Impact: bug fix

Don't use per_cpu_offset() to determine if it valid to access a
per-cpu variable for a given cpu number.  It is not a valid assumption
on x86-64 anymore. Use cpu_possible() instead.
Signed-off-by: NBrian Gerst <brgerst@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: cleanup and bug fix

Use the linker to create symbols for certain per-cpu variables
that are offset by __per_cpu_load.  This allows the removal of
the runtime fixup of the GDT pointer, which fixes a bug with
resume reported by Jiri Slaby.
Reported-by: NJiri Slaby <jirislaby@gmail.com>
Signed-off-by: NBrian Gerst <brgerst@gmail.com>
Acked-by: NJiri Slaby <jirislaby@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: bug fix

IA-64 needs to put percpu data in the seperate section even on UP.
Fixes regression caused by "percpu: refactor percpu.h"
Signed-off-by: NBrian Gerst <brgerst@gmail.com>
Acked-by: NTony Luck <tony.luck@intel.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: fix link failure on certain toolchains with specific configs

Recent percpu change made x86_64 split .data.init section into three
separate segments - data.init, percpu and data.init2.  data.init2 gets
.data.nosave and .bss.* and is followed by .notes segment.  Depending
on configuration both segments might contain no data, in which case
the tool chain makes the section header to contain offset beyond the
end of the file.

modpost isn't too happy about it and fails build - as reported by
Pawel Dziekonski:

    Building modules, stage 2.
    MODPOST 416 modules
    FATAL: vmlinux is truncated. sechdrs[i].sh_offset=10354688 >
    sizeof(*hrd)=64
    make[1]: *** [__modpost] Error 1

Teach modpost that NOBITS section may point beyond the end of the file
and that .modinfo can't be NOBITS.
Reported-by: NPawel Dziekonski <dzieko@gmail.com>
Signed-off-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Make the following style cleanups:

* drop unnecessary //#include from xen-asm_32.S
* compulsive adding of space after comma
* reformat multiline comments
Signed-off-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Enable the use of the direct vcpu-access operations on 64-bit.
Signed-off-by: NJeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: NH. Peter Anvin <hpa@linux.intel.com>

Now that x86-64 has directly accessible percpu variables, it can also
implement the direct versions of these operations, which operate on a
vcpu_info structure directly embedded in the percpu area.

In fact, the 64-bit versions are more or less identical, and so can be
shared.  The only two differences are:
 1. xen_restore_fl_direct takes its argument in eax on 32-bit, and rdi on 64-bit.
    Unfortunately it isn't possible to directly refer to the 2nd lsb of rdi directly
    (as you can with %ah), so the code isn't quite as dense.
 2. check_events needs to variants to save different registers.
Signed-off-by: NJeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: NH. Peter Anvin <hpa@linux.intel.com>

We need to access percpu data fairly early, so set up the percpu
registers as soon as possible.  We only need to load the appropriate
segment register.  We already have a GDT, but its hard to change it
early because we need to manipulate the pagetable to do so, and that
hasn't been set up yet.

Also, set the kernel stack when bringing up secondary CPUs.  If we
don't they all end up sharing the same stack...
Signed-off-by: NJeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: NH. Peter Anvin <hpa@linux.intel.com>

Moving the mmu code from enlighten.c to mmu.c inadvertently broke the
32-bit build.  Fix it.
Signed-off-by: NJeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: NH. Peter Anvin <hpa@linux.intel.com>

Impact: Bug fix

A hunk went missing in the original patch, and callee-save callsites were
not marked as returning the upper 32-bit of result, causing Badness.
Signed-off-by: NJeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>

Impact: fix regression with kexec with vmlinux

Split data.init into data.init, percpu, data.init2 sections
instead of let data.init wrap percpu secion.

Thus kexec loading will be happy, because sections will not
overlap.

Before the patch we have:

Elf file type is EXEC (Executable file)
Entry point 0x200000
There are 6 program headers, starting at offset 64

Program Headers:
  Type           Offset             VirtAddr           PhysAddr
                 FileSiz            MemSiz              Flags  Align
  LOAD           0x0000000000200000 0xffffffff80200000 0x0000000000200000
                 0x0000000000ca6000 0x0000000000ca6000  R E    200000
  LOAD           0x0000000000ea6000 0xffffffff80ea6000 0x0000000000ea6000
                 0x000000000014dfe0 0x000000000014dfe0  RWE    200000
  LOAD           0x0000000001000000 0xffffffffff600000 0x0000000000ff4000
                 0x0000000000000888 0x0000000000000888  RWE    200000
  LOAD           0x00000000011f6000 0xffffffff80ff6000 0x0000000000ff6000
                 0x0000000000073086 0x0000000000a2d938  RWE    200000
  LOAD           0x0000000001400000 0x0000000000000000 0x000000000106a000
                 0x00000000001d2ce0 0x00000000001d2ce0  RWE    200000
  NOTE           0x00000000009e2c1c 0xffffffff809e2c1c 0x00000000009e2c1c
                 0x0000000000000024 0x0000000000000024         4

 Section to Segment mapping:
  Segment Sections...
   00     .text .notes __ex_table .rodata __bug_table .pci_fixup .builtin_fw __ksymtab __ksymtab_gpl __ksymtab_strings __init_rodata __param
   01     .data .init.rodata .data.cacheline_aligned .data.read_mostly
   02     .vsyscall_0 .vsyscall_fn .vsyscall_gtod_data .vsyscall_1 .vsyscall_2 .vgetcpu_mode .jiffies
   03     .data.init_task .smp_locks .init.text .init.data .init.setup .initcall.init .con_initcall.init .x86_cpu_dev.init .altinstructions .altinstr_replacement .exit.text .init.ramfs .bss
   04     .data.percpu
   05     .notes

After patch we've got:

Elf file type is EXEC (Executable file)
Entry point 0x200000
There are 7 program headers, starting at offset 64

Program Headers:
  Type           Offset             VirtAddr           PhysAddr
                 FileSiz            MemSiz              Flags  Align
  LOAD           0x0000000000200000 0xffffffff80200000 0x0000000000200000
                 0x0000000000ca6000 0x0000000000ca6000  R E    200000
  LOAD           0x0000000000ea6000 0xffffffff80ea6000 0x0000000000ea6000
                 0x000000000014dfe0 0x000000000014dfe0  RWE    200000
  LOAD           0x0000000001000000 0xffffffffff600000 0x0000000000ff4000
                 0x0000000000000888 0x0000000000000888  RWE    200000
  LOAD           0x00000000011f6000 0xffffffff80ff6000 0x0000000000ff6000
                 0x0000000000073086 0x0000000000073086  RWE    200000
  LOAD           0x0000000001400000 0x0000000000000000 0x000000000106a000
                 0x00000000001d2ce0 0x00000000001d2ce0  RWE    200000
  LOAD           0x000000000163d000 0xffffffff8123d000 0x000000000123d000
                 0x0000000000000000 0x00000000007e6938  RWE    200000
  NOTE           0x00000000009e2c1c 0xffffffff809e2c1c 0x00000000009e2c1c
                 0x0000000000000024 0x0000000000000024         4

 Section to Segment mapping:
  Segment Sections...
   00     .text .notes __ex_table .rodata __bug_table .pci_fixup .builtin_fw __ksymtab __ksymtab_gpl __ksymtab_strings __init_rodata __param
   01     .data .init.rodata .data.cacheline_aligned .data.read_mostly
   02     .vsyscall_0 .vsyscall_fn .vsyscall_gtod_data .vsyscall_1 .vsyscall_2 .vgetcpu_mode .jiffies
   03     .data.init_task .smp_locks .init.text .init.data .init.setup .initcall.init .con_initcall.init .x86_cpu_dev.init .altinstructions .altinstr_replacement .exit.text .init.ramfs
   04     .data.percpu
   05     .bss
   06     .notes
Signed-off-by: NYinghai Lu <yinghai@kernel.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Zach says:
> Enable/Disable have no clobbers at all.
> Save clobbers only return value, %eax
> Restore also clobbers nothing.

This is precisely compatible with the calling convention, so we can
just call them directly without wrapping.

(Compile tested only.)
Signed-off-by: NJeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>

Impact: bugfix

In the 32-bit calling convention, %eax:%edx is used to return 64-bit
values.  Don't save and restore %edx around wrapped functions, or they
can't return a full 64-bit result.
Signed-off-by: NJeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>

Impact: fix xen booting

We need to access percpu data fairly early, so set up the percpu
registers as soon as possible.  We only need to load the appropriate
segment register.  We already have a GDT, but its hard to change it
early because we need to manipulate the pagetable to do so, and that
hasn't been set up yet.
Signed-off-by: NJeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

Impact: split out a function, no functional change

Xen needs to be able to access percpu data from very early on.  For
various reasons, it cannot also load the gdt at that time.   It does,
however, have a pefectly functional gdt at that point, so there's no
pressing need to reload the gdt.

Split the function to load the segment registers off, so Xen can call
it directly.
Signed-off-by: NJeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

Impact: cleanup, prepare for xen boot fix.

Xen needs to call this function very early to setup the GDT and
per-cpu segments.  Remove the call to smp_processor_id() and just
pass in the cpu number.
Signed-off-by: NBrian Gerst <brgerst@gmail.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

Impact: fix possible tlb mis-flushing on UV

uv_flush_send_and_wait() should return a pointer if the broadcast
remote tlb shootdown requests fail. That causes the conventional IPI
method of shootdown to be used.
Signed-off-by: NCliff Wickman <cpw@sgi.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

Impact: Fix build when CONFIG_PARAVIRT_DEBUG is enabled

Fix missed convertion to using callee-saved calls for pud_val, which
causes a compile error when CONFIG_PARAVIRT_DEBUG is enabled.
Signed-off-by: NJeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: NH. Peter Anvin <hpa@linux.intel.com>

Impact: Optimization

In the native case, pte_val, make_pte, etc are all just identity
functions, so there's no need to clobber a lot of registers over them.

(This changes the 32-bit callee-save calling convention to return both
EAX and EDX so functions can return 64-bit values.)
Signed-off-by: NJeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>

Impact: Optimization

Functions with the callee save calling convention clobber many fewer
registers than the normal C calling convention.  Implement variants of
PVOP_V?CALL* accordingly.  This only bothers with functions up to 3
args, since functions with more args may as well use the normal
calling convention.
Signed-off-by: NJeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>

Impact: Optimization

One of the problems with inserting a pile of C calls where previously
there were none is that the register pressure is greatly increased.
The C calling convention says that the caller must expect a certain
set of registers may be trashed by the callee, and that the callee can
use those registers without restriction.  This includes the function
argument registers, and several others.

This patch seeks to alleviate this pressure by introducing wrapper
thunks that will do the register saving/restoring, so that the
callsite doesn't need to worry about it, but the callee function can
be conventional compiler-generated code.  In many cases (particularly
performance-sensitive cases) the callee will be in assembler anyway,
and need not use the compiler's calling convention.

Standard calling convention is:
	 arguments	    return	scratch
x86-32	 eax edx ecx	    eax		?
x86-64	 rdi rsi rdx rcx    rax		r8 r9 r10 r11

The thunk preserves all argument and scratch registers.  The return
register is not preserved, and is available as a scratch register for
unwrapped callee code (and of course the return value).

Wrapped function pointers are themselves wrapped in a struct
paravirt_callee_save structure, in order to get some warning from the
compiler when functions with mismatched calling conventions are used.

The most common paravirt ops, both statically and dynamically, are
interrupt enable/disable/save/restore, so handle them first.  This is
particularly easy since their calls are handled specially anyway.

XXX Deal with VMI.  What's their calling convention?
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>

Impact: Optimization

Each asm paravirt-ops call says what registers are available for
clobbering.  This patch makes use of this to selectively save/restore
registers around each pvops call.  In many cases this significantly
shrinks code size.
Signed-off-by: NJeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>

Impact: Fix latent bug

The clobber is trying to say that anything except RDI is available for
clobbering, but actually clobbers everything.  This hasn't mattered
because the clobbers were basically ignored, but subsequent patches
will rely on them.
Signed-off-by: NJeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>

Impact: Optimization

Several paravirt ops implementations simply return their arguments,
the most obvious being the make_pte/pte_val class of operations on
native.

On 32-bit, the identity function is literally a no-op, as the calling
convention uses the same registers for the first argument and return.
On 64-bit, it can be implemented with a single "mov".

This patch adds special identity functions for 32 and 64 bit argument,
and machinery to recognize them and replace them with either nops or a
mov as appropriate.

At the moment, the only users for the identity functions are the
pagetable entry conversion functions.

The result is a measureable improvement on pagetable-heavy benchmarks
(2-3%, reducing the pvops overhead from 5 to 2%).
Signed-off-by: NJeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>

Impact: Cleanup

Move remaining mmu-related stuff into mmu.c.
A general cleanup, and lay the groundwork for later patches.
Signed-off-by: NJeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>

Impact: fix linker screwup on x86_32

Recent x86_64 zerobased patches introduced PERCPU_VADDR() to put
.data.percpu to a predefined address and re-defined PERCPU() in terms
of it.  The new macro defined one extra symbol, __per_cpu_load, for
LMA of the section so that the init data could be accessed.  This new
symbol introduced the following problems to x86_32.

1. If __per_cpu_load is defined outside of .data.percpu as an absolute
   symbol, relocation generation for relocatable kernel fails due to
   absolute relocation.

2. If __per_cpu_load is put inside .data.percpu with absolute address
   assignment to work around #1, linker gets confused and under
   certain configurations ends up relocating the symbol against
   .data.percpu such that the load address gets added on top of
   already set load address.

As x86_32 doesn't use predefined address for .data.percpu, there's no
need for it to care about the possibility of __per_cpu_load being
different from __per_cpu_start.

This patch defines PERCPU() separately so that __per_cpu_load is
defined inside .data.percpu so that everything is ordinary
linking-wise.
Signed-off-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Commit de33c8db ("Fix OOPS in
mmap_region() when merging adjacent VM_LOCKED file segments") unified
the vma merging of anonymous and file maps to just one place, which
simplified the code and fixed a use-after-free bug that could cause an
oops.

But by doing the merge opportunistically before even having called
->mmap() on the file method, it now compares two different 'vm_flags'
values: the pre-mmap() value of the new not-yet-formed vma, and previous
mappings of the same file around it.

And in doing so, it refused to merge the common file case, which adds a
marker to say "I can be made non-linear".

This fixes it by just adding a set of flags that don't have to match,
because we know they are ok to merge.  Currently it's only that single
VM_CAN_NONLINEAR flag, but at least conceptually there could be others
in the future.
Reported-and-acked-by: NHugh Dickins <hugh@veritas.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Greg KH <gregkh@suse.de>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Conflicts:
	kernel/irq/handle.c

* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
  ext4: Remove bogus BUG() check in ext4_bmap()
  ext4: Fix building with EXT4FS_DEBUG
  ext4: Initialize the new group descriptor when resizing the filesystem
  ext4: Fix ext4_free_blocks() w/o a journal when files have indirect blocks
  jbd2: On a __journal_expect() assertion failure printk "JBD2", not "EXT3-fs"
  ext3: Add sanity check to make_indexed_dir
  ext4: Add sanity check to make_indexed_dir
  ext4: only use i_size_high for regular files
  ext4: fix wrong use of do_div

* 'for-linus' of git://git.kernel.dk/linux-2.6-block:
  cfq-iosched: Allow RT requests to pre-empt ongoing BE timeslice
  block: add sysfs file for controlling io stats accounting
  Mark mandatory elevator functions in the biodoc.txt
  include/linux: Add bsg.h to the Kernel exported headers
  block: silently error an unsupported barrier bio
  block: Fix documentation for blkdev_issue_flush()
  block: add bio_rw_flagged() for testing bio->bi_rw
  block: seperate bio/request unplug and sync bits
  block: export SSD/non-rotational queue flag through sysfs
  Fix small typo in bio.h's documentation
  block: get rid of the manual directory counting in blktrace
  block: Allow empty integrity profile
  block: Remove obsolete BUG_ON
  block: Don't verify integrity metadata on read error

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6: (29 commits)
  tulip: fix 21142 with 10Mbps without negotiation
  drivers/net/skfp: if !capable(CAP_NET_ADMIN): inverted logic
  gianfar: Fix Wake-on-LAN support
  smsc911x: timeout reaches -1
  smsc9420: fix interrupt signalling test failures
  ucc_geth: Change uec phy id to the same format as gianfar's
  wimax: fix build issue when debugfs is disabled
  netxen: fix memory leak in drivers/net/netxen_nic_init.c
  tun: Add some missing TUN compat ioctl translations.
  ipv4: fix infinite retry loop in IP-Config
  net: update documentation ip aliases
  net: Fix OOPS in skb_seq_read().
  net: Fix frag_list handling in skb_seq_read
  netxen: revert jumbo ringsize
  ath5k: fix locking in ath5k_config
  cfg80211: print correct intersected regulatory domain
  cfg80211: Fix sanity check on 5 GHz when processing country IE
  iwlwifi: fix kernel oops when ucode DMA memory allocation failure
  rtl8187: Fix error in setting OFDM power settings for RTL8187L
  mac80211: remove Michael Wu as maintainer
  ...

This fixes a crash observed when non-existant enable_ms function is
called for jsm driver.
Signed-off-by: NScott Kilau <Scott.Kilau@digi.com>
Signed-off-by: NPaul Larson <pl@linux.vnet.ibm.com>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This patch adds the ability to pre-empt an ongoing BE timeslice when a RT
request is waiting for the current timeslice to complete. This reduces the
wait time to disk for RT requests from an upper bound of 4 (current value
of cfq_quantum) to 1 disk request.

Applied Jens' suggeested changes to avoid the rb lookup and use !cfq_class_rt()
and retested.

Latency(secs) for the RT task when doing sequential reads from 10G file.
                       | only RT | RT + BE | RT + BE + this patch
small (512 byte) reads | 143     | 163     | 145
large (1Mb) reads      | 142     | 158     | 146
Signed-off-by: NDivyesh Shah <dpshah@google.com>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

This allows us to turn off disk stat accounting completely, for the cases
where the 0.5-1% reduction in system time is important.
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

biodoc.txt mentions that elevator functions marked with * are mandatory, but
no function is marked with *. Mark the 3 functions which should be
implemented by any io scheduler.
Signed-off-by: NNikanth Karthikesan <knikanth@suse.de>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>