linux-stable.git/fs, branch v3.0.39

mm: compaction: introduce sync-light migration for use by compaction

2012-08-01T19:27:18+00:00

commit a6bc32b899223a877f595ef9ddc1e89ead5072b8 upstream.

Stable note: Not tracked in Buzilla. This was part of a series that
	reduced interactivity stalls experienced when THP was enabled.
	These stalls were particularly noticable when copying data
	to a USB stick but the experiences for users varied a lot.

This patch adds a lightweight sync migrate operation MIGRATE_SYNC_LIGHT
mode that avoids writing back pages to backing storage.  Async compaction
maps to MIGRATE_ASYNC while sync compaction maps to MIGRATE_SYNC_LIGHT.
For other migrate_pages users such as memory hotplug, MIGRATE_SYNC is
used.

This avoids sync compaction stalling for an excessive length of time,
particularly when copying files to a USB stick where there might be a
large number of dirty pages backed by a filesystem that does not support
->writepages.

[aarcange@redhat.com: This patch is heavily based on Andrea's work]
[akpm@linux-foundation.org: fix fs/nfs/write.c build]
[akpm@linux-foundation.org: fix fs/btrfs/disk-io.c build]
Signed-off-by: Mel Gorman 
Reviewed-by: Rik van Riel 
Cc: Andrea Arcangeli 
Cc: Minchan Kim 
Cc: Dave Jones 
Cc: Jan Kara 
Cc: Andy Isaacson 
Cc: Nai Xia 
Cc: Johannes Weiner 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds 
Signed-off-by: Mel Gorman 
Signed-off-by: Greg Kroah-Hartman

mm: compaction: determine if dirty pages can be migrated without blocking within ->migratepage

2012-08-01T19:27:17+00:00

commit b969c4ab9f182a6e1b2a0848be349f99714947b0 upstream.

Stable note: Not tracked in Bugzilla. A fix aimed at preserving page
	aging information by reducing LRU list churning had the side-effect
	of reducing THP allocation success rates. This was part of a series
	to restore the success rates while preserving the reclaim fix.

Asynchronous compaction is used when allocating transparent hugepages to
avoid blocking for long periods of time.  Due to reports of stalling,
there was a debate on disabling synchronous compaction but this severely
impacted allocation success rates.  Part of the reason was that many dirty
pages are skipped in asynchronous compaction by the following check;

	if (PageDirty(page) && !sync &&
		mapping->a_ops->migratepage != migrate_page)
			rc = -EBUSY;

This skips over all mapping aops using buffer_migrate_page() even though
it is possible to migrate some of these pages without blocking.  This
patch updates the ->migratepage callback with a "sync" parameter.  It is
the responsibility of the callback to fail gracefully if migration would
block.

Signed-off-by: Mel Gorman 
Reviewed-by: Rik van Riel 
Cc: Andrea Arcangeli 
Cc: Minchan Kim 
Cc: Dave Jones 
Cc: Jan Kara 
Cc: Andy Isaacson 
Cc: Nai Xia 
Cc: Johannes Weiner 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds 
Signed-off-by: Mel Gorman 
Signed-off-by: Greg Kroah-Hartman

UBIFS: fix a bug in empty space fix-up

2012-08-01T19:26:54+00:00

commit c6727932cfdb13501108b16c38463c09d5ec7a74 upstream.

UBIFS has a feature called "empty space fix-up" which is a quirk to work-around
limitations of dumb flasher programs. Namely, of those flashers that are unable
to skip NAND pages full of 0xFFs while flashing, resulting in empty space at
the end of half-filled eraseblocks to be unusable for UBIFS. This feature is
relatively new (introduced in v3.0).

The fix-up routine (fixup_free_space()) is executed only once at the very first
mount if the superblock has the 'space_fixup' flag set (can be done with -F
option of mkfs.ubifs). It basically reads all the UBIFS data and metadata and
writes it back to the same LEB. The routine assumes the image is pristine and
does not have anything in the journal.

There was a bug in 'fixup_free_space()' where it fixed up the log incorrectly.
All but one LEB of the log of a pristine file-system are empty. And one
contains just a commit start node. And 'fixup_free_space()' just unmapped this
LEB, which resulted in wiping the commit start node. As a result, some users
were unable to mount the file-system next time with the following symptom:

UBIFS error (pid 1): replay_log_leb: first log node at LEB 3:0 is not CS node
UBIFS error (pid 1): replay_log_leb: log error detected while replaying the log at LEB 3:0

The root-cause of this bug was that 'fixup_free_space()' wrongly assumed
that the beginning of empty space in the log head (c->lhead_offs) was known
on mount. However, it is not the case - it was always 0. UBIFS does not store
in it the master node and finds out by scanning the log on every mount.

The fix is simple - just pass commit start node size instead of 0 to
'fixup_leb()'.

Signed-off-by: Artem Bityutskiy
Reported-by: Iwo Mergler
Tested-by: Iwo Mergler
Reported-by: James Nute
Signed-off-by: Greg Kroah-Hartman

cifs: always update the inode cache with the results from a FIND_*

2012-08-01T19:26:53+00:00

commit cd60042cc1392e79410dc8de9e9c1abb38a29e57 upstream.

When we get back a FIND_FIRST/NEXT result, we have some info about the
dentry that we use to instantiate a new inode. We were ignoring and
discarding that info when we had an existing dentry in the cache.

Fix this by updating the inode in place when we find an existing dentry
and the uniqueid is the same.

Reported-and-Tested-by: Andrew Bartlett 
Reported-by: Bill Robertson 
Reported-by: Dion Edwards 
Signed-off-by: Jeff Layton 
Signed-off-by: Steve French 
Signed-off-by: Greg Kroah-Hartman

fifo: Do not restart open() if it already found a partner

2012-07-19T15:58:21+00:00

commit 05d290d66be6ef77a0b962ebecf01911bd984a78 upstream.

If a parent and child process open the two ends of a fifo, and the
child immediately exits, the parent may receive a SIGCHLD before its
open() returns.  In that case, we need to make sure that open() will
return successfully after the SIGCHLD handler returns, instead of
throwing EINTR or being restarted.  Otherwise, the restarted open()
would incorrectly wait for a second partner on the other end.

The following test demonstrates the EINTR that was wrongly thrown from
the parent’s open().  Change .sa_flags = 0 to .sa_flags = SA_RESTART
to see a deadlock instead, in which the restarted open() waits for a
second reader that will never come.  (On my systems, this happens
pretty reliably within about 5 to 500 iterations.  Others report that
it manages to loop ~forever sometimes; YMMV.)

  #include 
  #include 
  #include 
  #include 
  #include 
  #include 
  #include 
  #include 

  #define CHECK(x) do if ((x) == -1) {perror(#x); abort();} while(0)

  void handler(int signum) {}

  int main()
  {
      struct sigaction act = {.sa_handler = handler, .sa_flags = 0};
      CHECK(sigaction(SIGCHLD, &act, NULL));
      CHECK(mknod("fifo", S_IFIFO | S_IRWXU, 0));
      for (;;) {
          int fd;
          pid_t pid;
          putc('.', stderr);
          CHECK(pid = fork());
          if (pid == 0) {
              CHECK(fd = open("fifo", O_RDONLY));
              _exit(0);
          }
          CHECK(fd = open("fifo", O_WRONLY));
          CHECK(close(fd));
          CHECK(waitpid(pid, NULL, 0));
      }
  }

This is what I suspect was causing the Git test suite to fail in
t9010-svn-fe.sh:

	http://bugs.debian.org/678852

Signed-off-by: Anders Kaseorg 
Reviewed-by: Jonathan Nieder 
Signed-off-by: Linus Torvalds 
Signed-off-by: Greg Kroah-Hartman

block: fix infinite loop in __getblk_slow

2012-07-19T15:58:20+00:00

commit 91f68c89d8f35fe98ea04159b9a3b42d0149478f upstream.

Commit 080399aaaf35 ("block: don't mark buffers beyond end of disk as
mapped") exposed a bug in __getblk_slow that causes mount to hang as it
loops infinitely waiting for a buffer that lies beyond the end of the
disk to become uptodate.

The problem was initially reported by Torsten Hilbrich here:

    https://lkml.org/lkml/2012/6/18/54

and also reported independently here:

    http://www.sysresccd.org/forums/viewtopic.php?f=13&t=4511

and then Richard W.M.  Jones and Marcos Mello noted a few separate
bugzillas also associated with the same issue.  This patch has been
confirmed to fix:

    https://bugzilla.redhat.com/show_bug.cgi?id=835019

The main problem is here, in __getblk_slow:

        for (;;) {
                struct buffer_head * bh;
                int ret;

                bh = __find_get_block(bdev, block, size);
                if (bh)
                        return bh;

                ret = grow_buffers(bdev, block, size);
                if (ret < 0)
                        return NULL;
                if (ret == 0)
                        free_more_memory();
        }

__find_get_block does not find the block, since it will not be marked as
mapped, and so grow_buffers is called to fill in the buffers for the
associated page.  I believe the for (;;) loop is there primarily to
retry in the case of memory pressure keeping grow_buffers from
succeeding.  However, we also continue to loop for other cases, like the
block lying beond the end of the disk.  So, the fix I came up with is to
only loop when grow_buffers fails due to memory allocation issues
(return value of 0).

The attached patch was tested by myself, Torsten, and Rich, and was
found to resolve the problem in call cases.

Signed-off-by: Jeff Moyer 
Reported-and-Tested-by: Torsten Hilbrich 
Tested-by: Richard W.M. Jones 
Reviewed-by: Josh Boyer 
[ Jens is on vacation, taking this directly  - Linus ]
Signed-off-by: Linus Torvalds 
Signed-off-by: Greg Kroah-Hartman

fs: ramfs: file-nommu: add SetPageUptodate()

2012-07-16T15:47:52+00:00

commit fea9f718b3d68147f162ed2d870183ce5e0ad8d8 upstream.

There is a bug in the below scenario for !CONFIG_MMU:

 1. create a new file
 2. mmap the file and write to it
 3. read the file can't get the correct value

Because

  sys_read() -> generic_file_aio_read() -> simple_readpage() -> clear_page()

which causes the page to be zeroed.

Add SetPageUptodate() to ramfs_nommu_expand_for_mapping() so that
generic_file_aio_read() do not call simple_readpage().

Signed-off-by: Bob Liu 
Cc: Hugh Dickins 
Cc: David Howells 
Cc: Geert Uytterhoeven 
Cc: Greg Ungerer 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds 
Signed-off-by: Greg Kroah-Hartman

eCryptfs: Properly check for O_RDONLY flag before doing privileged open

2012-07-16T15:47:50+00:00

commit 9fe79d7600497ed8a95c3981cbe5b73ab98222f0 upstream.

If the first attempt at opening the lower file read/write fails,
eCryptfs will retry using a privileged kthread. However, the privileged
retry should not happen if the lower file's inode is read-only because a
read/write open will still be unsuccessful.

The check for determining if the open should be retried was intended to
be based on the access mode of the lower file's open flags being
O_RDONLY, but the check was incorrectly performed. This would cause the
open to be retried by the privileged kthread, resulting in a second
failed open of the lower file. This patch corrects the check to
determine if the open request should be handled by the privileged
kthread.

Signed-off-by: Tyler Hicks 
Reported-by: Dan Carpenter 
Acked-by: Dan Carpenter 
Signed-off-by: Greg Kroah-Hartman

eCryptfs: Fix lockdep warning in miscdev operations

2012-07-16T15:47:49+00:00

commit 60d65f1f07a7d81d3eb3b91fc13fca80f2fdbb12 upstream.

Don't grab the daemon mutex while holding the message context mutex.
Addresses this lockdep warning:

 ecryptfsd/2141 is trying to acquire lock:
  (&ecryptfs_msg_ctx_arr[i].mux){+.+.+.}, at: [] ecryptfs_miscdev_read+0x143/0x470 [ecryptfs]

 but task is already holding lock:
  (&(*daemon)->mux){+.+...}, at: [] ecryptfs_miscdev_read+0x21c/0x470 [ecryptfs]

 which lock already depends on the new lock.

 the existing dependency chain (in reverse order) is:

 -> #1 (&(*daemon)->mux){+.+...}:
        [] lock_acquire+0x9d/0x220
        [] __mutex_lock_common+0x5a/0x4b0
        [] mutex_lock_nested+0x44/0x50
        [] ecryptfs_send_miscdev+0x97/0x120 [ecryptfs]
        [] ecryptfs_send_message+0x134/0x1e0 [ecryptfs]
        [] ecryptfs_generate_key_packet_set+0x2fe/0xa80 [ecryptfs]
        [] ecryptfs_write_metadata+0x108/0x250 [ecryptfs]
        [] ecryptfs_create+0x130/0x250 [ecryptfs]
        [] vfs_create+0xb4/0x120
        [] do_last+0x8c5/0xa10
        [] path_openat+0xd9/0x460
        [] do_filp_open+0x42/0xa0
        [] do_sys_open+0xf8/0x1d0
        [] sys_open+0x21/0x30
        [] system_call_fastpath+0x16/0x1b

 -> #0 (&ecryptfs_msg_ctx_arr[i].mux){+.+.+.}:
        [] __lock_acquire+0x1bf8/0x1c50
        [] lock_acquire+0x9d/0x220
        [] __mutex_lock_common+0x5a/0x4b0
        [] mutex_lock_nested+0x44/0x50
        [] ecryptfs_miscdev_read+0x143/0x470 [ecryptfs]
        [] vfs_read+0xb3/0x180
        [] sys_read+0x4d/0x90
        [] system_call_fastpath+0x16/0x1b

Signed-off-by: Tyler Hicks 
Signed-off-by: Greg Kroah-Hartman

eCryptfs: Gracefully refuse miscdev file ops on inherited/passed files

2012-07-16T15:47:49+00:00

commit 8dc6780587c99286c0d3de747a2946a76989414a upstream.

File operations on /dev/ecryptfs would BUG() when the operations were
performed by processes other than the process that originally opened the
file. This could happen with open files inherited after fork() or file
descriptors passed through IPC mechanisms. Rather than calling BUG(), an
error code can be safely returned in most situations.

In ecryptfs_miscdev_release(), eCryptfs still needs to handle the
release even if the last file reference is being held by a process that
didn't originally open the file. ecryptfs_find_daemon_by_euid() will not
be successful, so a pointer to the daemon is stored in the file's
private_data. The private_data pointer is initialized when the miscdev
file is opened and only used when the file is released.

https://launchpad.net/bugs/994247

Signed-off-by: Tyler Hicks 
Reported-by: Sasha Levin 
Tested-by: Sasha Levin 
Signed-off-by: Greg Kroah-Hartman