25 Sep, 2009
1 commit
-
The old RW_DATA_SECTION had INIT_TASK_DATA (which was
more-than-PAGE_SIZE-aligned), followed by a bunch of small alignment
stuff, followed by more PAGE_SIZE-aligned stuff, so you wasted memory
in the middle of .data re-aligning back up to PAGE_SIZE.This patch sorts the sections by alignment requirements, which should
pack them essentially optimally.Signed-off-by: Tim Abbott
Reviewed-by: Sam Ravnborg
Signed-off-by: Linus Torvalds
18 Sep, 2009
1 commit
-
Merge reason: Pick up kernel/softirq.c update for dependent fix.
Signed-off-by: Ingo Molnar
13 Sep, 2009
1 commit
-
__start_mcount_loc[] is unused after init, yet occupies RAM forever
as part of .rodata. 152kiB is typical on a 64-bit architecture. Instead,
__start_mcount_loc should be in the interval [__init_begin, __init_end)
so that the space is reclaimed after init.__start_mcount_loc[] is generated during the load portion
of kernel build, and is used only by ftrace_init(). ftrace_init is declared
'__init' and is in .init.text, which is freed after init.
__start_mcount_loc is placed into .rodata by a call to MCOUNT_REC inside
the RO_DATA macro of include/asm-generic/vmlinux.lds.h. The array *is*
read-only, but more importantly it is not used after init. So the call to
MCOUNT_REC should be moved from RO_DATA to INIT_DATA.This patch has been tested on x86_64 with CONFIG_DEBUG_PAGEALLOC=y
which verifies that the address range never is accessed after init.Signed-off-by: John Reiser
LKML-Reference:
Signed-off-by: Steven Rostedt
14 Aug, 2009
1 commit
-
Conflicts:
arch/sparc/kernel/smp_64.c
arch/x86/kernel/cpu/perf_counter.c
arch/x86/kernel/setup_percpu.c
drivers/cpufreq/cpufreq_ondemand.c
mm/percpu.cConflicts in core and arch percpu codes are mostly from commit
ed78e1e078dd44249f88b1dd8c76dafb39567161 which substituted many
num_possible_cpus() with nr_cpu_ids. As for-next branch has moved all
the first chunk allocators into mm/percpu.c, the changes are moved
from arch code to mm/percpu.c.Signed-off-by: Tejun Heo
18 Jul, 2009
1 commit
-
The BSS section macros in vmlinux.lds.h currently place the .sbss
input section outside the bounds of [__bss_start, __bss_end]. On all
architectures except for microblaze that handle both .sbss and
__bss_start/__bss_end, this is wrong: the .sbss input section is
within the range [__bss_start, __bss_end]. Relatedly, the example
code at the top of the file actually has __bss_start/__bss_end defined
twice; I believe the right fix here is to define them in the
BSS_SECTION macro but not in the BSS macro.Another problem with the current macros is that several
architectures have an ALIGN(4) or some other small number just before
__bss_stop in their linker scripts. The BSS_SECTION macro currently
hardcodes this to 4; while it should really be an argument. It also
ignores its sbss_align argument; fix that.mn10300 is the only user at present of any of the macros touched by
this patch. It looks like mn10300 actually was incorrectly converted
to use the new BSS() macro (the alignment of 4 prior to conversion was
a __bss_stop alignment, but the argument to the BSS macro is a start
alignment). So fix this as well.I'd like acks from Sam and David on this one. Also CCing Paul, since
he has a patch from me which will need to be updated to use
BSS_SECTION(0, PAGE_SIZE, 4) once this gets merged.Signed-off-by: Tim Abbott
Cc: Paul Mundt
Cc: David Howells
Signed-off-by: Sam Ravnborg
09 Jul, 2009
1 commit
-
Discarded sections in different archs share some commonality but have
considerable differences. This led to linker script for each arch
implementing its own /DISCARD/ definition, which makes maintaining
tedious and adding new entries error-prone.This patch makes all linker scripts to move discard definitions to the
end of the linker script and use the common DISCARDS macro. As ld
uses the first matching section definition, archs can include default
discarded sections by including them earlier in the linker script.ia64 is notable because it first throws away some ia64 specific
subsections and then include the rest of the sections into the final
image, so those sections must be discarded before the inclusion.defconfig compile tested for x86, x86-64, powerpc, powerpc64, ia64,
alpha, sparc, sparc64 and s390. Michal Simek tested microblaze.Signed-off-by: Tejun Heo
Acked-by: Paul Mundt
Acked-by: Mike Frysinger
Tested-by: Michal Simek
Cc: linux-arch@vger.kernel.org
Cc: Michal Simek
Cc: microblaze-uclinux@itee.uq.edu.au
Cc: Sam Ravnborg
Cc: Tony Luck
05 Jul, 2009
1 commit
-
* git://git.kernel.org/pub/scm/linux/kernel/git/sam/kbuild-fixes:
kbuild: finally remove the obsolete variable $TOPDIR
gitignore: ignore scripts/ihex2fw
Kbuild: Disable the -Wformat-security gcc flag
gitignore: ignore gcov output files
kbuild: deb-pkg ship changelog
Add new __init_task_data macro to be used in arch init_task.c files.
asm-generic/vmlinux.lds.h: shuffle INIT_TASK* macro names in vmlinux.lds.h
Add new macros for page-aligned data and bss sections.
asm-generic/vmlinux.lds.h: Fix up RW_DATA_SECTION definition.
04 Jul, 2009
1 commit
-
Pull linus#master to merge PER_CPU_DEF_ATTRIBUTES and alpha build fix
changes. As alpha in percpu tree uses 'weak' attribute instead of
inline assembly, there's no need for __used attribute.Conflicts:
arch/alpha/include/asm/percpu.h
arch/mn10300/kernel/vmlinux.lds.S
include/linux/percpu-defs.h
01 Jul, 2009
1 commit
-
The ctors section for each object file is eight byte aligned (on 64 bit).
However the __ctors_start symbol starts at an arbitrary address dependent
on the size of the previous sections.Therefore the linker may add some zeroes after __ctors_start to make sure
the ctors contents are properly aligned. However the extra zeroes at the
beginning aren't expected by the code. When walking the functions
pointers contained in there and extra zeroes are added this may result in
random jumps. So make sure that the __ctors_start symbol is always
aligned as well.Fixes this crash on an allyesconfig on s390:
[ 0.582482] Kernel BUG at 0000000000000012 [verbose debug info unavailable]
[ 0.582489] illegal operation: 0001 [#1] SMP DEBUG_PAGEALLOC
[ 0.582496] Modules linked in:
[ 0.582501] CPU: 0 Tainted: G W 2.6.31-rc1-dirty #273
[ 0.582506] Process swapper (pid: 1, task: 000000003f218000, ksp: 000000003f2238e8)
[ 0.582510] Krnl PSW : 0704200180000000 0000000000000012 (0x12)
[ 0.582518] R:0 T:1 IO:1 EX:1 Key:0 M:1 W:0 P:0 AS:0 CC:2 PM:0 EA:3
[ 0.582524] Krnl GPRS: 0000000000036727 0000000000000010 0000000000000001 0000000000000001
[ 0.582529] 00000000001dfefa 0000000000000000 0000000000000000 0000000000000040
[ 0.582534] 0000000001fff0f0 0000000001790628 0000000002296048 0000000002296048
[ 0.582540] 00000000020c438e 0000000001786000 0000000002014a66 000000003f223e60
[ 0.582553] Krnl Code:>0000000000000012: 0000 unknown
[ 0.582559] 0000000000000014: 0000 unknown
[ 0.582564] 0000000000000016: 0000 unknown
[ 0.582570] 0000000000000018: 0000 unknown
[ 0.582575] 000000000000001a: 0000 unknown
[ 0.582580] 000000000000001c: 0000 unknown
[ 0.582585] 000000000000001e: 0000 unknown
[ 0.582591] 0000000000000020: 0000 unknown
[ 0.582596] Call Trace:
[ 0.582599] ([] kernel_init+0x622/0x7a0)
[ 0.582607] [] kernel_thread_starter+0x6/0xc
[ 0.582615] [] kernel_thread_starter+0x0/0xc
[ 0.582621] INFO: lockdep is turned off.
[ 0.582624] Last Breaking-Event-Address:
[ 0.582627] [] kernel_init+0x640/0x7a0Cc: Peter Oberparleiter
Cc: Ingo Molnar
Cc: Martin Schwidefsky
Signed-off-by: Heiko Carstens
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
27 Jun, 2009
2 commits
-
We recently added a INIT_TASK(align) in include/asm-generic/vmlinux.lds.h,
but there is already a macro INIT_TASK in include/linux/init_task.h, which
is quite confusing. We should switch the macro in the linker script to
INIT_TASK_DATA. (Sorry that I missed this in reviewing the patch). Since
the macros are new, there is only one user of the INIT_TASK in
vmlinux.lds.h, arch/mn10300/kernel/vmlinux.lds.S.However, we are currently using INIT_TASK_DATA for laying down an entire
.data.init_task section. So rename that to INIT_TASK_DATA_SECTION.I would be worried about changing the meaning of INIT_TASK_DATA, but the
old INIT_TASK_DATA implementation had no users, and in fact if anyone had
tried to use it, it would have failed to compile because it didn't pass
the alignment to the old INIT_TASK.Signed-off-by: Tim Abbott
Cc: David Howells
Cc: Jesper Nilsson -
RW_DATA_SECTION is defined to take 4 different alignment parameters,
while NOSAVE_DATA currently uses a fixed PAGE_SIZE alignment as noted
in the comments.There are presently no in-tree users of this at present, and I just
stumbled across this while implementing the simplified script on a new
architecture port, which subsequently resulted in a syntax error.Signed-off-by: Paul Mundt
Signed-off-by: Sam Ravnborg
24 Jun, 2009
1 commit
-
x86 throws away .discard section but no other archs do. Also,
.discard is not thrown away while linking modules. Make every arch
and module linking throw it away. This will be used to define dummy
variables for percpu declarations and definitions.This patch is based on Ivan Kokshaysky's alpha percpu patch.
[ Impact: always throw away everything in .discard ]
Signed-off-by: Tejun Heo
Cc: Ivan Kokshaysky
Cc: Richard Henderson
Cc: Russell King
Cc: Haavard Skinnemoen
Cc: Bryan Wu
Cc: Mikael Starvik
Cc: Jesper Nilsson
Cc: David Howells
Cc: Yoshinori Sato
Cc: Tony Luck
Cc: Hirokazu Takata
Cc: Geert Uytterhoeven
Cc: Michal Simek
Cc: Ralf Baechle
Cc: Kyle McMartin
Cc: Benjamin Herrenschmidt
Cc: Paul Mackerras
Cc: Martin Schwidefsky
Cc: Heiko Carstens
Cc: Paul Mundt
Cc: David S. Miller
Cc: Jeff Dike
Cc: Chris Zankel
Cc: Rusty Russell
Cc: Ingo Molnar
23 Jun, 2009
1 commit
-
In asm-generic/vmlinux.lds.h, name INIT_RAM_FS consistently, no matter the
setting of CONFIG_BLK_DEV_INITRD. This corrects:commit ef53dae8658cf0e93d380983824a661067948d87
Author: Sam Ravnborg
Date: Sun Jun 7 20:46:37 2009 +0200
Subject: Improve vmlinux.lds.h support for arch specific linker scriptsSigned-off-by: David Howells
Acked-by: Sam Ravnborg
Signed-off-by: Linus Torvalds
19 Jun, 2009
1 commit
-
Call constructors (gcc-generated initcall-like functions) during kernel
start and module load. Constructors are e.g. used for gcov data
initialization.Disable constructor support for usermode Linux to prevent conflicts with
host glibc.Signed-off-by: Peter Oberparleiter
Acked-by: Rusty Russell
Acked-by: WANG Cong
Cc: Sam Ravnborg
Cc: Jeff Dike
Cc: Andi Kleen
Cc: Huang Ying
Cc: Li Wei
Cc: Michael Ellerman
Cc: Ingo Molnar
Cc: Heiko Carstens
Cc: Martin Schwidefsky
Cc: Al Viro
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
15 Jun, 2009
2 commits
-
* 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/sam/kbuild-next: (53 commits)
.gitignore: ignore *.lzma files
kbuild: add generic --set-str option to scripts/config
kbuild: simplify argument loop in scripts/config
kbuild: handle non-existing options in scripts/config
kallsyms: generalize text region handling
kallsyms: support kernel symbols in Blackfin on-chip memory
documentation: make version fix
kbuild: fix a compile warning
gitignore: Add GNU GLOBAL files to top .gitignore
kbuild: fix delay in setlocalversion on readonly source
README: fix misleading pointer to the defconf directory
vmlinux.lds.h update
kernel-doc: cleanup perl script
Improve vmlinux.lds.h support for arch specific linker scripts
kbuild: fix headers_exports with boolean expression
kbuild/headers_check: refine extern check
kbuild: fix "Argument list too long" error for "make headers_check",
ignore *.patch files
Remove bashisms from scripts
menu: fix embedded menu presentation
... -
Updated after review by Tim Abbott.
- Use HEAD_TEXT_SECTION
- Drop use of section-names.h and delete file
- Introduce EXIT_CALLDeleting section-names.h required a few simple
updates of init.hSigned-off-by: Sam Ravnborg
Cc: Tim Abbott
10 Jun, 2009
2 commits
-
To support alingment of the individual architecture specific linker scripts
provide a set of general definitions in vmlinux.lds.hWith these definitions applied the diverse linekr scripts can be reduced
in line count and their readability are improved - IMO.A sample linker script is included to give the preferred
order of the sections for the architectures that do not
have any special requirments.These definitions are also a first step towards eventual
support for -ffunction-sections.
The definitions makes it much easier to do a global
renaming of section names - but the main purpose is
to clean up the linker scripts.Tim Aboot has provided a lot of inputs to improve
the definitions - all faults are mine.Signed-off-by: Sam Ravnborg
Cc: Tim Abbott -
- add .init.rodata to INIT_DATA, and group all initconst flavors
together
- move strings generated from __setup_param() into .init.rodata
- add .*init.rodata to modpost's sets of init sections
- make modpost warn about references between meminit and cpuinit
as well as memexit and cpuexit sections (as CPU and memory
hotplug are independently selectable features)Signed-off-by: Jan Beulich
Signed-off-by: Sam Ravnborg
07 May, 2009
1 commit
-
Merge reason: tracing/core was on a .30-rc1 base and was missing out on
on a handful of tracing fixes present in .30-rc5-almost.Signed-off-by: Ingo Molnar
28 Apr, 2009
1 commit
-
The old refok sections
.text.init.refok
.data.init.refok
.exit.text.refokhave been deprecated since commit
312b1485fb509c9bc32eda28ad29537896658cb8. After the other patches in
this patch series nothing is put in these sections, so clean things up
by eliminating all the remaining references to them.Signed-off-by: Tim Abbott
Acked-by: Sam Ravnborg
Signed-off-by: Linus Torvalds
27 Apr, 2009
1 commit
-
This patch is preparation for replacing all uses of ".head.text" or
".text.head" in the kernel with macros, so that the section name can
later be changed without having to touch a lot of the kernel.Since some linker scripts do more complex things than referencing
HEAD_TEXT, we add a HEAD_TEXT_SECTION macro that just contains the
actual name.I've defined HEAD_TEXT_SECTION in a new header,
include/linux/section-names.h, so that this section name only needs to
appear in one place. I anticipate creating similar macro structures
for a number of other section names.The long-term goal here is to be able to change the kernel's magic
section names to those that are compatible with -ffunction-sections
-fdata-sections. This requires renaming all magic sections with names
of the form ".text.foo".Signed-off-by: Tim Abbott
Signed-off-by: Linus Torvalds
14 Apr, 2009
1 commit
-
Add a new config option, CONFIG_EVENT_TRACING that gets selected
when CONFIG_TRACING is selected and adds everything needed by the stuff
in trace_export - basically all the event tracing support needed by e.g.
bprint, minus the actual events, which are only included if
CONFIG_EVENT_TRACER is selected.So CONFIG_EVENT_TRACER can be used to turn on or off the generated events
(what I think of as the 'event tracer'), while CONFIG_EVENT_TRACING turns
on or off the base event tracing support used by both the event tracer and
the other things such as bprint that can't be configured out.Signed-off-by: Tom Zanussi
Cc: Steven Rostedt
Cc: fweisbec@gmail.com
LKML-Reference:
Signed-off-by: Ingo Molnar
02 Apr, 2009
1 commit
-
Conflicts:
include/linux/slub_def.h
lib/Kconfig.debug
mm/slob.c
mm/slub.c
28 Mar, 2009
1 commit
-
Conflicts:
arch/parisc/kernel/irq.c
arch/x86/include/asm/fixmap_64.h
arch/x86/include/asm/setup.h
kernel/irq/handle.cSemantic merge:
arch/x86/include/asm/fixmap.hSigned-off-by: Ingo Molnar
25 Mar, 2009
1 commit
-
This patch combines Greg Bank's dprintk() work with the existing dynamic
printk patchset, we are now calling it 'dynamic debug'.The new feature of this patchset is a richer /debugfs control file interface,
(an example output from my system is at the bottom), which allows fined grained
control over the the debug output. The output can be controlled by function,
file, module, format string, and line number.for example, enabled all debug messages in module 'nf_conntrack':
echo -n 'module nf_conntrack +p' > /mnt/debugfs/dynamic_debug/control
to disable them:
echo -n 'module nf_conntrack -p' > /mnt/debugfs/dynamic_debug/control
A further explanation can be found in the documentation patch.
Signed-off-by: Greg Banks
Signed-off-by: Jason Baron
Signed-off-by: Greg Kroah-Hartman
13 Mar, 2009
1 commit
-
Impact: new feature
This adds the generic support for syscalls tracing. This is
currently exploited through a devoted tracer but other tracing
engines can use it. (They just have to play with
{start,stop}_ftrace_syscalls() and use the display callbacks
unless they want to override them.)The syscalls prototypes definitions are abused here to steal
some metadata informations:- syscall name, param types, param names, number of params
The syscall addr is not directly saved during this definition
because we don't know if its prototype is available in the
namespace. But we don't really need it. The arch has just to
build a function able to resolve the syscall number to its
metadata struct.The current tracer prints the syscall names, parameters names
and values (and their types optionally). Currently the value is
a raw hex but higher level values diplaying is on my TODO list.Signed-off-by: Frederic Weisbecker
LKML-Reference:
Signed-off-by: Ingo Molnar
10 Mar, 2009
1 commit
09 Mar, 2009
1 commit
-
Impact: fix kernel crash when using trace_printk()
trace_printk_fmt section is defined into the readonly section.
But we do:trace_printk_fmt = fmt;
to fill in that table of format strings - which is not read-only.
Under CONFIG_DEBUG_RODATA=y this crashes ...Cc: Frederic Weisbecker
Cc: Steven Rostedt
Cc: Peter Zijlstra
LKML-Reference:
Signed-off-by: Ingo Molnar
08 Mar, 2009
1 commit
-
…xtedit' into tracing/core
07 Mar, 2009
1 commit
-
Impact: add a generic printk() for tracing, like trace_printk()
trace_bprintk() uses the infrastructure to record events on ring_buffer.
[ fweisbec@gmail.com: ported to latest -tip, made it work if
!CONFIG_MODULES, never free the format strings from modules
because we can't keep track of them and conditionnaly create
the ftrace format strings section (reported by Steven Rostedt) ]Signed-off-by: Lai Jiangshan
Signed-off-by: Frederic Weisbecker
Acked-by: Steven Rostedt
LKML-Reference:
Signed-off-by: Ingo Molnar
06 Mar, 2009
1 commit
-
Conflicts:
arch/x86/Kconfig
block/blktrace.c
kernel/irq/handle.cSemantic conflict:
kernel/trace/blktrace.cSigned-off-by: Ingo Molnar
25 Feb, 2009
1 commit
-
This patch creates the event tracing infrastructure of ftrace.
It will create the files:/debug/tracing/available_events
/debug/tracing/set_eventThe available_events will list the trace points that have been
registered with the event tracer.set_events will allow the user to enable or disable an event hook.
example:
# echo sched_wakeup > /debug/tracing/set_event
Will enable the sched_wakeup event (if it is registered).
# echo "!sched_wakeup" >> /debug/tracing/set_event
Will disable the sched_wakeup event (and only that event).
# echo > /debug/tracing/set_event
Will disable all events (notice the '>')
# cat /debug/tracing/available_events > /debug/tracing/set_event
Will enable all registered event hooks.
Signed-off-by: Steven Rostedt
31 Jan, 2009
1 commit
-
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: Tejun Heo
Signed-off-by: Ingo Molnar
30 Jan, 2009
1 commit
-
This reverts commit 5a611268b69f05262936dd177205acbce4471358.
It is causing occasional boot crashes, caused by certain
linker versions (GNU ld version 2.18.50.0.6-2 20080403) messing up:82dcc000 D __per_cpu_load
c16e6000 A __per_cpu_load_absThe __per_cpu_load value is out of whack. Hpa noticed the following
detail:* (gdb) p/x -(0xc16e6000-0x82dcc000)
* $2 = 0xc16e6000
* I.e. one is the other << 1The two symbols should be equal.
Signed-off-by: Ingo Molnar
26 Jan, 2009
1 commit
-
This patch fixes this linker error:
WARNING: Absolute relocations present
Offset Info Type Sym.Value Sym.Name
c0a4e07d 00e78001 R_386_32 c0ab0000 __per_cpu_loadNow, __per_cpu_load is a section-relative symbol:
c0aa4000 D __per_cpu_load
c0aa4000 A __per_cpu_load_absSigned-off-by: Brian Gerst
Signed-off-by: Ingo Molnar
20 Jan, 2009
2 commits
-
Impact: cleanup
With .data.percpu.first in place, PERCPU_VADDR_PREALLOC() is no longer
necessary. Kill it.Signed-off-by: Tejun Heo
-
Impact: cleanup
Refactor the DEFINE_PER_CPU_* macros and add .data.percpu.first
section.Signed-off-by: Brian Gerst
Signed-off-by: Tejun Heo
17 Jan, 2009
1 commit
-
The newly added PERCPU_*() macros define and use __per_cpu_load but
VMLINUX_SYMBOL() was missing from usages causing build failures on
archs where linker visible symbol is different from C symbols
(e.g. blackfin).Signed-off-by: Tejun Heo
16 Jan, 2009
2 commits
-
[ Based on original patch from Christoph Lameter and Mike Travis. ]
Currently pdas and percpu areas are allocated separately. %gs points
to local pda and percpu area can be reached using pda->data_offset.
This patch folds pda into percpu area.Due to strange gcc requirement, pda needs to be at the beginning of
the percpu area so that pda->stack_canary is at %gs:40. To achieve
this, a new percpu output section macro - PERCPU_VADDR_PREALLOC() - is
added and used to reserve pda sized chunk at the start of the percpu
area.After this change, for boot cpu, %gs first points to pda in the
data.init area and later during setup_per_cpu_areas() gets updated to
point to the actual pda. This means that setup_per_cpu_areas() need
to reload %gs for CPU0 while clearing pda area for other cpus as cpu0
already has modified it when control reaches setup_per_cpu_areas().This patch also removes now unnecessary get_local_pda() and its call
sites.A lot of this patch is taken from Mike Travis' "x86_64: Fold pda into
per cpu area" patch.Signed-off-by: Tejun Heo
Signed-off-by: Ingo Molnar -
[ Based on original patch from Christoph Lameter and Mike Travis. ]
This patch makes percpu symbols zerobased on x86_64 SMP by adding
PERCPU_VADDR() to vmlinux.lds.h which helps setting explicit vaddr on
the percpu output section and using it in vmlinux_64.lds.S. A new
PHDR is added as existing ones cannot contain sections near address
zero. PERCPU_VADDR() also adds a new symbol __per_cpu_load which
always points to the vaddr of the loaded percpu data.init region.The following adjustments have been made to accomodate the address
change.* code to locate percpu gdt_page in head_64.S is updated to add the
load address to the gdt_page offset.* __per_cpu_load is used in places where access to the init data area
is necessary.* pda->data_offset is initialized soon after C code is entered as zero
value doesn't work anymore.This patch is mostly taken from Mike Travis' "x86_64: Base percpu
variables at zero" patch.Signed-off-by: Tejun Heo
Signed-off-by: Ingo Molnar