Currently cpu and unit are always identity mapped. To allow more
efficient large page support on NUMA and lazy allocation for possible
but offline cpus, cpu -> unit mapping needs to be non-linear and/or
sparse. This can be easily implemented by adding a cpu -> unit
mapping array and using it whenever looking up the matching unit for a
cpu.
The only unusal conversion is in pcpu_chunk_addr_search(). The passed
in address is unit0 based and unit0 might not be in use so it needs to
be converted to address of an in-use unit. This is easily done by
adding the unit offset for the current processor.
[ Impact: allows non-linear/sparse cpu -> unit mapping, no visible change yet ]
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: David Miller <davem@davemloft.net>
percpu core doesn't need to tack all the allocated pages. It needs to
know whether certain pages are populated and a way to reverse map
address to page when freeing. This patch drops pcpu_chunk->page[] and
use populated bitmap and vmalloc_to_page() lookup instead. Using
vmalloc_to_page() exclusively is also possible but complicates first
chunk handling, inflates cache footprint and prevents non-standard
memory allocation for percpu memory.
pcpu_chunk->page[] was used to track each page's allocation and
allowed asymmetric population which happens during failure path;
however, with single bitmap for all units, this is no longer possible.
Bite the bullet and rewrite (de)populate functions so that things are
done in clearly separated steps such that asymmetric population
doesn't happen. This makes the (de)population process much more
modular and will also ease implementing non-standard memory usage in
the future (e.g. large pages).
This makes @get_page_fn parameter to pcpu_setup_first_chunk()
unnecessary. The parameter is dropped and all first chunk helpers are
updated accordingly. Please note that despite the volume most changes
to first chunk helpers are symbol renames for variables which don't
need to be referenced outside of the helper anymore.
This change reduces memory usage and cache footprint of pcpu_chunk.
Now only #unit_pages bits are necessary per chunk.
[ Impact: reduced memory usage and cache footprint for bookkeeping ]
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: David Miller <davem@davemloft.net>
Now that all first chunk allocator helpers allocate and map the first
chunk themselves, there's no need to have optional default alloc/map
in pcpu_setup_first_chunk(). Drop @populate_pte_fn and only leave
@dyn_size optional and make all other params mandatory.
This makes it much easier to follow what pcpu_setup_first_chunk() is
doing and what actual differences tweaking each parameter results in.
[ Impact: drop unused code path ]
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Ingo Molnar <mingo@elte.hu>
Pull linus#master to merge PER_CPU_DEF_ATTRIBUTES and alpha build fix
changes. As alpha in percpu tree uses 'weak' attribute instead of
inline assembly, there's no need for __used attribute.
Conflicts:
arch/alpha/include/asm/percpu.h
arch/mn10300/kernel/vmlinux.lds.S
include/linux/percpu-defs.h
The tftpboot build was failing with missing file errors.
It turns out that $(obj)/image wasn't being generated which was causing the a.out conversion to be skipped and hence piggyback to be called with nonexistent files.
Signed-off-by: Julian Calaby <julian.calaby@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Kjetil Oftedal mentioned that piggyback_32 was failing
when building a sparc image.
I tracked this down to the fact that the kernel no longer
provided an absolute symbol named "end".
Commit 86ed40bd6f ("sparc: unify sections.h")
renamed end to _end but failed to update piggyback_32.
Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
Cc: Kjetil Oftedal <oftedal@gmail.com>
Cc: Robert Reif <reif@earthlink.net>
Signed-off-by: Julian Calaby <julian.calaby@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch fixes the following build warnings:
arch/sparc/boot/piggyback_64.c: In function 'main':
arch/sparc/boot/piggyback_64.c:44: warning: 'end' may be used uninitialized in this function
arch/sparc/boot/piggyback_64.c:44: warning: 'start' may be used uninitialized in this function
Signed-off-by: Julian Calaby <julian.calaby@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The page allocator and SLAB are available at this point now,
and if we still try to use bootmem allocations here the kernel
spits out warnings.
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit e74e396204 incorrectly added
HAVE_LEGACY_PER_CPU_AREA to sparc64 although it already has been
converted to dynamic percpu allocator. Drop both
HAVE_{LEGACY|DYNAMIC}_PER_CPU_AREA.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: David Miller <davem@davemloft.net>
x86 throws away .discard section but no other archs do. Also,
.discard is not thrown away while linking modules. Make every arch
and module linking throw it away. This will be used to define dummy
variables for percpu declarations and definitions.
This patch is based on Ivan Kokshaysky's alpha percpu patch.
[ Impact: always throw away everything in .discard ]
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Haavard Skinnemoen <hskinnemoen@atmel.com>
Cc: Bryan Wu <cooloney@kernel.org>
Cc: Mikael Starvik <starvik@axis.com>
Cc: Jesper Nilsson <jesper.nilsson@axis.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Hirokazu Takata <takata@linux-m32r.org>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: David S. Miller <davem@davemloft.net>
Cc: Jeff Dike <jdike@addtoit.com>
Cc: Chris Zankel <chris@zankel.net>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Ingo Molnar <mingo@elte.hu>
This patch makes most !CONFIG_HAVE_SETUP_PER_CPU_AREA archs use
dynamic percpu allocator. The first chunk is allocated using
embedding helper and 8k is reserved for modules. This ensures that
the new allocator behaves almost identically to the original allocator
as long as static percpu variables are concerned, so it shouldn't
introduce much breakage.
s390 and alpha use custom SHIFT_PERCPU_PTR() to work around addressing
range limit the addressing model imposes. Unfortunately, this breaks
if the address is specified using a variable, so for now, the two
archs aren't converted.
The following architectures are affected by this change.
* sh
* arm
* cris
* mips
* sparc(32)
* blackfin
* avr32
* parisc (broken, under investigation)
* m32r
* powerpc(32)
As this change makes the dynamic allocator the default one,
CONFIG_HAVE_DYNAMIC_PER_CPU_AREA is replaced with its invert -
CONFIG_HAVE_LEGACY_PER_CPU_AREA, which is added to yet-to-be converted
archs. These archs implement their own setup_per_cpu_areas() and the
conversion is not trivial.
* powerpc(64)
* sparc(64)
* ia64
* alpha
* s390
Boot and batch alloc/free tests on x86_32 with debug code (x86_32
doesn't use default first chunk initialization). Compile tested on
sparc(32), powerpc(32), arm and alpha.
Kyle McMartin reported that this change breaks parisc. The problem is
still under investigation and he is okay with pushing this patch
forward and fixing parisc later.
[ Impact: use dynamic allocator for most archs w/o custom percpu setup ]
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Reviewed-by: Christoph Lameter <cl@linux.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Russell King <rmk@arm.linux.org.uk>
Cc: Mikael Starvik <starvik@axis.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Bryan Wu <cooloney@kernel.org>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Matthew Wilcox <matthew@wil.cx>
Cc: Grant Grundler <grundler@parisc-linux.org>
Cc: Hirokazu Takata <takata@linux-m32r.org>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Ingo Molnar <mingo@elte.hu>
This allows the callers to now pass down the full set of FAULT_FLAG_xyz
flags to handle_mm_fault(). All callers have been (mechanically)
converted to the new calling convention, there's almost certainly room
for architectures to clean up their code and then add FAULT_FLAG_RETRY
when that support is added.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit b696fdc259 ("sparc64: Defer
cpu_data() setup until end of per-cpu data initialization.") broke
bootup for UP builds because the cpu_data() initialization only
occurs in setup_per_cpu_areas() which is never compiled in nor
called in UP builds.
Fix this up by calling the setups directly from init_64.c when
non-SMP.
Reported-by: Alexander Beregalov <a.beregalov@gmail.com>
Tested-by: Alexander Beregalov <a.beregalov@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This function was only used by pci_claim_resource(), and the last commit
deleted that use.
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* akpm: (182 commits)
fbdev: bf54x-lq043fb: use kzalloc over kmalloc/memset
fbdev: *bfin*: fix __dev{init,exit} markings
fbdev: *bfin*: drop unnecessary calls to memset
fbdev: bfin-t350mcqb-fb: drop unused local variables
fbdev: blackfin has __raw I/O accessors, so use them in fb.h
fbdev: s1d13xxxfb: add accelerated bitblt functions
tcx: use standard fields for framebuffer physical address and length
fbdev: add support for handoff from firmware to hw framebuffers
intelfb: fix a bug when changing video timing
fbdev: use framebuffer_release() for freeing fb_info structures
radeon: P2G2CLK_ALWAYS_ONb tested twice, should 2nd be P2G2CLK_DAC_ALWAYS_ONb?
s3c-fb: CPUFREQ frequency scaling support
s3c-fb: fix resource releasing on error during probing
carminefb: fix possible access beyond end of carmine_modedb[]
acornfb: remove fb_mmap function
mb862xxfb: use CONFIG_OF instead of CONFIG_PPC_OF
mb862xxfb: restrict compliation of platform driver to PPC
Samsung SoC Framebuffer driver: add Alpha Channel support
atmel-lcdc: fix pixclock upper bound detection
offb: use framebuffer_alloc() to allocate fb_info struct
...
Manually fix up conflicts due to kmemcheck in mm/slab.c
Convert most arches to use asm-generic/kmap_types.h.
Move the KM_FENCE_ macro additions into asm-generic/kmap_types.h,
controlled by __WITH_KM_FENCE from each arch's kmap_types.h file.
Would be nice to be able to add custom KM_types per arch, but I don't yet
see a nice, clean way to do that.
Built on x86_64, i386, mips, sparc, alpha(tonyb), powerpc(tonyb), and
68k(tonyb).
Note: avr32 should be able to remove KM_PTE2 (since it's not used) and
then just use the generic kmap_types.h file. Get avr32 maintainer
approval.
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Cc: <linux-arch@vger.kernel.org>
Acked-by: Mike Frysinger <vapier@gentoo.org>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Bryan Wu <cooloney@kernel.org>
Cc: Mikael Starvik <starvik@axis.com>
Cc: Hirokazu Takata <takata@linux-m32r.org>
Cc: "Luck Tony" <tony.luck@intel.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* create mm/init-mm.c, move init_mm there
* remove INIT_MM, initialize init_mm with C99 initializer
* unexport init_mm on all arches:
init_mm is already unexported on x86.
One strange place is some OMAP driver (drivers/video/omap/) which
won't build modular, but it's already wants get_vm_area() export.
Somebody should look there.
[akpm@linux-foundation.org: add missing #includes]
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Mike Frysinger <vapier.adi@gmail.com>
Cc: Americo Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
CPU_MASK_ALL is the (deprecated) "all bits set" cpumask, defined as so:
#define CPU_MASK_ALL (cpumask_t) { { ... } }
Taking the address of such a temporary is questionable at best,
unfortunately 321a8e9d (cpumask: add CPU_MASK_ALL_PTR macro) added
CPU_MASK_ALL_PTR:
#define CPU_MASK_ALL_PTR (&CPU_MASK_ALL)
Which formalizes this practice. One day gcc could bite us over this
usage (though we seem to have gotten away with it so far).
[Description by Rusty Russell]
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch moves code common to of_device_32.c and of_device_64.c into
of_device_common.h and of_device_common.c.
The only functional difference is in sparc32 where of_bus_default_map is
used in place of of_bus_sbus_map because they are equivelent.
There is still room for further code consolidation with some minor
refactoring.
Boot tested on sparc32 and compile tested on sparc64.
Signed-off-by: Robert Reif <reif@earthlink.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
This modifies SPARC32 to use struct dma_map ops. It means that we can
remove dma-mapping_{32|64}.h.
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Tested-by: Robert Reif <reif@earthlink.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch converts dma_map_single and dma_unmap_single to use
map_page and unmap_page respectively and removes unnecessary
map_single and unmap_single. map_page can be used to implement
map_single but the opposite is impossible. Having only dma_map_page in
struct dma_ops is enough.
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Tested-by: Robert Reif <reif@earthlink.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
This adds sync_single_for_device() and sync_sg_for_device() to struct
dma_ops in order to unify dma-mpping_{32|64}.h. dma-mpping_32.h needs them though dma-mpping_64.h doesn't.
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Tested-by: Robert Reif <reif@earthlink.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Tested-by: Robert Reif <reif@earthlink.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
irq_choose_cpu() should compare the affinity mask against cpu_online_map
rather than CPU_MASK_ALL, since irq_select_affinity() sets the interrupt's
affinity mask to cpu_online_map "and" CPU_MASK_ALL (which ends up being
just cpu_online_map). The mask comparison in irq_choose_cpu() will always
fail since the two masks are not the same. So the CPU chosen is the first CPU
in the intersection of cpu_online_map and CPU_MASK_ALL, which is always CPU0.
That means all interrupts are reassigned to CPU0...
Distributing interrupts to CPUs in a linearly increasing round robin fashion
is not optimal for the UltraSPARC T1/T2. Also, the irq_rover in
irq_choose_cpu() causes an interrupt to be assigned to a different
processor each time the interrupt is allocated and released. This may lead
to an unbalanced distribution over time.
A static mapping of interrupts to processors is done to optimize and balance
interrupt distribution. For the T1/T2, interrupts are spread to different
cores first, and then to strands within a core.
The following is some benchmarks showing the effects of interrupt
distribution on a T2. The test was done with iperf using a pair of T5220
boxes, each with a 10GBe NIU (XAUI) connected back to back.
TCP | Stock Linear RR IRQ Optimized IRQ
Streams | 2.6.30-rc5 Distribution Distribution
| GBits/sec GBits/sec GBits/sec
--------+-----------------------------------------
1 0.839 0.862 0.868
8 1.16 4.96 5.88
16 1.15 6.40 8.04
100 1.09 7.28 8.68
Signed-off-by: Hong H. Pham <hong.pham@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This gets us real close to the generic implementation of
setup_per_cpu_areas() except:
1) We store the per-cpu offset into the trap_block[], whereas
the generic code has it's own static array.
2) We have to initialize the %g5 register to hold the boot cpu's
per-cpu area offset.
3) The OBP/MDESC cpu info scan is performed at the end.
Signed-off-by: David S. Miller <davem@davemloft.net>
Now that we defer the cpu_data() initializations to the end of per-cpu
setup, we can get rid of this local hack we had to setup the per-cpu
areas eary.
This is a necessary step in order to support HAVE_DYNAMIC_PER_CPU_AREA
since the per-cpu setup must run when page structs are available.
Signed-off-by: David S. Miller <davem@davemloft.net>
We need to split up the cpu present mask setup from the cpu_data
initialization, and this is a first step towards that.
Signed-off-by: David S. Miller <davem@davemloft.net>
Later we're going to want to get at these definitions from
asm/percpu.h and that's not possible via cpudata.h because
of the set of dependencies the non-trap_block[] stuff has.
Signed-off-by: David S. Miller <davem@davemloft.net>
This really isn't necessary at all, a local variable suits the
job just fine.
This frees up 8 bytes in the trap_block[] that we can use later
to store the per-cpu base addresses.
Signed-off-by: David S. Miller <davem@davemloft.net>
Everyone cut and paste this comment from my original one. We now do
it generically, so cut the comments.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Cc: Amerigo Wang <amwang@redhat.com>
It's theoretically possible that there are exception table entries
which point into the (freed) init text of modules. These could cause
future problems if other modules get loaded into that memory and cause
an exception as we'd see the wrong fixup. The only case I know of is
kvm-intel.ko (when CONFIG_CC_OPTIMIZE_FOR_SIZE=n).
Amerigo fixed this long-standing FIXME in the x86 version, but this
patch is more general.
This implements trim_init_extable(); most archs are simple since they
use the standard lib/extable.c sort code. Alpha and IA64 use relative
addresses in their fixups, so thier trimming is a slight variation.
Sparc32 is unique; it doesn't seem to define ARCH_HAS_SORT_EXTABLE,
yet it defines its own sort_extable() which overrides the one in lib.
It doesn't sort, so we have to mark deleted entries instead of
actually trimming them.
Inspired-by: Amerigo Wang <amwang@redhat.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Cc: linux-alpha@vger.kernel.org
Cc: sparclinux@vger.kernel.org
Cc: linux-ia64@vger.kernel.org
The current asm-generic/page.h only contains the get_order
function, and asm-generic/uaccess.h only implements
unaligned accesses. This renames the file to getorder.h
and uaccess-unaligned.h to make room for new page.h
and uaccess.h file that will be usable by all simple
(e.g. nommu) architectures.
Signed-off-by: Remis Lima Baima <remis.developer@googlemail.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
The existing asm-generic/atomic.h only defines the
atomic_long type. This renames it to atomic-long.h
so we have a place to add a truly generic atomic.h
that can be used on all non-SMP systems.
Signed-off-by: Remis Lima Baima <remis.developer@googlemail.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Ingo Molnar <mingo@elte.hu>
