When I removed the powermac support from arch/ppc/kernel/pci.c,
I overlooked the fact that that file is used in 32-bit ARCH=powerpc
builds. To prevent problems in future, restore the original version
of that file as arch/powerpc/kernel/pci_32.c, and use that.
Signed-off-by: Paul Mackerras <paulus@samba.org>
This makes it possible to build kernels for PReP and/or CHRP
with ARCH=ppc by removing the (non-building) powermac support.
It's now also possible to select PReP and CHRP independently.
Powermac users should now build with ARCH=powerpc instead of
ARCH=ppc. (This does mean that it is no longer possible to
build a 32-bit kernel for a G5.)
Signed-off-by: Paul Mackerras <paulus@samba.org>
tmp_buf_sem sems to be a common name for something completely unused...
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Acked-by: Greg Kroah-Hartman <gregkh@suse.de> ("usb portion")
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
The arch/powerpc version of process.c exports get_wchan itself. When
I moved ARCH=ppc over to using arch/powerpc/kernel/process.c the
get_wchan export in arch/ppc/kernel/ppc_ksyms.c became redundant, so
remove it.
Signed-off-by: Paul Mackerras <paulus@samba.org>
(cherry picked from 9871166ad692121d6b944159ef3f053570158ea8 commit)
The following implements support for instantiation of 8MB D-TLB
entries for the kernel direct virtual mapping on 8xx, thus reducing TLB
space consumed for the kernel.
Test used: writing 40MB from /dev/zero to file in ext2fs over
RAMDISK.
$ time dd if=/dev/zero of=file bs=4k count=10000
VANILLA 8MB kernel data pages
real 0m11.485s real 0m11.267s
user 0m0.218s user 0m0.250s
sys 0m8.939s sys 0m9.108s
real 0m11.518s real 0m10.978s
user 0m0.203s user 0m0.222s
sys 0m9.585s sys 0m9.138s
real 0m11.554s real 0m10.967s
user 0m0.228s user 0m0.222s
sys 0m9.497s sys 0m9.127s
real 0m11.633s real 0m11.286s
user 0m0.214s user 0m0.196s
sys 0m9.529s sys 0m9.134s
and averages for both:
real 11.54750 real 11.12450
Which is a 3.6% improvement in execution time. More improvement is
expected for loads with larger kernel data footprint (real workloads).
Signed-off-by: Marcelo Tosatti <marcelo.tosatti@cyclades.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
The gianfar driver changed how it required MDIO bus and phy id's
to be passed to it. Also, it no longer passes the physical address
of the MDIO bus. Instead we have a proper platform device.
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
in amigahw.h custom renamed to amiga_custom, in drivers with few instances the
same replacement, in the rest - #define custom amiga_custom in driver itself
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Cc: Roman Zippel <zippel@linux-m68k.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
)
From: Ingo Molnar <mingo@elte.hu>
This is the latest version of the scheduler cache-hot-auto-tune patch.
The first problem was that detection time scaled with O(N^2), which is
unacceptable on larger SMP and NUMA systems. To solve this:
- I've added a 'domain distance' function, which is used to cache
measurement results. Each distance is only measured once. This means
that e.g. on NUMA distances of 0, 1 and 2 might be measured, on HT
distances 0 and 1, and on SMP distance 0 is measured. The code walks
the domain tree to determine the distance, so it automatically follows
whatever hierarchy an architecture sets up. This cuts down on the boot
time significantly and removes the O(N^2) limit. The only assumption
is that migration costs can be expressed as a function of domain
distance - this covers the overwhelming majority of existing systems,
and is a good guess even for more assymetric systems.
[ People hacking systems that have assymetries that break this
assumption (e.g. different CPU speeds) should experiment a bit with
the cpu_distance() function. Adding a ->migration_distance factor to
the domain structure would be one possible solution - but lets first
see the problem systems, if they exist at all. Lets not overdesign. ]
Another problem was that only a single cache-size was used for measuring
the cost of migration, and most architectures didnt set that variable
up. Furthermore, a single cache-size does not fit NUMA hierarchies with
L3 caches and does not fit HT setups, where different CPUs will often
have different 'effective cache sizes'. To solve this problem:
- Instead of relying on a single cache-size provided by the platform and
sticking to it, the code now auto-detects the 'effective migration
cost' between two measured CPUs, via iterating through a wide range of
cachesizes. The code searches for the maximum migration cost, which
occurs when the working set of the test-workload falls just below the
'effective cache size'. I.e. real-life optimized search is done for
the maximum migration cost, between two real CPUs.
This, amongst other things, has the positive effect hat if e.g. two
CPUs share a L2/L3 cache, a different (and accurate) migration cost
will be found than between two CPUs on the same system that dont share
any caches.
(The reliable measurement of migration costs is tricky - see the source
for details.)
Furthermore i've added various boot-time options to override/tune
migration behavior.
Firstly, there's a blanket override for autodetection:
migration_cost=1000,2000,3000
will override the depth 0/1/2 values with 1msec/2msec/3msec values.
Secondly, there's a global factor that can be used to increase (or
decrease) the autodetected values:
migration_factor=120
will increase the autodetected values by 20%. This option is useful to
tune things in a workload-dependent way - e.g. if a workload is
cache-insensitive then CPU utilization can be maximized by specifying
migration_factor=0.
I've tested the autodetection code quite extensively on x86, on 3
P3/Xeon/2MB, and the autodetected values look pretty good:
Dual Celeron (128K L2 cache):
---------------------
migration cost matrix (max_cache_size: 131072, cpu: 467 MHz):
---------------------
[00] [01]
[00]: - 1.7(1)
[01]: 1.7(1) -
---------------------
cacheflush times [2]: 0.0 (0) 1.7 (1784008)
---------------------
Here the slow memory subsystem dominates system performance, and even
though caches are small, the migration cost is 1.7 msecs.
Dual HT P4 (512K L2 cache):
---------------------
migration cost matrix (max_cache_size: 524288, cpu: 2379 MHz):
---------------------
[00] [01] [02] [03]
[00]: - 0.4(1) 0.0(0) 0.4(1)
[01]: 0.4(1) - 0.4(1) 0.0(0)
[02]: 0.0(0) 0.4(1) - 0.4(1)
[03]: 0.4(1) 0.0(0) 0.4(1) -
---------------------
cacheflush times [2]: 0.0 (33900) 0.4 (448514)
---------------------
Here it can be seen that there is no migration cost between two HT
siblings (CPU#0/2 and CPU#1/3 are separate physical CPUs). A fast memory
system makes inter-physical-CPU migration pretty cheap: 0.4 msecs.
8-way P3/Xeon [2MB L2 cache]:
---------------------
migration cost matrix (max_cache_size: 2097152, cpu: 700 MHz):
---------------------
[00] [01] [02] [03] [04] [05] [06] [07]
[00]: - 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1)
[01]: 19.2(1) - 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1)
[02]: 19.2(1) 19.2(1) - 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1)
[03]: 19.2(1) 19.2(1) 19.2(1) - 19.2(1) 19.2(1) 19.2(1) 19.2(1)
[04]: 19.2(1) 19.2(1) 19.2(1) 19.2(1) - 19.2(1) 19.2(1) 19.2(1)
[05]: 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) - 19.2(1) 19.2(1)
[06]: 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) - 19.2(1)
[07]: 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) -
---------------------
cacheflush times [2]: 0.0 (0) 19.2 (19281756)
---------------------
This one has huge caches and a relatively slow memory subsystem - so the
migration cost is 19 msecs.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Ashok Raj <ashok.raj@intel.com>
Signed-off-by: Ken Chen <kenneth.w.chen@intel.com>
Cc: <wilder@us.ibm.com>
Signed-off-by: John Hawkes <hawkes@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Commit 5388fb1025 made signal_32.c
use discard_lazy_cpu_state, which broke ARCH=ppc because that
uses the common signal_32.c but has its own process.c. Make ARCH=ppc
use the common process.c to fix this and to reduce the amount
of duplicated code.
Signed-off-by: Paul Mackerras <paulus@samba.org>
arch: Use <linux/capability.h> where capable() is used.
Signed-off-by: Randy Dunlap <rdunlap@xenotime.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Updated Kconfig & Makefiles in prep for adding support for the Freescale
MPC83xx family of processors to arch/powerpc. Moved around some config
options that are more globally applicable to other PowerPC processors.
Added a temporary config option (83xx) to match existing arch/ppc support
for the MPC83xx line.
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
- In case of system crash, current state of cpu registers is saved in memory
in elf note format. So far memory for storing elf notes was being allocated
statically for NR_CPUS.
- This patch introduces dynamic allocation of memory for storing elf notes.
It uses alloc_percpu() interface. This should lead to better memory usage.
- Introduced based on Andi Kleen's and Eric W. Biederman's suggestions.
- This patch also moves memory allocation for elf notes from architecture
dependent portion to architecture independent portion. Now crash_notes is
architecture independent. The whole idea is that size of memory to be
allocated per cpu (MAX_NOTE_BYTES) can be architecture dependent and
allocation of this memory can be architecture independent.
Signed-off-by: Vivek Goyal <vgoyal@in.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
In 2.6.14, we had the following definition of _GLOBAL() in
include/asm-ppc/processor.h:
#define _GLOBAL(n)\
.stabs __stringify(n:F-1),N_FUN,0,0,n;\
.globl n;\
n:
In 2.6.15, as part of the great powerpc merge, we moved this definition to
include/asm-powerpc/ppc_asm.h, where it appears (to 32-bit code) as:
#define _GLOBAL(n) \
.text; \
.stabs __stringify(n:F-1),N_FUN,0,0,n;\
.globl n; \
n:
Mostly, this is fine. However, we also have the following, in
arch/ppc/boot/common/util.S:
.section ".relocate_code","xa"
[...]
_GLOBAL(flush_instruction_cache)
[...]
_GLOBAL(flush_data_cache)
[...]
The addition of the .text section definition in the definition of
_GLOBAL overrides the .relocate_code section definition. As a result,
these two functions don't end up in .relocate_code, so they don't get
relocated correctly, and the boot fails.
There's another suspicious-looking usage at kernel/swsusp.S:37 that
someone should look into. I did not exhaustively search the source
tree, though.
The following is the minimal patch that fixes the immediate problem.
I could easily be convinced that the _GLOBAL definition should be
modified to remove the ".text;" line either instead of, or in addition
to, this fix.
Signed-off-by: Paul Janzen <pcj@linux.sez.to>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Configurable 16-bit UID and friends support
This allows turning off the legacy 16 bit UID interfaces on embedded platforms.
text data bss dec hex filename
3330172 529036 190556 4049764 3dcb64 vmlinux-baseline
3328268 529040 190556 4047864 3dc3f8 vmlinux
From: Adrian Bunk <bunk@stusta.de>
UID16 was accidentially disabled for !EMBEDDED.
Signed-off-by: Matt Mackall <mpm@selenic.com>
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
