Some recent benchmarking on btrfs showed that a major scaling bottleneck
on large systems on btrfs is currently the xattr lookup on every write.

Why xattr lookup on every write I hear you ask?

write wants to drop suid and security related xattrs that could set o
capabilities for executables.  To do that it currently looks up
security.capability on EVERY write (even for non executables) to decide
whether to drop it or not.

In btrfs this causes an additional tree walk, hitting some per file system
locks and quite bad scalability. In a simple read workload on a 8S
system I saw over 90% CPU time in spinlocks related to that.

Chris Mason tells me this is also a problem in ext4, where it hits
the global mbcache lock.

This patch adds a simple per inode to avoid this problem.  We only
do the lookup once per file and then if there is no xattr cache
the decision. All xattr changes clear the flag.

I also used the same flag to avoid the suid check, although
that one is pretty cheap.

A file system can also set this flag when it creates the inode,
if it has a cheap way to do so.  This is done for some common file systems
in followon patches.

With this patch a major part of the lock contention disappears
for btrfs. Some testing on smaller systems didn't show significant
performance changes, but at least it helps the larger systems
and is generally more efficient.

v2: Rename is_sgid. add file system helper.
Cc: chris.mason@oracle.com
Cc: josef@redhat.com
Cc: viro@zeniv.linux.org.uk
Cc: agruen@linbit.com
Cc: Serge E. Hallyn <serue@us.ibm.com>
Signed-off-by: NAndi Kleen <ak@linux.intel.com>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

For filesystems such as nilfs2 and xfs that use block_page_mkwrite, modify that
function to wait for pending writeback before allowing the page to become
writable.  This is needed to stabilize pages during writeback for those two
filesystems.
Signed-off-by: NDarrick J. Wong <djwong@us.ibm.com>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

When grabbing a page for a buffered IO write, the mm should wait for writeback
on the page to complete so that the page does not become writable during the IO
operation.  This change is needed to provide page stability during writes for
all filesystems.
Signed-off-by: NDarrick J. Wong <djwong@us.ibm.com>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

configfs does not have problems with references to unlinked directories.

CC: Joel Becker <jlbec@evilplan.org>
Signed-off-by: NSage Weil <sage@newdream.net>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

fat does not have problems with references to unlinked directories.

CC: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
Signed-off-by: NSage Weil <sage@newdream.net>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Hpfs has no problems with references to unlinked directories.

We leave one dentry_unhash call in place, in hpfs_unlink's strange path
where it tries to truncate a file because the disk is full.  I'm not sure
what the full story is there.

CC: Mikulas Patocka <mikulas@artax.karlin.mff.cuni.cz>
Signed-off-by: NSage Weil <sage@newdream.net>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Minix has no issues with references to unlinked directories.
Signed-off-by: NSage Weil <sage@newdream.net>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Fuse has no problems with references to unlinked directories.

CC: Miklos Szeredi <miklos@szeredi.hu>
CC: fuse-devel@lists.sourceforge.net
Signed-off-by: NSage Weil <sage@newdream.net>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Coda has no problems with references to unlinked directories.

CC: Jan Harkes <jaharkes@cs.cmu.edu>
CC: coda@cs.cmu.edu
CC: codalist@coda.cs.cmu.edu
Signed-off-by: NSage Weil <sage@newdream.net>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

afs has no problems with references to unlinked directories.

CC: David Howells <dhowells@redhat.com>
CC: linux-afs@lists.infradead.org
Signed-off-by: NSage Weil <sage@newdream.net>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

affs has no problems with references to unlinked directories.
Signed-off-by: NSage Weil <sage@newdream.net>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

9p has no problems with references to unlinked directories.

CC: Eric Van Hensbergen <ericvh@gmail.com>
CC: Ron Minnich <rminnich@sandia.gov>
CC: Latchesar Ionkov <lucho@ionkov.net>
CC: v9fs-developer@lists.sourceforge.net
Signed-off-by: NSage Weil <sage@newdream.net>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

ncpfs does not handle references to unlinked directories (or so it would
seem given the ncp_rmdir check).  Since it is also possible to rename over
an empty directory, perform the same check here.

CC: Petr Vandrovec <petr@vandrovec.name>
CC: linux-kernel@vger.kernel.org
Signed-off-by: NSage Weil <sage@newdream.net>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

ncpfs returns EBUSY if there are any references to the directory.  The
dentry_unhash call only unhashes the dentry if there are no references.

CC: Petr Vandrovec <petr@vandrovec.name>
CC: linux-kernel@vger.kernel.org
Signed-off-by: NSage Weil <sage@newdream.net>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

ecryptfs does not have problems with references to unlinked directories.

CC: Tyler Hicks <tyhicks@linux.vnet.ibm.com>
CC: Dustin Kirkland <kirkland@canonical.com>
CC: ecryptfs-devel@lists.launchpad.net
Signed-off-by: NSage Weil <sage@newdream.net>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

hostfs does not have problems with references to unlinked directories.

CC: Jeff Dike <jdike@addtoit.com>
CC: Richard Weinberger <richard@nod.at>
CC: user-mode-linux-devel@lists.sourceforge.net
Signed-off-by: NSage Weil <sage@newdream.net>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

hfsplus does not have problems with references to unlinked directories.
Signed-off-by: NSage Weil <sage@newdream.net>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

hfs does not have problems with references to unlinked directories.
Signed-off-by: NSage Weil <sage@newdream.net>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

omfs does not have problems with references to unlinked directories.

CC: Bob Copeland <me@bobcopeland.com>
CC: linux-karma-devel@lists.sourceforge.net
Signed-off-by: NSage Weil <sage@newdream.net>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

udf does not have problems with references to unlinked directories.

CC: Jan Kara <jack@suse.cz>
Signed-off-by: NSage Weil <sage@newdream.net>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Reiserfs does not have problems with references to unlinked directories.

CC: reiserfs-devel@vger.kernel.org
Signed-off-by: NSage Weil <sage@newdream.net>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

ufs does not have problems with references to unlinked directories.

CC: Evgeniy Dushistov <dushistov@mail.ru>
Signed-off-by: NSage Weil <sage@newdream.net>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

ubifs does not have problems with references to unlinked directories.

CC: Artem Bityutskiy <dedekind1@gmail.com>
CC: Adrian Hunter <adrian.hunter@nokia.com>
CC: linux-mtd@lists.infradead.org
Signed-off-by: NSage Weil <sage@newdream.net>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

nilfs2 does not have problems with references to unlinked directories.

CC: KONISHI Ryusuke <konishi.ryusuke@lab.ntt.co.jp>
CC: linux-nilfs@vger.kernel.org
Signed-off-by: NSage Weil <sage@newdream.net>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

logfs does not have problems with references to unlinked directories.

CC: Joern Engel <joern@logfs.org>
CC: logfs@logfs.org
Signed-off-by: NSage Weil <sage@newdream.net>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

jfs does not have problems with references to unlinked directories.

CC: Dave Kleikamp <shaggy@kernel.org>
CC: jfs-discussion@lists.sourceforge.net
Signed-off-by: NSage Weil <sage@newdream.net>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

jffs2 does not have problems with references to unlinked directories.

CC: David Woodhouse <dwmw2@infradead.org>
CC: linux-mtd@lists.infradead.org
Signed-off-by: NSage Weil <sage@newdream.net>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

sysv does not have problems with references to unlinked directories.

CC: Christoph Hellwig <hch@infradead.org>
Signed-off-by: NSage Weil <sage@newdream.net>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Bfs does not have problems with references to unlinked directories.

CC: tigran@aivazian.fsnet.co.uk
Signed-off-by: NSage Weil <sage@newdream.net>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Move the lock order description after all the includes, remove several
fairly outdated and/or incorrect comments, move Andrea's
copyright/changelog to the top where it belongs, remove the pointless
filename in the top of the file comment, and remove to useless macros.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

The descriptions of bio_add_page() and bio_add_pc_page() are slightly
inconsistent; improve them.
Signed-off-by: NAndreas Gruenbacher <agruen@kernel.org>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Return -ENODATA when trying to read a user.* attribute which cannot
exist: user space otherwise does not have a reasonable way to
distinguish between non-existent and inaccessible attributes.

Likewise, return -ENODATA when an unprivileged process tries to read a
trusted.* attribute: to unprivileged processes, those attributes are
invisible (listxattr() won't include them).

Related to this bug report: https://bugzilla.redhat.com/660613Signed-off-by: NAndreas Gruenbacher <agruen@kernel.org>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Tell the filesystem if we just updated timestamp (I_DIRTY_SYNC) or
anything else, so that the filesystem can track internally if it
needs to push out a transaction for fdatasync or not.

This is just the prototype change with no user for it yet.  I plan
to push large XFS changes for the next merge window, and getting
this trivial infrastructure in this window would help a lot to avoid
tree interdependencies.

Also remove incorrect comments that ->dirty_inode can't block.  That
has been changed a long time ago, and many implementations rely on it.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

... and kill a useless local variable in follow_dotdot_rcu(), while
we are at it - follow_mount_rcu(nd, path, inode) *always* assigned
value to *inode, and always it had been path->dentry->d_inode (aka
nd->path.dentry->d_inode, since it always got &nd->path as the second
argument).
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Merge branch 'upstream/tidy-xen-mmu-2.6.39' of git://git.kernel.org/pub/scm/linux/kernel/git/jeremy/xen

* 'upstream/tidy-xen-mmu-2.6.39' of git://git.kernel.org/pub/scm/linux/kernel/git/jeremy/xen:
  xen: fix compile without CONFIG_XEN_DEBUG_FS
  Use arbitrary_virt_to_machine() to deal with ioremapped pud updates.
  Use arbitrary_virt_to_machine() to deal with ioremapped pmd updates.
  xen/mmu: remove all ad-hoc stats stuff
  xen: use normal virt_to_machine for ptes
  xen: make a pile of mmu pvop functions static
  vmalloc: remove vmalloc_sync_all() from alloc_vm_area()
  xen: condense everything onto xen_set_pte
  xen: use mmu_update for xen_set_pte_at()
  xen: drop all the special iomap pte paths.

Right now security_get_user_sids() will pass in a NULL avd pointer to
avc_has_perm_noaudit(), which then forces that function to have a dummy
entry for that case and just generally test it.

Don't do it.  The normal callers all pass a real avd pointer, and this
helper function is incredibly hot.  So don't make avc_has_perm_noaudit()
do conditional stuff that isn't needed for the common case.

This also avoids some duplicated stack space.
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

* git://git.kernel.org/pub/scm/linux/kernel/git/pkl/squashfs-linus:
  Squashfs: update email address
  Squashfs: add extra sanity checks at mount time
  Squashfs: add sanity checks to fragment reading at mount time
  Squashfs: add sanity checks to lookup table reading at mount time
  Squashfs: add sanity checks to id reading at mount time
  Squashfs: add sanity checks to xattr reading at mount time
  Squashfs: reverse order of filesystem table reading
  Squashfs: move table allocation into squashfs_read_table()

The implementation of find_next_bit_le() on m68knommu is identical with
the generic implementation of find_next_bit_le().
Signed-off-by: NAkinobu Mita <akinobu.mita@gmail.com>
Cc: Greg Ungerer <gerg@uclinux.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>