ConnectX HCA supports shrinking WQEs, so that a single work request
can be made of multiple units of wqe_shift.  This way, WRs can differ
in size, and do not have to be a power of 2 in size, saving memory and
speeding up send WR posting.  Unfortunately, if we do this then the
wqe_index field in CQEs can't be used to look up the WR ID anymore, so
our implementation does this only if selective signaling is off.

Further, on 32-bit platforms, we can't use vmap() to make the QP
buffer virtually contigious. Thus we have to use constant-sized WRs to
make sure a WR is always fully within a single page-sized chunk.

Finally, we use WRs with the NOP opcode to avoid wrapping around the
queue buffer in the middle of posting a WR, and we set the
NoErrorCompletion bit to avoid getting completions with error for NOP
WRs.  However, NEC is only supported starting with firmware 2.2.232,
so we use constant-sized WRs for older firmware.  And, since MLX QPs
only support SEND, we use constant-sized WRs in this case.

When stamping during NOP posting, do stamping following setting of the
NOP WQE valid bit.
Signed-off-by: NMichael S. Tsirkin <mst@dev.mellanox.co.il>
Signed-off-by: NJack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Now that struct mlx4_buf.u is a struct instead of a union because of
the vmap() changes, there's no point in having a struct at all.  So
move .direct and .page_list directly into struct mlx4_buf and get rid
of a bunch of unnecessary ".u"s.
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Since kernel virtual memory is not a problem on 64-bit systems, there
is no reason to use our own 2-layer page mapping scheme for large
kernel queue buffers on such systems.  Instead, map the page list to a
single virtually contiguous buffer with vmap(), so that can we access
buffer memory via direct indexing.
Signed-off-by: NMichael S. Tsirkin <mst@dev.mellanox.co.il>
Signed-off-by: NJack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

We use struct mlx4_buf for kernel QP, CQ and SRQ buffers, and the code
to look up an entry is duplicated in get_cqe_from_buf() and the QP and
SRQ versions of get_wqe().  Factor this out into mlx4_buf_offset().

This will also make it easier to switch over to using vmap() for buffers.
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

* 'release' of git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux-2.6:
  [IA64] make pfm_get_task work with virtual pids
  [IA64] honor notify_die() returning NOTIFY_STOP
  [IA64] remove dead code: __cpu_{down,die} from !HOTPLUG_CPU
  [IA64] Appoint kvm/ia64 Maintainers
  [IA64] ia64_set_psr should use srlz.i
  [IA64] Export three symbols for module use
  [IA64] mca style cleanup
  [IA64] sn_hwperf semaphore to mutex
  [IA64] generalize attribute of fsyscall_gtod_data
  [IA64] efi.c Add /* never reached */ annotation
  [IA64] efi.c Spelling/punctuation fixes
  [IA64] Make efi.c mostly fit in 80 columns
  [IA64] aliasing-test: fix gcc warnings on non-ia64
  [IA64] Slim-down __clear_bit_unlock
  [IA64] Fix the order of atomic operations in restore_previous_kprobes on ia64
  [IA64] constify function pointer tables
  [IA64] fix userspace compile error in gcc_intrin.h

* 'for-linus' of git://git390.osdl.marist.edu/pub/scm/linux-2.6:
  [S390] dcss: Initialize workqueue before using it.
  [S390] Remove BUILD_BUG_ON() in vmem code.
  [S390] sclp_tty/sclp_vt220: Fix scheduling while atomic
  [S390] dasd: fix panic caused by alias device offline
  [S390] dasd: add ifcc handling
  [S390] latencytop s390 support.
  [S390] Implement ext2_find_next_bit.
  [S390] Cleanup & optimize bitops.
  [S390] Define GENERIC_LOCKBREAK.
  [S390] console: allow vt220 console to be the only console
  [S390] Fix couple of section mismatches.
  [S390] Fix smp_call_function_mask semantics.
  [S390] Fix linker script.
  [S390] DEBUG_PAGEALLOC support for s390.
  [S390] cio: Add shutdown callback for ccwgroup.
  [S390] cio: Update documentation.
  [S390] cio: Clean up chsc response code handling.
  [S390] cio: make sense id procedure work with partial hardware response

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6: (21 commits)
  [PKT_SCHED]: vlan tag match
  [NET]: Add if_addrlabel.h to sanitized headers.
  [NET] rtnetlink.c: remove no longer used functions
  [ICMP]: Restore pskb_pull calls in receive function
  [INET]: Fix accidentally broken inet(6)_hash_connect's port offset calculations.
  [NET]: Remove further references to net-modules.txt
  bluetooth rfcomm tty: destroy before tty_close()
  bluetooth: blacklist another Broadcom BCM2035 device
  drivers/bluetooth/btsdio.c: fix double-free
  drivers/bluetooth/bpa10x.c: fix memleak
  bluetooth: uninlining
  bluetooth: hidp_process_hid_control remove unnecessary parameter dealing
  tun: impossible to deassert IFF_ONE_QUEUE or IFF_NO_PI
  hamradio: fix dmascc section mismatch
  [SCTP]: Fix kernel panic while received AUTH chunk with BAD shared key identifier
  [SCTP]: Fix kernel panic while received AUTH chunk while enabled auth
  [IPV4]: Formatting fix for /proc/net/fib_trie.
  [IPV6]: Fix sysctl compilation error.
  [NET_SCHED]: Add #ifdef CONFIG_NET_EMATCH in net/sched/cls_flow.c (latest git broken build)
  [IPV4]: Fix compile error building without CONFIG_FS_PROC
  ...

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/sparc-2.6:
  [SPARC64]  pci_sun4v.c: Section fixes.

* 'agp-patches' of git://git.kernel.org/pub/scm/linux/kernel/git/airlied/agp-2.6:
  agp: remove flush_agp_mappings calls from new flush handling code
  intel-agp: introduce IS_I915 and do some cleanups..
  [intel_agp] fix name for G35 chipset
  intel-agp: fixup resource handling in flush code.
  intel-agp: add new chipset ID
  agp: remove unnecessary pci_dev_put
  agp: remove uid comparison as security check
  fix AGP warning
  agp/intel: Add chipset flushing support for i8xx chipsets.
  intel-agp: add chipset flushing support
  agp: add chipset flushing support to AGP interface

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband:
  RDMA/nes: Add a driver for NetEffect RNICs
  IB/mthca: Return proper error codes from mthca_fmr_alloc()
  IB: Avoid marking __devinitdata as const
  IB/mlx4: Actually print out the driver version
  IB/ib_mthca: Pre-link receive WQEs in Tavor mode
  IB/mthca: Remove checks for srq->first_free < 0
  IB/fmr_pool: Allocate page list for pool FMRs only when caching enabled
  IB/srp: Retry stale connections
  mlx4_core: Don't read reserved fields in mlx4_QUERY_ADAPTER()
  IB/mthca: Don't read reserved fields in mthca_QUERY_ADAPTER()
  IPoIB: Remove a misleading debug print
  IPoIB: Handle bonding failover race for connected neighbours too
  IB/mthca: Fix and simplify page size calculation in mthca_reg_phys_mr()
  IB/ehca: Add PMA support
  IB/ehca: Update sma_attr also in case of disruptive config change
  IB/ehca: Prevent sending UD packets to QP0
  IB/cm: Add interim support for routed paths
  mlx4_core: Fix more section mismatches

Also fixed the include syntax while I was there.
Signed-off-by: NJeff Dike <jdike@linux.intel.com>
Cc: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Redo the calculation of NR_syscalls since that disappeared from i386 and
use a similar mechanism on x86_64.

We now figure out the size of the system call table in arch code and stick
that in syscall_table_size.  arch/um/kernel/skas/syscall.c defines
NR_syscalls in terms of that since its the only thing that needs to know
how many system calls there are.

The old mechananism that was used on x86_64 is gone.

arch/um/include/sysdep-i386/syscalls.h got some formatting since I was
looking at it.
Signed-off-by: NJeff Dike <jdike@linux.intel.com>
Cc: WANG Cong <xiyou.wangcong@gmail.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Tweak the UML defconfig -
      we probably don't need 256 old-style ptys - this slows down udev
noticably
      enable hostfs
      disable slab debugging - another noticable performance hit
Signed-off-by: NJeff Dike <jdike@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The port_sem is already used as a mutex since it's using DECLARE_MUTEX(), but
the underlying construct is still a semaphore ..  This patch switches it over
to a struct mutex.
Signed-off-by: NDaniel Walker <dwalker@mvista.com>
Signed-off-by: NJeff Dike <jdike@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The plug_mem_mutex is already used as a mutex since it's using
DECLARE_MUTEX(), but the underlying construct is still a semaphore ..  This
patch switches it over to a struct mutex.
Signed-off-by: NDaniel Walker <dwalker@mvista.com>
Signed-off-by: NJeff Dike <jdike@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The ldt.semaphore conforms to the new struct mutex requirments, so I converted
it to use the new API and changed the name.
Signed-off-by: NDaniel Walker <dwalker@mvista.com>
Signed-off-by: NJeff Dike <jdike@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Downgrade one of the MAC validity checks.  If it's one that could be possibly
assigned to a physical NIC, then nothing will break.  So, emit a warning in
this case, but keep the requested MAC.
Signed-off-by: NJeff Dike <jdike@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This patch takes care of a problem with the stopping code.

The function inside the while condition returns 0 to signify a problem.  A
problem could be for example a bad command or a bad version of the mconsole
client.  A bad command would terminate the stopping loop and resume the
kernel.  This is a problem.

A better solution is to make the loop infinite and don't leave it until we are
explicitly told to.
Signed-off-by: NKarol Swietlicki <magotari@gmail.com>
Signed-off-by: NJeff Dike <jdike@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

John Reiser noticed that a physical memory region was being mapped twice.

This patch fixes that, and it inlines the responsible function, as that had
only one caller.

Cc: John Reiser <jreiser@BitWagon.com>
Signed-off-by: NJeff Dike <jdike@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

TOPDIR is obsolete, use srctree instead.  This patch removes TOPDIR from all
UML Makefiles.

Cc: Sam Ravnborg <sam@ravnborg.org>
Signed-off-by: NWANG Cong <xiyou.wangcong@gmail.com>
Signed-off-by: NJeff Dike <jdike@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The 3-level page table fixes forgot to remove a couple now-unused fields from
struct mm_context.
Signed-off-by: NJeff Dike <jdike@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Calling init_registers inside the skas3 checking causes mysterious crashes if
it doesn't happen because the skas3 checking is bypassed.  This patch moves it
to os_early_checks.
Signed-off-by: NJeff Dike <jdike@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Some printks were missing newlines.
Signed-off-by: NJeff Dike <jdike@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Style fixes in arch/um/sys-x86_64:
	updated copyrights
	CodingStyle fixes
	added severities to printks which needed them

A bunch of functions in sys-*/ptrace_user.c turn out to be unused, so they and
their declarations are gone.
Signed-off-by: NJeff Dike <jdike@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

avoid-overflows-in-kernel-timec.patch makes CONFIG_HZ necessary for a
successful build.  UML lacks a definition, so this patch adds one.  It also
changes the hard-wired definition of HZ to CONFIG_HZ.

Note: this patch is a good idea even in the absence of hpa's time fixes.

Cc: "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: NJeff Dike <jdike@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

A couple more DEBUG_SHIRQ fixes.

The previous mconsole blocking fix exposed the lack of O_NONBLOCK on the
mconsole socket.

Also, winch_interrupt started crashing because it is called at irq free time
and it tries to dereference tty->driver_data, which has already been set to
NULL.

I added some error cleanup in mconsole_init while I was there.

Cc: "Karol Swietlicki" <magotari@gmail.com>
Signed-off-by: NJeff Dike <jdike@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The fakehd switch lost its implementation at some point.  Since no one is
screaming for it, we might as well remove it.
Signed-off-by: NJeff Dike <jdike@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The .a flags in openflags never had an implementation.
Signed-off-by: NJeff Dike <jdike@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Add some more commentary about various pieces of global data not needing
locking.

Also got rid of unmap_physmem since that is no longer used.
Signed-off-by: NJeff Dike <jdike@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

init_irq_signals doesn't need to be called from the context of a new process.
It initializes handlers, which are useless in process context.  With that call
gone, init_irq_signals has only one caller, so it can be inlined into
init_new_thread_signals.
Signed-off-by: NJeff Dike <jdike@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This patch tidies the signal handling code slightly.

pending is renamed to signals_pending for symmetry with signals_enabled.

remove_sigstack was unused, so can be deleted.

The value of change_sig was never used, so it is now void and the
return value is not calculated any more.
Signed-off-by: NJeff Dike <jdike@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

To convert from tv_nsec to tv_usec, one needs to divide by 1000, not multiply.
Signed-off-by: NDominique Quatravaux <dominique@quatravaux.org>
Signed-off-by: NJeff Dike <jdike@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Joe Perches noticed some printks in smp.c that needed fixing.

While I was in there, I did the usual tidying in arch/um/kernel, which
should be fairly style-clean at this point:
	copyright updates
	emacs formatting comments removal
	include tidying
	style fixes

Cc: Joe Perches <joe@perches.com>
Signed-off-by: NJeff Dike <jdike@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

sig_handler_common_skas needs significant modernization, starting with
its name and storage class.

There is no need to hide the true type of the sigcontext pointer, so
the void * dummy parameter can be replaced with a sigcontext *sc.

The array of uml_pt_regs structs used in the page fault case are gone,
replaced by a local variable.  This is also used in the non-segfault
case instead of the copy in the task_struct.  Since it's local, the
special handling of the is_user flag can go away.

There hasn't been any special treatment of SIGUSR1 in ages, so the
line that enables it can be deleted.

The special treatment of SIGSEGV similarly goes away, but to
compensate, SA_NODEFER is added to sa_mask when registering a signal
handler.
Signed-off-by: NJeff Dike <jdike@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This patch moves sig_handler_common_skas from
arch/um/os-Linux/skas/trap.c to its only caller in
arch/um/os-Linux/signal.c.  trap.c is now empty, so it can be removed.

This is code movement only - the significant cleanup needed here is
done in the next patch.
Signed-off-by: NJeff Dike <jdike@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Kill a process that tries to branch into a stub and execute a system
call.  There are no security implications here - a system call in a
stub is treated the same as a system call anywhere else.  But if a
process is trying to branch into a stub, either it is trying something
nasty or it has gone haywire, so it's a good idea to get rid of it in
either case.
Signed-off-by: NJeff Dike <jdike@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Get rid of some syscall counters which haven't been useful in ages.
Signed-off-by: NJeff Dike <jdike@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

A bit of defensive programming - during development, it ocassionally
happens that a call to init_new_context is missed, resulting in
context holding a host pid of zero.  When that address space is torn
down, destroy_context does a kill(0), which instantly kills the whole
UML without any errors whatsoever.

This patch add a check for pids less than 2, to also catch 1 and
negative pids.
Signed-off-by: NJeff Dike <jdike@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Style fixes to arch/um/os/helper.c and tidying up the breakpoint fix a
bit.

helper.c gets all the usual style fixes -
	 updated copyright
	 all printks get severities

Also -
	 errval changes to err in helper_child
	 fixed an obsolete comment
	 run_helper was killing a child process which is guaranteed to
be dead or dying anyway

Removed the nohang and pname arguments from helper_wait and fixed the
declaration and callers.  nohang was used only in the slirp driver and
I don't think it was needed.  I think pname was a bit of overkill in
putting out an error message when something goes wrong.
Signed-off-by: NJeff Dike <jdike@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

signals_enabled and pending have requirements on the order in which they are
modified.  This used to be done by declaring them volatile and putting an mb()
where the ordering requirements were in effect.

After getting a better (I hope) understanding of how to do this correctly, the
volatile declarations are gone and the mb()'s replaced by barrier()'s.

One of the mb()'s was deleted because I see no problematic writes that could
be re-ordered past that point.
Signed-off-by: NJeff Dike <jdike@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>