This further reduces contention with the transport_lock, and allows us
to convert to using a non-bh-safe spinlock, since the list is now never
accessed from a bh context.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

Simplify the code to avoid a full copy of the struct xdr_skb_reader.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

Ensure that we don't hog the workqueue thread by requeuing the job
every 64 loops.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

The backchannel request has no associated task, so it is going nowhere
until we call xprt_complete_bc_request().
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

Instead add a mechanism to ensure that the request doesn't disappear
from underneath us while copying from the socket. We do this by
preventing xprt_release() from freeing the XDR buffers until the
flag RPC_TASK_MSG_RECV has been cleared from the request.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>
Reviewed-by: NChuck Lever <chuck.lever@oracle.com>

If a request is on the commit list, but is locked, we will currently skip
it, which can lead to livelocking when the commit count doesn't reduce
to zero.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

Now that we no longer hold the inode->i_lock when manipulating the
commit lists, it is safe to call pnfs_put_lseg() again.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

Switch from using the inode->i_lock for this to avoid contention with
other metadata manipulation.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

Rather than forcing us to take the inode->i_lock just in order to bump
the number.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

The commit lists can get very large, so using the inode->i_lock can
end up affecting general metadata performance.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

Split out the 2 cases so that we can treat the locking differently.
The issue is that the locking in the pageswapcache cache is highly
linked to the commit list locking.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

Hide the locking from nfs_lock_and_join_requests() so that we can
separate out the requirements for swapcache pages.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

Fix up the test in nfs_page_group_covers_page(). The simplest implementation
is to check that we have a set of intersecting or contiguous subrequests
that connect page offset 0 to nfs_page_length(req->wb_page).
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

nfs_page_group_lock() is now always called with the 'nonblock'
parameter set to 'false'.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

At this point, we only expect ever to potentially see PG_REMOVE and
PG_TEARDOWN being set on the subrequests.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

Since nfs_page_group_destroy() does not take any locks on the requests
to be freed, we need to ensure that we don't inadvertently free the
request in nfs_destroy_unlinked_subrequests() while the last reference
is being released elsewhere.

Do this by:

1) Taking a reference to the request unless it is already being freed
2) Checking (under the page group lock) if PG_TEARDOWN is already set before
   freeing an unreferenced request in nfs_destroy_unlinked_subrequests()
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

When locking the entire group in order to remove subrequests,
the locks are always taken in order, and with the page group
lock being taken after the page head is locked. The intention
is that:

1) The lock on the group head guarantees that requests may not
   be removed from the group (although new entries could be appended
   if we're not holding the group lock).
2) It is safe to drop and retake the page group lock while iterating
   through the list, in particular when waiting for a subrequest lock.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

We should no longer need the inode->i_lock, now that we've
straightened out the request locking. The locking schema is now:

1) Lock page head request
2) Lock the page group
3) Lock the subrequests one by one

Note that there is a subtle race with nfs_inode_remove_request() due
to the fact that the latter does not lock the page head, when removing
it from the struct page. Only the last subrequest is locked, hence
we need to re-check that the PagePrivate(page) is still set after
we've locked all the subrequests.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

nfs_try_to_update_request() should be able to cope now.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

Simplify the code, and avoid some flushes to disk.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

Both nfs_destroy_unlinked_subrequests() and nfs_lock_and_join_requests()
manipulate the inode flags adjusting the NFS_I(inode)->nrequests.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

We don't want nfs_lock_and_join_requests() to start fiddling with
the request before the call to nfs_page_group_sync_on_bit().
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

Request offsets and sizes are not guaranteed to be stable unless you
are holding the request locked.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

All other callers of nfs_page_group_lock() appear to already hold the
page lock on the head page, so doing it in the opposite order here
is inefficient, although not deadlock prone since we roll back all
locks on contention.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

Yes, this is a situation that should never happen (hence the WARN_ON)
but we should still ensure that we free up the locks and references to
the faulty pages.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

This fixes a race with nfs_page_group_sync_on_bit() whereby the
call to wake_up_bit() in nfs_page_group_unlock() could occur after
the page header had been freed.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

Micro-optimisation to move the lockless check into the for(;;) loop.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

Add a lockless check for whether or not the page might be carrying
an existing writeback before we grab the inode->i_lock.
Reported-by: NChuck Lever <chuck.lever@oracle.com>
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

We don't expect the page header lock to ever be held across I/O, so
it should always be safe to wait for it, even if we're doing nonblocking
writebacks.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

If we're recovering a nfs4_state, then we should try to use that instead
of looking up a new stateid. Only do that if the inodes match, though.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

When doing open by filehandle we don't really want to lookup a new inode,
but rather update the one we've got. Add a helper which does this for us.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

Pull MIPS fixes from Ralf Baechle:
 "Another round of MIPS fixes:

   - compressed boot: Ignore a generated .c file

   - VDSO: Fix a register clobber list

   - DECstation: Fix an int-handler.S CPU_DADDI_WORKAROUNDS regression

   - Octeon: Fix recent cleanups that cleaned away a bit too much thus
     breaking the arch side of the EDAC and USB drivers.

   - uasm: Fix duplicate const in "const struct foo const bar[]" which
     GCC 7.1 no longer accepts.

   - Fix race on setting and getting cpu_online_mask

   - Fix preemption issue. To do so cleanly introduce macro to get the
     size of L3 cache line.

   - Revert include cleanup that sometimes results in build error

   - MicroMIPS uses bit 0 of the PC to indicate microMIPS mode. Make
     sure this bit is set for kernel entry as well.

   - Prevent configuring the kernel for both microMIPS and MT. There are
     no such CPUs currently and thus the combination is unsupported and
     results in build errors.

  This has been sitting in linux-next for a few days and has survived
  automated testing by Imagination's test farm. No known regressions
  pending except a number of issues that crept up due to lots of people
  switching to GCC 7.1"

* 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus:
  MIPS: Set ISA bit in entry-y for microMIPS kernels
  MIPS: Prevent building MT support for microMIPS kernels
  MIPS: PCI: Fix smp_processor_id() in preemptible
  MIPS: Introduce cpu_tcache_line_size
  MIPS: DEC: Fix an int-handler.S CPU_DADDI_WORKAROUNDS regression
  MIPS: VDSO: Fix clobber lists in fallback code paths
  Revert "MIPS: Don't unnecessarily include kmalloc.h into <asm/cache.h>."
  MIPS: OCTEON: Fix USB platform code breakage.
  MIPS: Octeon: Fix broken EDAC driver.
  MIPS: gitignore: ignore generated .c files
  MIPS: Fix race on setting and getting cpu_online_mask
  MIPS: mm: remove duplicate "const" qualifier on insn_table

Merge tag 'driver-core-4.13-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core

Pull driver core fixes from Greg KH:
 "Here are three firmware core fixes for 4.13-rc5.

  All three of these fix reported issues and have been floating around
  for a few weeks. They have been in linux-next with no reported
  problems"

* tag 'driver-core-4.13-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core:
  firmware: avoid invalid fallback aborts by using killable wait
  firmware: fix batched requests - send wake up on failure on direct lookups
  firmware: fix batched requests - wake all waiters

Pull char/misc fixes from Greg KH:
 "Here are two patches for 4.13-rc5.

  One is a fix for a reported thunderbolt issue, and the other a fix for
  an MEI driver issue. Both have been in linux-next with no reported
  issues"

* tag 'char-misc-4.13-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc:
  thunderbolt: Do not enumerate more ports from DROM than the controller has
  mei: exclude device from suspend direct complete optimization

Pull tty/serial fixes from Greg KH:
 "Here are two tty serial driver fixes for 4.13-rc5. One is a revert of
  a -rc1 patch that turned out to not be a good idea, and the other is a
  fix for the pl011 serial driver.

  Both have been in linux-next with no reported issues"

* tag 'tty-4.13-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/tty:
  Revert "serial: Delete dead code for CIR serial ports"
  tty: pl011: fix initialization order of QDF2400 E44