Add hooks to allow a paravirt implementation to track the lifetime of
an mm. Paravirtualization requires three hooks, but only two are
needed in common code. They are:
arch_dup_mmap, which is called when a new mmap is created at fork
arch_exit_mmap, which is called when the last process reference to an
mm is dropped, which typically happens on exit and exec.
The third hook is activate_mm, which is called from the arch-specific
activate_mm() macro/function, and so doesn't need stub versions for
other architectures. It's called when an mm is first used.
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Signed-off-by: Andi Kleen <ak@suse.de>
Cc: linux-arch@vger.kernel.org
Cc: James Bottomley <James.Bottomley@SteelEye.com>
Acked-by: Ingo Molnar <mingo@elte.hu>
Allocating PDA and GDT at boot is a pain. Using simple per-cpu variables adds
happiness (although we need the GDT page-aligned for Xen, which we do in a
followup patch).
[akpm@linux-foundation.org: build fix]
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Andi Kleen <ak@suse.de>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
The page_test_and_clear_dirty primitive really consists of two
operations, page_test_dirty and the page_clear_dirty. The combination
of the two is not an atomic operation, so it makes more sense to have
two separate operations instead of one.
In addition to the improved readability of the s390 version of
SetPageUptodate, it now avoids the page_test_dirty operation which is
an insert-storage-key-extended (iske) instruction which is an expensive
operation.
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Here is the current version of the 64 bit divide common code.
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since lazy MMU batching mode still allows interrupts to enter, it is
possible for interrupt handlers to try to use kmap_atomic, which fails when
lazy mode is active, since the PTE update to highmem will be delayed. The
best workaround is to issue an explicit flush in kmap_atomic_functions
case; this is the only way nested PTE updates can happen in the interrupt
handler.
Thanks to Jeremy Fitzhardinge for noting the bug and suggestions on a fix.
This patch gets reverted again when we start 2.6.22 and the bug gets fixed
differently.
Signed-off-by: Zachary Amsden <zach@vmware.com>
Cc: Andi Kleen <ak@muc.de>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This reverts commit 39d61db0ed.
The commit was buggy in multiple ways:
- the conversion to ilog2() was incorrect to begin with
- it tested the wrong #defines, so on all architectures but FRV you'd
never see the bug except for constant arguments.
- the new "get_order()" macro used its arguments multiple times, and
didn't even parenthesize them properly
- despite the comments, it was not true that you could use it for
constant initializers, since not all architectures even use the
generic page.h header file.
All of the problems are individually fixable, but it all boils down to:
better just revert it, and re-do it from scratch.
Cc: David Howells <dhowells@redhat.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The VMI ROM has a mode where hypercalls can be queued and batched. This turns
out to be a significant win during context switch, but must be done at a
specific point before side effects to CPU state are visible to subsequent
instructions. This is similar to the MMU batching hooks already provided.
The same hooks could be used by the Xen backend to implement a context switch
multicall.
To explain a bit more about lazy modes in the paravirt patches, basically, the
idea is that only one of lazy CPU or MMU mode can be active at any given time.
Lazy MMU mode is similar to this lazy CPU mode, and allows for batching of
multiple PTE updates (say, inside a remap loop), but to avoid keeping some
kind of state machine about when to flush cpu or mmu updates, we just allow
one or the other to be active. Although there is no real reason a more
comprehensive scheme could not be implemented, there is also no demonstrated
need for this extra complexity.
Signed-off-by: Zachary Amsden <zach@vmware.com>
Signed-off-by: Andi Kleen <ak@suse.de>
Cc: Andi Kleen <ak@suse.de>
Cc: Jeremy Fitzhardinge <jeremy@xensource.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Chris Wright <chrisw@sous-sol.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
This defines a simple and minimalist programming interface for GPIO APIs:
- Documentation/gpio.txt ... describes things (read it)
- include/asm-arm/gpio.h ... defines the ARM hook, which just punts
to <asm/arch/gpio.h> for any implementation
- include/asm-generic/gpio.h ... implement "can sleep" variants as calling
the normal ones, for systems that don't handle i2c expanders.
The immediate need for such a cross-architecture API convention is to support
drivers that work the same on AT91 ARM and AVR32 AP7000 chips, which embed many
of the same controllers but have different CPUs. However, several other users
have been reported, including a driver for a hardware watchdog chip and some
handhelds.org multi-CPU button drivers.
Signed-off-by: David Brownell <dbrownell@users.sourceforge.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit 9ac7849e35 causes this on S390:
drivers/built-in.o: In function `dmam_noncoherent_release':
dma-mapping.c:(.text+0x1515c): undefined reference to `dma_free_noncoherent'
drivers/built-in.o: In function `dmam_free_noncoherent':
undefined reference to `dma_free_noncoherent'
drivers/built-in.o: In function `dmam_alloc_noncoherent':
undefined reference to `dma_alloc_noncoherent'
make: *** [.tmp_vmlinux1] Error 1
Cc: Tejun Heo <htejun@gmail.com>
Acked-by: Jeff Garzik <jeff@garzik.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
With CONFIG_SPARSEMEM=y:
mm/rmap.c:579: warning: format '%lx' expects type 'long unsigned int', but argument 2 has type 'int'
Make __page_to_pfn() return unsigned long.
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Remove the last vestiges of the long-deprecated "MAP_ANON" page protection
flag: use "MAP_ANONYMOUS" instead.
Signed-off-by: Robert P. J. Day <rpjday@mindspring.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
On the Maple board, the AMD8111 IDE is in legacy mode... except that it
appears on IRQ 20 instead of IRQ 15. For drivers/ide this was handled by
the architecture's "pci_get_legacy_ide_irq()" function, but in libata we
just hard-code the numbers 14 and 15.
This patch provides asm-powerpc/libata-portmap.h which maps the IRQ as
appropriate, having added a pci_dev argument to the
ATA_{PRIM,SECOND}ARY_IRQ macros.
There's probably a better way to do this -- especially if we observe
that the _only_ case in which this seemingly-generic
"pci_get_legacy_ide_irq()" function returns anything other than 14 and
15 for primary and secondary respectively is the case of the AMD8111 on
the Maple board -- couldn't we handle that with a special case in the
pata_amd driver, or perhaps with a PCI quirk for Maple to switch it into
native mode during early boot and assign resources properly?
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
WARN_ON() ever triggering is a kernel bug. Do not try to paper over this
fact by suggesting to the user that this is 'only' a warning, as the
following recent commit does:
commit 30e25b71e7
Author: Jeremy Fitzhardinge <jeremy@goop.org>
Date: Fri Dec 8 02:36:24 2006 -0800
[PATCH] Fix generic WARN_ON message
A warning is a warning, not a BUG.
( it might make sense to rename BUG() to CRASH() and BUG_ON() to
CRASH_ON(), but that does not change the fact that WARN_ON()
signals a kernel bug. )
i and others objected to this change during lkml review:
http://marc.theaimsgroup.com/?l=linux-kernel&m=116115160710533&w=2
still the change slipped upstream - grumble :)
Also, use the standard "BUG: " format to make it easier to grep logs and
to make it easier to google for kernel bugs.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch is designed to fix:
- Disk eating corruptor on KT7 after resume from RAM
- VIA IRQ handling
- VIA fixups for bus lockups after resume from RAM
The core of this is to add a table of resume fixups run at resume time.
We need to do this for a variety of boards and features, but particularly
we need to do this to get various critical VIA fixups done on resume.
The second part of the problem is to handle VIA IRQ number rules which
are a bit odd and need special handling for PIC interrupts. Various
patches broke various boxes and while this one may not be perfect
(hopefully it is) it ensures the workaround is applied to the right
devices only.
From: Jean Delvare <khali@linux-fr.org>
Now that PCI quirks are replayed on software resume, we can safely
re-enable the Asus SMBus unhiding quirk even when software suspend support
is enabled.
[akpm@osdl.org: fix const warning]
Signed-off-by: Alan Cox <alan@redhat.com>
Cc: Jean Delvare <khali@linux-fr.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
It has caused more problems than it ever really solved, and is
apparently not getting cleaned up and fixed. We can put it back when
it's stable and isn't likely to make warning or bug events worse.
In the meantime, enable frame pointers for more readable stack traces.
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
We should not initialize rootfs before all the core initializers have
run. So do it as a separate stage just before starting the regular
driver initializers.
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This is the grungy swap all the occurrences in the right places patch that
goes with the updates. At this point we have the same functionality as
before (except that sgttyb() returns speeds not zero) and are ready to
begin turning new stuff on providing nobody reports lots of bugs
If you are a tty driver author converting an out of tree driver the only
impact should be termios->ktermios name changes for the speed/property
setting functions from your upper layers.
If you are implementing your own TCGETS function before then your driver
was broken already and its about to get a whole lot more painful for you so
please fix it 8)
Also fill in c_ispeed/ospeed on init for most devices, although the current
code will do this for you anyway but I'd like eventually to lose that extra
paranoia
[akpm@osdl.org: bluetooth fix]
[mp3@de.ibm.com: sclp fix]
[mp3@de.ibm.com: warning fix for tty3270]
[hugh@veritas.com: fix tty_ioctl powerpc build]
[jdike@addtoit.com: uml: fix ->set_termios declaration]
Signed-off-by: Alan Cox <alan@redhat.com>
Signed-off-by: Martin Peschke <mp3@de.ibm.com>
Acked-by: Peter Oberparleiter <oberpar@de.ibm.com>
Cc: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Jeff Dike <jdike@addtoit.com>
Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Alter get_order() so that it can make use of ilog2() on a constant to produce
a constant value, retaining the ability for an arch to override it in the
non-const case.
Signed-off-by: David Howells <dhowells@redhat.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
A warning is a warning, not a BUG.
Signed-off-by: Jeremy Fitzhardinge <jeremy@goop.org>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch adds common handling for kernel BUGs, for use by architectures as
they wish. The code is derived from arch/powerpc.
The advantages of having common BUG handling are:
- consistent BUG reporting across architectures
- shared implementation of out-of-line file/line data
- implement CONFIG_DEBUG_BUGVERBOSE consistently
This means that in inline impact of BUG is just the illegal instruction
itself, which is an improvement for i386 and x86-64.
A BUG is represented in the instruction stream as an illegal instruction,
which has file/line information associated with it. This extra information is
stored in the __bug_table section in the ELF file.
When the kernel gets an illegal instruction, it first confirms it might
possibly be from a BUG (ie, in kernel mode, the right illegal instruction).
It then calls report_bug(). This searches __bug_table for a matching
instruction pointer, and if found, prints the corresponding file/line
information. If report_bug() determines that it wasn't a BUG which caused the
trap, it returns BUG_TRAP_TYPE_NONE.
Some architectures (powerpc) implement WARN using the same mechanism; if the
illegal instruction was the result of a WARN, then report_bug(Q) returns
CONFIG_DEBUG_BUGVERBOSE; otherwise it returns BUG_TRAP_TYPE_BUG.
lib/bug.c keeps a list of loaded modules which can be searched for __bug_table
entries. The architecture must call
module_bug_finalize()/module_bug_cleanup() from its corresponding
module_finalize/cleanup functions.
Unsetting CONFIG_DEBUG_BUGVERBOSE will reduce the kernel size by some amount.
At the very least, filename and line information will not be recorded for each
but, but architectures may decide to store no extra information per BUG at
all.
Unfortunately, gcc doesn't have a general way to mark an asm() as noreturn, so
architectures will generally have to include an infinite loop (or similar) in
the BUG code, so that gcc knows execution won't continue beyond that point.
gcc does have a __builtin_trap() operator which may be useful to achieve the
same effect, unfortunately it cannot be used to actually implement the BUG
itself, because there's no way to get the instruction's address for use in
generating the __bug_table entry.
[randy.dunlap@oracle.com: Handle BUG=n, GENERIC_BUG=n to prevent build errors]
[bunk@stusta.de: include/linux/bug.h must always #include <linux/module.h]
Signed-off-by: Jeremy Fitzhardinge <jeremy@goop.org>
Cc: Andi Kleen <ak@muc.de>
Cc: Hugh Dickens <hugh@veritas.com>
Cc: Michael Ellerman <michael@ellerman.id.au>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Make the contents of the userspace asm/setup.h header consistent on all
architectures:
- export setup.h to userspace on all architectures
- export only COMMAND_LINE_SIZE to userspace
- frv: move COMMAND_LINE_SIZE from param.h
- i386: remove duplicate COMMAND_LINE_SIZE from param.h
- arm:
- export ATAGs to userspace
- change u8/u16/u32 to __u8/__u16/__u32
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Acked-by: Russell King <rmk@arm.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Pass struct dev pointer to dma_cache_sync()
dma_cache_sync() is ill-designed in that it does not have a struct device
pointer argument which makes proper support for systems that consist of a
mix of coherent and non-coherent DMA devices hard. Change dma_cache_sync
to take a struct device pointer as first argument and fix all its callers
to pass it.
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Cc: James Bottomley <James.Bottomley@steeleye.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Greg KH <greg@kroah.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
dma_is_consistent() is ill-designed in that it does not have a struct
device pointer argument which makes proper support for systems that consist
of a mix of coherent and non-coherent DMA devices hard. Change
dma_is_consistent to take a struct device pointer as first argument and fix
the sole caller to pass it.
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Cc: James Bottomley <James.Bottomley@steeleye.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Greg KH <greg@kroah.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Introduce pagefault_{disable,enable}() and use these where previously we did
manual preempt increments/decrements to make the pagefault handler do the
atomic thing.
Currently they still rely on the increased preempt count, but do not rely on
the disabled preemption, this might go away in the future.
(NOTE: the extra barrier() in pagefault_disable might fix some holes on
machines which have too many registers for their own good)
[heiko.carstens@de.ibm.com: s390 fix]
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Nick Piggin <npiggin@suse.de>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
The .eh_frame section contents is never written to, so it can as well
benefit from CONFIG_DEBUG_RODATA.
Diff-ed against firstfloor tree.
Signed-off-by: Jan Beulich <jbeulich@novell.com>
Signed-off-by: Andi Kleen <ak@suse.de>
Ld knows about 2 kinds of symbols, absolute and section
relative. Section relative symbols symbols change value
when a section is moved and absolute symbols do not.
Currently in the linker script we have several labels
marking the beginning and ending of sections that
are outside of sections, making them absolute symbols.
Having a mixture of absolute and section relative
symbols refereing to the same data is currently harmless
but it is confusing.
This must be done carefully as newer revs of ld do not place
symbols that appear in sections without data and instead
ld makes those symbols global :(
My ultimate goal is to build a relocatable kernel. The
safest and least intrusive technique is to generate
relocation entries so the kernel can be relocated at load
time. The only penalty would be an increase in the size
of the kernel binary. The problem is that if absolute and
relocatable symbols are not properly specified absolute symbols
will be relocated or section relative symbols won't be, which
is fatal.
The practical motivation is that when generating kernels that
will run from a reserved area for analyzing what caused
a kernel panic, it is simpler if you don't need to hard code
the physical memory location they will run at, especially
for the distributions.
[AK: and merged:]
o Also put a message so that in future people can be aware of it and
avoid introducing absolute symbols.
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: Vivek Goyal <vgoyal@in.ibm.com>
Signed-off-by: Andi Kleen <ak@suse.de>
Add arch specific dev_archdata to struct device
Adds an arch specific struct dev_arch to struct device. This enables
architecture to add specific fields to every device in the system, like
DMA operation pointers, NUMA node ID, firmware specific data, etc...
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: Andi Kleen <ak@suse.de>
Acked-By: David Howells <dhowells@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
This is a quick hack to overcome the fact that SRCU currently does not
allow static initializers, and we need to sometimes initialize those
things before any other initializers (even "core" ones) can do so.
Currently we don't allow this at all for modules, and the only user that
needs is right now is cpufreq. As reported by Thomas Gleixner:
"Commit b4dfdbb3c7 ("[PATCH] cpufreq:
make the transition_notifier chain use SRCU breaks cpu frequency
notification users, which register the callback > on core_init
level."
Cc: Thomas Gleixner <tglx@timesys.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Arjan van de Ven <arjan@infradead.org>
Cc: Andrew Morton <akpm@osdl.org>,
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
The multithreaded-probing code has a problem: after one initcall level (eg,
core_initcall) has been processed, we will then start processing the next
level (postcore_initcall) while the kernel threads which are handling
core_initcall are still executing. This breaks the guarantees which the
layered initcalls previously gave us.
IOW, we want to be multithreaded _within_ an initcall level, but not between
different levels.
Fix that up by causing the probing code to wait for all outstanding probes at
one level to complete before we start processing the next level.
Cc: Greg KH <greg@kroah.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Add a vmlinux.lds.h helper macro for defining the eight-level initcall table,
teach all the architectures to use it.
This is a prerequisite for a patch which performs initcall synchronisation for
multithreaded-probing.
Cc: Greg KH <greg@kroah.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
[ Added AVR32 as well ]
Signed-off-by: Haavard Skinnemoen <hskinnemoen@atmel.com>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This changes the dwarf2 unwinder to do a binary search for CIEs
instead of a linear work. The linker is unfortunately not
able to build a proper lookup table at link time, instead it creates
one at runtime as soon as the bootmem allocator is usable (so you'll continue
using the linear lookup for the first [hopefully] few calls).
The code should be ready to utilize a build-time created table once
a fixed linker becomes available.
Signed-off-by: Jan Beulich <jbeulich@novell.com>
Signed-off-by: Andi Kleen <ak@suse.de>
In most cases the return value of WARN_ON() is ignored. If the generic
definition for the !CONFIG_BUG case is used this will result in a warning:
CC kernel/sched.o
In file included from include/linux/bio.h:25,
from include/linux/blkdev.h:14,
from kernel/sched.c:39:
include/linux/ioprio.h: In function âtask_ioprioâ:
include/linux/ioprio.h:50: warning: statement with no effect
kernel/sched.c: In function âcontext_switchâ:
kernel/sched.c:1834: warning: statement with no effect
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This likely profiling is pretty fun. I found a few possible problems
in sched.c.
This patch may be not measurable, but when I did measure long ago,
nooping (un)likely cost a couple of % on scheduler heavy benchmarks, so
it all adds up.
Tweak some branch hints:
- the 2nd 64 bits in the bitmask is likely to be populated, because it
contains the first 28 bits (nearly 3/4) of the normal priorities.
(ratio of 669669:691 ~= 1000:1).
- it isn't unlikely that context switching switches to another process. it
might be very rapidly switching to and from the idle process (ratio of
475815:419004 and 471330:423544). Let the branch predictor decide.
- preempt_enable seems to be very often called in a nested preempt_disable
or with interrupts disabled (ratio of 3567760:87965 ~= 40:1)
Signed-off-by: Nick Piggin <npiggin@suse.de>
Acked-by: Ingo Molnar <mingo@elte.hu>
Cc: Daniel Walker <dwalker@mvista.com>
Cc: Hua Zhong <hzhong@gmail.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Trivial typo fix in the "syntax error if percpu macros are incorrectly
used" patch. I misspelled "identifier" in all places. D'Oh!
Thanks to Dirk Mueller to point this out.
Signed-off-by: Jan Blunck <jblunck@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Tim and Ananiev report that the recent WARN_ON_ONCE changes cause increased
cache misses with the tbench workload. Apparently due to the access to the
newly-added static variable.
Rearrange the code so that we don't touch that variable unless the warning is
going to trigger.
Also rework the logic so that the static variable starts out at zero, so we
can move it into bss.
It would seem logical to mark the static variable as __read_mostly too. But
it would be wrong, because that would put it back into the vmlinux image, and
the kernel will never read from this variable in normal operation anyway.
Unless the compiler or hardware go and do some prefetching on us?
For some reason this patch shrinks softirq.o text by 40 bytes.
Cc: Tim Chen <tim.c.chen@intel.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: "Ananiev, Leonid I" <leonid.i.ananiev@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Maintain a per-CPU global "struct pt_regs *" variable which can be used instead
of passing regs around manually through all ~1800 interrupt handlers in the
Linux kernel.
The regs pointer is used in few places, but it potentially costs both stack
space and code to pass it around. On the FRV arch, removing the regs parameter
from all the genirq function results in a 20% speed up of the IRQ exit path
(ie: from leaving timer_interrupt() to leaving do_IRQ()).
Where appropriate, an arch may override the generic storage facility and do
something different with the variable. On FRV, for instance, the address is
maintained in GR28 at all times inside the kernel as part of general exception
handling.
Having looked over the code, it appears that the parameter may be handed down
through up to twenty or so layers of functions. Consider a USB character
device attached to a USB hub, attached to a USB controller that posts its
interrupts through a cascaded auxiliary interrupt controller. A character
device driver may want to pass regs to the sysrq handler through the input
layer which adds another few layers of parameter passing.
I've build this code with allyesconfig for x86_64 and i386. I've runtested the
main part of the code on FRV and i386, though I can't test most of the drivers.
I've also done partial conversion for powerpc and MIPS - these at least compile
with minimal configurations.
This will affect all archs. Mostly the changes should be relatively easy.
Take do_IRQ(), store the regs pointer at the beginning, saving the old one:
struct pt_regs *old_regs = set_irq_regs(regs);
And put the old one back at the end:
set_irq_regs(old_regs);
Don't pass regs through to generic_handle_irq() or __do_IRQ().
In timer_interrupt(), this sort of change will be necessary:
- update_process_times(user_mode(regs));
- profile_tick(CPU_PROFILING, regs);
+ update_process_times(user_mode(get_irq_regs()));
+ profile_tick(CPU_PROFILING);
I'd like to move update_process_times()'s use of get_irq_regs() into itself,
except that i386, alone of the archs, uses something other than user_mode().
Some notes on the interrupt handling in the drivers:
(*) input_dev() is now gone entirely. The regs pointer is no longer stored in
the input_dev struct.
(*) finish_unlinks() in drivers/usb/host/ohci-q.c needs checking. It does
something different depending on whether it's been supplied with a regs
pointer or not.
(*) Various IRQ handler function pointers have been moved to type
irq_handler_t.
Signed-Off-By: David Howells <dhowells@redhat.com>
(cherry picked from 1b16e7ac850969f38b375e511e3fa2f474a33867 commit)
Many files include the filename at the beginning, serveral used a wrong one.
Signed-off-by: Uwe Zeisberger <Uwe_Zeisberger@digi.com>
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Now that ptep_establish has a definition in PAE i386 3-level paging code, the
only paging model which is insane enough to have multi-word hardware PTEs
which are not efficient to set atomically, we can remove the ghost of
set_pte_atomic from other architectures which falesly duplicated it, and
remove all knowledge of it from the generic pgtable code.
set_pte_atomic is now a private pte operator which is specific to i386
Signed-off-by: Zachary Amsden <zach@vmware.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Jeremy Fitzhardinge <jeremy@xensource.com>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Implement lazy MMU update hooks which are SMP safe for both direct and shadow
page tables. The idea is that PTE updates and page invalidations while in
lazy mode can be batched into a single hypercall. We use this in VMI for
shadow page table synchronization, and it is a win. It also can be used by
PPC and for direct page tables on Xen.
For SMP, the enter / leave must happen under protection of the page table
locks for page tables which are being modified. This is because otherwise,
you end up with stale state in the batched hypercall, which other CPUs can
race ahead of. Doing this under the protection of the locks guarantees the
synchronization is correct, and also means that spurious faults which are
generated during this window by remote CPUs are properly handled, as the page
fault handler must re-check the PTE under protection of the same lock.
Signed-off-by: Zachary Amsden <zach@vmware.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Change pte_clear_full to a more appropriately named pte_clear_not_present,
allowing optimizations when not-present mapping changes need not be reflected
in the hardware TLB for protected page table modes. There is also another
case that can use it in the fremap code.
Signed-off-by: Zachary Amsden <zach@vmware.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Letting WARN_ON/WARN_ON_ONCE return the condition means that you could do
if (WARN_ON(blah)) {
handle_impossible_case
}
Rather than
if (unlikely(blah)) {
WARN_ON(1)
handle_impossible_case
}
I checked all the newly added WARN_ON_ONCE users and none of them test the
return status so we can still change it.
[akpm@osdl.org: warning fix]
[akpm@osdl.org: build fix]
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
The param section is an array of "kernel_param" structures, storing only
constant data: pointer to name, permission of the variable pointed to by
(void *)arg and pointers to set/get methods.
Move end_rodata down to include __param section in the read-only range used
by CONFIG_DEBUG_RODATA.
Signed-off-by: Marcelo Tosatti <marcelo@kvack.org>
Acked-by: Arjan van de Ven <arjan@infradead.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Parsing generic pgtable.h in assembler is simply crazy. None of this file is
needed in assembler code, and C inline functions and structures routine break
one or more different compiles.
Signed-off-by: Zachary Amsden <zach@vmware.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch will pack any .note.* section into a PT_NOTE segment in the output
file.
To do this, we tell ld that we need a PT_NOTE segment. This requires us to
start explicitly mapping sections to segments, so we also need to explicitly
create PT_LOAD segments for text and data, and map the sections to them
appropriately. Fortunately, each section will default to its previous
section's segment, so it doesn't take many changes to vmlinux.lds.S.
This only changes i386 for now, but I presume the corresponding changes for
other architectures will be as simple.
This change also adds <linux/elfnote.h>, which defines C and Assembler macros
for actually creating ELF notes.
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Hollis Blanchard <hollisb@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
One of the changes necessary for shared page tables is to standardize the
pxx_page macros. pte_page and pmd_page have always returned the struct
page associated with their entry, while pte_page_kernel and pmd_page_kernel
have returned the kernel virtual address. pud_page and pgd_page, on the
other hand, return the kernel virtual address.
Shared page tables needs pud_page and pgd_page to return the actual page
structures. There are very few actual users of these functions, so it is
simple to standardize their usage.
Since this is basic cleanup, I am submitting these changes as a standalone
patch. Per Hugh Dickins' comments about it, I am also changing the
pxx_page_kernel macros to pxx_page_vaddr to clarify their meaning.
Signed-off-by: Dave McCracken <dmccr@us.ibm.com>
Cc: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
get_cpu_var()/per_cpu()/__get_cpu_var() arguments must be simple
identifiers. Otherwise the arch dependent implementations might break.
This patch enforces the correct usage of the macros by producing a syntax
error if the variable is not a simple identifier.
Signed-off-by: Jan Blunck <jblunck@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
several targets have no ....at() family and m32r calls its only chown variant
chown32(), with __NR_chown being undefined. creat(2) is also absent in some
targets.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
There's useful stuff in <linux/timex.h> but <asm/timex.h> has nothing for
userspace. Stop exporting it, and include it only from within the existing
#ifdef __KERNEL__ part of <linux/timex.h>
This fixes a 'make headers_check' failure on i386 because asm-i386/timex.h
includes both asm-i386/tsc.h and asm-i386/processor.h, neither of which are
exported to userspace. It's not entirely clear _why_ it includes either of
these, but it does.
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Kill host_set->next
Fix simplex support
Allow per platform setting of IDE legacy bases
Some of this can be tidied further later on, in particular all the
legacy port gunge belongs as a PCI quirk/PCI header decode to understand
the special legacy IDE rules in the PCI spec.
Longer term Jeff also wants to move the request_irq/free_irq out of core
which will make this even cleaner.
tj: folded in three followup patches - ata_piix-fix, broken-arch-fix
and fix-new-legacy-handling, and separated per-dev xfermask into
separate patch preceding this one. Folded in fixes are...
* ata_piix-fix: fix build failure due to host_set->next removal
* broken-arch-fix: add missing include/asm-*/libata-portmap.h
* fix-new-legacy-handling:
* In ata_pci_init_legacy_port(), probe_num was incorrectly
incremented during initialization of the secondary port and
probe_ent->n_ports was incorrectly fixed to 1.
* Both legacy ports ended up having the same hard_port_no.
* When printing port information, both legacy ports printed
the first irq.
Signed-off-by: Alan Cox <alan@redhat.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Tejun Heo <htejun@gmail.com>
There's no excuse for userspace abusing this kernel header -- the kernel's
headers are not intended to provide a library of helper routines for
userspace. Using <asm/io.h> from userspace is broken on most architectures
anyway. Just say 'no'.
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This isn't suitable for userspace to see -- the kernel headers are not a
random library of stuff for userspace; they're only there to define the
kernel<->user ABI for system libraries and tools. Anything which _was_
abusing asm/atomic.h from userspace was probably broken anyway -- as it often
didn't even give atomic operation.
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Remove asm/irq.h from the exported headers -- there was never any good reason
for it to have been listed.
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* master.kernel.org:/pub/scm/linux/kernel/git/davej/cpufreq:
Move workqueue exports to where the functions are defined.
[CPUFREQ] Misc cleanups in ondemand.
[CPUFREQ] Make ondemand sampling per CPU and remove the mutex usage in sampling path.
[CPUFREQ] Add queue_delayed_work_on() interface for workqueues.
[CPUFREQ] Remove slowdown from ondemand sampling path.
Generic lock debugging:
- generalized lock debugging framework. For example, a bug in one lock
subsystem turns off debugging in all lock subsystems.
- got rid of the caller address passing (__IP__/__IP_DECL__/etc.) from
the mutex/rtmutex debugging code: it caused way too much prototype
hackery, and lockdep will give the same information anyway.
- ability to do silent tests
- check lock freeing in vfree too.
- more finegrained debugging options, to allow distributions to
turn off more expensive debugging features.
There's no separate 'held mutexes' list anymore - but there's a 'held locks'
stack within lockdep, which unifies deadlock detection across all lock
classes. (this is independent of the lockdep validation stuff - lockdep first
checks whether we are holding a lock already)
Here are the current debugging options:
CONFIG_DEBUG_MUTEXES=y
CONFIG_DEBUG_LOCK_ALLOC=y
which do:
config DEBUG_MUTEXES
bool "Mutex debugging, basic checks"
config DEBUG_LOCK_ALLOC
bool "Detect incorrect freeing of live mutexes"
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Add the per_cpu_offset() generic method. (used by the lock validator)
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Add __start_rodata and __end_rodata to sections.h to avoid extern
declarations. Needed by s390 code (see following patch).
[akpm@osdl.org: update architectures]
Cc: Arjan van de Ven <arjan@infradead.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Andi Kleen <ak@muc.de>
Acked-by: Kyle McMartin <kyle@mcmartin.ca>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Allow to tie upper bits of syscall bitmap in audit rules to kernel-defined
sets of syscalls. Infrastructure, a couple of classes (with 32bit counterparts
for biarch targets) and actual tie-in on i386, amd64 and ia64.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Remove slowdown from ondemand sampling path. This reduces the code path length
in dbs_check_cpu() by half. slowdown was not used by ondemand by default.
If there are any user level tools that were using this tunable, they
may report error now.
Signed-off-by: Alexey Starikovskiy <alexey.y.starikovskiy@intel.com>
Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Dave Jones <davej@redhat.com>
Temporarily add EXPORT_UNUSED_SYMBOL and EXPORT_UNUSED_SYMBOL_GPL. These
will be used as a transition measure for symbols that aren't used in the
kernel and are on the way out. When a module uses such a symbol, a warning
is printk'd at modprobe time.
The main reason for removing unused exports is size: eacho export takes
roughly between 100 and 150 bytes of kernel space in the binary. This
patch gives users the option to immediately get this size gain via a config
option.
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
There are several instances of per_cpu(foo, raw_smp_processor_id()), which
is semantically equivalent to __get_cpu_var(foo) but without the warning
that smp_processor_id() can give if CONFIG_DEBUG_PREEMPT is enabled. For
those architectures with optimized per-cpu implementations, namely ia64,
powerpc, s390, sparc64 and x86_64, per_cpu() turns into more and slower
code than __get_cpu_var(), so it would be preferable to use __get_cpu_var
on those platforms.
This defines a __raw_get_cpu_var(x) macro which turns into per_cpu(x,
raw_smp_processor_id()) on architectures that use the generic per-cpu
implementation, and turns into __get_cpu_var(x) on the architectures that
have an optimized per-cpu implementation.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Ingo Molnar <mingo@elte.hu>
Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Considering that there isn't a lot of hw we can depend on during resume,
this is about as good as it gets.
This is x86-only for now, although the basic concept (and most of the
code) will certainly work on almost any platform.
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
We have architectures where the size of page_to_pfn and pfn_to_page are
significant enough to overall image size that they wish to push them out of
line. However, in the process we have grown a second copy of the
implementation of each of these routines for each memory model. Share the
implmentation exposing it either inline or out-of-line as required.
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* git://git.infradead.org/hdrcleanup-2.6: (63 commits)
[S390] __FD_foo definitions.
Switch to __s32 types in joystick.h instead of C99 types for consistency.
Add <sys/types.h> to headers included for userspace in <linux/input.h>
Move inclusion of <linux/compat.h> out of user scope in asm-x86_64/mtrr.h
Remove struct fddi_statistics from user view in <linux/if_fddi.h>
Move user-visible parts of drivers/s390/crypto/z90crypt.h to include/asm-s390
Revert include/media changes: Mauro says those ioctls are only used in-kernel(!)
Include <linux/types.h> and use __uXX types in <linux/cramfs_fs.h>
Use __uXX types in <linux/i2o_dev.h>, include <linux/ioctl.h> too
Remove private struct dx_hash_info from public view in <linux/ext3_fs.h>
Include <linux/types.h> and use __uXX types in <linux/affs_hardblocks.h>
Use __uXX types in <linux/divert.h> for struct divert_blk et al.
Use __u32 for elf_addr_t in <asm-powerpc/elf.h>, not u32. It's user-visible.
Remove PPP_FCS from user view in <linux/ppp_defs.h>, remove __P mess entirely
Use __uXX types in user-visible structures in <linux/nbd.h>
Don't use 'u32' in user-visible struct ip_conntrack_old_tuple.
Use __uXX types for S390 DASD volume label definitions which are user-visible
S390 BIODASDREADCMB ioctl should use __u64 not u64 type.
Remove unneeded inclusion of <linux/time.h> from <linux/ufs_fs.h>
Fix private integer types used in V4L2 ioctls.
...
Manually resolve conflict in include/linux/mtd/physmap.h
This adds the Kbuild files listing the files which are to be installed by
the 'headers_install' make target, in generic directories.
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
If we move a mapping from one virtual address to another,
and this changes the virtual color of the mapping to those
pages, we can see corrupt data due to D-cache aliasing.
Check for and deal with this by overriding the move_pte()
macro. Set things up so that other platforms can cleanly
override the move_pte() macro too.
Signed-off-by: David S. Miller <davem@davemloft.net>
Turn some macros into inline functions and add proper type checking as
well as being more readable. Also a minor comment adjustment.
Signed-off-by: Nicolas Pitre <nico@cam.org>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
local_t's were defined to be unsigned. This increases confusion because
atomic_t's are signed. The patch goes through and changes all implementations
to use signed longs throughout.
Also, x86-64 was using 32-bit quantities for the value passed into local_add()
and local_sub(). Fixed.
All (actually, both) existing users have been audited.
(Also s/__inline__/inline/ in x86_64/local.h)
Cc: Andi Kleen <ak@muc.de>
Cc: Benjamin LaHaise <bcrl@kvack.org>
Cc: Kyle McMartin <kyle@parisc-linux.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Now that Christoph Lameter's atomic_long_t support is merged in mainline,
might as well convert asm-generic/local.h to use it, so the same code can
be used for both sizes of 32 and 64-bit unsigned longs.
akpm sayeth:
Q:
Is there any particular reason why these routines weren't simply
implemented with local_save/restore_flags, if they are only meant to
guarantee atomicity to the local cpu? I'm sure on most platforms this
would be more efficient than using an atomic...
A:
The whole _point_ of local_t is to avoid local_irq_disable(). It's
designed to exploit the fact that many CPUs can do incs and decs in a way
which is atomic wrt local interrupts, but not atomic wrt SMP.
But this patch makes sense, because asm-generic/local.h is just a fallback
implementation for architectures which either cannot perform these
local-irq-atomic operations, or its maintainers haven't yet got around to
implementing them.
We need more work done on local_t in the 2.6.17 timeframe - they're defined as
unsigned long, but some architectures implement them as signed long.
Signed-off-by: Kyle McMartin <kyle@parisc-linux.org>
Cc: Benjamin LaHaise <bcrl@kvack.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
- fix: initialize the robust list(s) to NULL in copy_process.
- doc update
- cleanup: rename _inuser to _inatomic
- __user cleanups and other small cleanups
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Arjan van de Ven <arjan@infradead.org>
Cc: Ulrich Drepper <drepper@redhat.com>
Cc: Andi Kleen <ak@muc.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patchset provides a new (written from scratch) implementation of robust
futexes, called "lightweight robust futexes". We believe this new
implementation is faster and simpler than the vma-based robust futex solutions
presented before, and we'd like this patchset to be adopted in the upstream
kernel. This is version 1 of the patchset.
Background
----------
What are robust futexes? To answer that, we first need to understand what
futexes are: normal futexes are special types of locks that in the
noncontended case can be acquired/released from userspace without having to
enter the kernel.
A futex is in essence a user-space address, e.g. a 32-bit lock variable
field. If userspace notices contention (the lock is already owned and someone
else wants to grab it too) then the lock is marked with a value that says
"there's a waiter pending", and the sys_futex(FUTEX_WAIT) syscall is used to
wait for the other guy to release it. The kernel creates a 'futex queue'
internally, so that it can later on match up the waiter with the waker -
without them having to know about each other. When the owner thread releases
the futex, it notices (via the variable value) that there were waiter(s)
pending, and does the sys_futex(FUTEX_WAKE) syscall to wake them up. Once all
waiters have taken and released the lock, the futex is again back to
'uncontended' state, and there's no in-kernel state associated with it. The
kernel completely forgets that there ever was a futex at that address. This
method makes futexes very lightweight and scalable.
"Robustness" is about dealing with crashes while holding a lock: if a process
exits prematurely while holding a pthread_mutex_t lock that is also shared
with some other process (e.g. yum segfaults while holding a pthread_mutex_t,
or yum is kill -9-ed), then waiters for that lock need to be notified that the
last owner of the lock exited in some irregular way.
To solve such types of problems, "robust mutex" userspace APIs were created:
pthread_mutex_lock() returns an error value if the owner exits prematurely -
and the new owner can decide whether the data protected by the lock can be
recovered safely.
There is a big conceptual problem with futex based mutexes though: it is the
kernel that destroys the owner task (e.g. due to a SEGFAULT), but the kernel
cannot help with the cleanup: if there is no 'futex queue' (and in most cases
there is none, futexes being fast lightweight locks) then the kernel has no
information to clean up after the held lock! Userspace has no chance to clean
up after the lock either - userspace is the one that crashes, so it has no
opportunity to clean up. Catch-22.
In practice, when e.g. yum is kill -9-ed (or segfaults), a system reboot is
needed to release that futex based lock. This is one of the leading
bugreports against yum.
To solve this problem, 'Robust Futex' patches were created and presented on
lkml: the one written by Todd Kneisel and David Singleton is the most advanced
at the moment. These patches all tried to extend the futex abstraction by
registering futex-based locks in the kernel - and thus give the kernel a
chance to clean up.
E.g. in David Singleton's robust-futex-6.patch, there are 3 new syscall
variants to sys_futex(): FUTEX_REGISTER, FUTEX_DEREGISTER and FUTEX_RECOVER.
The kernel attaches such robust futexes to vmas (via
vma->vm_file->f_mapping->robust_head), and at do_exit() time, all vmas are
searched to see whether they have a robust_head set.
Lots of work went into the vma-based robust-futex patch, and recently it has
improved significantly, but unfortunately it still has two fundamental
problems left:
- they have quite complex locking and race scenarios. The vma-based
patches had been pending for years, but they are still not completely
reliable.
- they have to scan _every_ vma at sys_exit() time, per thread!
The second disadvantage is a real killer: pthread_exit() takes around 1
microsecond on Linux, but with thousands (or tens of thousands) of vmas every
pthread_exit() takes a millisecond or more, also totally destroying the CPU's
L1 and L2 caches!
This is very much noticeable even for normal process sys_exit_group() calls:
the kernel has to do the vma scanning unconditionally! (this is because the
kernel has no knowledge about how many robust futexes there are to be cleaned
up, because a robust futex might have been registered in another task, and the
futex variable might have been simply mmap()-ed into this process's address
space).
This huge overhead forced the creation of CONFIG_FUTEX_ROBUST, but worse than
that: the overhead makes robust futexes impractical for any type of generic
Linux distribution.
So it became clear to us, something had to be done. Last week, when Thomas
Gleixner tried to fix up the vma-based robust futex patch in the -rt tree, he
found a handful of new races and we were talking about it and were analyzing
the situation. At that point a fundamentally different solution occured to
me. This patchset (written in the past couple of days) implements that new
solution. Be warned though - the patchset does things we normally dont do in
Linux, so some might find the approach disturbing. Parental advice
recommended ;-)
New approach to robust futexes
------------------------------
At the heart of this new approach there is a per-thread private list of robust
locks that userspace is holding (maintained by glibc) - which userspace list
is registered with the kernel via a new syscall [this registration happens at
most once per thread lifetime]. At do_exit() time, the kernel checks this
user-space list: are there any robust futex locks to be cleaned up?
In the common case, at do_exit() time, there is no list registered, so the
cost of robust futexes is just a simple current->robust_list != NULL
comparison. If the thread has registered a list, then normally the list is
empty. If the thread/process crashed or terminated in some incorrect way then
the list might be non-empty: in this case the kernel carefully walks the list
[not trusting it], and marks all locks that are owned by this thread with the
FUTEX_OWNER_DEAD bit, and wakes up one waiter (if any).
The list is guaranteed to be private and per-thread, so it's lockless. There
is one race possible though: since adding to and removing from the list is
done after the futex is acquired by glibc, there is a few instructions window
for the thread (or process) to die there, leaving the futex hung. To protect
against this possibility, userspace (glibc) also maintains a simple per-thread
'list_op_pending' field, to allow the kernel to clean up if the thread dies
after acquiring the lock, but just before it could have added itself to the
list. Glibc sets this list_op_pending field before it tries to acquire the
futex, and clears it after the list-add (or list-remove) has finished.
That's all that is needed - all the rest of robust-futex cleanup is done in
userspace [just like with the previous patches].
Ulrich Drepper has implemented the necessary glibc support for this new
mechanism, which fully enables robust mutexes. (Ulrich plans to commit these
changes to glibc-HEAD later today.)
Key differences of this userspace-list based approach, compared to the vma
based method:
- it's much, much faster: at thread exit time, there's no need to loop
over every vma (!), which the VM-based method has to do. Only a very
simple 'is the list empty' op is done.
- no VM changes are needed - 'struct address_space' is left alone.
- no registration of individual locks is needed: robust mutexes dont need
any extra per-lock syscalls. Robust mutexes thus become a very lightweight
primitive - so they dont force the application designer to do a hard choice
between performance and robustness - robust mutexes are just as fast.
- no per-lock kernel allocation happens.
- no resource limits are needed.
- no kernel-space recovery call (FUTEX_RECOVER) is needed.
- the implementation and the locking is "obvious", and there are no
interactions with the VM.
Performance
-----------
I have benchmarked the time needed for the kernel to process a list of 1
million (!) held locks, using the new method [on a 2GHz CPU]:
- with FUTEX_WAIT set [contended mutex]: 130 msecs
- without FUTEX_WAIT set [uncontended mutex]: 30 msecs
I have also measured an approach where glibc does the lock notification [which
it currently does for !pshared robust mutexes], and that took 256 msecs -
clearly slower, due to the 1 million FUTEX_WAKE syscalls userspace had to do.
(1 million held locks are unheard of - we expect at most a handful of locks to
be held at a time. Nevertheless it's nice to know that this approach scales
nicely.)
Implementation details
----------------------
The patch adds two new syscalls: one to register the userspace list, and one
to query the registered list pointer:
asmlinkage long
sys_set_robust_list(struct robust_list_head __user *head,
size_t len);
asmlinkage long
sys_get_robust_list(int pid, struct robust_list_head __user **head_ptr,
size_t __user *len_ptr);
List registration is very fast: the pointer is simply stored in
current->robust_list. [Note that in the future, if robust futexes become
widespread, we could extend sys_clone() to register a robust-list head for new
threads, without the need of another syscall.]
So there is virtually zero overhead for tasks not using robust futexes, and
even for robust futex users, there is only one extra syscall per thread
lifetime, and the cleanup operation, if it happens, is fast and
straightforward. The kernel doesnt have any internal distinction between
robust and normal futexes.
If a futex is found to be held at exit time, the kernel sets the highest bit
of the futex word:
#define FUTEX_OWNER_DIED 0x40000000
and wakes up the next futex waiter (if any). User-space does the rest of
the cleanup.
Otherwise, robust futexes are acquired by glibc by putting the TID into the
futex field atomically. Waiters set the FUTEX_WAITERS bit:
#define FUTEX_WAITERS 0x80000000
and the remaining bits are for the TID.
Testing, architecture support
-----------------------------
I've tested the new syscalls on x86 and x86_64, and have made sure the parsing
of the userspace list is robust [ ;-) ] even if the list is deliberately
corrupted.
i386 and x86_64 syscalls are wired up at the moment, and Ulrich has tested the
new glibc code (on x86_64 and i386), and it works for his robust-mutex
testcases.
All other architectures should build just fine too - but they wont have the
new syscalls yet.
Architectures need to implement the new futex_atomic_cmpxchg_inuser() inline
function before writing up the syscalls (that function returns -ENOSYS right
now).
This patch:
Add placeholder futex_atomic_cmpxchg_inuser() implementations to every
architecture that supports futexes. It returns -ENOSYS.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Arjan van de Ven <arjan@infradead.org>
Acked-by: Ulrich Drepper <drepper@redhat.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch removes zone_mem_map.
pfn_to_page uses pgdat, page_to_pfn uses zone. page_to_pfn can use pgdat
instead of zone, which is only one user of zone_mem_map. By modifing it,
we can remove zone_mem_map.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Dave Hansen <haveblue@us.ibm.com>
Cc: Christoph Lameter <christoph@lameter.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
There are 3 memory models, FLATMEM, DISCONTIGMEM, SPARSEMEM.
Each arch has its own page_to_pfn(), pfn_to_page() for each models.
But most of them can use the same arithmetic.
This patch adds asm-generic/memory_model.h, which includes generic
page_to_pfn(), pfn_to_page() definitions for each memory model.
When CONFIG_OUT_OF_LINE_PFN_TO_PAGE=y, out-of-line functions are
used instead of macro. This is enabled by some archs and reduces
text size.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Andi Kleen <ak@muc.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Russell King <rmk@arm.linux.org.uk>
Cc: Ian Molton <spyro@f2s.com>
Cc: Mikael Starvik <starvik@axis.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: Hirokazu Takata <takata.hirokazu@renesas.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Kazumoto Kojima <kkojima@rr.iij4u.or.jp>
Cc: Richard Curnow <rc@rc0.org.uk>
Cc: William Lee Irwin III <wli@holomorphy.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jeff Dike <jdike@addtoit.com>
Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it>
Cc: Miles Bader <uclinux-v850@lsi.nec.co.jp>
Cc: Chris Zankel <chris@zankel.net>
Cc: "Luck, Tony" <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Currently include/asm-generic/bitops.h is not referenced from anywhere. But
it will be the benefit of those who are trying to port Linux to another
architecture.
So update it by same manner
Signed-off-by: Akinobu Mita <mita@miraclelinux.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch introduces the C-language equivalents of the functions below:
int minix_test_and_set_bit(int nr, volatile unsigned long *addr);
int minix_set_bit(int nr, volatile unsigned long *addr);
int minix_test_and_clear_bit(int nr, volatile unsigned long *addr);
int minix_test_bit(int nr, const volatile unsigned long *addr);
unsigned long minix_find_first_zero_bit(const unsigned long *addr,
unsigned long size);
In include/asm-generic/bitops/minix.h
and include/asm-generic/bitops/minix-le.h
This code largely copied from: include/asm-sparc/bitops.h
Signed-off-by: Akinobu Mita <mita@miraclelinux.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch introduces the C-language equivalents of the functions below:
int ext2_set_bit_atomic(int nr, volatile unsigned long *addr);
int ext2_clear_bit_atomic(int nr, volatile unsigned long *addr);
In include/asm-generic/bitops/ext2-atomic.h
This code largely copied from: include/asm-sparc/bitops.h
Signed-off-by: Akinobu Mita <mita@miraclelinux.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch introduces the C-language equivalents of the functions below:
int ext2_set_bit(int nr, volatile unsigned long *addr);
int ext2_clear_bit(int nr, volatile unsigned long *addr);
int ext2_test_bit(int nr, const volatile unsigned long *addr);
unsigned long ext2_find_first_zero_bit(const unsigned long *addr,
unsigned long size);
unsinged long ext2_find_next_zero_bit(const unsigned long *addr,
unsigned long size);
In include/asm-generic/bitops/ext2-non-atomic.h
This code largely copied from:
include/asm-powerpc/bitops.h
include/asm-parisc/bitops.h
Signed-off-by: Akinobu Mita <mita@miraclelinux.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Build fix for s390 declare __u32 and __u64.
Signed-off-by: Akinobu Mita <mita@miraclelinux.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch introduces the C-language equivalents of the functions below:
unsigned int hweight32(unsigned int w);
unsigned int hweight16(unsigned int w);
unsigned int hweight8(unsigned int w);
unsigned long hweight64(__u64 w);
In include/asm-generic/bitops/hweight.h
This code largely copied from: include/linux/bitops.h
Signed-off-by: Akinobu Mita <mita@miraclelinux.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch introduces the C-language equivalent of the function: int ffs(int
x);
In include/asm-generic/bitops/ffs.h
This code largely copied from: include/linux/bitops.h
Signed-off-by: Akinobu Mita <mita@miraclelinux.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch introduces the C-language equivalent of the function: int
sched_find_first_bit(const unsigned long *b);
In include/asm-generic/bitops/sched.h
This code largely copied from: include/asm-powerpc/bitops.h
Signed-off-by: Akinobu Mita <mita@miraclelinux.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch introduces the C-language equivalents of the functions below:
unsigned logn find_next_bit(const unsigned long *addr, unsigned long size,
unsigned long offset);
unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
unsigned long offset);
unsigned long find_first_zero_bit(const unsigned long *addr,
unsigned long size);
unsigned long find_first_bit(const unsigned long *addr, unsigned long size);
In include/asm-generic/bitops/find.h
This code largely copied from: arch/powerpc/lib/bitops.c
Signed-off-by: Akinobu Mita <mita@miraclelinux.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch introduces the C-language equivalent of the function: int
fls64(__u64 x);
In include/asm-generic/bitops/fls64.h
This code largely copied from: include/linux/bitops.h
Signed-off-by: Akinobu Mita <mita@miraclelinux.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch introduces the C-language equivalent of the function: int fls(int
x);
In include/asm-generic/bitops/fls.h
This code largely copied from: include/linux/bitops.h
Signed-off-by: Akinobu Mita <mita@miraclelinux.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch introduces the C-language equivalent of the function: unsigned long
ffz(unsigned long word);
In include/asm-generic/bitops/ffz.h
This code largely copied from: include/asm-parisc/bitops.h
Signed-off-by: Akinobu Mita <mita@miraclelinux.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch introduces the C-language equivalent of the function: unsigned long
__ffs(unsigned long word);
In include/asm-generic/bitops/__ffs.h
This code largely copied from: include/asm-sparc/bitops.h
Signed-off-by: Akinobu Mita <mita@miraclelinux.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
