Linux-ext4 Archive on lore.kernel.org
 help / color / Atom feed
From: Jan Kara <jack@suse.cz>
To: <linux-fsdevel@vger.kernel.org>
Cc: <linux-ext4@vger.kernel.org>, <linux-xfs@vger.kernel.org>,
	Ted Tso <tytso@mit.edu>, Christoph Hellwig <hch@infradead.org>,
	Amir Goldstein <amir73il@gmail.com>,
	Dave Chinner <david@fromorbit.com>, Jan Kara <jack@suse.cz>
Subject: [PATCH 5/7] xfs: Convert to use i_mapping_sem
Date: Tue, 13 Apr 2021 13:28:49 +0200
Message-ID: <20210413112859.32249-5-jack@suse.cz> (raw)
In-Reply-To: <20210413105205.3093-1-jack@suse.cz>

Use i_mapping_sem instead of XFS internal i_mmap_lock. The intended
purpose of i_mapping_sem is exactly the same.

Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/xfs/xfs_file.c  | 12 ++++++-----
 fs/xfs/xfs_inode.c | 51 +++++++++++++++++++++++++---------------------
 fs/xfs/xfs_inode.h |  1 -
 fs/xfs/xfs_super.c |  2 --
 4 files changed, 35 insertions(+), 31 deletions(-)

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index a007ca0711d9..a76404708312 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)
+ *     i_mapping_sem (XFS - 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..bffceaec11a9 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: i_mapping_sem 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 -> i_mapping_sem -> page_lock -> i_ilock
  *
  * mmap_lock locking order:
  *
  * i_rwsem -> page lock -> mmap_lock
- * mmap_lock -> i_mmap_lock -> page_lock
+ * mmap_lock -> i_mapping_sem -> 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.
+ * i_mapping_sem 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 i_mapping_sem. 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_sem,
+				  XFS_MMAPLOCK_DEP(lock_flags));
+	} else if (lock_flags & XFS_MMAPLOCK_SHARED) {
+		down_read_nested(&VFS_I(ip)->i_mapping_sem,
+				 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_sem))
 			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_sem))
 			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_sem);
 	else if (lock_flags & XFS_MMAPLOCK_SHARED)
-		mrunlock_shared(&ip->i_mmaplock);
+		up_read(&VFS_I(ip)->i_mapping_sem);
 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_sem);
 	else if (lock_flags & XFS_MMAPLOCK_SHARED)
-		mrunlock_shared(&ip->i_mmaplock);
+		up_read(&VFS_I(ip)->i_mapping_sem);
 
 	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_sem);
 	if (lock_flags & XFS_IOLOCK_EXCL)
 		downgrade_write(&VFS_I(ip)->i_rwsem);
 
@@ -358,8 +361,10 @@ 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_sem,
+						     0);
+		return rwsem_is_locked(&VFS_I(ip)->i_mapping_sem);
 	}
 
 	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);
 }
-- 
2.31.0.99.g0d91da736d9f.dirty


  parent reply index

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-04-13 11:28 [PATCH 0/7 RFC v3] fs: Hole punch vs page cache filling races Jan Kara
2021-04-13 11:28 ` [PATCH 1/7] mm: Fix comments mentioning i_mutex Jan Kara
2021-04-13 12:38   ` Christoph Hellwig
2021-04-13 11:28 ` [PATCH 2/7] mm: Protect operations adding pages to page cache with i_mapping_lock Jan Kara
2021-04-13 12:57   ` Christoph Hellwig
2021-04-13 13:56     ` Jan Kara
2021-04-14  0:01   ` Dave Chinner
2021-04-14 12:23     ` Jan Kara
2021-04-14 21:57       ` Dave Chinner
2021-04-15 13:11         ` Jan Kara
2021-04-14 22:25     ` Matthew Wilcox
2021-04-15  2:05       ` Dave Chinner
2021-04-13 11:28 ` [PATCH 3/7] ext4: Convert to use inode->i_mapping_sem Jan Kara
2021-04-13 11:28 ` [PATCH 4/7] ext2: Convert to using i_mapping_sem Jan Kara
2021-04-13 11:28 ` Jan Kara [this message]
2021-04-13 13:05   ` [PATCH 5/7] xfs: Convert to use i_mapping_sem Christoph Hellwig
2021-04-13 13:42     ` Jan Kara
2021-04-13 11:28 ` [PATCH 6/7] zonefs: Convert to using i_mapping_sem Jan Kara
2021-04-13 11:28 ` [PATCH 7/7] fs: Remove i_mapping_sem protection from .page_mkwrite handlers Jan Kara
2021-04-13 13:09 ` [PATCH 0/7 RFC v3] fs: Hole punch vs page cache filling races Christoph Hellwig
2021-04-13 14:17   ` Jan Kara
2021-04-19 15:20 ` Matthew Wilcox
2021-04-19 16:25   ` Jan Kara
2021-04-20 22:12   ` Dave Chinner

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=20210413112859.32249-5-jack@suse.cz \
    --to=jack@suse.cz \
    --cc=amir73il@gmail.com \
    --cc=david@fromorbit.com \
    --cc=hch@infradead.org \
    --cc=linux-ext4@vger.kernel.org \
    --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

Linux-ext4 Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-ext4/0 linux-ext4/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-ext4 linux-ext4/ https://lore.kernel.org/linux-ext4 \
		linux-ext4@vger.kernel.org
	public-inbox-index linux-ext4

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-ext4


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git