In order to incorporate async requests, we need to allow for a more
general way to do things on receive, rather than just waking up a
process.
Turn the task pointer in the mid_q_entry into a callback function and a
generic data pointer. When a response comes in, or the socket is
reconnected, cifsd can call the callback function in order to wake up
the process.
The default is to just wake up the current process which should mean no
change in behavior for existing code.
Also, clean up the locking in cifs_reconnect. There doesn't seem to be
any need to hold both the srv_mutex and GlobalMid_Lock when walking the
list of mids.
Reviewed-by: Suresh Jayaraman <sjayaraman@suse.de>
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
Make it use a switch statement based on the value of the midStatus. If
the resp_buf is set, then MID_RESPONSE_RECEIVED is too.
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
We only want to force a reconnect to the server under very limited and
specific circumstances. Now that we have processes waiting indefinitely
for responses, we shouldn't reach this point unless a reconnect is
already in process. Thus, there's no reason to re-mark the server for
reconnect here.
Reviewed-by: Suresh Jayaraman <sjayaraman@suse.de>
Reviewed-by: Pavel Shilovsky <piastryyy@gmail.com>
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
The client should not be timing out on individual SMB requests. Too much
of the state between client and server is tied to the state of the
socket. If we time out requests and issue spurious disconnects then that
comprimises data integrity.
Instead of doing this complicated dance where we try to decide how long
to wait for a response for particular requests, have the client instead
wait indefinitely for a response. Also, use a TASK_KILLABLE sleep here
so that fatal signals will break out of this waiting.
Later patches will add support for detecting dead peers and forcing
reconnects based on that.
Reviewed-by: Suresh Jayaraman <sjayaraman@suse.de>
Reviewed-by: Pavel Shilovsky <piastryyy@gmail.com>
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
If a DACL has entries for ACEs for SID Everyone and Authenticated Users,
factor in mask in respective entries during calculation of permissions
for all three, user, group, and other.
http://technet.microsoft.com/en-us/library/bb463216.aspx
Signed-off-by: Shirish Pargaonkar <shirishpargaonkar@gmail.com>
Reviewed-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
NTLM response length was changed to 16 bytes instead of 24 bytes
that are sent in Tree Connection Request during share-level security
share mounts. Revert it back to 24 bytes.
Reported-and-Tested-by: Grzegorz Ozanski <grzegorz.ozanski@intel.com>
Acked-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Shirish Pargaonkar <shirishpargaonkar@gmail.com>
Acked-by: Suresh Jayaraman <sjayaraman@suse.de>
Cc: stable@kernel.org
Signed-off-by: Steve French <sfrench@us.ibm.com>
Reviewed-by: Suresh Jayaraman <sjayaraman@suse.de>
Reviewed-by: Pavel Shilovsky <piastryyy@gmail.com>
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
In later patches, we're going to need to have finer-grained control
over the addition and removal of these structs from the pending_mid_q
and we'll need to be able to call the destructor while holding the
spinlock. Move the locked sections out of both routines and into
the callers. Fix up current callers of DeleteMidQEntry to call a new
routine that dequeues the entry and then destroys it.
Reviewed-by: Suresh Jayaraman <sjayaraman@suse.de>
Reviewed-by: Pavel Shilovsky <piastryyy@gmail.com>
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
It's an atomic_t and the code accesses the "counter" field in it directly
instead of using atomic_read(). It also is sometimes accessed under a
spinlock and sometimes not. Move it out of the spinlock since we don't need
belt-and-suspenders for something that's just informational.
Reviewed-by: Suresh Jayaraman <sjayaraman@suse.de>
Reviewed-by: Pavel Shilovsky <piastryyy@gmail.com>
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
The cifsSesInfo pointer is only used to get at the server.
Reviewed-by: Suresh Jayaraman <sjayaraman@suse.de>
Reviewed-by: Pavel Shilovsky <piastryyy@gmail.com>
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
The TCP_Server_Info is refcounted and every SMB session holds a
reference to it. Thus, smb_ses_list is always going to be empty when
cifsd is coming down. This is dead code.
Reviewed-by: Suresh Jayaraman <sjayaraman@suse.de>
Reviewed-by: Pavel Shilovsky <piastryyy@gmail.com>
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
If CIFSSMBWrite2 returns -EAGAIN, then the error should be considered
temporary. CIFS should retry the write instead of setting an error on
the mapping and returning.
For WB_SYNC_ALL, just retry the write immediately. In the WB_SYNC_NONE
case, call redirty_page_for_writeback on all of the pages that didn't
get written out and then move on.
Also, fix up the handling of a short write with a successful return
code. MS-CIFS says that 0 bytes_written means ENOSPC or EFBIG. It
doesn't mention what a short, but non-zero write means, so for now
treat it as we would an -EAGAIN return.
Reviewed-by: Suresh Jayaraman <sjayaraman@suse.de>
Reviewed-by: Pavel Shilovsky <piastryyy@gmail.com>
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
When we get oplock break notification we should set the appropriate
value of OplockLevel field in oplock break acknowledge according to
the oplock level held by the client in this time. As we only can have
level II oplock or no oplock in the case of oplock break, we should be
aware only about clientCanCacheRead field in cifsInodeInfo structure.
Also fix bug connected with wrong interpretation of OplockLevel field
during oplock break notification processing.
Signed-off-by: Pavel Shilovsky <piastryyy@gmail.com>
Cc: <stable@kernel.org>
Signed-off-by: Steve French <sfrench@us.ibm.com>
* git://git.kernel.org/pub/scm/linux/kernel/git/sfrench/cifs-2.6:
cifs: add cruid= mount option
cifs: cFYI the entire error code in map_smb_to_linux_error
Unexport do_add_mount() and make ->d_automount() return the vfsmount to be
added rather than calling do_add_mount() itself. follow_automount() will then
do the addition.
This slightly complicates things as ->d_automount() normally wants to add the
new vfsmount to an expiration list and start an expiration timer. The problem
with that is that the vfsmount will be deleted if it has a refcount of 1 and
the timer will not repeat if the expiration list is empty.
To this end, we require the vfsmount to be returned from d_automount() with a
refcount of (at least) 2. One of these refs will be dropped unconditionally.
In addition, follow_automount() must get a 3rd ref around the call to
do_add_mount() lest it eat a ref and return an error, leaving the mount we
have open to being expired as we would otherwise have only 1 ref on it.
d_automount() should also add the the vfsmount to the expiration list (by
calling mnt_set_expiry()) and start the expiration timer before returning, if
this mechanism is to be used. The vfsmount will be unlinked from the
expiration list by follow_automount() if do_add_mount() fails.
This patch also fixes the call to do_add_mount() for AFS to propagate the mount
flags from the parent vfsmount.
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Make CIFS use the new d_automount() dentry operation rather than abusing
follow_link() on directories.
[NOTE: THIS IS UNTESTED!]
Signed-off-by: David Howells <dhowells@redhat.com>
Cc: Steve French <sfrench@samba.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Add a dentry op (d_manage) to permit a filesystem to hold a process and make it
sleep when it tries to transit away from one of that filesystem's directories
during a pathwalk. The operation is keyed off a new dentry flag
(DCACHE_MANAGE_TRANSIT).
The filesystem is allowed to be selective about which processes it holds and
which it permits to continue on or prohibits from transiting from each flagged
directory. This will allow autofs to hold up client processes whilst letting
its userspace daemon through to maintain the directory or the stuff behind it
or mounted upon it.
The ->d_manage() dentry operation:
int (*d_manage)(struct path *path, bool mounting_here);
takes a pointer to the directory about to be transited away from and a flag
indicating whether the transit is undertaken by do_add_mount() or
do_move_mount() skipping through a pile of filesystems mounted on a mountpoint.
It should return 0 if successful and to let the process continue on its way;
-EISDIR to prohibit the caller from skipping to overmounted filesystems or
automounting, and to use this directory; or some other error code to return to
the user.
->d_manage() is called with namespace_sem writelocked if mounting_here is true
and no other locks held, so it may sleep. However, if mounting_here is true,
it may not initiate or wait for a mount or unmount upon the parameter
directory, even if the act is actually performed by userspace.
Within fs/namei.c, follow_managed() is extended to check with d_manage() first
on each managed directory, before transiting away from it or attempting to
automount upon it.
follow_down() is renamed follow_down_one() and should only be used where the
filesystem deliberately intends to avoid management steps (e.g. autofs).
A new follow_down() is added that incorporates the loop done by all other
callers of follow_down() (do_add/move_mount(), autofs and NFSD; whilst AFS, NFS
and CIFS do use it, their use is removed by converting them to use
d_automount()). The new follow_down() calls d_manage() as appropriate. It
also takes an extra parameter to indicate if it is being called from mount code
(with namespace_sem writelocked) which it passes to d_manage(). follow_down()
ignores automount points so that it can be used to mount on them.
__follow_mount_rcu() is made to abort rcu-walk mode if it hits a directory with
DCACHE_MANAGE_TRANSIT set on the basis that we're probably going to have to
sleep. It would be possible to enter d_manage() in rcu-walk mode too, and have
that determine whether to abort or not itself. That would allow the autofs
daemon to continue on in rcu-walk mode.
Note that DCACHE_MANAGE_TRANSIT on a directory should be cleared when it isn't
required as every tranist from that directory will cause d_manage() to be
invoked. It can always be set again when necessary.
==========================
WHAT THIS MEANS FOR AUTOFS
==========================
Autofs currently uses the lookup() inode op and the d_revalidate() dentry op to
trigger the automounting of indirect mounts, and both of these can be called
with i_mutex held.
autofs knows that the i_mutex will be held by the caller in lookup(), and so
can drop it before invoking the daemon - but this isn't so for d_revalidate(),
since the lock is only held on _some_ of the code paths that call it. This
means that autofs can't risk dropping i_mutex from its d_revalidate() function
before it calls the daemon.
The bug could manifest itself as, for example, a process that's trying to
validate an automount dentry that gets made to wait because that dentry is
expired and needs cleaning up:
mkdir S ffffffff8014e05a 0 32580 24956
Call Trace:
[<ffffffff885371fd>] :autofs4:autofs4_wait+0x674/0x897
[<ffffffff80127f7d>] avc_has_perm+0x46/0x58
[<ffffffff8009fdcf>] autoremove_wake_function+0x0/0x2e
[<ffffffff88537be6>] :autofs4:autofs4_expire_wait+0x41/0x6b
[<ffffffff88535cfc>] :autofs4:autofs4_revalidate+0x91/0x149
[<ffffffff80036d96>] __lookup_hash+0xa0/0x12f
[<ffffffff80057a2f>] lookup_create+0x46/0x80
[<ffffffff800e6e31>] sys_mkdirat+0x56/0xe4
versus the automount daemon which wants to remove that dentry, but can't
because the normal process is holding the i_mutex lock:
automount D ffffffff8014e05a 0 32581 1 32561
Call Trace:
[<ffffffff80063c3f>] __mutex_lock_slowpath+0x60/0x9b
[<ffffffff8000ccf1>] do_path_lookup+0x2ca/0x2f1
[<ffffffff80063c89>] .text.lock.mutex+0xf/0x14
[<ffffffff800e6d55>] do_rmdir+0x77/0xde
[<ffffffff8005d229>] tracesys+0x71/0xe0
[<ffffffff8005d28d>] tracesys+0xd5/0xe0
which means that the system is deadlocked.
This patch allows autofs to hold up normal processes whilst the daemon goes
ahead and does things to the dentry tree behind the automouter point without
risking a deadlock as almost no locks are held in d_manage() and none in
d_automount().
Signed-off-by: David Howells <dhowells@redhat.com>
Was-Acked-by: Ian Kent <raven@themaw.net>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
In commit 3e4b3e1f we separated the "uid" mount option such that it
no longer determined the owner of the credential cache by default. When
we did this, we added a new option to cifs.upcall (--legacy-uid) to
try to make it so that it would behave the same was as it did before.
This ignored a rather important point -- the kernel has no way to know
what options are being passed to cifs.upcall, so it doesn't know what
uid it should use to determine whether to match an existing krb5 session.
The simplest solution is to simply add a new "cruid=" mount option that
only governs the uid owner of the credential cache for the mount.
Unfortunately, this means that the --legacy-uid option in cifs.upcall was
ill-considered and is now useless, but I don't see a better way to deal
with this.
A patch for the mount.cifs manpage will follow once this patch has been
accepted.
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
Reduce false inode collisions by using the CreationTime like an
i_generation field. This way, even if the server ends up reusing
a uniqueid after a delete/create cycle, we can avoid matching
the inode incorrectly.
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
We call CIFSSMBUnixSetPathInfo in these functions, but we have a
filehandle since an open was just done. Switch these functions to
use CIFSSMBUnixSetFileInfo instead.
In practice, these codepaths are only used if posix opens are broken.
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
...and while we're at it, reduce the number of calls into the seq_*
functions by prepending spaces to strings.
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
I see no real need to leave these sorts of options under an
EXPERIMENTAL ifdef. Since you need a mount option to turn this code
on, that only blows out the testing matrix.
local_leases has been under the EXPERIMENTAL tag for some time, but
it's only the mount option that's under this label. Move it out
from under this tag.
The NTLMSSP code is also under EXPERIMENTAL, but it needs a mount
option to turn it on, and in the future any distro will reasonably
want this enabled. Go ahead and move it out from under the
EXPERIMENTAL tag.
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Acked-by: Suresh Jayaraman <sjayaraman@suse.de>
Signed-off-by: Steve French <sfrench@us.ibm.com>
A number of places that deal with RFC1001/1002 negotiations have bare
"15" or "16" values. Replace them with RFC_1001_NAME_LEN and
RFC_1001_NAME_LEN_WITH_NULL.
The patch also cleans up some checkpatch warnings for code surrounding
the changes. This should apply cleanly on top of the patch to remove
Local_System_Name.
Reported-and-Reviwed-by: Shirish Pargaonkar <shirishpargaonkar@gmail.com>
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
The server->sequence_number is already protected by the srv_mutex. The
GlobalMid_lock is unneeded here.
Reviewed-by: Shirish Pargaonkar <shirishpargaonkar@gmail.com>
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
dcache_inode_lock can be replaced with per-inode locking. Use existing
inode->i_lock for this. This is slightly non-trivial because we sometimes
need to find the inode from the dentry, which requires d_inode to be
stabilised (either with refcount or d_lock).
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
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>
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>
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>
Add a new lock, dcache_inode_lock, to protect the inode's i_dentry list
from concurrent modification. d_alias is also protected by d_lock.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
Change d_hash so it may be called from lock-free RCU lookups. See similar
patch for d_compare for details.
For in-tree filesystems, this is just a mechanical change.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
Change d_compare so it may be called from lock-free RCU lookups. This
does put significant restrictions on what may be done from the callback,
however there don't seem to have been any problems with in-tree fses.
If some strange use case pops up that _really_ cannot cope with the
rcu-walk rules, we can just add new rcu-unaware callbacks, which would
cause name lookup to drop out of rcu-walk mode.
For in-tree filesystems, this is just a mechanical change.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
Use vfat's method for dealing with negative dentries to preserve case,
rather than overwrite dentry name in d_revalidate, which is a bit ugly
and also gets in the way of doing lock-free path walking.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
Make the code more general for use in posix and non-posix open.
Reviewed-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Pavel Shilovsky <piastryyy@gmail.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
Delete cifs_open_inode_helper and move non-posix open related things
to cifs_nt_open function.
Reviewed-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Pavel Shilovsky <piastryyy@gmail.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
If we have a share mounted by non-standard port and try to mount another share
on the same host with standard port, we connect to the first share again -
that's wrong. This patch fixes this bug.
Signed-off-by: Pavel Shilovsky <piastryyy@gmail.com>
Reviewed-by: Jeff Layton <jlayton@samba.org>
Signed-off-by: Steve French <sfrench@us.ibm.com>
Make connect logic more ip-protocol independent and move RFC1001 stuff into
a separate function. Also replace union addr in TCP_Server_Info structure
with sockaddr_storage.
Signed-off-by: Pavel Shilovsky <piastryyy@gmail.com>
Reviewed-and-Tested-by: Jeff Layton <jlayton@samba.org>
Signed-off-by: Steve French <sfrench@us.ibm.com>
Indicate to the server a capability of NTLM2 session security (NTLM2 Key)
during ntlmssp protocol exchange in one of the bits of the flags field.
If server supports this capability, send NTLM2 key even if signing is not
required on the server.
If the server requires signing, the session keys exchanged for NTLMv2
and NTLM2 session security in auth packet of the nlmssp exchange are same.
Send the same flags in authenticate message (type 3) that client sent in
negotiate message (type 1).
Remove function setup_ntlmssp_neg_req
Make sure ntlmssp negotiate and authenticate messages are zero'ed
before they are built.
Reported-and-Tested-by: Robbert Kouprie <robbert@exx.nl>
Signed-off-by: Shirish Pargaonkar <shirishpargaonkar@gmail.com>
Acked-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
Instead, use fatfs's method for dealing with negative dentries to
preserve case, rather than overwrite dentry name in d_revalidate, which
is a bit ugly and also gets in the way of doing lock-free path walking.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
Signed-off-by: Steve French <sfrench@us.ibm.com>
As the FIXME points out correctly, now filldir() itself returns -EOVERFLOW if
it not possible to represent the inode number supplied by the filesystem in
the field provided by userspace.
Signed-off-by: Suresh Jayaraman <sjayaraman@suse.de>
Reviewed-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
It's possible that cifs_mount will call cifs_build_path_to_root on a
newly instantiated cifs_sb. In that case, it's likely that the
master_tlink pointer has not yet been instantiated.
Fix this by having cifs_build_path_to_root take a cifsTconInfo pointer
as well, and have the caller pass that in.
Reported-and-Tested-by: Robbert Kouprie <robbert@exx.nl>
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
This function will return 0 if everything went ok. Commit 9d002df4
however added a block of code after the following check for
rc == -EREMOTE. With that change and when rc == 0, doing the
"goto mount_fail_check" here skips that code, leaving the tlink_tree
and master_tlink pointer unpopulated. That causes an oops later
in cifs_root_iget.
Reported-and-Tested-by: Robbert Kouprie <robbert@exx.nl>
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
...this string is zeroed out and nothing ever changes it.
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
Some of the code under CONFIG_CIFS_ACL is dependent upon code under
CONFIG_CIFS_EXPERIMENTAL, but the Kconfig options don't reflect that
dependency. Move more of the ACL code out from under
CONFIG_CIFS_EXPERIMENTAL and under CONFIG_CIFS_ACL.
Also move find_readable_file out from other any sort of Kconfig
option and make it a function normally compiled in.
Reported-and-Acked-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
Jeff Layton
Shirish Pargaonkar
Steve French
Pavel Shilovsky
Linus Torvalds
David Howells
Al Viro
Nick Piggin
Suresh Jayaraman
Jeff Layton