1. 03 Feb, 2007 1 commit
  2. 23 Jan, 2007 2 commits
  3. 11 Jan, 2007 1 commit
  4. 13 Dec, 2006 1 commit
    • Chen, Kenneth W's avatar
      [PATCH] optimize o_direct on block devices · e61c9018
      Chen, Kenneth W authored
      
      
      Implement block device specific .direct_IO method instead of going through
      generic direct_io_worker for block device.
      
      direct_io_worker() is fairly complex because it needs to handle O_DIRECT on
      file system, where it needs to perform block allocation, hole detection,
      extents file on write, and tons of other corner cases.  The end result is
      that it takes tons of CPU time to submit an I/O.
      
      For block device, the block allocation is much simpler and a tight triple
      loop can be written to iterate each iovec and each page within the iovec in
      order to construct/prepare bio structure and then subsequently submit it to
      the block layer.  This significantly speeds up O_D on block device.
      
      [akpm@osdl.org: small speedup]
      Signed-off-by: default avatarKen Chen <kenneth.w.chen@intel.com>
      Cc: Christoph Hellwig <hch@lst.de>
      Cc: Zach Brown <zach.brown@oracle.com>
      Signed-off-by: default avatarAndrew Morton <akpm@osdl.org>
      Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
      e61c9018
  5. 08 Dec, 2006 7 commits
  6. 07 Dec, 2006 2 commits
  7. 31 Oct, 2006 1 commit
  8. 30 Oct, 2006 2 commits
  9. 28 Oct, 2006 1 commit
  10. 01 Oct, 2006 3 commits
  11. 30 Sep, 2006 3 commits
  12. 29 Sep, 2006 2 commits
    • Jason Baron's avatar
      [PATCH] block_dev.c mutex_lock_nested() fix · 87d7c8ac
      Jason Baron authored
      
      
      In the case below we are locking the whole disk not a partition.  This
      change simply brings the code in line with the piece above where when we
      are the 'first' opener, and we are a partition.
      Signed-off-by: default avatarJason Baron <jbaron@redhat.com>
      Acked-by: default avatarPeter Zijlstra <a.p.zijlstra@chello.nl>
      Signed-off-by: default avatarAndrew Morton <akpm@osdl.org>
      Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
      87d7c8ac
    • Andrew Morton's avatar
      [PATCH] blockdev.c: check driver layer errors · 4d7dd8fd
      Andrew Morton authored
      
      
      Check driver layer errors.
      
      Fix from: "Jun'ichi Nomura" <j-nomura@ce.jp.nec.com>
      
      In blockdevc-check-errors.patch, add_bd_holder() is modified to return error
      values when some of its operation failed.  Among them, it returns -EEXIST when
      a given bd_holder object already exists in the list.
      
      However, in this case, the function completed its work successfully and need
      no action by its caller other than freeing unused bd_holder object.  So I
      think it's better to return success after freeing by itself.
      
      Otherwise, bd_claim-ing with same claim pointer will fail.
      Typically, lvresize will fails with following message:
        device-mapper: reload ioctl failed: Invalid argument
      and you'll see messages like below in kernel log:
        device-mapper: table: 254:13: linear: dm-linear: Device lookup failed
        device-mapper: ioctl: error adding target to table
      
      Similarly, it should not add bd_holder to the list if either one of symlinking
      fails.  I don't have a test case for this to happen but it should cause
      dereference of freed pointer.
      
      If a matching bd_holder is found in bd_holder_list, add_bd_holder() completes
      its job by just incrementing the reference count.  In this case, it should be
      considered as success but it used to return 'fail' to let the caller free
      temporary bd_holder.  Fixed it to return success and free given object by
      itself.
      
      Also, if either one of symlinking fails, the bd_holder should not be added to
      the list so that it can be discarded later.  Otherwise, the caller will free
      bd_holder which is in the list.
      Signed-off-by: default avatarJun'ichi Nomura <j-nomura@ce.jp.nec.com>
      Cc: "Randy.Dunlap" <rdunlap@xenotime.net>
      Signed-off-by: default avatarAndrew Morton <akpm@osdl.org>
      Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
      4d7dd8fd
  13. 27 Aug, 2006 1 commit
    • Peter Zijlstra's avatar
      [PATCH] lockdep: fix blkdev_open() warning · 6946bd63
      Peter Zijlstra authored
      
      
      On Wed, 2006-08-09 at 07:57 +0200, Rolf Eike Beer wrote:
      > =============================================
      > [ INFO: possible recursive locking detected ]
      > ---------------------------------------------
      > parted/7929 is trying to acquire lock:
      >  (&bdev->bd_mutex){--..}, at: [<c105eb8d>] __blkdev_put+0x1e/0x13c
      >
      > but task is already holding lock:
      >  (&bdev->bd_mutex){--..}, at: [<c105eec6>] do_open+0x72/0x3a8
      >
      > other info that might help us debug this:
      > 1 lock held by parted/7929:
      >  #0:  (&bdev->bd_mutex){--..}, at: [<c105eec6>] do_open+0x72/0x3a8
      > stack backtrace:
      >  [<c1003aad>] show_trace_log_lvl+0x58/0x15b
      >  [<c100495f>] show_trace+0xd/0x10
      >  [<c1004979>] dump_stack+0x17/0x1a
      >  [<c102dee5>] __lock_acquire+0x753/0x99c
      >  [<c102e3b0>] lock_acquire+0x4a/0x6a
      >  [<c1204501>] mutex_lock_nested+0xc8/0x20c
      >  [<c105eb8d>] __blkdev_put+0x1e/0x13c
      >  [<c105ecc4>] blkdev_put+0xa/0xc
      >  [<c105f18a>] do_open+0x336/0x3a8
      >  [<c105f21b>] blkdev_open+0x1f/0x4c
      >  [<c1057b40>] __dentry_open+0xc7/0x1aa
      >  [<c1057c91>] nameidata_to_filp+0x1c/0x2e
      >  [<c1057cd1>] do_filp_open+0x2e/0x35
      >  [<c1057dd7>] do_sys_open+0x38/0x68
      >  [<c1057e33>] sys_open+0x16/0x18
      >  [<c1002845>] sysenter_past_esp+0x56/0x8d
      
      OK, I'm having a look here; its all new to me so bear with me.
      
      blkdev_open() calls
        do_open(bdev, ...,BD_MUTEX_NORMAL) and takes
          mutex_lock_nested(&bdev->bd_mutex, BD_MUTEX_NORMAL)
      
      then something fails, and we're thrown to:
      
      out_first: where
          if (bdev != bdev->bd_contains)
            blkdev_put(bdev->bd_contains) which is
              __blkdev_put(bdev->bd_contains, BD_MUTEX_NORMAL) which does
                mutex_lock_nested(&bdev->bd_contains->bd_mutex, BD_MUTEX_NORMAL) <--- lockdep trigger
      
      When going to out_first, dbev->bd_contains is either bdev or whole, and
      since we take the branch it must be whole. So it seems to me the
      following patch would be the right one:
      
      [akpm@osdl.org: compile fix]
      Signed-off-by: default avatarPeter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Arjan van de Ven <arjan@linux.intel.com>
      Acked-by: default avatarNeilBrown <neilb@suse.de>
      Signed-off-by: default avatarAndrew Morton <akpm@osdl.org>
      Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
      6946bd63
  14. 03 Jul, 2006 1 commit
    • Ingo Molnar's avatar
      [PATCH] lockdep: annotate blkdev nesting · 663d440e
      Ingo Molnar authored
      
      
      Teach special (recursive) locking code to the lock validator.
      
      Effects on non-lockdep kernels:
      
      - the introduction of the following function variants:
      
        extern struct block_device *open_partition_by_devnum(dev_t, unsigned);
      
        extern int blkdev_put_partition(struct block_device *);
      
        static int
        blkdev_get_whole(struct block_device *bdev, mode_t mode, unsigned flags);
      
       which on non-lockdep are the same as open_by_devnum(), blkdev_put()
       and blkdev_get().
      
      - a subclass parameter to do_open(). [unused on non-lockdep]
      
      - a subclass parameter to __blkdev_put(), which is a new internal
        function for the main blkdev_put*() functions. [parameter unused
        on non-lockdep kernels, except for two sanity check WARN_ON()s]
      
      these functions carry no semantical difference - they only express
      object dependencies towards the lockdep subsystem.
      Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      Signed-off-by: default avatarArjan van de Ven <arjan@linux.intel.com>
      Cc: Neil Brown <neilb@cse.unsw.edu.au>
      Signed-off-by: default avatarAndrew Morton <akpm@osdl.org>
      Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
      663d440e
  15. 30 Jun, 2006 1 commit
  16. 28 Jun, 2006 1 commit
  17. 26 Jun, 2006 1 commit
  18. 23 Jun, 2006 1 commit
    • David Howells's avatar
      [PATCH] VFS: Permit filesystem to override root dentry on mount · 454e2398
      David Howells authored
      
      
      Extend the get_sb() filesystem operation to take an extra argument that
      permits the VFS to pass in the target vfsmount that defines the mountpoint.
      
      The filesystem is then required to manually set the superblock and root dentry
      pointers.  For most filesystems, this should be done with simple_set_mnt()
      which will set the superblock pointer and then set the root dentry to the
      superblock's s_root (as per the old default behaviour).
      
      The get_sb() op now returns an integer as there's now no need to return the
      superblock pointer.
      
      This patch permits a superblock to be implicitly shared amongst several mount
      points, such as can be done with NFS to avoid potential inode aliasing.  In
      such a case, simple_set_mnt() would not be called, and instead the mnt_root
      and mnt_sb would be set directly.
      
      The patch also makes the following changes:
      
       (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount
           pointer argument and return an integer, so most filesystems have to change
           very little.
      
       (*) If one of the convenience function is not used, then get_sb() should
           normally call simple_set_mnt() to instantiate the vfsmount. This will
           always return 0, and so can be tail-called from get_sb().
      
       (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the
           dcache upon superblock destruction rather than shrink_dcache_anon().
      
           This is required because the superblock may now have multiple trees that
           aren't actually bound to s_root, but that still need to be cleaned up. The
           currently called functions assume that the whole tree is rooted at s_root,
           and that anonymous dentries are not the roots of trees which results in
           dentries being left unculled.
      
           However, with the way NFS superblock sharing are currently set to be
           implemented, these assumptions are violated: the root of the filesystem is
           simply a dummy dentry and inode (the real inode for '/' may well be
           inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries
           with child trees.
      
           [*] Anonymous until discovered from another tree.
      
       (*) The documentation has been adjusted, including the additional bit of
           changing ext2_* into foo_* in the documentation.
      
      [akpm@osdl.org: convert ipath_fs, do other stuff]
      Signed-off-by: default avatarDavid Howells <dhowells@redhat.com>
      Acked-by: default avatarAl Viro <viro@zeniv.linux.org.uk>
      Cc: Nathan Scott <nathans@sgi.com>
      Cc: Roland Dreier <rolandd@cisco.com>
      Signed-off-by: default avatarAndrew Morton <akpm@osdl.org>
      Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
      454e2398
  19. 22 Jun, 2006 1 commit
    • OGAWA Hirofumi's avatar
      [PATCH] Fix a race condition between ->i_mapping and iput() · 09d967c6
      OGAWA Hirofumi authored
      
      
      This race became a cause of oops, and can reproduce by the following.
      
          while true; do
      	dd if=/dev/zero of=/dev/.static/dev/hdg1 bs=512 count=1000 & sync
          done
      
      This race condition was between __sync_single_inode() and iput().
      
                cpu0 (fs's inode)                 cpu1 (bdev's inode)
                -----------------                 -------------------
                                             close("/dev/hda2")
                                             [...]
      __sync_single_inode()
         /* copy the bdev's ->i_mapping */
         mapping = inode->i_mapping;
      
                                             generic_forget_inode()
                                                bdev_clear_inode()
      					     /* restre the fs's ->i_mapping */
      				             inode->i_mapping = &inode->i_data;
      				          /* bdev's inode was freed */
                                                destroy_inode(inode);
      
         if (wait) {
            /* dereference a freed bdev's mapping->host */
            filemap_fdatawait(mapping);  /* Oops */
      
      Since __sync_single_inode() is only taking a ref-count of fs's inode, the
      another process can be close() and freeing the bdev's inode while writing
      fs's inode.  So, __sync_signle_inode() accesses the freed ->i_mapping,
      oops.
      
      This patch takes a ref-count on the bdev's inode for the fs's inode before
      setting a ->i_mapping, and the clear_inode() of the fs's inode does iput() on
      the bdev's inode.  So if the fs's inode is still living, bdev's inode
      shouldn't be freed.
      Signed-off-by: default avatarOGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
      Signed-off-by: default avatarAndrew Morton <akpm@osdl.org>
      Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
      09d967c6
  20. 01 May, 2006 1 commit
  21. 28 Mar, 2006 1 commit
  22. 27 Mar, 2006 2 commits
  23. 26 Mar, 2006 2 commits
  24. 24 Mar, 2006 1 commit