Replace all GFP_KERNEL and ls_allocation with GFP_NOFS.
ls_allocation would be GFP_KERNEL for userland lockspaces
and GFP_NOFS for file system lockspaces.

It was discovered that any lockspaces on the system can
affect all others by triggering memory reclaim in the
file system which could in turn call back into the dlm
to acquire locks, deadlocking dlm threads that were
shared by all lockspaces, like dlm_recv.
Signed-off-by: NDavid Teigland <teigland@redhat.com>

The code to set up sctp sockets was not using the sockfd_lookup()
and sockfd_put() routines to translate an fd to a socket.  The
direct fget and fput calls were resulting in error messages from
alloc_fd().

Also clean up two log messages and remove a third, related to
setting up sctp associations.
Signed-off-by: NDavid Teigland <teigland@redhat.com>

The recently added dlm_lowcomms_connect_node() from
391fbdc5 does not work
when using SCTP instead of TCP.  The sctp connection code
has nothing to do without data to send.  Check for no data
in the sctp connection code and do nothing instead of
triggering a BUG.  Also have connect_node() do nothing
when the protocol is sctp.
Signed-off-by: NDavid Teigland <teigland@redhat.com>

Make all seq_operations structs const, to help mitigate against
revectoring user-triggerable function pointers.

This is derived from the grsecurity patch, although generated from scratch
because it's simpler than extracting the changes from there.
Signed-off-by: NJames Morris <jmorris@namei.org>
Acked-by: NSerge Hallyn <serue@us.ibm.com>
Acked-by: NCasey Schaufler <casey@schaufler-ca.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Using kernel_sendpage() is cleaner and safer than following
sock->ops ourselves.
Signed-off-by: NPaolo Bonzini <bonzini@gnu.org>
Signed-off-by: NDavid Teigland <teigland@redhat.com>

Closing a connection to a node can create problems if there are
outstanding messages for that node.  The problems include dlm_send
spinning attempting to reconnect, or BUG from tcp_connect_to_sock()
attempting to use a partially closed connection.

To cleanly close a connection, we now first attempt to send any pending
messages, cancel any remaining workqueue work, and flag the connection
as closed to avoid reconnect attempts.
Signed-off-by: NLars Marowsky-Bree <lmb@suse.de>
Signed-off-by: NChristine Caulfield <ccaulfie@redhat.com>
Signed-off-by: NDavid Teigland <teigland@redhat.com>

The last correction to the tcp_connect_to_sock error exit path,
commit a89d63a1, can free an already
freed socket, due to collision with a previous (incomplete) attempt
to fix the same issue, commit 311f6fc7.
Signed-off-by: NCasey Dahlin <cdahlin@redhat.com>
Signed-off-by: NDavid Teigland <teigland@redhat.com>

In the tcp_connect_to_sock() error exit path, the socket
allocated at the top of the function was not being freed.
Signed-off-by: NCasey Dahlin <cdahlin@redhat.com>
Signed-off-by: NDavid Teigland <teigland@redhat.com>

This makes generic netlink network namespace aware. No
generic netlink families except for the controller family
are made namespace aware, they need to be checked one by
one and then set the family->netnsok member to true.

A new function genlmsg_multicast_netns() is introduced to
allow sending a multicast message in a given namespace,
for example when it applies to an object that lives in
that namespace, a new function genlmsg_multicast_allns()
to send a message to all network namespaces (for objects
that do not have an associated netns).

The function genlmsg_multicast() is changed to multicast
the message in just init_net, which is currently correct
for all generic netlink families since they only work in
init_net right now. Some will later want to work in all
net namespaces because they do not care about the netns
at all -- those will have to be converted to use one of
the new functions genlmsg_multicast_allns() or
genlmsg_multicast_netns() whenever they are made netns
aware in some way.

After this patch families can easily decide whether or
not they should be available in all net namespaces. Many
genl families us it for objects not related to networking
and should therefore be available in all namespaces, but
that will have to be done on a per family basis.

Note that this doesn't touch on the checkpoint/restart
problem where network namespaces could be used, genl
families and multicast groups are numbered globally and
I see no easy way of changing that, especially since it
must be possible to multicast to all network namespaces
for those families that do not care about netns.
Signed-off-by: NJohannes Berg <johannes@sipsolutions.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Fix a regression from the original addition of nfs lock support
586759f0.  When a synchronous
(non-nfs) plock completes, the waiting thread will wake up and
free the op struct.  This races with the user thread in
dev_write() which goes on to read the op's callback field to
check if the lock is async and needs a callback.  This check
can happen on the freed op.  The fix is to note the callback
value before the op can be freed.
Signed-off-by: NDavid Teigland <teigland@redhat.com>

  CC [M]  fs/dlm/lock.o
fs/dlm/lock.c: In function ‘find_rsb’:
fs/dlm/lock.c:438: warning: ‘r’ may be used uninitialized in this function

Since r is used on the error path to set r_ret, set it to NULL.
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>
Signed-off-by: NDavid Teigland <teigland@redhat.com>

Change some GFP_KERNEL allocations to use either GFP_NOFS or
ls_allocation (when available) which the fs sets to GFP_NOFS.
The point is to prevent allocations from going back into the
cluster fs in places where that might lead to deadlock.
Signed-off-by: NDavid Teigland <teigland@redhat.com>

Make network connections to other nodes earlier, in the context of
dlm_recoverd.  This avoids connecting to nodes from dlm_send where we
try to avoid allocations which could possibly deadlock if memory reclaim
goes into the cluster fs which may try to do a dlm operation.
Signed-off-by: NChristine Caulfield <ccaulfie@redhat.com>
Signed-off-by: NDavid Teigland <teigland@redhat.com>

When a lockspace was joined multiple times, the global dlm
use count was incremented when it should not have been.  This
caused the global dlm threads to not be stopped when all
lockspaces were eventually be removed.
Signed-off-by: NDavid Teigland <teigland@redhat.com>

| fs/gfs2/lock_dlm.c:207: warning: passing argument 1 of 'dlm_new_lockspace' discards qualifiers from pointer target type
Signed-off-by: NGeert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: NDavid Teigland <teigland@redhat.com>

Using offsetof() to calculate name length does not work because
it does not produce consistent results with with structure packing.
This caused memcpy to corrupt memory by copying 4 extra bytes off
the end of the buffer on 64 bit kernels with 32 bit userspace
(the only case where this 32/64 compat code is used).

The fix is to calculate name length directly from the start instead
of trying to derive it later using count and offsetof.
Signed-off-by: NDavid Teigland <teigland@redhat.com>

Return immediately from dlm_unlock(CANCEL) if the lock is
granted and not being converted; there's nothing to cancel.
Signed-off-by: NDavid Teigland <teigland@redhat.com>

When a conversion completes successfully and finds that a cancel
of the convert is still in progress (which is now a moot point),
preemptively clear the state associated with outstanding cancel.
That state could cause a subsequent conversion to be ignored.

Also, improve the consistency and content of error and debug
messages in this area.
Signed-off-by: NDavid Teigland <teigland@redhat.com>

Integer nodeids can be too large for the idr code; use a hash
table instead.
Signed-off-by: NChristine Caulfield <ccaulfie@redhat.com>
Signed-off-by: NDavid Teigland <teigland@redhat.com>

Signed-off-by: NJoe Perches <joe@perches.com>
Signed-off-by: NDavid Teigland <teigland@redhat.com>

Signed-off-by: NJoe Perches <joe@perches.com>
Signed-off-by: NDavid Teigland <teigland@redhat.com>

The ls_dirtbl[].lock was an rwlock, but since it was only used in write
mode a spinlock will suffice.
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>
Signed-off-by: NDavid Teigland <teigland@redhat.com>

dlm_posix_get fills out the relevant fields in the file_lock before
returning when there is a lock conflict, but doesn't clean out any of
the other fields in the file_lock.

When nfsd does a NFSv4 lockt call, it sets the fl_lmops to
nfsd_posix_mng_ops before calling the lower fs. When the lock comes back
after testing a lock on GFS2, it still has that field set. This confuses
nfsd into thinking that the file_lock is a nfsd4 lock.

Fix this by making DLM reinitialize the file_lock before copying the
fields from the conflicting lock.
Signed-off-by: NJeff Layton <jlayton@redhat.com>
Signed-off-by: NDavid Teigland <teigland@redhat.com>

We should use the original copy of the file_lock, fl, instead
of the copy, flc in the lockd notify callback.  The range in flc has
been modified by posix_lock_file(), so it will not match a copy of the
lock in lockd.
Signed-off-by: NDavid Teigland <teigland@redhat.com>

The rwlock is almost always used in write mode, so there's no reason
to not use a spinlock instead.
Signed-off-by: NDavid Teigland <teigland@redhat.com>

The old code would leak iterators and leave reference counts on
rsbs because it was ignoring the "stop" seq callback.  The code
followed an example that used the seq operations differently.
This new code is based on actually understanding how the seq
operations work.  It also improves things by saving the hash bucket
in the position to avoid cycling through completed buckets in start.
Siged-off-by: NDavd Teigland <teigland@redhat.com>

fs/dlm/ast.c: In function 'dlm_astd':
fs/dlm/ast.c:64: warning: 'bastmode' may be used uninitialized in this function

Cleans code up.
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NDavid Teigland <teigland@redhat.com>

The new debugfs entry dumps all rsb and lkb structures, and includes
a lot more information than has been available before.  This includes
the new timestamps added by a previous patch for debugging callback
issues.
Signed-off-by: NDavid Teigland <teigland@redhat.com>

Record the time the latest blocking callback was queued for
a lock.  This will be used for debugging in combination with
lock queue timestamp changes in the previous patch.
Signed-off-by: NDavid Teigland <teigland@redhat.com>

Use ktime instead of jiffies for timestamping lkb's.  Also stamp the
time on every lkb whenever it's added to a resource queue, instead of
just stamping locks subject to timeouts.  This will allow us to use
timestamps more widely for debugging all locks.
Signed-off-by: NDavid Teigland <teigland@redhat.com>

The lkb bastmode value is set in the context of processing the
lock, and read by the dlm_astd thread.  Because it's accessed
in these two separate contexts, the writing/reading ought to
be done under a lock.  This is simple to do by setting it and
reading it when the lkb is added to and removed from dlm_astd's
callback list which is properly locked.
Signed-off-by: NDavid Teigland <teigland@redhat.com>

Just before delivering a blocking callback (bast), the dlm_astd
thread checks again that the granted mode of the lkb actually
blocks the mode requested by the bast.  The idea behind this was
originally that the granted mode may have changed since the bast
was queued, making the callback now unnecessary.  Reasons for
removing this extra check are:
- dlm_astd doesn't lock the rsb before reading the lkb grmode, so
  it's not technically safe (this removes the long standing FIXME)
- after running some tests, it doesn't appear the check ever actually
  eliminates a bast
- delivering an unnecessary blocking callback isn't a bad thing and
  can happen anyway
Signed-off-by: NDavid Teigland <teigland@redhat.com>

This is a one-liner to use cond_resched() rather than schedule()
in the ast delivery loop. It should not be necessary to schedule
every time, so this will save some cpu time while continuing to
allow scheduling when required.
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>
Signed-off-by: NDavid Teigland <teigland@redhat.com>

The pages used in lowcomms are not highmem, so kmap is not necessary.

Cc: Christine Caulfield <ccaulfie@redhat.com>
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>
Signed-off-by: NDavid Teigland <teigland@redhat.com>

fs/dlm/dir.c:419:14: warning: incorrect type in assignment (different base types)
fs/dlm/dir.c:419:14:    expected unsigned short [unsigned] [addressable] [assigned] [usertype] be_namelen
fs/dlm/dir.c:419:14:    got restricted __be16 [usertype] <noident>
Signed-off-by: NHarvey Harrison <harvey.harrison@gmail.com>
Signed-off-by: NDavid Teigland <teigland@redhat.com>

Use ls_allocation for memory allocations, which a cluster fs sets to
GFP_NOFS.  Use GFP_NOFS for allocations when no lockspace struct is
available.  Taking dlm locks needs to avoid calling back into the
cluster fs because write-out can require taking dlm locks.

Cc: Christine Caulfield <ccaulfie@redhat.com>
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>
Signed-off-by: NDavid Teigland <teigland@redhat.com>

this warning:

  fs/dlm/netlink.c: In function ‘dlm_timeout_warn’:
  fs/dlm/netlink.c:131: warning: ‘send_skb’ may be used uninitialized in this function

triggers because GCC does not recognize the (correct) error flow
between prepare_data() and send_skb.

Annotate it.
Signed-off-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Fixes a regression from commit 0f8e0d9a,
"dlm: allow multiple lockspace creates".

An extraneous 'else' slipped into a code fragment being moved from
release_lockspace() to dlm_release_lockspace().  The result of the
unwanted 'else' is that dlm threads and structures are not stopped
and cleaned up when the final dlm lockspace is removed.  Trying to
create a new lockspace again afterward will fail with
"kmem_cache_create: duplicate cache dlm_conn" because the cache
was not previously destroyed.
Signed-off-by: NDavid Teigland <teigland@redhat.com>

sparc32:

fs/dlm/config.c:397: error: expected identifier or '(' before '{' token
fs/dlm/config.c: In function 'drop_node':
fs/dlm/config.c:589: warning: initialization from incompatible pointer type
fs/dlm/config.c:589: warning: initialization from incompatible pointer type
fs/dlm/config.c: In function 'release_node':
fs/dlm/config.c:601: warning: initialization from incompatible pointer type
fs/dlm/config.c:601: warning: initialization from incompatible pointer type
fs/dlm/config.c: In function 'show_node':
fs/dlm/config.c:717: warning: initialization from incompatible pointer type
fs/dlm/config.c:717: warning: initialization from incompatible pointer type
fs/dlm/config.c: In function 'store_node':
fs/dlm/config.c:726: warning: initialization from incompatible pointer type
fs/dlm/config.c:726: warning: initialization from incompatible pointer type

Cc: Christine Caulfield <ccaulfie@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NDavid Teigland <teigland@redhat.com>

BLK from recent pushdown is not needed.
Signed-off-by: NDavid Teigland <teigland@redhat.com>