Pull second wave of NFS client updates from Trond Myklebust:

 - Patches from Bryan to allow splitting of the NFSv2/v3/v4 code into
   separate modules.

 - Fix Oopses in the NFSv4 idmapper

 - Fix a deadlock whereby rpciod tries to allocate a new socket and ends
   up recursing into the NFS code due to memory reclaim.

 - Increase the number of permitted callback connections.

* tag 'nfs-for-3.6-2' of git://git.linux-nfs.org/projects/trondmy/linux-nfs:
  nfs: explicitly reject LOCK_MAND flock() requests
  nfs: increase number of permitted callback connections.
  SUNRPC: return negative value in case rpcbind client creation error
  NFS: Convert v4 into a module
  NFS: Convert v3 into a module
  NFS: Convert v2 into a module
  NFS: Keep module parameters in the generic NFS client
  NFS: Split out remaining NFS v4 inode functions
  NFS: Pass super operations and xattr handlers in the nfs_subversion
  NFS: Only initialize the ACL client in the v3 case
  NFS: Create a try_mount rpc op
  NFS: Remove the NFS v4 xdev mount function
  NFS: Add version registering framework
  NFS: Fix a number of bugs in the idmapper
  nfs: skip commit in releasepage if we're freeing memory for fs-related reasons
  sunrpc: clarify comments on rpc_make_runnable
  pnfsblock: bail out partial page IO

Pull networking update from David S. Miller:
 "I think Eric Dumazet and I have dealt with all of the known routing
  cache removal fallout.  Some other minor fixes all around.

  1) Fix RCU of cached routes, particular of output routes which require
     liberation via call_rcu() instead of call_rcu_bh().  From Eric
     Dumazet.

  2) Make sure we purge net device references in cached routes properly.

  3) TG3 driver bug fixes from Michael Chan.

  4) Fix reported 'expires' value in ipv6 routes, from Li Wei.

  5) TUN driver ioctl leaks kernel bytes to userspace, from Mathias
     Krause."

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (22 commits)
  ipv4: Properly purge netdev references on uncached routes.
  ipv4: Cache routes in nexthop exception entries.
  ipv4: percpu nh_rth_output cache
  ipv4: Restore old dst_free() behavior.
  bridge: make port attributes const
  ipv4: remove rt_cache_rebuild_count
  net: ipv4: fix RCU races on dst refcounts
  net: TCP early demux cleanup
  tun: Fix formatting.
  net/tun: fix ioctl() based info leaks
  tg3: Update version to 3.124
  tg3: Fix race condition in tg3_get_stats64()
  tg3: Add New 5719 Read DMA workaround
  tg3: Fix Read DMA workaround for 5719 A0.
  tg3: Request APE_LOCK_PHY before PHY access
  ipv6: fix incorrect route 'expires' value passed to userspace
  mISDN: Bugfix only few bytes are transfered on a connection
  seeq: use PTR_RET at init_module of driver
  bnx2x: remove cast around the kmalloc in bnx2x_prev_mark_path
  ipv4: clean up put_child
  ...

Pull battery updates from Anton Vorontsov:
 "The tag contains just a few battery-related changes for v3.6.  It's is
  all pretty straightforward, except one thing.

  One of our patches added thermal support for power supply class, but
  thermal/ subsystem changed under our feet.  We (well, Stephen, that
  is) caught the issue and it was decided[1] that I'd just delay the
  battery pull request, and then will fix it up by merging upstream back
  into battery tree at the specific commit.

  That's not all though: another[2] small fixup for thermal subsystem
  was needed to get rid of a warning in power supply subsystem (the
  warning was not drivers/power's "fault", the thermal registration
  function just needed a proper const annotation, which is also done by
  a small commit on top of the merge.

  So, to sum this up:
   - The 'master' branch of the battery tree was in the -next tree for
     weeks, was never rebased, altered etc.  It should be all OK;
   - Although, for-v3.6 tag contains the 'master' branch + merge + the
     warning fix.

  [1] http://lkml.org/lkml/2012/6/19/23
  [2] http://lkml.org/lkml/2012/6/18/28"

* tag 'for-v3.6' of git://git.infradead.org/battery-2.6: (23 commits)
  thermal: Constify 'type' argument for the registration routine
  olpc-battery: update CHARGE_FULL_DESIGN property for BYD LiFe batteries
  olpc-battery: Add VOLTAGE_MAX_DESIGN property
  charger-manager: Fix build break related to EXTCON
  lp8727_charger: Move header file into platform_data directory
  power_supply: Add min/max alert properties for CAPACITY, TEMP, TEMP_AMBIENT
  bq27x00_battery: Add support for BQ27425 chip
  charger-manager: Set current limit of regulator for over current protection
  charger-manager: Use EXTCON Subsystem to detect charger cables for charging
  test_power: Add VOLTAGE_NOW and BATTERY_TEMP properties
  test_power: Add support for USB AC source
  gpio-charger: Use cansleep version of gpio_set_value
  bq27x00_battery: Add support for power average and health properties
  sbs-battery: Don't trigger false supply_changed event
  twl4030_charger: Allow charger to control the regulator that feeds it
  twl4030_charger: Add backup-battery charging
  twl4030_charger: Fix some typos
  max17042_battery: Support CHARGE_COUNTER power supply attribute
  smb347-charger: Add constant charge and current properties
  power_supply: Add constant charge_current and charge_voltage properties
  ...

Pull perf updates from Ingo Molnar:
 "The biggest changes are Intel Nehalem-EX PMU uncore support, uprobes
  updates/cleanups/fixes from Oleg and diverse tooling updates (mostly
  fixes) now that Arnaldo is back from vacation."

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (40 commits)
  uprobes: __replace_page() needs munlock_vma_page()
  uprobes: Rename vma_address() and make it return "unsigned long"
  uprobes: Fix register_for_each_vma()->vma_address() check
  uprobes: Introduce vaddr_to_offset(vma, vaddr)
  uprobes: Teach build_probe_list() to consider the range
  uprobes: Remove insert_vm_struct()->uprobe_mmap()
  uprobes: Remove copy_vma()->uprobe_mmap()
  uprobes: Fix overflow in vma_address()/find_active_uprobe()
  uprobes: Suppress uprobe_munmap() from mmput()
  uprobes: Uprobe_mmap/munmap needs list_for_each_entry_safe()
  uprobes: Clean up and document write_opcode()->lock_page(old_page)
  uprobes: Kill write_opcode()->lock_page(new_page)
  uprobes: __replace_page() should not use page_address_in_vma()
  uprobes: Don't recheck vma/f_mapping in write_opcode()
  perf/x86: Fix missing struct before structure name
  perf/x86: Fix format definition of SNB-EP uncore QPI box
  perf/x86: Make bitfield unsigned
  perf/x86: Fix LLC-* and node-* events on Intel SandyBridge
  perf/x86: Add Intel Nehalem-EX uncore support
  perf/x86: Fix typo in format definition of uncore PCU filter
  ...

Pull powerpc updates from Benjamin Herrenschmidt:
 "Kumar sent me a handful of Freescale related fixes and I added another
  regression fix to the pile.

  PS.  I -will- eventually learn about that signed tag business :-)"

* 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc:
  powerpc/kvm/book3s_32: Fix MTMSR_EERI macro
  powerpc/85xx: p1022ds: fix DIU/LBC switching with NAND enabled
  powerpc/85xx: p1022ds: disable the NAND flash node if video is enabled
  powerpc/85xx: Fix sram_offset parameter type
  powerpc/85xx: P3041DS - change espi input-clock from 40MHz to 35MHz
  powerpc/85xx: Fix pci base address error for p2020rdb-pc in dts

Pull s390 updates from Martin Schwidefsky:
 "This it the second batch of s390 patches for the 3.6 merge window.
  Included is enablement for two common code changes, killable page
  faults and sorted exception tables.  And the regular set of cleanup
  and bug fix patches."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux:
  s390: make use of user_mode() macro where possible
  s390/mm: rename user_mode variable to addressing_mode
  s390/mm: fix fault handling for page table walk case
  s390/mm: make page faults killable
  s390: update defconfig
  s390/mm: downgrade page table after fork of a 31 bit process
  s390/ipl: Use diagnose 8 command separation
  s390/linker script: use RO_DATA_SECTION
  s390/exceptions: sort exception table at build time
  s390/debug: remove module_exit function / move EXPORT_SYMBOLs

When a device is unregistered, we have to purge all of the
references to it that may exist in the entire system.

If a route is uncached, we currently have no way of accomplishing
this.

So create a global list that is scanned when a network device goes
down.  This mirrors the logic in net/core/dst.c's dst_ifdown().
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Pull nfsd changes from J. Bruce Fields:
 "This has been an unusually quiet cycle--mostly bugfixes and cleanup.
  The one large piece is Stanislav's work to containerize the server's
  grace period--but that in itself is just one more step in a
  not-yet-complete project to allow fully containerized nfs service.

  There are a number of outstanding delegation, container, v4 state, and
  gss patches that aren't quite ready yet; 3.7 may be wilder."

* 'nfsd-next' of git://linux-nfs.org/~bfields/linux: (35 commits)
  NFSd: make boot_time variable per network namespace
  NFSd: make grace end flag per network namespace
  Lockd: move grace period management from lockd() to per-net functions
  LockD: pass actual network namespace to grace period management functions
  LockD: manage grace list per network namespace
  SUNRPC: service request network namespace helper introduced
  NFSd: make nfsd4_manager allocated per network namespace context.
  LockD: make lockd manager allocated per network namespace
  LockD: manage grace period per network namespace
  Lockd: add more debug to host shutdown functions
  Lockd: host complaining function introduced
  LockD: manage used host count per networks namespace
  LockD: manage garbage collection timeout per networks namespace
  LockD: make garbage collector network namespace aware.
  LockD: mark host per network namespace on garbage collect
  nfsd4: fix missing fault_inject.h include
  locks: move lease-specific code out of locks_delete_lock
  locks: prevent side-effects of locks_release_private before file_lock is initialized
  NFSd: set nfsd_serv to NULL after service destruction
  NFSd: introduce nfsd_destroy() helper
  ...

Input path is mostly run under RCU and doesnt touch dst refcnt

But output path on forwarding or UDP workloads hits
badly dst refcount, and we have lot of false sharing, for example
in ipv4_mtu() when reading rt->rt_pmtu

Using a percpu cache for nh_rth_output gives a nice performance
increase at a small cost.

24 udpflood test on my 24 cpu machine (dummy0 output device)
(each process sends 1.000.000 udp frames, 24 processes are started)

before : 5.24 s
after : 2.06 s
For reference, time on linux-3.5 : 6.60 s
Signed-off-by: NEric Dumazet <edumazet@google.com>
Tested-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

commit 404e0a8b (net: ipv4: fix RCU races on dst refcounts) tried
to solve a race but added a problem at device/fib dismantle time :

We really want to call dst_free() as soon as possible, even if sockets
still have dst in their cache.
dst_release() calls in free_fib_info_rcu() are not welcomed.

Root of the problem was that now we also cache output routes (in
nh_rth_output), we must use call_rcu() instead of call_rcu_bh() in
rt_free(), because output route lookups are done in process context.

Based on feedback and initial patch from David Miller (adding another
call_rcu_bh() call in fib, but it appears it was not the right fix)

I left the inet_sk_rx_dst_set() helper and added __rcu attributes
to nh_rth_output and nh_rth_input to better document what is going on in
this code.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Pull Ceph changes from Sage Weil:
 "Lots of stuff this time around:

   - lots of cleanup and refactoring in the libceph messenger code, and
     many hard to hit races and bugs closed as a result.
   - lots of cleanup and refactoring in the rbd code from Alex Elder,
     mostly in preparation for the layering functionality that will be
     coming in 3.7.
   - some misc rbd cleanups from Josh Durgin that are finally going
     upstream
   - support for CRUSH tunables (used by newer clusters to improve the
     data placement)
   - some cleanup in our use of d_parent that Al brought up a while back
   - a random collection of fixes across the tree

  There is another patch coming that fixes up our ->atomic_open()
  behavior, but I'm going to hammer on it a bit more before sending it."

Fix up conflicts due to commits that were already committed earlier in
drivers/block/rbd.c, net/ceph/{messenger.c, osd_client.c}

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: (132 commits)
  rbd: create rbd_refresh_helper()
  rbd: return obj version in __rbd_refresh_header()
  rbd: fixes in rbd_header_from_disk()
  rbd: always pass ops array to rbd_req_sync_op()
  rbd: pass null version pointer in add_snap()
  rbd: make rbd_create_rw_ops() return a pointer
  rbd: have __rbd_add_snap_dev() return a pointer
  libceph: recheck con state after allocating incoming message
  libceph: change ceph_con_in_msg_alloc convention to be less weird
  libceph: avoid dropping con mutex before fault
  libceph: verify state after retaking con lock after dispatch
  libceph: revoke mon_client messages on session restart
  libceph: fix handling of immediate socket connect failure
  ceph: update MAINTAINERS file
  libceph: be less chatty about stray replies
  libceph: clear all flags on con_close
  libceph: clean up con flags
  libceph: replace connection state bits with states
  libceph: drop unnecessary CLOSED check in socket state change callback
  libceph: close socket directly from ceph_con_close()
  ...

We have no mechanism to emulate LOCK_MAND locks on NFSv4, so explicitly
return -EINVAL if someone requests it.
Signed-off-by: NJeff Layton <jlayton@redhat.com>
Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

By default a sunrpc service is limited to (N+3)*20 connections
where N is the number of threads.  This is 80 when N==1.
If this number is exceeded a warning is printed suggesting that
the number of threads be increased.  However with services which
run a single thread, this is impossible.

For such services there is a ->sv_maxconn setting that can be
used to forcibly increase the limit, and silence the message.
This is used by lockd.

The nfs client uses a sunrpc service to handle callbacks and
it too is single-threaded, so to avoid the useless messages,
and to allow a reasonable number of concurrent connections,
we need to set ->sv_maxconn.  1024 seems like a good number.
Signed-off-by: NNeilBrown <neilb@suse.de>
Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

thermal_zone_device_register() does not modify 'type' argument, so it is
safe to declare it as const. Otherwise, if we pass a const string, we are
getting the ugly warning:

CC drivers/power/power_supply_core.o
drivers/power/power_supply_core.c: In function 'psy_register_thermal':
drivers/power/power_supply_core.c:204:6: warning: passing argument 1 of 'thermal_zone_device_register' discards 'const' qualifier from pointer target type [enabled by default]
include/linux/thermal.h:140:29: note: expected 'char *' but argument is of type 'const char *'
Signed-off-by: NAnton Vorontsov <anton.vorontsov@linaro.org>
Acked-by: NJean Delvare <khali@linux-fr.org>

This merge is performed to take commit c56f5c03 ("Thermal: Make
Thermal trip points writeable") out of Linus' tree and then fixup power
supply class. This is needed since thermal stuff added a new argument:

  CC      drivers/power/power_supply_core.o
drivers/power/power_supply_core.c: In function ‘psy_register_thermal’:
drivers/power/power_supply_core.c:204:6: warning: passing argument 3 of ‘thermal_zone_device_register’ makes integer from pointer without a cast [enabled by default]
include/linux/thermal.h:154:29: note: expected ‘int’ but argument is of type ‘struct power_supply *’
drivers/power/power_supply_core.c:204:6: error: too few arguments to function ‘thermal_zone_device_register’
include/linux/thermal.h:154:29: note: declared here
make[1]: *** [drivers/power/power_supply_core.o] Error 1
make: *** [drivers/power/] Error 2
Signed-off-by: NAnton Vorontsov <anton.vorontsov@linaro.org>

Commit b38c77d8 moved the MTMSR_EERI macro from the KVM code to generic
ppc_asm.h code. However, while adding it in the headers for the ppc32 case,
it missed out to remove the former definition in the KVM code.

This patch fixes compilation on server type PPC32 targets with CONFIG_KVM
enabled.
Signed-off-by: NAlexander Graf <agraf@suse.de>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>

Kumar says:

"A few patches that missed the initial 3.6 window.  These are bug fixes at
this point."

Pull writeback updates from Wu Fengguang:
 "Use time based periods to age the writeback proportions, which can
  adapt equally well to fast/slow devices."

Fix up trivial conflict in comment in fs/sync.c

* tag 'writeback-proportions' of git://git.kernel.org/pub/scm/linux/kernel/git/wfg/linux:
  writeback: Fix some comment errors
  block: Convert BDI proportion calculations to flexible proportions
  lib: Fix possible deadlock in flexible proportion code
  lib: Proportions with flexible period

Pull NFS client updates from Trond Myklebust:
 "Features include:
   - More preparatory patches for modularising NFSv2/v3/v4.  Split out
     the various NFSv2/v3/v4-specific code into separate files
   - More preparation for the NFSv4 migration code
   - Ensure that OPEN(O_CREATE) observes the pNFS mds threshold
     parameters
   - pNFS fast failover when the data servers are down
   - Various cleanups and debugging patches"

* tag 'nfs-for-3.6-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (67 commits)
  nfs: fix fl_type tests in NFSv4 code
  NFS: fix pnfs regression with directio writes
  NFS: fix pnfs regression with directio reads
  sunrpc: clnt: Add missing braces
  nfs: fix stub return type warnings
  NFS: exit_nfs_v4() shouldn't be an __exit function
  SUNRPC: Add a missing spin_unlock to gss_mech_list_pseudoflavors
  NFS: Split out NFS v4 client functions
  NFS: Split out the NFS v4 filesystem types
  NFS: Create a single nfs_clone_super() function
  NFS: Split out NFS v4 server creating code
  NFS: Initialize the NFS v4 client from init_nfs_v4()
  NFS: Move the v4 getroot code to nfs4getroot.c
  NFS: Split out NFS v4 file operations
  NFS: Initialize v4 sysctls from nfs_init_v4()
  NFS: Create an init_nfs_v4() function
  NFS: Split out NFS v4 inode operations
  NFS: Split out NFS v3 inode operations
  NFS: Split out NFS v2 inode operations
  NFS: Clean up nfs4_proc_setclientid() and friends
  ...

Pull MFD fix from Samuel Ortiz:
 "This one fixes an s5m8767 regulator build breakage due to a merge
  conflict caused by the MFD s5m API changes."

* tag 'mfd-for-linus-3.6-1' of git://git.kernel.org/pub/scm/linux/kernel/git/sameo/mfd-2.6:
  regulator: Fix an s5m8767 build failure

Pull media updates from Mauro Carvalho Chehab:
 "This is the first part of the media patches for v3.6.

  This patch series contain:
   - new DVB frontend: rtl2832
   - new video drivers: adv7393
   - some unused files got removed
   - a selection API cleanup between V4L2 and V4L2 subdev API's
   - a major redesign at v4l-ioctl2, in order to clean it up
   - several driver fixes and improvements."

* 'v4l_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-media: (174 commits)
  v4l: Export v4l2-common.h in include/linux/Kbuild
  media: Revert "[media] Terratec Cinergy S2 USB HD Rev.2"
  [media] media: Use pr_info not homegrown pr_reg macro
  [media] Terratec Cinergy S2 USB HD Rev.2
  [media] v4l: Correct conflicting V4L2 subdev selection API documentation
  [media] Feature removal: V4L2 selections API target and flag definitions
  [media] v4l: Unify selection flags documentation
  [media] v4l: Unify selection flags
  [media] v4l: Common documentation for selection targets
  [media] v4l: Unify selection targets across V4L2 and V4L2 subdev interfaces
  [media] v4l: Remove "_ACTUAL" from subdev selection API target definition names
  [media] V4L: Remove "_ACTIVE" from the selection target name definitions
  [media] media: dvb-usb: print mac address via native %pM
  [media] s5p-tv: Use module_i2c_driver in sii9234_drv.c file
  [media] media: gpio-ir-recv: add allowed_protos for platform data
  [media] s5p-jpeg: Use module_platform_driver in jpeg-core.c file
  [media] saa7134: fix spelling of detach in label
  [media] cx88-blackbird: replace ioctl by unlocked_ioctl
  [media] cx88: don't use current_norm
  [media] cx88: fix a number of v4l2-compliance violations
  ...

Create a simple helper that handles the common case of calling
__rbd_refresh_header() while holding the ctl_mutex.
Signed-off-by: NAlex Elder <elder@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> 

Add a new parameter to __rbd_refresh_header() through which the
version of the header object is passed back to the caller.  In most
cases this isn't needed.  The main motivation is to normalize
(almost) all calls to __rbd_refresh_header() so they are all
wrapped immediately by mutex_lock()/mutex_unlock().
Signed-off-by: NAlex Elder <elder@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> 

This fixes a few issues in rbd_header_from_disk():
    - There is a check intended to catch overflow, but it's wrong in
      two ways.
	- First, the type we don't want to overflow is size_t, not
	  unsigned int, and there is now a SIZE_MAX we can use for
	  use with that type.
	- Second, we're allocating the snapshot ids and snapshot
	  image sizes separately (each has type u64; on disk they
          grouped together as a rbd_image_header_ondisk structure).
	  So we can use the size of u64 in this overflow check.
    - If there are no snapshots, then there should be no snapshot
      names.  Enforce this, and issue a warning if we encounter a
      header with no snapshots but a non-zero snap_names_len.
    - When saving the snapshot names into the header, be more direct
      in defining the offset in the on-disk structure from which
      they're being copied by using "snap_count" rather than "i"
      in the array index.
    - If an error occurs, the "snapc" and "snap_names" fields are
      freed at the end of the function.  Make those fields be null
      pointers after they're freed, to be explicit that they are
      no longer valid.
    - Finally, move the definition of the local variable "i" to the
      innermost scope in which it's needed.
Signed-off-by: NAlex Elder <elder@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> 

All of the callers of rbd_req_sync_op() except one pass a non-null
"ops" pointer.  The only one that does not is rbd_req_sync_read(),
which passes CEPH_OSD_OP_READ as its "opcode" and, CEPH_OSD_FLAG_READ
for "flags".

By allocating the ops array in rbd_req_sync_read() and moving the
special case code for the null ops pointer into it, it becomes
clear that much of that code is not even necessary.

In addition, the "opcode" argument to rbd_req_sync_op() is never
actually used, so get rid of that.
Signed-off-by: NAlex Elder <elder@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> 

rbd_header_add_snap() passes the address of a version variable to
rbd_req_sync_exec(), but it ignores the result.  Just pass a null
pointer instead.
Signed-off-by: NAlex Elder <elder@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> 

Either rbd_create_rw_ops() will succeed, or it will fail because a
memory allocation failed.  Have it just return a valid pointer or
null rather than stuffing a pointer into a provided address and
returning an errno.
Signed-off-by: NAlex Elder <elder@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> 

It's not obvious whether the snapshot pointer whose address is
provided to __rbd_add_snap_dev() will be assigned by that function.
Change it to return the snapshot, or a pointer-coded errno in the
event of a failure.
Signed-off-by: NAlex Elder <elder@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> 

We drop the lock when calling the ->alloc_msg() con op, which means
we need to (a) not clobber con->in_msg without the mutex held, and (b)
we need to verify that we are still in the OPEN state when we retake
it to avoid causing any mayhem.  If the state does change, -EAGAIN
will get us back to con_work() and loop.
Signed-off-by: NSage Weil <sage@inktank.com>
Reviewed-by: NAlex Elder <elder@inktank.com>

This function's calling convention is very limiting.  In particular,
we can't return any error other than ENOMEM (and only implicitly),
which is a problem (see next patch).

Instead, return an normal 0 or error code, and make the skip a pointer
output parameter.  Drop the useless in_hdr argument (we have the con
pointer).
Signed-off-by: NSage Weil <sage@inktank.com>
Reviewed-by: NAlex Elder <elder@inktank.com>

The ceph_fault() function takes the con mutex, so we should avoid
dropping it before calling it.  This fixes a potential race with
another thread calling ceph_con_close(), or _open(), or similar (we
don't reverify con->state after retaking the lock).

Add annotation so that lockdep realizes we will drop the mutex before
returning.
Signed-off-by: NSage Weil <sage@inktank.com>
Reviewed-by: NAlex Elder <elder@inktank.com>

We drop the con mutex when delivering a message.  When we retake the
lock, we need to verify we are still in the OPEN state before
preparing to read the next tag, or else we risk stepping on a
connection that has been closed.
Signed-off-by: NSage Weil <sage@inktank.com>
Reviewed-by: NAlex Elder <elder@inktank.com>

Revoke all mon_client messages when we shut down the old connection.
This is mostly moot since we are re-using the same ceph_connection,
but it is cleaner.
Signed-off-by: NSage Weil <sage@inktank.com>
Reviewed-by: NAlex Elder <elder@inktank.com>

If the connect() call immediately fails such that sock == NULL, we
still need con_close_socket() to reset our socket state to CLOSED.
Signed-off-by: NSage Weil <sage@inktank.com>
Reviewed-by: NAlex Elder <elder@inktank.com>

 * shiny new inktank.com email addresses
 * add include/linux/crush directory (previous oversight)
Signed-off-by: NSage Weil <sage@inktank.com>
Reviewed-by: NAlex Elder <elder@inktank.com>

There are many (normal) conditions that can lead to us getting
unexpected replies, include cluster topology changes, osd failures,
and timeouts.  There's no need to spam the console about it.
Signed-off-by: NSage Weil <sage@inktank.com>
Reviewed-by: NAlex Elder <elder@inktank.com>

Signed-off-by: NSage Weil <sage@inktank.com>

Rename flags with CON_FLAG prefix, move the definitions into the c file,
and (better) document their meaning.
Signed-off-by: NSage Weil <sage@inktank.com>

Use a simple set of 6 enumerated values for the socket states (CON_STATE_*)
and use those instead of the state bits.  All of the con->state checks are
now under the protection of the con mutex, so this is safe.  It also
simplifies many of the state checks because we can check for anything other
than the expected state instead of various bits for races we can think of.

This appears to hold up well to stress testing both with and without socket
failure injection on the server side.
Signed-off-by: NSage Weil <sage@inktank.com>