A migration event will replace the rpc_xprt used by an rpc_clnt. To
ensure this can be done safely, all references to cl_xprt must now use
a form of rcu_dereference().
Special care is taken with rpc_peeraddr2str(), which returns a pointer
to memory whose lifetime is the same as the rpc_xprt.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
[ cel: fix lockdep splats and layering violations ]
[ cel: forward ported to 3.4 ]
[ cel: remove rpc_max_reqs(), add rpc_net_ns() ]
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Currently, wait queue, used for polling of RPC pipe changes from user-space,
is a part of RPC pipe. But the pipe data itself can be released on NFS umount
prior to dentry-inode pair, connected to it (is case of this pair is open by
some process).
This is not a problem for almost all pipe users, because all PipeFS file
operations checks pipe reference prior to using it.
Except evenfd. This thing registers itself with "poll" file operation and thus
has a reference to pipe wait queue. This leads to oopses on destroying eventfd
after NFS umount (like rpc_idmapd do) since not pipe data left to the point
already.
The solution is to wait queue from pipe data to internal RPC inode data. This
looks more logical, because this wiat queue used only for user-space processes,
which already holds inode reference.
Note: upcalls have to get pipe->dentry prior to dereferecing wait queue to make
sure, that mount point won't disappear from underneath us.
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
There are 2 tightly bound objects: pipe data (created for kernel needs, has
reference to dentry, which depends on PipeFS mount/umount) and PipeFS
dentry/inode pair (created on mount for user-space needs). They both
independently may have or have not a valid reference to each other.
This means, that we have to make sure, that pipe->dentry reference is valid on
upcalls, and dentry->pipe reference is valid on downcalls. The latter check is
absent - my fault.
IOW, PipeFS dentry can be opened by some process (rpc.idmapd for example), but
it's pipe data can belong to NFS mount, which was unmounted already and thus
pipe data was destroyed.
To fix this, pipe reference have to be set to NULL on rpc_unlink() and checked
on PipeFS file operations instead of pipe->dentry check.
Note: PipeFS "poll" file operation will be updated in next patch, because it's
logic is more complicated.
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
This patch removes static rpc_mnt variable and its creation and destruction
routines, because they are not used anymore.
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
v2:
1) Added "nfs_idmap_init" and "nfs_idmap_quit" definitions for kernels built
without CONFIG_NFS_V4 option set.
This patch subscribes NFS clients to RPC pipefs notifications. Idmap notifier
is registering on NFS module load. This notifier callback is responsible for
creation/destruction of PipeFS idmap pipe dentry for NFS4 clients.
Since ipdmap pipe is created in rpc client pipefs directory, we have make sure,
that this directory has been created already. IOW RPC client notifier callback
has been called already. To achive this, PipeFS notifier priorities has been
introduced (RPC clients notifier priority is greater than NFS idmap one).
But this approach gives another problem: unlink for RPC client directory will
be called before NFS idmap pipe unlink on UMOUNT event and will fail, because
directory is not empty.
The solution, introduced in this patch, is to try to remove client directory
once again after idmap pipe was unlinked. This looks like ugly hack, so
probably it should be replaced in some more elegant way.
Note that no locking required in notifier callback because PipeFS superblock
pointer is passed as an argument from it's creation or destruction routine and
thus we can be sure about it's validity.
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
This patch looks late due to GSS AUTH patches sent already. But it fixes a flaw
in RPC PipeFS pipes handling.
I've added this patch in the series, because this series related to pipes. But
it should be a part of previous series named "SUNPRC: cleanup PipeFS for
network-namespace-aware users".
Pipe dentry can be created and destroyed many times during pipe life cycle.
This actually means, that we can't set pipe->ops to NULL in rpc_close_pipes()
and use this variable as a flag, indicating, that pipe's dentry is unlinking.
To follow this restriction, this patch replaces "pipe->ops = NULL" assignment
and checks for NULL with "pipe->dentry = NULL" assignment and checks for
NULL respectively.
This patch also removes check for non-NULL pipe->ops (or pipe->dentry) in
rpc_close_pipes() because it always non-NULL now.
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
This patch subscribes RPC clients to RPC pipefs notifications. RPC clients
notifier block is registering with pipefs initialization during SUNRPC module
init.
This notifier callback is responsible for RPC client PipeFS directory and GSS
pipes creation. For pipes creation and destruction two additional callbacks
were added to struct rpc_authops.
Note that no locking required in notifier callback because PipeFS superblock
pointer is passed as an argument from it's creation or destruction routine and
thus we can be sure about it's validity.
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
This patch is a final step towards to removing PipeFS inode references from
kernel code other than PipeFS itself. It makes all kernel SUNRPC PipeFS users
depends on pipe private data, which state depend on their specific operations,
etc.
This patch completes SUNRPC PipeFS preparations and allows to create pipe
private data and PipeFS dentries independently.
Next step will be making SUNPRC PipeFS dentries allocated by SUNRPC PipeFS
network namespace aware routines.
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
RPC pipe upcall doesn't requires only private pipe data. Thus RPC inode
references in this code can be removed.
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
This patch removes redundant RPC inode references from PipeFS. These places are
actually where pipes operations are performed.
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Generally, pipe data is used only for pipes, and thus allocating space for it
on every RPC inode allocation is redundant. This patch splits private SUNRPC
PipeFS pipe data and inode, makes pipe data allocated only for pipe inodes.
This patch is also is a next step towards to to removing PipeFS inode
references from kernel code other than PipeFS itself.
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Currenly, inode i_lock is used to provide concurrent access to SUNPRC PipeFS
pipes. It looks redundant, since now other use of inode is present in most of
these places and thus can be easely replaced, which will allow to remove most
of inode references from PipeFS code. This is a first step towards to removing
PipeFS inode references from kernel code other than PipeFS itself.
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
During per-net pipes creation and destruction we have to make sure, that pipefs
sb exists for the whole creation/destruction cycle. This is done by using
special mutex which controls pipefs sb reference on network namespace context.
Helper consists of two parts: first of them (rpc_get_dentry_net) searches for
dentry with specified name and returns with mutex taken on success. When pipe
creation or destructions is completed, caller should release this mutex by
rpc_put_dentry_net call.
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
We have modules (like, pNFS blocklayout module) which creates pipes on
rpc_pipefs. Thus we need per-net operations for them. To make it possible we
require appropriate super block. So we have to put sb link on network namespace
context. Note, that it's not strongly required to create pipes in per-net
operations. IOW, if pipefs wasn't mounted yet, that no sb link reference will
present on network namespace and in this case we need just need to pass through
pipe creation. Pipe dentry will be created during pipefs mount notification.
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
In all places, where pipefs dentries are created, only directory inode is
actually required to create new dentry. And all this directories has root
pipefs dentry as their parent. So we actually don't need this pipefs mount
point at all if some pipefs lookup method will be provided.
IOW, all we really need is just superblock and simple lookup method to find
root's child dentry with appropriate name. And this patch introduces this
method.
Note, that no locking implemented in rpc_d_lookup_sb(). So it can be used only
in case of assurance, that pipefs superblock still exist. IOW, we can use this
method only in pipefs mount-umount notification subscribers callbacks.
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
They will be used to notify subscribers about pipefs superblock creation and
destruction.
Subcribers will have to create their dentries on passed superblock on mount
event and destroy otherwise.
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
We want to be sure that network namespace is still alive while we have pipefs
mounted.
This will be required later, when RPC pipefs will be mounting only from
user-space context.
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
This is the initial step of RPC pipefs virtualization. It changes nothing to
current pipefs behaviour except that mount of pipefs in other than init_net
network namespace context will provide only root tree. No other dentries will
be visible.
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
This patch-set was created in context of clone of git branch:
git://git.linux-nfs.org/projects/trondmy/nfs-2.6.git.
v2:
1) Rebased of current repo state (i.e. all commits were pulled before apply)
I feel it is ready for inclusion if no objections will appear.
SUNRPC pipefs non-exclusive pipe creation code looks obsolete. IOW, as I see
it, all pipes are creating with unique full path and only once.
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Seeing that just about every destructor got that INIT_LIST_HEAD() copied into
it, there is no point whatsoever keeping this INIT_LIST_HEAD in inode_init_once();
the cost of taking it into inode_init_always() will be negligible for pipes
and sockets and negative for everything else. Not to mention the removal of
boilerplate code from ->destroy_inode() instances...
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
* 'nfs-for-3.2' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (26 commits)
Check validity of cl_rpcclient in nfs_server_list_show
NFS: Get rid of the nfs_rdata_mempool
NFS: Don't rely on PageError in nfs_readpage_release_partial
NFS: Get rid of unnecessary calls to ClearPageError() in read code
NFS: Get rid of nfs_restart_rpc()
NFS: Get rid of the unused nfs_write_data->flags field
NFS: Get rid of the unused nfs_read_data->flags field
NFSv4: Translate NFS4ERR_BADNAME into ENOENT when applied to a lookup
NFS: Remove the unused "lookupfh()" version of nfs4_proc_lookup()
NFS: Use the inode->i_version to cache NFSv4 change attribute information
SUNRPC: Remove unnecessary export of rpc_sockaddr2uaddr
SUNRPC: Fix rpc_sockaddr2uaddr
nfs/super.c: local functions should be static
pnfsblock: fix writeback deadlock
pnfsblock: fix NULL pointer dereference
pnfs: recoalesce when ld read pagelist fails
pnfs: recoalesce when ld write pagelist fails
pnfs: make _set_lo_fail generic
pnfsblock: add missing rpc_put_mount and path_put
SUNRPC/NFS: make rpc pipe upcall generic
...
The same function is used by idmap, gss and blocklayout code. Make it
generic.
Signed-off-by: Peng Tao <peng_tao@emc.com>
Signed-off-by: Jim Rees <rees@umich.edu>
Cc: stable@kernel.org [3.0]
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
sunrpc implements the rpc_pipefs filesystem type.
Add the alias to have the module requested automatically by the kernel
when the filesystem is mounted.
Signed-off-by: Michal Schmidt <mschmidt@redhat.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Make the case labels the same indent as the switch.
git diff -w shows 80 column line reflowing.
Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
* 'nfs-for-2.6.38' of git://git.linux-nfs.org/projects/trondmy/nfs-2.6: (89 commits)
NFS fix the setting of exchange id flag
NFS: Don't use vm_map_ram() in readdir
NFSv4: Ensure continued open and lockowner name uniqueness
NFS: Move cl_delegations to the nfs_server struct
NFS: Introduce nfs_detach_delegations()
NFS: Move cl_state_owners and related fields to the nfs_server struct
NFS: Allow walking nfs_client.cl_superblocks list outside client.c
pnfs: layout roc code
pnfs: update nfs4_callback_recallany to handle layouts
pnfs: add CB_LAYOUTRECALL handling
pnfs: CB_LAYOUTRECALL xdr code
pnfs: change lo refcounting to atomic_t
pnfs: check that partial LAYOUTGET return is ignored
pnfs: add layout to client list before sending rpc
pnfs: serialize LAYOUTGET(openstateid)
pnfs: layoutget rpc code cleanup
pnfs: change how lsegs are removed from layout list
pnfs: change layout state seqlock to a spinlock
pnfs: add prefix to struct pnfs_layout_hdr fields
pnfs: add prefix to struct pnfs_layout_segment fields
...
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>
Change d_delete from a dentry deletion notification to a dentry caching
advise, more like ->drop_inode. Require it to be constant and idempotent,
and not take d_lock. This is how all existing filesystems use the callback
anyway.
This makes fine grained dentry locking of dput and dentry lru scanning
much simpler.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
Instead of always assigning an increasing inode number in new_inode
move the call to assign it into those callers that actually need it.
For now callers that need it is estimated conservatively, that is
the call is added to all filesystems that do not assign an i_ino
by themselves. For a few more filesystems we can avoid assigning
any inode number given that they aren't user visible, and for others
it could be done lazily when an inode number is actually needed,
but that's left for later patches.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
* 'config' of git://git.kernel.org/pub/scm/linux/kernel/git/arnd/bkl:
BKL: introduce CONFIG_BKL.
dabusb: remove the BKL
sunrpc: remove the big kernel lock
init/main.c: remove BKL notations
blktrace: remove the big kernel lock
rtmutex-tester: make it build without BKL
dvb-core: kill the big kernel lock
dvb/bt8xx: kill the big kernel lock
tlclk: remove big kernel lock
fix rawctl compat ioctls breakage on amd64 and itanic
uml: kill big kernel lock
parisc: remove big kernel lock
cris: autoconvert trivial BKL users
alpha: kill big kernel lock
isapnp: BKL removal
s390/block: kill the big kernel lock
hpet: kill BKL, add compat_ioctl
The sunrpc cache_ioctl function does not need the big kernel lock
because it uses its own queue_lock already.
rpc_pipe_ioctl apparently should be using i_lock like the other
operations on the pipe file descriptor do.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
There is a race between rpc_info_open and rpc_release_client()
in that nothing stops a process from opening the file after
the clnt->cl_kref goes to zero.
Fix this by using atomic_inc_unless_zero()...
Reported-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: stable@kernel.org
If rpc_queue_upcall() adds a new upcall to the rpci->pipe list just
after rpc_pipe_release calls rpc_purge_list(), but before it calls
gss_pipe_release (as rpci->ops->release_pipe(inode)), then the latter
will free a message without deleting it from the rpci->pipe list.
We will be left with a freed object on the rpc->pipe list. Most
frequent symptoms are kernel crashes in rpc.gssd system calls on the
pipe in question.
Reported-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: stable@kernel.org
Pushdown the bkl to rpc_pipe_ioctl.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: "J. Bruce Fields" <bfields@fieldses.org>
Cc: Neil Brown <neilb@suse.de>
Cc: Nfs <linux-nfs@vger.kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: John Kacur <jkacur@redhat.com>
Cc: Arnd Bergmann <arnd@arndb.de>
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6: (52 commits)
init: Open /dev/console from rootfs
mqueue: fix typo "failues" -> "failures"
mqueue: only set error codes if they are really necessary
mqueue: simplify do_open() error handling
mqueue: apply mathematics distributivity on mq_bytes calculation
mqueue: remove unneeded info->messages initialization
mqueue: fix mq_open() file descriptor leak on user-space processes
fix race in d_splice_alias()
set S_DEAD on unlink() and non-directory rename() victims
vfs: add NOFOLLOW flag to umount(2)
get rid of ->mnt_parent in tomoyo/realpath
hppfs can use existing proc_mnt, no need for do_kern_mount() in there
Mirror MS_KERNMOUNT in ->mnt_flags
get rid of useless vfsmount_lock use in put_mnt_ns()
Take vfsmount_lock to fs/internal.h
get rid of insanity with namespace roots in tomoyo
take check for new events in namespace (guts of mounts_poll()) to namespace.c
Don't mess with generic_permission() under ->d_lock in hpfs
sanitize const/signedness for udf
nilfs: sanitize const/signedness in dealing with ->d_name.name
...
Fix up fairly trivial (famous last words...) conflicts in
drivers/infiniband/core/uverbs_main.c and security/tomoyo/realpath.c
The function name must be followed by a space, hypen, space, and a
short description.
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
The NFSv4 and NFSv4.1 protocols both allow for the redirection of a client
from one server to another in order to support filesystem migration and
replication. For full protocol support, we need to add the ability to
convert a DNS host name into an IP address that we can feed to the RPC
client.
We'll reuse the sunrpc cache, now that it has been converted to work with
rpc_pipefs.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
In order to allow rpc_pipefs to create directories with different types of
subtrees, it is useful to allow the caller to customise the subtree filling
process.
In order to do so, we separate out the parts which are specific to making
an RPC client directory, and put them in a separate helper, then we convert
the process of filling the directory contents into a callback.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Trond Myklebust