Impact: fix kernel crash

Both oprofile and perfcounters register an NMI die handler, but only one
can handle the NMI.  Conveniently, oprofile unregisters it's notifier
when not actively in use, so setting it's notifier priority higher than
perfcounter's allows oprofile to borrow the NMI for the duration of it's
run.  Tested/works both as module and built-in.

While testing, I found that if kerneltop was generating NMIs at very
high frequency, the kernel may panic when oprofile registered it's
handler.  This turned out to be because oprofile registers it's handler
before reset_value has been allocated, so if an NMI comes in while it's
still setting up, kabOom.  Rather than try more invasive changes, I
followed the lead of other places in op_model_ppro.c, and simply
returned in that highly unlikely event.  (debug warnings attached)
Signed-off-by: NMike Galbraith <efault@gmx.de>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

With oprofile as a module, and unloaded by profiling script,
both oprofile and kerneltop work fine.. unless you leave kerneltop
running when you start profiling, then you may see badness.
Signed-off-by: NMike Galbraith <efault@gmx.de>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Fix:

  arch/x86/kernel/irqinit_32.c:124: warning: 'smp_intr_init' defined but not used
Signed-off-by: NJaswinder Singh Rajput <jaswinderrajput@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

don't kfree in use counters.

Running...

	while true; do perfstat -e 1 -c true; done

...on all cores for a while doesn't seem to be eating ram, and my oops
is gone.
Signed-off-by: NMike Galbraith <efault@gmx.de>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: cleanup

1. add smp_intr_init and apic_intr_init for 32bit, the same as 64bit
2. move the apic_intr_init() call before set gate with interrupt[i]
3. for 64bit, if ia32_emulation is not used, will make per_cpu to use 0x80 vector.

[ v2: should use !test_bit() instead of test_bit() with 32bit ]
Signed-off-by: NYinghai Lu <yinghai@kernel.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Fix:

WARNING: arch/x86/kernel/built-in.o(.text+0xdd0f): Section mismatch in reference from the function pmc_generic_enable() to the function .cpuinit.text:perf_counters_lapic_init()
The function pmc_generic_enable() references
the function __cpuinit perf_counters_lapic_init().
This is often because pmc_generic_enable lacks a __cpuinit
annotation or the annotation of perf_counters_lapic_init is wrong.
Signed-off-by: NMike Galbraith <efault@gmx.de>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Ratelimit performance counter interrupts to 100KHz per CPU.

This replaces the irq-delta-time based method.
Signed-off-by: NMike Galbraith <efault@gmx.de>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Starting kerneltop with only -c 100 seems to be a bad idea, it can
easily lock the system due to perfcounter IRQ overload.

So add throttling: if a new IRQ arrives in a shorter than
PERFMON_MIN_PERIOD_NS time, turn off perfcounters and untrottle them
from the next timer tick.
Signed-off-by: NMike Galbraith <efault@gmx.de>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: build fix

This build error:

 arch/x86/xen/suspend.c:22: error: implicit declaration of function 'fix_to_virt'
 arch/x86/xen/suspend.c:22: error: 'FIX_PARAVIRT_BOOTMAP' undeclared (first use in this function)
 arch/x86/xen/suspend.c:22: error: (Each undeclared identifier is reported only once
 arch/x86/xen/suspend.c:22: error: for each function it appears in.)

triggers because the hardirq.h unification removed an implicit fixmap.h
include - on which arch/x86/xen/suspend.c depended. Add the fixmap.h
include explicitly.
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Conflicts:
	arch/x86/include/asm/hardirq_32.h
	arch/x86/include/asm/hardirq_64.h

Semantic merge:
	arch/x86/include/asm/hardirq.h
	[ added apic_perf_irqs field. ]
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: shrink size of irq_cpustat_t when possible
Signed-off-by: NBrian Gerst <brgerst@gmail.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

Impact: cleanup
Signed-off-by: NBrian Gerst <brgerst@gmail.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

Impact: better code generation and removal of unused field for 32bit

In general, use the 64-bit version.
Signed-off-by: NBrian Gerst <brgerst@gmail.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

Impact: cleanup

APIC definitions aren't needed here.  Remove the include and fix
up the fallout.

tj: added include to mce_intel_64.c.
Signed-off-by: NBrian Gerst <brgerst@gmail.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

Impact: bogus irq_cpustat field removed

idle_timestamp is left over from the removed irqbalance code.
Signed-off-by: NBrian Gerst <brgerst@gmail.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

Conflicts:
	include/linux/syscalls.h

Make X86 SGI Ultraviolet support configurable. Saves about 13K of text size
on my modest config.

   text    data     bss     dec     hex filename
6770537 1158680  694356 8623573  8395d5 vmlinux
6757492 1157664  694228 8609384  835e68 vmlinux.nouv
Signed-off-by: NNick Piggin <npiggin@suse.de>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Fix more build-failure fallout from the UV cleanup - the UV drivers
were not updated to include <asm/uv/uv.h>.
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Fix:

  arch/x86/mm/tlb.c:47: error: ‘CONFIG_X86_INTERNODE_CACHE_BYTES’ undeclared here (not in a function)

The CONFIG_X86_INTERNODE_CACHE_BYTES symbol is only defined on 64-bit,
because vsmp support is 64-bit only. Define it on 32-bit too - where it
will always be equal to X86_L1_CACHE_BYTES.

Also move the default of X86_L1_CACHE_BYTES (which is separate from the
more commonly used L1_CACHE_SHIFT kconfig symbol) from 128 bytes to
64 bytes.
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Conflicts:
	arch/x86/mm/fault.c

Fix:

 arch/x86/mm/srat_64.c: In function ‘acpi_numa_processor_affinity_init’:
 arch/x86/mm/srat_64.c:141: error: implicit declaration of function ‘get_uv_system_type’
 arch/x86/mm/srat_64.c:141: error: ‘UV_X2APIC’ undeclared (first use in this function)
 arch/x86/mm/srat_64.c:141: error: (Each undeclared identifier is reported only once
 arch/x86/mm/srat_64.c:141: error: for each function it appears in.)

A couple of UV definitions were moved to asm/uv/uv.h, but srat_64.c did
not include that header. Add it.
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: cleanup

Now that it's unified, move the (SMP) TLB flushing code from arch/x86/kernel/
to arch/x86/mm/, where it belongs logically.
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Conflicts:
	arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
	arch/x86/kernel/tlb_32.c

Merge it here because both the cpumask changes and the ongoing percpu
work is touching the TLB code. The percpu changes take precedence, as
they eliminate tlb_32.c altogether.
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: file rename

tlb_64.c is now the tlb code for both 32 and 64.  Rename it to tlb.c.
Signed-off-by: NTejun Heo <tj@kernel.org>

Impact: less contention when issuing invalidate IPI, cleanup

Make x86_32 use the same tlb code as 64bit.  The 64bit code uses
multiple IPI vectors for tlb shootdown to reduce contention.  This
patch makes x86_32 allocate the same 8 IPIs as x86_64 and share the
code paths.

Note that the usage of asmlinkage is inconsistent for x86_32 and 64
and calls for further cleanup.  This has been noted with a FIXME
comment in tlb_64.c.
Signed-off-by: NTejun Heo <tj@kernel.org>

Impact: clean up, ipi vector number reordering for x86_32

Make the following changes to prepare for tlb merge.

* reorder x86_32 ip vectors

* adjust tlb_32.c and tlb_64.c such that their logics coincide exactly
	- on spurious invalidate ipi, tlb_32 acks the irq
	- tlb_64 now has proper memory barriers around clearing
          flush_cpumask (no change in generated code)

* unexport flush_tlb_page from tlb_32.c, there's no user

* use unsigned int for cpu id

* drop unnecessary includes from tlb_64.c
Signed-off-by: NTejun Heo <tj@kernel.org>

Impact: cleanup

Make the following uv related cleanups.

* collect visible uv related definitions and interfaces into uv/uv.h
  and use it.  this cleans up the messy situation where on 64bit, uv
  is defined properly, on 32bit generic it's dummy and on the rest
  undefined.  after this clean up, uv is defined on 64 and dummy on
  32.

* update uv_flush_tlb_others() such that it takes cpumask of
  to-be-flushed cpus as argument, instead of that minus self, and
  returns yet-to-be-flushed cpumask, instead of modifying the passed
  in parameter.  this interface change will ease dummy implementation
  of uv_flush_tlb_others() and makes uv tlb flush related stuff
  defined in tlb_uv proper.
Signed-off-by: NTejun Heo <tj@kernel.org>

Impact: cleanup, better irq_regs code generation for x86_64

Make 64-bit use the same optimizations as 32-bit.
Signed-off-by: NBrian Gerst <brgerst@gmail.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

Impact: cleanup

tj: * changed cpu to unsigned as was done on mmu_context_64.h as cpu
      id is officially unsigned int
    * added missing ';' to 32bit version of deactivate_mm()
Signed-off-by: NBrian Gerst <brgerst@gmail.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

Impact: cleanup

%fs is currently set to __KERNEL_DS at boot, and conditionally
switched to __KERNEL_PERCPU for secondary cpus.  Instead, initialize
GDT_ENTRY_PERCPU to the same attributes as GDT_ENTRY_KERNEL_DS and
set %fs to __KERNEL_PERCPU unconditionally.
Signed-off-by: NBrian Gerst <brgerst@gmail.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

Impact: slightly better code generation for percpu_to_op()

The processor will sign-extend 32-bit immediate values in 64-bit
operations.  Use the 'e' constraint ("32-bit signed integer constant,
or a symbolic reference known to fit that range") for 64-bit constants.
Signed-off-by: NBrian Gerst <brgerst@gmail.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

Impact: cleanup && more compact percpu area layout with future changes

Move 64-bit GDT to page-aligned section and clean up comment
formatting.
Signed-off-by: NBrian Gerst <brgerst@gmail.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

Impact: cleanup

In switch_to(), instead of taking offset to irq_stack_union.stack,
make it a proper percpu access using __percpu_arg() and per_cpu_var().
Signed-off-by: NTejun Heo <tj@kernel.org>

Impact: cleanup, restructure code to improve assembly

gcc isn't _all_ that smart about spilling registers to stack or reusing
stack slots, even with branch annotations. do_page_fault contained a lot
of functionality, so split unlikely paths into their own functions, and
mark them as noinline just to be sure. I consider this actually to be
somewhat of a cleanup too: the main function now contains about half
the number of lines so the normal path is easier to read, while the error
cases are also nicely split away.

Also, ensure the order of arguments to functions is always the same: regs,
addr, error_code. This can reduce code size a tiny bit, and just looks neater
too.

And add a couple of branch annotations.

Before:
  do_page_fault:
          subq    $360, %rsp      #,

After:
  do_page_fault:
          subq    $56, %rsp       #,

bloat-o-meter:
  add/remove: 8/0 grow/shrink: 0/1 up/down: 2222/-1680 (542)
  function                                     old     new   delta
  __bad_area_nosemaphore                         -     506    +506
  no_context                                     -     474    +474
  vmalloc_fault                                  -     424    +424
  spurious_fault                                 -     358    +358
  mm_fault_error                                 -     272    +272
  bad_area_access_error                          -      89     +89
  bad_area                                       -      89     +89
  bad_area_nosemaphore                           -      10     +10
  do_page_fault                               2464     784   -1680

Yes, the total size increases by 542 bytes, due to the extra function calls.
But these will very rarely be called (except for vmalloc_fault) in a normal
workload. Importantly, do_page_fault is less than 1/3rd it's original size,
and touches far less stack.

Existing gotos and branch hints did move a lot of the infrequently used text
out of the fastpath, but that's even further improved after this patch.
Signed-off-by: NNick Piggin <npiggin@suse.de>
Acked-by: NLinus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: fix bootup crash

The cpumask is now passed in as a reference to mm->cpu_vm_mask, not on
the stack - hence it is not constant anymore during the TLB flush.

That way it could race and some static sanity checks would trigger:

[  238.154287] ------------[ cut here ]------------
[  238.156039] kernel BUG at arch/x86/kernel/tlb_32.c:130!
[  238.156039] invalid opcode: 0000 [#1] SMP
[  238.156039] last sysfs file: /sys/class/net/eth2/address
[  238.156039] Modules linked in:
[  238.156039]
[  238.156039] Pid: 6493, comm: ifup-eth Not tainted (2.6.29-rc2-tip #1) P4DC6
[  238.156039] EIP: 0060:[<c0118f87>] EFLAGS: 00010202 CPU: 2
[  238.156039] EIP is at native_flush_tlb_others+0x35/0x158
[  238.156039] EAX: c0ef972c EBX: f6143301 ECX: 00000000 EDX: 00000000
[  238.156039] ESI: f61433a8 EDI: f6143200 EBP: f34f3e00 ESP: f34f3df0
[  238.156039]  DS: 007b ES: 007b FS: 00d8 GS: 0000 SS: 0068
[  238.156039] Process ifup-eth (pid: 6493, ti=f34f2000 task=f399ab00 task.ti=f34f2000)
[  238.156039] Stack:
[  238.156039]  ffffffff f61433a8 ffffffff f6143200 f34f3e18 c0118e9c 00000000 f6143200
[  238.156039]  f61433a8 f5bec738 f34f3e28 c0119435 c2b5b830 f6143200 f34f3e34 c01c2dc3
[  238.156039]  bffd9000 f34f3e60 c01c3051 00000000 ffffffff f34f3e4c 00000000 00000071
[  238.156039] Call Trace:
[  238.156039]  [<c0118e9c>] ? flush_tlb_others+0x52/0x5b
[  238.156039]  [<c0119435>] ? flush_tlb_mm+0x7f/0x8b
[  238.156039]  [<c01c2dc3>] ? tlb_finish_mmu+0x2d/0x55
[  238.156039]  [<c01c3051>] ? exit_mmap+0x124/0x170
[  238.156039]  [<c013e965>] ? mmput+0x40/0xf5
[  238.156039]  [<c01e4788>] ? flush_old_exec+0x640/0x94b
[  238.156039]  [<c01ddb4e>] ? fsnotify_access+0x37/0x39
[  238.156039]  [<c01e3435>] ? kernel_read+0x39/0x4b
[  238.156039]  [<c021bc8a>] ? load_elf_binary+0x4a1/0x11bb
[  238.156039]  [<c01c0af9>] ? might_fault+0x51/0x9c
[  238.156039]  [<c010a2cc>] ? paravirt_read_tsc+0x20/0x4f
[  238.156039]  [<c010a406>] ? native_sched_clock+0x5d/0x60
[  238.156039]  [<c01e2fda>] ? search_binary_handler+0xab/0x2c4
[  238.156039]  [<c021b7e9>] ? load_elf_binary+0x0/0x11bb
[  238.156039]  [<c04ae9a5>] ? _raw_read_unlock+0x21/0x46
[  238.156039]  [<c021b7e9>] ? load_elf_binary+0x0/0x11bb
[  238.156039]  [<c01e2fe1>] ? search_binary_handler+0xb2/0x2c4
[  238.156039]  [<c01e4076>] ? do_execve+0x21c/0x2ee
[  238.156039]  [<c01029b7>] ? sys_execve+0x51/0x8c
[  238.156039]  [<c0103eaf>] ? sysenter_do_call+0x12/0x43

Fix it by not assuming that the cpumask is constant.
Signed-off-by: NIngo Molnar <mingo@elte.hu>