KASan uses constructors for initializing redzones for global variables.
Globals instrumentation in GCC 4.9.2 produces constructors with priority
(.init_array.00099)

Currently kernel ignores such constructors.  Only constructors with
default priority supported (.init_array)

This patch adds support for constructors with priorities.  For kernel
image we put pointers to constructors between __ctors_start/__ctors_end
and do_ctors() will call them on start up.  For modules we merge
.init_array.* sections into resulting .init_array.  Module code properly
handles constructors in .init_array section.
Signed-off-by: NAndrey Ryabinin <a.ryabinin@samsung.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Konstantin Serebryany <kcc@google.com>
Cc: Dmitry Chernenkov <dmitryc@google.com>
Signed-off-by: NAndrey Konovalov <adech.fo@gmail.com>
Cc: Yuri Gribov <tetra2005@gmail.com>
Cc: Konstantin Khlebnikov <koct9i@gmail.com>
Cc: Sasha Levin <sasha.levin@oracle.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

IOMMU drivers must be initialised before any of their upstream devices,
otherwise the relevant iommu_ops won't be configured for the bus in
question. To solve this, a number of IOMMU drivers use initcalls to
initialise the driver before anything has a chance to be probed.

Whilst this solves the immediate problem, it leaves the job of probing
the IOMMU completely separate from the iommu_ops to configure the IOMMU,
which are called on a per-bus basis and require the driver to figure out
exactly which instance of the IOMMU is being requested. In particular,
the add_device callback simply passes a struct device to the driver,
which then has to parse firmware tables or probe buses to identify the
relevant IOMMU instance.

This patch takes the first step in addressing this problem by adding an
early initialisation pass for IOMMU drivers, giving them the ability to
store some per-instance data in their iommu_ops structure and store that
in their of_node. This can later be used when parsing OF masters to
identify the IOMMU instance in question.
Acked-by: NArnd Bergmann <arnd@arndb.de>
Acked-by: NJoerg Roedel <jroedel@suse.de>
Acked-by: NMarek Szyprowski <m.szyprowski@samsung.com>
Tested-by: NRobin Murphy <robin.murphy@arm.com>
Signed-off-by: NWill Deacon <will.deacon@arm.com>

This patch changes the __init_end address to a
page align address, so that free_initmem() can
free the whole .init section, because if the end
address is not page aligned, it will round down to
a page align address, then the tail unligned page
will not be freed.
Signed-off-by: Nwang <yalin.wang2010@gmail.com>
Acked-by: NCatalin Marinas <catalin.marinas@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

This fixes a typo that named the read_mostly section of percpu as
readmostly. It works fine with SMP because the linker script specifies
.data..percpu..readmostly. However, UP kernel builds don't have percpu
sections defined and the non-percpu version of the section is called
data..read_mostly, so .data..readmostly will float around and may break
things unexpectedly.

Looking at the original change that introduced data..percpu..readmostly
(commit c957ef2c), it looks like this
was the original intention.

Tested: Built UP kernel and confirmed the sections got merged.

- Before the patch:
$ objdump -h vmlinux.o  | grep '\.data\.\.read.*mostly'
38 .data..read_mostly 00004418  0000000000000000  0000000000000000  00431ac0  2**6
50 .data..readmostly 00000014  0000000000000000  0000000000000000  00444000  2**3

- After the patch:
$ objdump -h vmlinux.o  | grep '\.data\.\.read.*mostly'
38 .data..read_mostly 00004438  0000000000000000  0000000000000000  00431ac0  2**6
Signed-off-by: NZhengyu He <hzy@google.com>
Signed-off-by: NFilipe Brandenburger <filbranden@google.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

Add pci_fixup_suspend_late as a new pci_fixup_pass. The pass is called
from suspend_noirq and poweroff_noirq. Using the same pass for suspend
and hibernate is consistent with resume_early which is called by
resume_noirq and restore_noirq.

The new quirk pass is required for Thunderbolt support on Apple
hardware.
Signed-off-by: NAndreas Noever <andreas.noever@gmail.com>
Acked-by: NBjorn Helgaas <bhelgaas@google.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

This adds the infrastructure to generic earlycon for earlycon setup
using DT. The actual setup is not enabled until a following commit to
add the FDT parsing.
Signed-off-by: NRob Herring <robh@kernel.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Jiri Slaby <jslaby@suse.cz>
Cc: Arnd Bergmann <arnd@arndb.de>
Acked-by: NGrant Likely <grant.likely@linaro.org>

OF table sections all have the same pattern, so create a macro to define
them and insure consistency.
Acked-by: NArnd Bergmann <arnd@arndb.de>
Signed-off-by: NRob Herring <robh@kernel.org>

The cpu_method_of_table is the oddball of the various OF linker sections.
In preparation to have common linker section definitions, align the
cpu_method_of_table with the other definitions for the naming and ending
with a blank struct.
Acked-by: NArnd Bergmann <arnd@arndb.de>
Signed-off-by: NRob Herring <robh@kernel.org>
Cc: Russell King <linux@arm.linux.org.uk>

Make the irqchip OF match table section naming aligned with other
OF match table sections in preparation to have a common definition.
Acked-by: NArnd Bergmann <arnd@arndb.de>
Signed-off-by: NRob Herring <robh@kernel.org>

ARC Linux (not supporting native unaligned access) was failing
to boot because __start_kprobe_blacklist was not aligned.

This was because per generated vmlinux.lds it was emitted right
next to .rodata with strings etc hence could be randomly
unaligned.

Fix that by ensuring a word alignment. While 4 would suffice for
32bit arches and problem at hand, it is probably better to put 8.

| Path: (null) CPU: 0 PID: 1 Comm: swapper Not tainted
| 3.15.0-rc3-next-20140430 #2
| task: 8f044000 ti: 8f01e000 task.ti: 8f01e000
|
| [ECR   ]: 0x00230400 => Misaligned r/w from 0x800fb0d3
| [EFA   ]: 0x800fb0d3
| [BLINK ]: do_one_initcall+0x86/0x1bc
| [ERET  ]: init_kprobes+0x52/0x120
Signed-off-by: NVineet Gupta <vgupta@synopsys.com>
Cc: <torvalds@linux-foundation.org>
Cc: <rusty@rustcorp.com.au>
Cc: <rdunlap@infradead.org>
Cc: <jeremy@goop.org>
Cc: <arnd@arndb.de>
Cc: <dl9pf@gmx.de>
Cc: <sparse@chrisli.org>
Cc: <anil.s.keshavamurthy@intel.com>
Cc: <davem@davemloft.net>
Cc: <ananth@in.ibm.com>
Cc: <masami.hiramatsu.pt@hitachi.com>
Cc: <chrisw@sous-sol.org>
Cc: <akataria@vmware.com>
Cc: anton Kolesov <Anton.Kolesov@synopsys.com>
Link: http://lkml.kernel.org/r/5361DB14.7010406@synopsys.comSigned-off-by: NIngo Molnar <mingo@kernel.org>

Introduce NOKPROBE_SYMBOL() macro which builds a kprobes
blacklist at kernel build time.

The usage of this macro is similar to EXPORT_SYMBOL(),
placed after the function definition:

  NOKPROBE_SYMBOL(function);

Since this macro will inhibit inlining of static/inline
functions, this patch also introduces a nokprobe_inline macro
for static/inline functions. In this case, we must use
NOKPROBE_SYMBOL() for the inline function caller.

When CONFIG_KPROBES=y, the macro stores the given function
address in the "_kprobe_blacklist" section.

Since the data structures are not fully initialized by the
macro (because there is no "size" information),  those
are re-initialized at boot time by using kallsyms.
Signed-off-by: NMasami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Link: http://lkml.kernel.org/r/20140417081705.26341.96719.stgit@ltc230.yrl.intra.hitachi.co.jp
Cc: Alok Kataria <akataria@vmware.com>
Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Christopher Li <sparse@chrisli.org>
Cc: Chris Wright <chrisw@sous-sol.org>
Cc: David S. Miller <davem@davemloft.net>
Cc: Jan-Simon Möller <dl9pf@gmx.de>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: linux-arch@vger.kernel.org
Cc: linux-doc@vger.kernel.org
Cc: linux-sparse@vger.kernel.org
Cc: virtualization@lists.linux-foundation.org
Signed-off-by: NIngo Molnar <mingo@kernel.org>

Add support for custom reserved memory drivers. Call their init() function
for each reserved region and prepare for using operations provided by them
with by the reserved_mem->ops array.

Based on previous code provided by Josh Cartwright <joshc@codeaurora.org>
Signed-off-by: NMarek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: NGrant Likely <grant.likely@linaro.org>

The goal of multi-platform kernels is to remove the need for mach
directories and machine descriptors. To further that goal,
introduce CPU_METHOD_OF_DECLARE() to allow cpu hotplug/smp
support to be separated from the machine descriptors.
Implementers should specify an enable-method property in their
cpus node and then implement a matching set of smp_ops in their
hotplug/smp code, wiring it up with the CPU_METHOD_OF_DECLARE()
macro. When the kernel is compiled we'll collect all the
enable-method smp_ops into one section for use at boot.

At boot time we'll look for an enable-method in each cpu node and
try to match that against all known CPU enable methods in the
kernel. If there are no enable-methods in the cpu nodes we
fallback to the cpus node and try to use any enable-method found
there. If that doesn't work we fall back to the old way of using
the machine descriptor.
Acked-by: NMark Rutland <mark.rutland@arm.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: <devicetree@vger.kernel.org>
Signed-off-by: NStephen Boyd <sboyd@codeaurora.org>
Signed-off-by: NKumar Gala <galak@codeaurora.org>

This adds the .init_array section as yet another section with constructors. This
is needed because gcc could add __gcov_init calls to .init_array or .ctors
section, depending on gcc (and binutils) version .

v2: - reuse mod->ctors for .init_array section for modules, because gcc uses
      .ctors or .init_array, but not both at the same time
v3: - fail to load if that does happen somehow.
Signed-off-by: NFrantisek Hrbata <fhrbata@redhat.com>
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>

There are several tracepoints (mostly in RCU), that reference a string
pointer and uses the print format of "%s" to display the string that
exists in the kernel, instead of copying the actual string to the
ring buffer (saves time and ring buffer space).

But this has an issue with userspace tools that read the binary buffers
that has the address of the string but has no access to what the string
itself is. The end result is just output that looks like:

 rcu_dyntick:          ffffffff818adeaa 1 0
 rcu_dyntick:          ffffffff818adeb5 0 140000000000000
 rcu_dyntick:          ffffffff818adeb5 0 140000000000000
 rcu_utilization:      ffffffff8184333b
 rcu_utilization:      ffffffff8184333b

The above is pretty useless when read by the userspace tools. Ideally
we would want something that looks like this:

 rcu_dyntick:          Start 1 0
 rcu_dyntick:          End 0 140000000000000
 rcu_dyntick:          Start 140000000000000 0
 rcu_callback:         rcu_preempt rhp=0xffff880037aff710 func=put_cred_rcu 0/4
 rcu_callback:         rcu_preempt rhp=0xffff880078961980 func=file_free_rcu 0/5
 rcu_dyntick:          End 0 1

The trace_printk() which also only stores the address of the string
format instead of recording the string into the buffer itself, exports
the mapping of kernel addresses to format strings via the printk_format
file in the debugfs tracing directory.

The tracepoint strings can use this same method and output the format
to the same file and the userspace tools will be able to decipher
the address without any modification.

The tracepoint strings need its own section to save the strings because
the trace_printk section will cause the trace_printk() buffers to be
allocated if anything exists within the section. trace_printk() is only
used for debugging and should never exist in the kernel, we can not use
the trace_printk sections.

Add a new tracepoint_str section that will also be examined by the output
of the printk_format file.

Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: NSteven Rostedt <rostedt@goodmis.org>

Rework RapidIO switch drivers to add an option to build them as loadable
kernel modules.

This patch removes RapidIO-specific vmlinux section and converts switch
drivers to be compatible with LDM driver registration method.  To simplify
registration of device-specific callback routines this patch introduces
rio_switch_ops data structure.  The sw_sysfs() callback is removed from
the list of device-specific operations because under the new structure its
functions can be handled by switch driver's probe() and remove() routines.

If a specific switch device driver is not loaded the RapidIO subsystem
core will use default standard-based operations to configure a switch.
Because the current implementation of RapidIO enumeration/discovery method
relies on availability of device-specific operations for error management,
switch device drivers must be loaded before the RapidIO
enumeration/discovery starts.

This patch also moves several common routines from enumeration/discovery
module into the RapidIO core code to make switch-specific operations
accessible to all components of RapidIO subsystem.
Signed-off-by: NAlexandre Bounine <alexandre.bounine@idt.com>
Cc: Matt Porter <mporter@kernel.crashing.org>
Cc: Li Yang <leoli@freescale.com>
Cc: Kumar Gala <galak@kernel.crashing.org>
Cc: Andre van Herk <andre.van.herk@Prodrive.nl>
Cc: Micha Nelissen <micha.nelissen@Prodrive.nl>
Cc: Stef van Os <stef.van.os@Prodrive.nl>
Cc: Jean Delvare <jdelvare@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Delete all audit rules that were checking how the .cpuXYZ
related sections were inter-operating with other __init
like sections, now that __cpuinit is gone.  Update the linker
script to not have any knowledge of .cpuinit sections.

[lds.h update courtesy of Ralf Baechle <ralf@linux-mips.org>]

Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: NPaul Gortmaker <paul.gortmaker@windriver.com>

Ever since commit 45f035ab ("CONFIG_HOTPLUG should be always on"),
it has been basically impossible to build a kernel with CONFIG_HOTPLUG
turned off.  Remove all the remaining references to it.

Cc: Russell King <linux@arm.linux.org.uk>
Cc: Doug Thompson <dougthompson@xmission.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Steven Whitehouse <swhiteho@redhat.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: "Rafael J. Wysocki" <rjw@sisk.pl>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: NStephen Rothwell <sfr@canb.auug.org.au>
Acked-by: NMauro Carvalho Chehab <mchehab@redhat.com>
Acked-by: NHans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

We have CONFIG_SYMBOL_PREFIX, which three archs define to the string
"_".  But Al Viro broke this in "consolidate cond_syscall and
SYSCALL_ALIAS declarations" (in linux-next), and he's not the first to
do so.

Using CONFIG_SYMBOL_PREFIX is awkward, since we usually just want to
prefix it so something.  So various places define helpers which are
defined to nothing if CONFIG_SYMBOL_PREFIX isn't set:

1) include/asm-generic/unistd.h defines __SYMBOL_PREFIX.
2) include/asm-generic/vmlinux.lds.h defines VMLINUX_SYMBOL(sym)
3) include/linux/export.h defines MODULE_SYMBOL_PREFIX.
4) include/linux/kernel.h defines SYMBOL_PREFIX (which differs from #7)
5) kernel/modsign_certificate.S defines ASM_SYMBOL(sym)
6) scripts/modpost.c defines MODULE_SYMBOL_PREFIX
7) scripts/Makefile.lib defines SYMBOL_PREFIX on the commandline if
   CONFIG_SYMBOL_PREFIX is set, so that we have a non-string version
   for pasting.

(arch/h8300/include/asm/linkage.h defines SYMBOL_NAME(), too).

Let's solve this properly:
1) No more generic prefix, just CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX.
2) Make linux/export.h usable from asm.
3) Define VMLINUX_SYMBOL() and VMLINUX_SYMBOL_STR().
4) Make everyone use them.
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>
Reviewed-by: NJames Hogan <james.hogan@imgtec.com>
Tested-by: James Hogan <james.hogan@imgtec.com> (metag)

Modify of_clk_init function so that it will determine which
driver to initialize based on device tree instead of each driver
registering to it.

Based on a similar patch for drivers/irqchip by Thomas Petazzoni and
drivers/clocksource by Stephen Warren.
Signed-off-by: NPrashant Gaikwad <pgaikwad@nvidia.com>
Tested-by: NTony Prisk <linux@prisktech.co.nz>
Tested-by: NPawel Moll <pawel.moll@arm.com>
Tested-by: NRob Herring <rob.herring@calxeda.com>
Tested-by: NJosh Cartwright <josh.cartwright@ni.com>
Reviewed-by: NJosh Cartwright <josh.cartwright@ni.com>
Acked-by: NMaxime Ripard <maxime.ripard@anandra.org>
Signed-off-by: NMike Turquette <mturquette@linaro.org>
[mturquette@linaro.org: merge conflict from missing CLKSRC_OF_TABLES()]
Signed-off-by: NMike Turquette <mturquette@linaro.org>

With the recent creation of the drivers/irqchip/ directory, it is
desirable to move irq controller drivers here. At the moment, the only
driver here is irq-bcm2835, the driver for the irq controller found in
the ARM BCM2835 SoC, present in Rasberry Pi systems. This irq
controller driver was exporting its initialization function and its
irq handling function through a header file in
<linux/irqchip/bcm2835.h>.

When proposing to also move another irq controller driver in
drivers/irqchip, Rob Herring raised the very valid point that moving
things to drivers/irqchip was good in order to remove more stuff from
arch/arm, but if it means adding gazillions of headers files in
include/linux/irqchip/, it would not be very nice.

So, upon the suggestion of Rob Herring and Arnd Bergmann, this commit
introduces a small infrastructure that defines a central
irqchip_init() function in drivers/irqchip/irqchip.c, which is meant
to be called as the ->init_irq() callback of ARM platforms. This
function calls of_irq_init() with an array of match strings and init
functions generated from a special linker section.

Note that the irq controller driver initialization function is
responsible for setting the global handle_arch_irq() variable, so that
ARM platforms no longer have to define the ->handle_irq field in their
DT_MACHINE structure.

A global header, <linux/irqchip.h> is also added to expose the single
irqchip_init() function to the reset of the kernel.

A further commit moves the BCM2835 irq controller driver to this new
small infrastructure, therefore removing the include/linux/irqchip/
directory.
Signed-off-by: NThomas Petazzoni <thomas.petazzoni@free-electrons.com>
Reviewed-by: NStephen Warren <swarren@wwwdotorg.org>
Reviewed-by: NRob Herring <rob.herring@calxeda.com>
Acked-by: NArnd Bergmann <arnd@arndb.de>
[rob.herring: reword commit message to reflect use of linker sections.]
Signed-off-by: NRob Herring <rob.herring@calxeda.com>

It is desirable to move all clocksource drivers to drivers/clocksource,
yet each requires its own initialization function. We'd rather not
pollute <linux/> with a header for each function. Instead, create a
single of_clksrc_init() function which will determine which clocksource
driver to initialize based on device tree.

Based on a similar patch for drivers/irqchip by Thomas Petazzoni.
Signed-off-by: NStephen Warren <swarren@nvidia.com>

Follow-on MIPS patch will put an object here that needs 64K alignment
to minimize padding.

For those architectures that don't define BSS_FIRST_SECTIONS, there is
no change.
Signed-off-by: NDavid Daney <david.daney@cavium.com>
Cc: linux-mips@linux-mips.org
Cc: linux-arch@vger.kernel.org,
Cc: linux-kernel@vger.kernel.org
Acked-by: NArnd Bergmann <arnd@arndb.de>
Patchwork: https://patchwork.linux-mips.org/patch/4221/Signed-off-by: NRalf Baechle <ralf@linux-mips.org>

Instead of just sorting the ip's of the functions per ftrace page,
sort the entire list before adding them to the ftrace pages.

This will allow the bsearch algorithm to be sped up as it can
also sort by pages, not just records within a page.
Signed-off-by: NSteven Rostedt <rostedt@goodmis.org>

This patch adds a set of macros that can be used to declare
kernel parameters to be parsed _before_ initcalls at a chosen
level are executed.  We rename the now-unused "flags" field of
struct kernel_param as the level.  It's signed, for when we
use this for early params as well, in future.

Linker macro collating init calls had to be modified in order
to add additional symbols between levels that are later used
by the init code to split the calls into blocks.
Signed-off-by: NPawel Moll <pawel.moll@arm.com>
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>

Due to the alignment of following variables, these typically consume
more than just the single byte that 'bool' requires, and as there are a
few hundred instances, the cache pollution (not so much the waste of
memory) sums up.  Put these variables into their own section, outside of
any half way frequently used memory range.

Do the same also to the __warned variable of rcu_lockdep_assert().
(Don't, however, include the ones used by printk_once() and alike, as
they can potentially be hot.)
Signed-off-by: NJan Beulich <jbeulich@suse.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Markers have removed already twice:

1: fc537766
2: eb878b3b

But a little bit is still here.
Signed-off-by: NTkhai Kirill <tkhai@yandex.ru>
Signed-off-by: NGeert Uytterhoeven <geert@linux-m68k.org>

This patch places every exported symbol in its own section
(i.e. "___ksymtab+printk").  Thus the linker will use its SORT() directive
to sort and finally merge all symbol in the right and final section
(i.e. "__ksymtab").

The symbol prefixed archs use an underscore as prefix for symbols.
To avoid collision we use a different character to create the temporary
section names.

This work was supported by a hardware donation from the CE Linux Forum.
Signed-off-by: NAlessio Igor Bogani <abogani@kernel.org>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> (folded in '+' fixup)
Tested-by: NDirk Behme <dirk.behme@googlemail.com>

Introduce:

static __always_inline bool static_branch(struct jump_label_key *key);

instead of the old JUMP_LABEL(key, label) macro.

In this way, jump labels become really easy to use:

Define:

        struct jump_label_key jump_key;

Can be used as:

        if (static_branch(&jump_key))
                do unlikely code

enable/disale via:

        jump_label_inc(&jump_key);
        jump_label_dec(&jump_key);

that's it!

For the jump labels disabled case, the static_branch() becomes an
atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(),
atomic_dec() operations. We show testing results for this change below.

Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct.

Since we now require a 'struct jump_label_key *key', we can store a pointer into
the jump table addresses. In this way, we can enable/disable jump labels, in
basically constant time. This change allows us to completely remove the previous
hashtable scheme. Thanks to Peter Zijlstra for this re-write.

Testing:

I ran a series of 'tbench 20' runs 5 times (with reboots) for 3
configurations, where tracepoints were disabled.

jump label configured in
avg: 815.6

jump label *not* configured in (using atomic reads)
avg: 800.1

jump label *not* configured in (regular reads)
avg: 803.4
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20110316212947.GA8792@redhat.com>
Signed-off-by: NJason Baron <jbaron@redhat.com>
Suggested-by: NH. Peter Anvin <hpa@linux.intel.com>
Tested-by: NDavid Daney <ddaney@caviumnetworks.com>
Acked-by: NRalf Baechle <ralf@linux-mips.org>
Acked-by: NDavid S. Miller <davem@davemloft.net>
Acked-by: NMathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: NSteven Rostedt <rostedt@goodmis.org>

The two percpu helper macros have the section names duplicated.  So create
a new define to merge the two.  This also allows arches who need to link
things more directly themselves to avoid duplicating the input sections in
their linker script.
Signed-off-by: NMike Frysinger <vapier@gentoo.org>
Signed-off-by: NTejun Heo <tj@kernel.org>

Fixes generated by 'codespell' and manually reviewed.
Signed-off-by: NLucas De Marchi <lucas.demarchi@profusion.mobi>

Percpu allocator honors alignment request upto PAGE_SIZE and both the
percpu addresses in the percpu address space and the translated kernel
addresses should be aligned accordingly.  The calculation of the
former depends on the alignment of percpu output section in the kernel
image.

The linker script macros PERCPU_VADDR() and PERCPU() are used to
define this output section and the latter takes @align parameter.
Several architectures are using @align smaller than PAGE_SIZE breaking
percpu memory alignment.

This patch removes @align parameter from PERCPU(), renames it to
PERCPU_SECTION() and makes it always align to PAGE_SIZE.  While at it,
add PCPU_SETUP_BUG_ON() checks such that alignment problems are
reliably detected and remove percpu alignment comment recently added
in workqueue.c as the condition would trigger BUG way before reaching
there.

For um, this patch raises the alignment of percpu area.  As the area
is in .init, there shouldn't be any noticeable difference.

This problem was discovered by David Howells while debugging boot
failure on mn10300.
Signed-off-by: NTejun Heo <tj@kernel.org>
Acked-by: NMike Frysinger <vapier@gentoo.org>
Cc: uclinux-dist-devel@blackfin.uclinux.org
Cc: David Howells <dhowells@redhat.com>
Cc: Jeff Dike <jdike@addtoit.com>
Cc: user-mode-linux-devel@lists.sourceforge.net

Put x86 entry code into a separate link section: .entry.text.

Separating the entry text section seems to have performance
benefits - caused by more efficient instruction cache usage.

Running hackbench with perf stat --repeat showed that the change
compresses the icache footprint. The icache load miss rate went
down by about 15%:

 before patch:
         19417627  L1-icache-load-misses      ( +-   0.147% )

 after patch:
         16490788  L1-icache-load-misses      ( +-   0.180% )

The motivation of the patch was to fix a particular kprobes
bug that relates to the entry text section, the performance
advantage was discovered accidentally.

Whole perf output follows:

 - results for current tip tree:

  Performance counter stats for './hackbench/hackbench 10' (500 runs):

         19417627  L1-icache-load-misses      ( +-   0.147% )
       2676914223  instructions             #      0.497 IPC     ( +- 0.079% )
       5389516026  cycles                     ( +-   0.144% )

      0.206267711  seconds time elapsed   ( +-   0.138% )

 - results for current tip tree with the patch applied:

  Performance counter stats for './hackbench/hackbench 10' (500 runs):

         16490788  L1-icache-load-misses      ( +-   0.180% )
       2717734941  instructions             #      0.502 IPC     ( +- 0.079% )
       5414756975  cycles                     ( +-   0.148% )

      0.206747566  seconds time elapsed   ( +-   0.137% )
Signed-off-by: NJiri Olsa <jolsa@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Nick Piggin <npiggin@kernel.dk>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: masami.hiramatsu.pt@hitachi.com
Cc: ananth@in.ibm.com
Cc: davem@davemloft.net
Cc: 2nddept-manager@sdl.hitachi.co.jp
LKML-Reference: <20110307181039.GB15197@jolsa.redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Currently the syscall_meta structures for the syscall tracepoints are
placed in the __syscall_metadata section, and at link time, the linker
makes one large array of all these syscall metadata structures. On boot
up, this array is read (much like the initcall sections) and the syscall
data is processed.

The problem is that there is no guarantee that gcc will place complex
structures nicely together in an array format. Two structures in the
same file may be placed awkwardly, because gcc has no clue that they
are suppose to be in an array.

A hack was used previous to force the alignment to 4, to pack the
structures together. But this caused alignment issues with other
architectures (sparc).

Instead of packing the structures into an array, the structures' addresses
are now put into the __syscall_metadata section. As pointers are always the
natural alignment, gcc should always pack them tightly together
(otherwise initcall, extable, etc would also fail).

By having the pointers to the structures in the section, we can still
iterate the trace_events without causing unnecessary alignment problems
with other architectures, or depending on the current behaviour of
gcc that will likely change in the future just to tick us kernel developers
off a little more.

The __syscall_metadata section is also moved into the .init.data section
as it is now only needed at boot up.
Suggested-by: NDavid Miller <davem@davemloft.net>
Acked-by: NDavid S. Miller <davem@davemloft.net>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: NSteven Rostedt <rostedt@goodmis.org>

Make the tracepoints more robust, making them solid enough to handle compiler
changes by not relying on anything based on compiler-specific behavior with
respect to structure alignment. Implement an approach proposed by David Miller:
use an array of const pointers to refer to the individual structures, and export
this pointer array through the linker script rather than the structures per se.
It will consume 32 extra bytes per tracepoint (24 for structure padding and 8
for the pointers), but are less likely to break due to compiler changes.

History:

commit 7e066fb8 tracepoints: add DECLARE_TRACE() and DEFINE_TRACE()
added the aligned(32) type and variable attribute to the tracepoint structures
to deal with gcc happily aligning statically defined structures on 32-byte
multiples.

One attempt was to use a 8-byte alignment for tracepoint structures by applying
both the variable and type attribute to tracepoint structures definitions and
declarations. It worked fine with gcc 4.5.1, but broke with gcc 4.4.4 and 4.4.5.

The reason is that the "aligned" attribute only specify the _minimum_ alignment
for a structure, leaving both the compiler and the linker free to align on
larger multiples. Because tracepoint.c expects the structures to be placed as an
array within each section, up-alignment cause NULL-pointer exceptions due to the
extra unexpected padding.

(this patch applies on top of -tip)
Signed-off-by: NMathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: NDavid S. Miller <davem@davemloft.net>
LKML-Reference: <20110126222622.GA10794@Krystal>
CC: Frederic Weisbecker <fweisbec@gmail.com>
CC: Ingo Molnar <mingo@elte.hu>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Andrew Morton <akpm@linux-foundation.org>
CC: Peter Zijlstra <peterz@infradead.org>
CC: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: NSteven Rostedt <rostedt@goodmis.org>

Currently the trace_event structures are placed in the _ftrace_events
section, and at link time, the linker makes one large array of all
the trace_event structures. On boot up, this array is read (much like
the initcall sections) and the events are processed.

The problem is that there is no guarantee that gcc will place complex
structures nicely together in an array format. Two structures in the
same file may be placed awkwardly, because gcc has no clue that they
are suppose to be in an array.

A hack was used previous to force the alignment to 4, to pack the
structures together. But this caused alignment issues with other
architectures (sparc).

Instead of packing the structures into an array, the structures' addresses
are now put into the _ftrace_event section. As pointers are always the
natural alignment, gcc should always pack them tightly together
(otherwise initcall, extable, etc would also fail).

By having the pointers to the structures in the section, we can still
iterate the trace_events without causing unnecessary alignment problems
with other architectures, or depending on the current behaviour of
gcc that will likely change in the future just to tick us kernel developers
off a little more.

The _ftrace_event section is also moved into the .init.data section
as it is now only needed at boot up.
Suggested-by: NDavid Miller <davem@davemloft.net>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: NDavid S. Miller <davem@davemloft.net>
Signed-off-by: NSteven Rostedt <rostedt@goodmis.org>

Currently percpu readmostly subsection may share cachelines with other
percpu subsections which may result in unnecessary cacheline bounce
and performance degradation.

This patch adds @cacheline parameter to PERCPU() and PERCPU_VADDR()
linker macros, makes each arch linker scripts specify its cacheline
size and use it to align percpu subsections.

This is based on Shaohua's x86 only patch.
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Shaohua Li <shaohua.li@intel.com>

Currently only drivers that are built as modules have their versions
shown in /sys/module/<module_name>/version, but this information might
also be useful for built-in drivers as well. This especially important
for drivers that do not define any parameters - such drivers, if
built-in, are completely invisible from userspace.

This patch changes MODULE_VERSION() macro so that in case when we are
compiling built-in module, version information is stored in a separate
section. Kernel then uses this data to create 'version' sysfs attribute
in the same fashion it creates attributes for module parameters.
Signed-off-by: NDmitry Torokhov <dtor@vmware.com>
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>

The readmostly section should end at a cacheline aligned address,
otherwise the last several data might share cachline with other data and
make the readmostly data still have cache bounce.

For example, in ia64, secpath_cachep is the last readmostly data, and it
shares cacheline with init_uts_ns.

a000000100e80480 d secpath_cachep
a000000100e80488 D init_uts_ns
Signed-off-by: NShaohua Li <shaohua.li@intel.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: NTejun Heo <tj@kernel.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This patch adds support for linking device tree blob(s) into
vmlinux. Modifies asm-generic/vmlinux.lds.h to add linking
.dtb sections into vmlinux. To maintain compatiblity with the of/fdt
driver code platforms MUST copy the blob to a non-init memory location
before the kernel frees the .init.* sections in the image.

Modifies scripts/Makefile.lib to add a kbuild command to
compile DTS files to device tree blobs and a rule to create objects to
wrap the blobs for linking.

STRUCT_ALIGNMENT is defined in vmlinux.lds.h for use in the rule to
create wrapper objects for the dtb in Makefile.lib.  The
STRUCT_ALIGN() macro in vmlinux.lds.h is modified to use the
STRUCT_ALIGNMENT definition.

The DTB's are placed on 32 byte boundries to allow parsing the blob
with driver/of/fdt.c during early boot without having to copy the blob
to get the structure alignment GCC expects.

A DTB is linked in by adding the DTB object to the list of objects to
be linked into vmlinux in the archtecture specific Makefile using
   obj-y += foo.dtb.o
Signed-off-by: NDirk Brandewie <dirk.brandewie@gmail.com>
Acked-by: NMichal Marek <mmarek@suse.cz>
[grant.likely@secretlab.ca: cleaned up whitespace inconsistencies]
Signed-off-by: NGrant Likely <grant.likely@secretlab.ca>