Commit graph

488 commits

Author SHA1 Message Date
Nick Piggin
b74c79e993 fs: provide rcu-walk aware permission i_ops
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 17:50:29 +11:00
Nick Piggin
34286d6662 fs: rcu-walk aware d_revalidate method
Require filesystems be aware of .d_revalidate being called in rcu-walk
mode (nd->flags & LOOKUP_RCU). For now do a simple push down, returning
-ECHILD from all implementations.

Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 17:50:29 +11:00
Nick Piggin
fb045adb99 fs: dcache reduce branches in lookup path
Reduce some branches and memory accesses in dcache lookup by adding dentry
flags to indicate common d_ops are set, rather than having to check them.
This saves a pointer memory access (dentry->d_op) in common path lookup
situations, and saves another pointer load and branch in cases where we
have d_op but not the particular operation.

Patched with:

git grep -E '[.>]([[:space:]])*d_op([[:space:]])*=' | xargs sed -e 's/\([^\t ]*\)->d_op = \(.*\);/d_set_d_op(\1, \2);/' -e 's/\([^\t ]*\)\.d_op = \(.*\);/d_set_d_op(\&\1, \2);/' -i

Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 17:50:28 +11:00
Nick Piggin
fa0d7e3de6 fs: icache RCU free inodes
RCU free the struct inode. This will allow:

- Subsequent store-free path walking patch. The inode must be consulted for
  permissions when walking, so an RCU inode reference is a must.
- sb_inode_list_lock to be moved inside i_lock because sb list walkers who want
  to take i_lock no longer need to take sb_inode_list_lock to walk the list in
  the first place. This will simplify and optimize locking.
- Could remove some nested trylock loops in dcache code
- Could potentially simplify things a bit in VM land. Do not need to take the
  page lock to follow page->mapping.

The downsides of this is the performance cost of using RCU. In a simple
creat/unlink microbenchmark, performance drops by about 10% due to inability to
reuse cache-hot slab objects. As iterations increase and RCU freeing starts
kicking over, this increases to about 20%.

In cases where inode lifetimes are longer (ie. many inodes may be allocated
during the average life span of a single inode), a lot of this cache reuse is
not applicable, so the regression caused by this patch is smaller.

The cache-hot regression could largely be avoided by using SLAB_DESTROY_BY_RCU,
however this adds some complexity to list walking and store-free path walking,
so I prefer to implement this at a later date, if it is shown to be a win in
real situations. I haven't found a regression in any non-micro benchmark so I
doubt it will be a problem.

Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 17:50:26 +11:00
Nick Piggin
b5c84bf6f6 fs: dcache remove dcache_lock
dcache_lock no longer protects anything. remove it.

Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 17:50:23 +11:00
Nick Piggin
2fd6b7f507 fs: dcache scale subdirs
Protect d_subdirs and d_child with d_lock, except in filesystems that aren't
using dcache_lock for these anyway (eg. using i_mutex).

Note: if we change the locking rule in future so that ->d_child protection is
provided only with ->d_parent->d_lock, it may allow us to reduce some locking.
But it would be an exception to an otherwise regular locking scheme, so we'd
have to see some good results. Probably not worthwhile.

Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 17:50:21 +11:00
Nick Piggin
da5029563a fs: dcache scale d_unhashed
Protect d_unhashed(dentry) condition with d_lock. This means keeping
DCACHE_UNHASHED bit in synch with hash manipulations.

Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 17:50:21 +11:00
Nick Piggin
b7ab39f631 fs: dcache scale dentry refcount
Make d_count non-atomic and protect it with d_lock. This allows us to ensure a
0 refcount dentry remains 0 without dcache_lock. It is also fairly natural when
we start protecting many other dentry members with d_lock.

Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 17:50:21 +11:00
Henry C Chang
b6aa5901c7 ceph: mark user pages dirty on direct-io reads
For read operation, we have to set the argument _write_ of get_user_pages
to 1 since we will write data to pages. Also, we need to SetPageDirty before
releasing these pages.

Signed-off-by: Henry C Chang <henry_c_chang@tcloudcomputing.com>
Signed-off-by: Sage Weil <sage@newdream.net>
2010-12-17 09:54:40 -08:00
Sage Weil
92cf765237 ceph: fix null pointer dereference in ceph_init_dentry for nfs reexport
The fh_to_dentry etc. methods use ceph_init_dentry(), which assumes that
d_parent is defined.  It isn't for those callers, so check!

Signed-off-by: Sage Weil <sage@newdream.net>
2010-12-17 09:53:48 -08:00
Henry C Chang
ab226e21ad ceph: fix direct-io on non-page-aligned buffers
The user buffer may be 512-byte aligned, not page-aligned.  We were
assuming the buffer was page-aligned and only accounting for
non-page-aligned io offsets.

Signed-off-by: Henry C Chang <henry_c_chang@tcloudcomputing.com>
Signed-off-by: Sage Weil <sage@newdream.net>
2010-12-15 20:46:16 -08:00
Sage Weil
1cd275f609 ceph: fix ioctl magic
The ioctl magic was inadvertently changed in 571dba52.

Signed-off-by: Sage Weil <sage@newdream.net>
2010-12-06 09:45:22 -08:00
Herb Shiu
a5b10629ed ceph: Behave better when handling file lock replies.
Fill in the local lock with response data if appropriate,
and don't call posix_lock_file when reading locks.

Signed-off-by: Herb Shiu <herb_shiu@tcloudcomputing.com>
Acked-by: Greg Farnum <gregf@hq.newdream.net>
Signed-off-by: Sage Weil <sage@newdream.net>
2010-12-01 14:22:34 -08:00
Herb Shiu
637ae8d547 ceph: pass lock information by struct file_lock instead of as individual params.
Signed-off-by: Herb Shiu <herb_shiu@tcloudcomputing.com>
Acked-by: Greg Farnum <gregf@hq.newdream.net>
Signed-off-by: Sage Weil <sage@newdream.net>
2010-12-01 14:22:34 -08:00
Herb Shiu
25933abdd8 ceph: Handle file locks in replies from the MDS.
Previously the kernel client incorrectly assumed everything was a directory.

Signed-off-by: Herb Shiu <herb_shiu@tcloudcomputing.com>
Acked-by: Greg Farnum <gregf@hq.newdream.net>
Signed-off-by: Sage Weil <sage@newdream.net>
2010-12-01 14:22:27 -08:00
Sage Weil
884ea89276 ceph: avoid possible null deref in readdir after dir llseek
last may be NULL, but we dereference it in the else branch without
checking.  Normally it doesn't trigger because last == NULL when fpos == 2,
but it could happen on a newly opened dir if the user seeks forward.

Reported-by: Dan Carpenter <error27@gmail.com>
Signed-off-by: Sage Weil <sage@newdream.net>
2010-12-01 14:15:31 -08:00
Linus Torvalds
76db8ac45f Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client:
  ceph: fix readdir EOVERFLOW on 32-bit archs
  ceph: fix frag offset for non-leftmost frags
  ceph: fix dangling pointer
  ceph: explicitly specify page alignment in network messages
  ceph: make page alignment explicit in osd interface
  ceph: fix comment, remove extraneous args
  ceph: fix update of ctime from MDS
  ceph: fix version check on racing inode updates
  ceph: fix uid/gid on resent mds requests
  ceph: fix rdcache_gen usage and invalidate
  ceph: re-request max_size if cap auth changes
  ceph: only let auth caps update max_size
  ceph: fix open for write on clustered mds
  ceph: fix bad pointer dereference in ceph_fill_trace
  ceph: fix small seq message skipping
  Revert "ceph: update issue_seq on cap grant"
2010-11-19 15:32:22 -08:00
Sage Weil
3105c19c45 ceph: fix readdir EOVERFLOW on 32-bit archs
One of the readdir filldir_t callers was passing the raw ceph 64-bit ino
instead of the hashed 32-bit one, producing an EOVERFLOW in the filler
callback.  Fix this by calling the ceph_vino_to_ino() helper to do the
conversion.

Reported-by: Jan Smets <jan.smets@alcatel-lucent.com>
Tested-by: Jan Smets <jan.smets@alcatel-lucent.com>
Signed-off-by: Sage Weil <sage@newdream.net>
2010-11-18 09:15:07 -08:00
Arnd Bergmann
451a3c24b0 BKL: remove extraneous #include <smp_lock.h>
The big kernel lock has been removed from all these files at some point,
leaving only the #include.

Remove this too as a cleanup.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-11-17 08:59:32 -08:00
Sage Weil
7b88dadc13 ceph: fix frag offset for non-leftmost frags
We start at offset 2 for the leftmost frag, and 0 for subsequent frags.
When we reach the end (rightmost), we go back to 2.  This fixes readdir on
fragmented (large) directories.

Signed-off-by: Sage Weil <sage@newdream.net>
2010-11-11 16:48:59 -08:00
Sage Weil
a1629c3b24 ceph: fix dangling pointer
Clear fi->last_name when it's freed.  The only caller is rewinddir() (or
equivalent lseek).

Signed-off-by: Sage Weil <sage@newdream.net>
2010-11-11 15:24:06 -08:00
Sage Weil
b7495fc2ff ceph: make page alignment explicit in osd interface
We used to infer alignment of IOs within a page based on the file offset,
which assumed they matched.  This broke with direct IO that was not aligned
to pages (e.g., 512-byte aligned IO).  We were also trusting the alignment
specified in the OSD reply, which could have been adjusted by the server.

Explicitly specify the page alignment when setting up OSD IO requests.

Signed-off-by: Sage Weil <sage@newdream.net>
2010-11-09 12:43:12 -08:00
Sage Weil
e98b6fed84 ceph: fix comment, remove extraneous args
The offset/length arguments aren't used.

Signed-off-by: Sage Weil <sage@newdream.net>
2010-11-09 12:24:53 -08:00
Sage Weil
d8672d64b8 ceph: fix update of ctime from MDS
The client can have a newer ctime than the MDS due to AUTH_EXCL and
XATTR_EXCL caps as well; update the check in ceph_fill_file_time
appropriately.

This fixes cases where ctime/mtime goes backward under the right sequence
of local updates (e.g. chmod) and mds replies (e.g. subsequent stat that
goes to the MDS).

Signed-off-by: Sage Weil <sage@newdream.net>
2010-11-08 09:24:34 -08:00
Sage Weil
8bd59e0188 ceph: fix version check on racing inode updates
We may get updates on the same inode from multiple MDSs; generally we only
pay attention if the update is newer than what we already have.  The
exception is when an MDS sense unstable information, in which case we
always update.

The old > check got this wrong when our version was odd (e.g. 3) and the
reply version was even (e.g. 2): the older stale (v2) info would be
applied.  Fixed and clarified the comment.

Signed-off-by: Sage Weil <sage@newdream.net>
2010-11-08 09:23:12 -08:00
Sage Weil
cb4276cca4 ceph: fix uid/gid on resent mds requests
MDS requests can be rebuilt and resent in non-process context, but were
filling in uid/gid from current_fsuid/gid.  Put that information in the
request struct on request setup.

This fixes incorrect (and root) uid/gid getting set for requests that
are forwarded between MDSs, usually due to metadata migrations.

Signed-off-by: Sage Weil <sage@newdream.net>
2010-11-08 07:29:05 -08:00
Sage Weil
cd045cb42a ceph: fix rdcache_gen usage and invalidate
We used to use rdcache_gen to indicate whether we "might" have cached
pages.  Now we just look at the mapping to determine that.  However, some
old behavior remains from that transition.

First, rdcache_gen == 0 no longer means we have no pages.  That can happen
at any time (presumably when we carry FILE_CACHE).  We should not reset it
to zero, and we should not check that it is zero.

That means that the only purpose for rdcache_revoking is to resolve races
between new issues of FILE_CACHE and an async invalidate.  If they are
equal, we should invalidate.  On success, we decrement rdcache_revoking,
so that it is no longer equal to rdcache_gen.  Similarly, if we success
in doing a sync invalidate, set revoking = gen - 1.  (This is a small
optimization to avoid doing unnecessary invalidate work and does not
affect correctness.)

Signed-off-by: Sage Weil <sage@newdream.net>
2010-11-08 07:29:05 -08:00
Sage Weil
feb4cc9bb4 ceph: re-request max_size if cap auth changes
If the auth cap migrates to another MDS, clear requested_max_size so that
we resend any pending max_size increase requests.  This fixes potential
hangs on writes that extend a file and race with an cap migration between
MDSs.

Signed-off-by: Sage Weil <sage@newdream.net>
2010-11-07 09:39:23 -08:00
Sage Weil
912a9b0319 ceph: only let auth caps update max_size
Only the auth MDS has a meaningful max_size value for us, so only update it
in fill_inode if we're being issued an auth cap.  Otherwise, a random
stat result from a non-auth MDS can clobber a meaningful max_size, get
the client<->mds cap state out of sync, and make writes hang.

Specifically, even if the client re-requests a larger max_size (which it
will), the MDS won't respond because as far as it knows we already have a
sufficiently large value.

Signed-off-by: Sage Weil <sage@newdream.net>
2010-11-07 09:39:21 -08:00
Sage Weil
7421ab8041 ceph: fix open for write on clustered mds
Normally when we open a file we already have a cap, and simply update the
wanted set.  However, if we open a file for write, but don't have an auth
cap, that doesn't work; we need to open a new cap with the auth MDS.  Only
reuse existing caps if we are opening for read or the existing cap is auth.

Signed-off-by: Sage Weil <sage@newdream.net>
2010-11-07 09:07:15 -08:00
Sage Weil
d8b16b3d1c ceph: fix bad pointer dereference in ceph_fill_trace
We dereference *in a few lines down, but only set it on rename.  It is
apparently pretty rare for this to trigger, but I have been hitting it
with a clustered MDSs.

Signed-off-by: Sage Weil <sage@newdream.net>
2010-11-07 08:40:43 -08:00
Al Viro
a7f9fb205a convert ceph
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-10-29 04:17:18 -04:00
Sage Weil
2f56f56ad9 Revert "ceph: update issue_seq on cap grant"
This reverts commit d91f2438d8.

The intent of issue_seq is to distinguish between mds->client messages that
(re)create the cap and those that do not, which means we should _only_ be
updating that value in the create paths.  By updating it in handle_cap_grant,
we reset it to zero, which then breaks release.

The larger question is what workload/problem made me think it should be
updated here...

Signed-off-by: Sage Weil <sage@newdream.net>
2010-10-27 21:05:54 -07:00
Wu Fengguang
1b430beee5 writeback: remove nonblocking/encountered_congestion references
This removes more dead code that was somehow missed by commit 0d99519efe
(writeback: remove unused nonblocking and congestion checks).  There are
no behavior change except for the removal of two entries from one of the
ext4 tracing interface.

The nonblocking checks in ->writepages are no longer used because the
flusher now prefer to block on get_request_wait() than to skip inodes on
IO congestion.  The latter will lead to more seeky IO.

The nonblocking checks in ->writepage are no longer used because it's
redundant with the WB_SYNC_NONE check.

We no long set ->nonblocking in VM page out and page migration, because
a) it's effectively redundant with WB_SYNC_NONE in current code
b) it's old semantic of "Don't get stuck on request queues" is mis-behavior:
   that would skip some dirty inodes on congestion and page out others, which
   is unfair in terms of LRU age.

Inspired by Christoph Hellwig. Thanks!

Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: David Howells <dhowells@redhat.com>
Cc: Sage Weil <sage@newdream.net>
Cc: Steve French <sfrench@samba.org>
Cc: Chris Mason <chris.mason@oracle.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-10-26 16:52:05 -07:00
Sage Weil
efa4c1206e ceph: do not carry i_lock for readdir from dcache
We were taking dcache_lock inside of i_lock, which introduces a dependency
not found elsewhere in the kernel, complicationg the vfs locking
scalability work.  Since we don't actually need it here anyway, remove
it.

We only need i_lock to test for the I_COMPLETE flag, so be careful to do
so without dcache_lock held.

Signed-off-by: Sage Weil <sage@newdream.net>
2010-10-20 15:38:27 -07:00
Julia Lawall
61413c2f59 fs/ceph/xattr.c: Use kmemdup
Convert a sequence of kmalloc and memcpy to use kmemdup.

The semantic patch that performs this transformation is:
(http://coccinelle.lip6.fr/)

// <smpl>
@@
expression a,flag,len;
expression arg,e1,e2;
statement S;
@@

  a =
-  \(kmalloc\|kzalloc\)(len,flag)
+  kmemdup(arg,len,flag)
  <... when != a
  if (a == NULL || ...) S
  ...>
- memcpy(a,arg,len+1);
// </smpl>

Signed-off-by: Julia Lawall <julia@diku.dk>
Signed-off-by: Sage Weil <sage@newdream.net>
2010-10-20 15:38:26 -07:00
Greg Farnum
571dba52a3 ceph: add CEPH_MDS_OP_SETDIRLAYOUT and associated ioctl.
Signed-off-by: Sage Weil <sage@newdream.net>
2010-10-20 15:38:23 -07:00
Randy Dunlap
6f453ed6c0 ceph: fix debugfs warnings
Include "super.h" outside of CONFIG_DEBUG_FS to eliminate a compiler warning:

fs/ceph/debugfs.c:266: warning: 'struct ceph_fs_client' declared inside parameter list
fs/ceph/debugfs.c:266: warning: its scope is only this definition or declaration, which is probably not what you want
fs/ceph/debugfs.c:271: warning: 'struct ceph_fs_client' declared inside parameter list

Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
2010-10-20 15:38:21 -07:00
Sage Weil
496e59553c ceph: switch from BKL to lock_flocks()
Switch from using the BKL explicitly to the new lock_flocks() interface.
Eventually this will turn into a spinlock.

Signed-off-by: Sage Weil <sage@newdream.net>
2010-10-20 15:38:18 -07:00
Greg Farnum
fca4451acf ceph: preallocate flock state without locks held
When the lock_kernel() turns into lock_flocks() and a spinlock, we won't
be able to do allocations with the lock held.  Preallocate space without
the lock, and retry if the lock state changes out from underneath us.

Signed-off-by: Greg Farnum <gregf@hq.newdream.net>
Signed-off-by: Sage Weil <sage@newdream.net>
2010-10-20 15:38:17 -07:00
Sage Weil
18a38193ef ceph: use mapping->nrpages to determine if mapping is empty
This is simpler and faster.

Signed-off-by: Sage Weil <sage@newdream.net>
2010-10-20 15:38:15 -07:00
Sage Weil
93afd449aa ceph: only invalidate on check_caps if we actually have pages
The i_rdcache_gen value only implies we MAY have cached pages; actually
check the mapping to see if it's worth bothering with an invalidate.

Signed-off-by: Sage Weil <sage@newdream.net>
2010-10-20 15:38:15 -07:00
Sage Weil
4c32f5dda5 ceph: do not hide .snap in root directory
Snaps in the root directory are now supported by the MDS, and harmless on
older versions.

Signed-off-by: Sage Weil <sage@newdream.net>
2010-10-20 15:38:14 -07:00
Yehuda Sadeh
3d14c5d2b6 ceph: factor out libceph from Ceph file system
This factors out protocol and low-level storage parts of ceph into a
separate libceph module living in net/ceph and include/linux/ceph.  This
is mostly a matter of moving files around.  However, a few key pieces
of the interface change as well:

 - ceph_client becomes ceph_fs_client and ceph_client, where the latter
   captures the mon and osd clients, and the fs_client gets the mds client
   and file system specific pieces.
 - Mount option parsing and debugfs setup is correspondingly broken into
   two pieces.
 - The mon client gets a generic handler callback for otherwise unknown
   messages (mds map, in this case).
 - The basic supported/required feature bits can be expanded (and are by
   ceph_fs_client).

No functional change, aside from some subtle error handling cases that got
cleaned up in the refactoring process.

Signed-off-by: Sage Weil <sage@newdream.net>
2010-10-20 15:37:28 -07:00
Yehuda Sadeh
ae1533b62b ceph-rbd: osdc support for osd call and rollback operations
This will be used for rbd snapshots administration.

Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
2010-10-20 15:37:25 -07:00
Yehuda Sadeh
68b4476b0b ceph: messenger and osdc changes for rbd
Allow the messenger to send/receive data in a bio.  This is added
so that we wouldn't need to copy the data into pages or some other buffer
when doing IO for an rbd block device.

We can now have trailing variable sized data for osd
ops.  Also osd ops encoding is more modular.

Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
Signed-off-by: Sage Weil <sage@newdream.net>
2010-10-20 15:37:18 -07:00
Yehuda Sadeh
3499e8a5d4 ceph: refactor osdc requests creation functions
The osd requests creation are being decoupled from the
vino parameter, allowing clients using the osd to use
other arbitrary object names that are not necessarily
vino based. Also, calc_raw_layout now takes a snap id.

Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
Signed-off-by: Sage Weil <sage@newdream.net>
2010-10-20 15:36:01 -07:00
Yehuda Sadeh
7669a2c95e ceph: lookup pool in osdmap by name
Implement a pool lookup by name.  This will be used by rbd.

Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
Signed-off-by: Sage Weil <sage@newdream.net>
2010-10-20 15:35:36 -07:00
Sage Weil
d91f2438d8 ceph: update issue_seq on cap grant
We need to update the issue_seq on any grant operation, be it via an MDS
reply or a separate grant message.  The update in the grant path was
missing.  This broke cap release for inodes in which the MDS sent an
explicit grant message that was not soon after followed by a successful
MDS reply on the same inode.

Also fix the signedness on seq locals.

Signed-off-by: Sage Weil <sage@newdream.net>
2010-10-07 08:01:50 -07:00
Greg Farnum
21b559de56 ceph: send cap release message early on failed revoke.
If an MDS tries to revoke caps that we don't have, we want to send
releases early since they probably contain the caps message the MDS
is looking for.

Previously, we only sent the messages if we didn't have the inode either. But
in a multi-mds system we can retain the inode after dropping all caps for
a single MDS.

Signed-off-by: Greg Farnum <gregf@hq.newdream.net>
Signed-off-by: Sage Weil <sage@newdream.net>
2010-10-07 08:00:24 -07:00