We need to do this, otherwise the io schedulers don't get access to the
sync flag. Then they cannot tell the difference between a regular write
and an O_DIRECT write, which can cause a performance loss.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>

* 'release' of git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux-2.6:
  [IA64] kprobe clears qp bits for special instructions
  [IA64] enable trap code on slot 1
  [IA64] Take defensive stance on ia64_pal_get_brand_info()
  [IA64] fix possible XPC deadlock when disconnecting
  [IA64] - Reduce overhead of FP exception logging messages
  [IA64] fix arch/ia64/mm/contig.c:235: warning: unused variable `nid'
  [IA64] s/termios/ktermios/ in simserial.c
  [IA64] kexec/kdump: tidy up declaration of relocate_new_kernel_t
  [IA64] Kexec/Kdump: honour non-zero crashkernel offset.
  [IA64] CONFIG_KEXEC/CONFIG_CRASH_DUMP permutations
  [IA64] Do not call SN_SAL_SET_CPU_NUMBER twice on cpu 0

* master.kernel.org:/pub/scm/linux/kernel/git/davej/agpgart:
  [AGPGART] VIA and SiS AGP chipsets are x86-only
  [AGPGART] agp-amd64: section mismatches with HOTPLUG=n
  [AGPGART] Fix up misprogrammed bridges with incorrect AGPv2 rates.

* 'for-linus' of master.kernel.org:/pub/scm/linux/kernel/git/roland/infiniband:
  IPoIB: Make sure struct ipoib_neigh.queue is always initialized
  IB/iser: Use the new verbs DMA mapping functions
  IB/srp: Use new verbs IB DMA mapping functions
  IPoIB: Use the new verbs DMA mapping functions
  IB/core: Use the new verbs DMA mapping functions
  IB/ipath: Implement new verbs DMA mapping functions
  IB: Add DMA mapping functions to allow device drivers to interpose
  RDMA/cma: Export rdma cm interface to userspace
  RDMA/cma: Add support for RDMA_PS_UDP
  RDMA/cma: Allow early transition to RTS to handle lost CM messages
  RDMA/cma: Report connect info with connect events
  RDMA/cma: Remove unneeded qp_type parameter from rdma_cm
  IB/ipath: Fix IRQ for PCI Express HCAs
  RDMA/amso1100: Fix memory leak in c2_qp_modify()
  IB/iser: Remove unused "write-only" variables
  IB/ipath: Remove unused "write-only" variables
  IB/fmr: ib_flush_fmr_pool() may wait too long

* git://git.kernel.org/pub/scm/linux/kernel/git/bunk/trivial:
  Fix inotify maintainers entry
  Fix typo in new debug options.
  Jon needs a new shift key.
  fs: Convert kmalloc() + memset() to kzalloc() in fs/.
  configfs.h: Remove dead macro definitions.
  kconfig: Standardize "depends" -> "depends on" in Kconfig files
  e100: replace kmalloc with kcalloc
  um: replace kmalloc+memset with kzalloc
  fix typo in net/ipv4/ip_fragment.c
  include/linux/compiler.h: reject gcc 3 < gcc 3.2
  Kconfig: fix spelling error in config KALLSYMS help text
  Remove duplicate "have to" in comment
  Fix small typo in drivers/serial/icom.c
  Use consistent casing in help message
  EXT{2,3,4}_FS: remove outdated part of the help text

* master.kernel.org:/pub/scm/linux/kernel/git/wim/linux-2.6-watchdog:
  [WATCHDOG] pcwd_usb.c generic HID include file
  [WATCHDOG] watchdog miscdevice patch
  [WATCHDOG] rm9k_wdt: fix interrupt handler arguments
  [WATCHDOG] rm9k_wdt: fix compilation

There's no point in troubling the Alpha, IA-64, PowerPC and PARISC
people with SiS and VIA options.  Andrew thinks it helps find bugs,
but there's no evidence of that.
Signed-off-by: Matthew Wilcox <matthew@wil.cx>
Signed-off-by: Dave Jones <davej@redhat.com>

When CONFIG_HOTPLUG=n, agp_amd64_resume() calls nforce3_agp_init(),
which is __devinit == __init, so has been discarded and is not
usable for resume.

WARNING: drivers/char/agp/amd64-agp.o - Section mismatch: reference to .init.text: from .text between 'agp_amd64_resume' (at offset 0x249) and 'amd64_tlbflush'
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: Dave Jones <davej@redhat.com>

Move the initialization of ipoib_neigh's skb_queue into
ipoib_neigh_alloc(), since commit 2745b5b7 ("IPoIB: Fix skb leak when
freeing neighbour") will make iterate over the skb_queue to free any
packets left over when freeing the ipoib_neigh structure.

This fixes a crash when freeing ipoib_neigh structures allocated in
ipoib_mcast_send(), which otherwise don't have their skb_queue
initialized.
Signed-off-by: Roland Dreier <rolandd@cisco.com>

Now that the generic HID layer created include/linux/hid.h
we can use the HID_REQ_SET_REPORT and HID_DT_REPORT defines
directly from that include file.
Signed-off-by: Wim Van Sebroeck <wim@iguana.be>

Conflicts:

	drivers/cpufreq/cpufreq.c

Support for CN400 northbridge when ACPI C3 isn't available.
Tested on Epia SP13000. Thanks to Robert for testing it.
Signed-off-by: Rafa Bilski <rafalbilski@interia.pl>
Signed-off-by: Dave Jones <davej@redhat.com>

On board of Epia SP13000 is 10x133Mhz VIA Nehemiah. It is reported
as 10x200MHz. This patch is fixing this issue.
Signed-off-by: Rafa Bilski <rafalbilski@interia.pl>
Signed-off-by: Dave Jones <davej@redhat.com>

Convert iSER to use the new verbs DMA mapping functions for kernel
verbs consumers.
Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

Convert SRP to use the new verbs DMA mapping functions for kernel
verbs consumers.
Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

Convert IPoIB to use the new DMA mapping functions
for kernel verbs consumers.
Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

Support for Core CPUs was broken in two ways in speedstep-lib: for x86_64,
we missed a MSR definition; for both x86_64 and i386, the FSB calculation
was wrong by four (it's a quad-pumped bus). Also increase the accuracy
of the calculation.
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
Signed-off-by: Dave Jones <davej@redhat.com>

Convert code in core/ to use the new DMA mapping functions for kernel
verbs consumers.
Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

This patch implements the interposing DMA mapping functions to allow
support for IOMMUs and remove the dependence on phys_to_virt() and
bus_to_virt().
Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

The QLogic InfiniPath HCAs use programmed I/O instead of HW DMA.
This patch allows a verbs device driver to interpose on DMA mapping
function calls in order to avoid relying on bus_to_virt() and
phys_to_virt() to undo the mappings created by dma_map_single(),
dma_map_sg(), etc.
Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

Signed-off-by: Dave Jones <davej@redhat.com>

Fix the bug in duplicate states elimination in acpi-cpufreq.

Bug: Due to duplicate state elimiation in the loop earlier, the number
of valid_states can be less than perf->state_count, in which case
freq_table was ending up with some garbage/uninitialized entries
in the table.
Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
From:  Alexey Starikovskiy <alexey.y.starikovskiy@intel.com>
Signed-off-by: Dave Jones <davej@redhat.com>

On some systems there could be bits set in the upper half of
the control value provided by the _PSS object.  These bits are
only relevant for cpufreq drivers that use IO ports which are not
currently supported by the speedstep-centrino driver.  The current
MSR oriented code assumes that upper bits are not set and thus
fails to work correctly when they are.  e.g. the control and status
value equality check failed on the IBM x3650 even though the ACPI
spec allows inequality.
Signed-off-by: Gary Hade <garyhade@us.ibm.com>
Signed-off-by: Dave Jones <davej@redhat.com>

We don't need a temporary variable to get the PCI revision ID.
Signed-off-by: Jean Delvare <khali@linux-fr.org>
Signed-off-by: Dave Jones <davej@redhat.com>

On IA64 there exists some special instructions which
always need to be executed regradless of qp bits, such
as com.crel.unc, tbit.trel.unc etc.
This patch clears qp bits when inserting kprobe trap code
and disables probepoint on slot 1 for these special
instructions.
Signed-off-by: bibo,mao <bibo.mao@intel.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>

Because slot 1 of one instr bundle crosses border of two consecutive
8-bytes, kprobe on slot 1 is disabled. This patch enables kprobe on
slot1, it only replaces higher 8-bytes of the instruction bundle and
changes the exception code to ignore the low 12 bits of the break
number (which is across the border in the lower 8-bytes of the bundle).

For those instructions which must execute regardless qp bits,
kprobe on slot 1 is still disabled.
Signed-off-by: bibo,mao <bibo.mao@intel.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>

Stephane thought he saw a problem here (but was just confused
by the return value from ia64_pal_get_brand_info()).  But we
should be more defensive here in case an prototype PAL for
a future processor doesn't implement this PAL call.
Signed-off-by: Tony Luck <tony.luck@intel.com>

Export the rdma cm interfaces to userspace via a misc device.
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

Allow the use of UD QPs through the rdma_cm, in order to provide
address translation services for resolving IB addresses for datagram
messages using SIDR.
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

During connection establishment, the passive side of a connection can
receive messages from the active side before the connection event has
been delivered to the user.  Allow the passive side to send messages
in response to received data before the event is delivered.  To handle
the case where the connection messages are lost, a new rdma_notify()
function is added that users may invoke to force a connection into the
established state.
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

Connection information was never given to the recipient of a
connection request or reply message.  Only the event was delivered.
Report the connection data with the event to allows user to
reject the connection based on the requested parameters, or adjust
their resources to match the request.
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

The qp_type parameter into the rdma_cm is unneeded, and can be
misleading.  The QP type should be determined from the port space.
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

Commit 51f65ebc ("IB/ipath - program intconfig register using new HT
irq hook"), which fixed interrupts for HyperTransport HCAs, broke PCI
Express HCAs, because for those HCAs, the driver uses the value of
pdev->irq before pci_enable_msi() and ends up getting a totally bogus
IRQ number.  Fix this by using the value of pdev->irq after
pci_enable_msi().
Signed-off-by: Roland Dreier <rolandd@cisco.com>

vq_req is leaked in error cases.
Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

Remove variables that are set but then never looked at in the iSER
initiator.  These cleanups came from David Binderman's list of "set
but never used" warnings from icc.
Signed-off-by: Roland Dreier <rolandd@cisco.com>

Remove variables that are set but then never looked at in the ipath
driver.  These cleanups came from David Binderman's list of "set but
never used" warnings from icc.
Signed-off-by: Roland Dreier <rolandd@cisco.com>

ib_flush_fmr_pool() stashes away the request generation number
properly, but then goes ahead and rereads it every time it tests
whether the flush generation number has caught up.  This means that
there is a theoretical possibility of livelock, if the request
generation number keeps getting bumped and the flush generation number
never catches up.  The fix is simple: use the request generation
number read at the beginning of the function.

Also, atomic_inc() followed by atomic_read() can be replaced with
atomic_int_return().  There's no real requirement for atomicity here
but we might as well shrink the code.

This bug was discovered using David Binderman's list of "set but never
used" warnings from icc.
Signed-off-by: Roland Dreier <rolandd@cisco.com>

This patch eliminates a potential deadlock that is possible when XPC
disconnects a channel to a partition that has gone down. This deadlock will
occur if at least one of the kthreads created by XPC for the purpose of making
callouts to the channel's registerer is detained in the registerer and will
not be returning back to XPC until some registerer request occurs on the now
downed partition. The potential for a deadlock is removed by ensuring that
there always is a kthread available to make the channel disconnecting callout
to the registerer.
Signed-off-by: Dean Nelson <dcn@sgi.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>