in pages during copy in/out (for buffered IO) or require the
+ * mmap_lock in get_user_pages() to map the user pages into the kernel address
+ * space for direct IO. Similarly the i_rwsem cannot be taken inside a page
+ * fault because page faults already hold the mmap_lock.
  *
  * Hence to serialise fully against both syscall and mmap based IO, we need to
- * take both the i_rwsem and the i_mmap_lock. These locks should *only* be both
- * taken in places where we need to invalidate the page cache in a race
+ * take both the i_rwsem and the invalidate_lock. These locks should *only* be
+ * both taken in places where we need to invalidate the page cache in a race
  * free manner (e.g. truncate, hole punch and other extent manipulation
  * functions).
  */
@@ -190,10 +190,13 @@ xfs_ilock(
 				 XFS_IOLOCK_DEP(lock_flags));
 	}
 
-	if (lock_flags & XFS_MMAPLOCK_EXCL)
-		mrupdate_nested(&ip->i_mmaplock, XFS_MMAPLOCK_DEP(lock_flags));
-	else if (lock_flags & XFS_MMAPLOCK_SHARED)
-		mraccess_nested(&ip->i_mmaplock, XFS_MMAPLOCK_DEP(lock_flags));
+	if (lock_flags & XFS_MMAPLOCK_EXCL) {
+		down_write_nested(&VFS_I(ip)->i_mapping->invalidate_lock,
+				  XFS_MMAPLOCK_DEP(lock_flags));
+	} else if (lock_flags & XFS_MMAPLOCK_SHARED) {
+		down_read_nested(&VFS_I(ip)->i_mapping->invalidate_lock,
+				 XFS_MMAPLOCK_DEP(lock_flags));
+	}
 
 	if (lock_flags & XFS_ILOCK_EXCL)
 		mrupdate_nested(&ip->i_lock, XFS_ILOCK_DEP(lock_flags));
@@ -242,10 +245,10 @@ xfs_ilock_nowait(
 	}
 
 	if (lock_flags & XFS_MMAPLOCK_EXCL) {
-		if (!mrtryupdate(&ip->i_mmaplock))
+		if (!down_write_trylock(&VFS_I(ip)->i_mapping->invalidate_lock))
 			goto out_undo_iolock;
 	} else if (lock_flags & XFS_MMAPLOCK_SHARED) {
-		if (!mrtryaccess(&ip->i_mmaplock))
+		if (!down_read_trylock(&VFS_I(ip)->i_mapping->invalidate_lock))
 			goto out_undo_iolock;
 	}
 
@@ -260,9 +263,9 @@ xfs_ilock_nowait(
 
 out_undo_mmaplock:
 	if (lock_flags & XFS_MMAPLOCK_EXCL)
-		mrunlock_excl(&ip->i_mmaplock);
+		up_write(&VFS_I(ip)->i_mapping->invalidate_lock);
 	else if (lock_flags & XFS_MMAPLOCK_SHARED)
-		mrunlock_shared(&ip->i_mmaplock);
+		up_read(&VFS_I(ip)->i_mapping->invalidate_lock);
 out_undo_iolock:
 	if (lock_flags & XFS_IOLOCK_EXCL)
 		up_write(&VFS_I(ip)->i_rwsem);
@@ -309,9 +312,9 @@ xfs_iunlock(
 		up_read(&VFS_I(ip)->i_rwsem);
 
 	if (lock_flags & XFS_MMAPLOCK_EXCL)
-		mrunlock_excl(&ip->i_mmaplock);
+		up_write(&VFS_I(ip)->i_mapping->invalidate_lock);
 	else if (lock_flags & XFS_MMAPLOCK_SHARED)
-		mrunlock_shared(&ip->i_mmaplock);
+		up_read(&VFS_I(ip)->i_mapping->invalidate_lock);
 
 	if (lock_flags & XFS_ILOCK_EXCL)
 		mrunlock_excl(&ip->i_lock);
@@ -337,7 +340,7 @@ xfs_ilock_demote(
 	if (lock_flags & XFS_ILOCK_EXCL)
 		mrdemote(&ip->i_lock);
 	if (lock_flags & XFS_MMAPLOCK_EXCL)
-		mrdemote(&ip->i_mmaplock);
+		downgrade_write(&VFS_I(ip)->i_mapping->invalidate_lock);
 	if (lock_flags & XFS_IOLOCK_EXCL)
 		downgrade_write(&VFS_I(ip)->i_rwsem);
 
@@ -358,8 +361,11 @@ xfs_isilocked(
 
 	if (lock_flags & (XFS_MMAPLOCK_EXCL|XFS_MMAPLOCK_SHARED)) {
 		if (!(lock_flags & XFS_MMAPLOCK_SHARED))
-			return !!ip->i_mmaplock.mr_writer;
-		return rwsem_is_locked(&ip->i_mmaplock.mr_lock);
+			return !debug_locks ||
+				lockdep_is_held_type(
+					&VFS_I(ip)->i_mapping->invalidate_lock,
+					0);
+		return rwsem_is_locked(&VFS_I(ip)->i_mapping->invalidate_lock);
 	}
 
 	if (lock_flags & (XFS_IOLOCK_EXCL|XFS_IOLOCK_SHARED)) {
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 88ee4c3930ae..147537be751c 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -40,7 +40,6 @@ typedef struct xfs_inode {
 	/* Transaction and locking information. */
 	struct xfs_inode_log_item *i_itemp;	/* logging information */
 	mrlock_t		i_lock;		/* inode lock */
-	mrlock_t		i_mmaplock;	/* inode mmap IO lock */
 	atomic_t		i_pincount;	/* inode pin count */
 
 	/*
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index e5e0713bebcd..a1536a02aaa5 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -715,8 +715,6 @@ xfs_fs_inode_init_once(
 	atomic_set(&ip->i_pincount, 0);
 	spin_lock_init(&ip->i_flags_lock);
 
-	mrlock_init(&ip->i_mmaplock, MRLOCK_ALLOW_EQUAL_PRI|MRLOCK_BARRIER,
-		     "xfsino", ip->i_ino);
 	mrlock_init(&ip->i_lock, MRLOCK_ALLOW_EQUAL_PRI|MRLOCK_BARRIER,
 		     "xfsino", ip->i_ino);
 }
-- 
2.26.2


  parent reply	other threads:[~2021-04-23 17:30 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-04-23 17:29 [PATCH 0/12 v4] fs: Hole punch vs page cache filling races Jan Kara
2021-04-23 17:29 ` [PATCH 01/12] mm: Fix comments mentioning i_mutex Jan Kara
2021-04-23 17:29 ` [PATCH 02/12] mm: Protect operations adding pages to page cache with invalidate_lock Jan Kara
2021-04-23 18:30   ` Matthew Wilcox
2021-04-23 18:30     ` [f2fs-dev] " Matthew Wilcox
2021-04-23 23:04   ` Dave Chinner
2021-04-23 23:04     ` [f2fs-dev] " Dave Chinner
2021-04-26 15:46     ` Jan Kara
2021-04-26 15:46       ` [f2fs-dev] " Jan Kara
2021-04-23 17:29 ` [PATCH 03/12] ext4: Convert to use mapping->invalidate_lock Jan Kara
2021-04-23 17:29 ` [PATCH 04/12] ext2: Convert to using invalidate_lock Jan Kara
2021-04-23 17:29 ` Jan Kara [this message]
2021-04-23 22:39   ` [PATCH 05/12] xfs: Convert to use invalidate_lock Dave Chinner
2021-04-23 17:29 ` [PATCH 06/12] zonefs: Convert to using invalidate_lock Jan Kara
2021-04-26  6:40   ` Damien Le Moal
2021-04-26 16:24     ` Jan Kara
2021-04-23 17:29 ` [PATCH 07/12] f2fs: " Jan Kara
2021-04-23 19:15   ` kernel test robot
2021-04-23 19:15     ` kernel test robot
2021-04-23 20:05   ` kernel test robot
2021-04-23 20:05     ` kernel test robot
2021-04-23 17:29 ` [PATCH 08/12] fuse: " Jan Kara
2021-04-23 17:29 ` [PATCH 09/12] shmem: " Jan Kara
2021-04-29  4:12   ` Hugh Dickins
2021-04-29  4:12     ` Hugh Dickins
2021-04-29  9:30     ` Jan Kara
2021-04-23 17:29 ` [PATCH 10/12] shmem: Use invalidate_lock to protect fallocate Jan Kara
2021-04-23 19:27   ` kernel test robot
2021-04-23 19:27     ` kernel test robot
2021-04-29  3:24   ` Hugh Dickins
2021-04-29  3:24     ` Hugh Dickins
2021-04-29  9:20     ` Jan Kara
2021-04-23 17:29 ` [PATCH 11/12] ceph: Fix race between hole punch and page fault Jan Kara
2021-04-23 17:29 ` [PATCH 12/12] cifs: " Jan Kara
2021-04-23 22:07 ` [PATCH 0/12 v4] fs: Hole punch vs page cache filling races Dave Chinner
2021-04-23 22:07   ` [f2fs-dev] " Dave Chinner
2021-04-23 23:51   ` Matthew Wilcox
2021-04-23 23:51     ` [f2fs-dev] " Matthew Wilcox
2021-04-24  6:11     ` Christoph Hellwig
2021-04-24  6:11       ` [f2fs-dev] " Christoph Hellwig

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=20210423173018.23133-5-jack@suse.cz \
    --to=jack@suse.cz \
    --cc=amir73il@gmail.com \
    --cc=darrick.wong@oracle.com \
    --cc=david@fromorbit.com \
    --cc=hch@infradead.org \
    --cc=hch@lst.de \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-xfs@vger.kernel.org \
    --cc=tytso@mit.edu \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.