The address range size calculation inside local_flush_tlb_kernel_range()
is being truncated by a too small size variable holder on 64-bit systems.
The truncated size can result in an erroneous tlbsize check that means we
sit spinning inside a loop trying to flush a hige number of TLB entries.
This is for all intents and purposes a system hang. Fix by using an
appropriately sized valiable to hold the size.
[Ralf: Greg's original patch submission identified the issue and fixed one
instance in tlb-r4k.c but there there were several more. For consistency
I also modified tlb-r3k.c even though that file is only used on 32-bit.]
Signed-off-by: Greg Ungerer <gerg@snapgear.com>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Richard Sandiford's new code for inserting the cache-barriers, for GCC
4.3 and above and already incorporated in the current GCC-release, uses
a slightly different option-syntax.
Signed-off-by: peter fuerst <post@pfrst.de>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
The hang was caused by the use of disable_irq() from the interrupt handler
itself. Fixed by the use of disable_irq_nosync(). The issue was
triggered by:
commit 3aa551c9b4
Author: Thomas Gleixner <tglx@linutronix.de>
Date: Mon Mar 23 18:28:15 2009 +0100
genirq: add threaded interrupt handler support
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
The hang was caused by the use of disable_irq() from the interrupt handler
itself. Fixed by the use of disable_irq_nosync(). The issue was
triggered by:
commit 3aa551c9b4
Author: Thomas Gleixner <tglx@linutronix.de>
Date: Mon Mar 23 18:28:15 2009 +0100
genirq: add threaded interrupt handler support
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
* 'fixes-for-linus' of git://git.monstr.eu/linux-2.6-microblaze:
microblaze: Fix kind-of-intr checking against number of interrupts
microblaze: Update Microblaze defconfig
* 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc:
powerpc: Explicit alignment for .data.cacheline_aligned
powerpc/ps3: Update ps3_defconfig
powerpc/ftrace: Fix constraint to be early clobber
powerpc/ftrace: Use pr_devel() in ftrace.c
powerpc: Do not assert pte_locked for hugepage PTE entries
* 'tracing-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
tracing: Append prompt in /debug/tracing/README file
x86/function-graph: fix constraint for recording old return value
I don't think anything guarantees that the objects in data.page_aligned
are a multiple of PAGE_SIZE, thus the section may end on any boundary.
So the following section, .data.cacheline_aligned needs an explicit
alignment.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Refresh and set these options:
CONFIG_SYSFS_DEPRECATED_V2: y -> n
CONFIG_INPUT_JOYSTICK: y -> n
CONFIG_HID_SONY: n -> m
CONFIG_RTC_DRV_PS3: - -> m
Signed-off-by: Geoff Levand <geoffrey.levand@am.sony.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
After upgrading my distcc boxes from gcc 4.2.2 to 4.4.0, the function
graph tracer broke. This was discovered on my x86 boxes.
The issue is that gcc used the same register for an output as it did for
an input in an asm statement. I first thought this was a bug in gcc and
reported it. I was notified that gcc was correct and that the output had
to be flagged as an "early clobber".
I noticed that powerpc had the same issue and this patch fixes it.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
pr_debug() can now result in code being generated even when #DEBUG
is not defined. That's not really desirable in the ftrace code
which we want to be snappy.
With CONFIG_DYNAMIC_DEBUG=y:
size before:
text data bss dec hex filename
3334 672 4 4010 faa arch/powerpc/kernel/ftrace.o
size after:
text data bss dec hex filename
2616 360 4 2980 ba4 arch/powerpc/kernel/ftrace.o
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Xiaohui Xin and some other folks at Intel have been looking into what's
behind the performance hit of paravirt_ops when running native.
It appears that the hit is entirely due to the paravirtualized
spinlocks introduced by:
| commit 8efcbab674
| Date: Mon Jul 7 12:07:51 2008 -0700
|
| paravirt: introduce a "lock-byte" spinlock implementation
The extra call/return in the spinlock path is somehow
causing an increase in the cycles/instruction of somewhere around 2-7%
(seems to vary quite a lot from test to test). The working theory is
that the CPU's pipeline is getting upset about the
call->call->locked-op->return->return, and seems to be failing to
speculate (though I haven't seen anything definitive about the precise
reasons). This doesn't entirely make sense, because the performance
hit is also visible on unlock and other operations which don't involve
locked instructions. But spinlock operations clearly swamp all the
other pvops operations, even though I can't imagine that they're
nearly as common (there's only a .05% increase in instructions
executed).
If I disable just the pv-spinlock calls, my tests show that pvops is
identical to non-pvops performance on native (my measurements show that
it is actually about .1% faster, but Xiaohui shows a .05% slowdown).
Summary of results, averaging 10 runs of the "mmperf" test, using a
no-pvops build as baseline:
nopv Pv-nospin Pv-spin
CPU cycles 100.00% 99.89% 102.18%
instructions 100.00% 100.10% 100.15%
CPI 100.00% 99.79% 102.03%
cache ref 100.00% 100.84% 100.28%
cache miss 100.00% 90.47% 88.56%
cache miss rate 100.00% 89.72% 88.31%
branches 100.00% 99.93% 100.04%
branch miss 100.00% 103.66% 107.72%
branch miss rt 100.00% 103.73% 107.67%
wallclock 100.00% 99.90% 102.20%
The clear effect here is that the 2% increase in CPI is
directly reflected in the final wallclock time.
(The other interesting effect is that the more ops are
out of line calls via pvops, the lower the cache access
and miss rates. Not too surprising, but it suggests that
the non-pvops kernel is over-inlined. On the flipside,
the branch misses go up correspondingly...)
So, what's the fix?
Paravirt patching turns all the pvops calls into direct calls, so
_spin_lock etc do end up having direct calls. For example, the compiler
generated code for paravirtualized _spin_lock is:
<_spin_lock+0>: mov %gs:0xb4c8,%rax
<_spin_lock+9>: incl 0xffffffffffffe044(%rax)
<_spin_lock+15>: callq *0xffffffff805a5b30
<_spin_lock+22>: retq
The indirect call will get patched to:
<_spin_lock+0>: mov %gs:0xb4c8,%rax
<_spin_lock+9>: incl 0xffffffffffffe044(%rax)
<_spin_lock+15>: callq <__ticket_spin_lock>
<_spin_lock+20>: nop; nop /* or whatever 2-byte nop */
<_spin_lock+22>: retq
One possibility is to inline _spin_lock, etc, when building an
optimised kernel (ie, when there's no spinlock/preempt
instrumentation/debugging enabled). That will remove the outer
call/return pair, returning the instruction stream to a single
call/return, which will presumably execute the same as the non-pvops
case. The downsides arel 1) it will replicate the
preempt_disable/enable code at eack lock/unlock callsite; this code is
fairly small, but not nothing; and 2) the spinlock definitions are
already a very heavily tangled mass of #ifdefs and other preprocessor
magic, and making any changes will be non-trivial.
The other obvious answer is to disable pv-spinlocks. Making them a
separate config option is fairly easy, and it would be trivial to
enable them only when Xen is enabled (as the only non-default user).
But it doesn't really address the common case of a distro build which
is going to have Xen support enabled, and leaves the open question of
whether the native performance cost of pv-spinlocks is worth the
performance improvement on a loaded Xen system (10% saving of overall
system CPU when guests block rather than spin). Still it is a
reasonable short-term workaround.
[ Impact: fix pvops performance regression when running native ]
Analysed-by: "Xin Xiaohui" <xiaohui.xin@intel.com>
Analysed-by: "Li Xin" <xin.li@intel.com>
Analysed-by: "Nakajima Jun" <jun.nakajima@intel.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Acked-by: H. Peter Anvin <hpa@zytor.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Xen-devel <xen-devel@lists.xensource.com>
LKML-Reference: <4A0B62F7.5030802@goop.org>
[ fixed the help text ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jwessel/linux-2.6-kgdb:
kgdb: gdb documentation fix
kgdb,i386: use address that SP register points to in the exception frame
sysrq, intel_fb: fix sysrq g collision
* 'for-linus' of git://git.kernel.dk/linux-2.6-block:
Revert "mm: add /proc controls for pdflush threads"
viocd: needs to depend on BLOCK
block: fix the bio_vec array index out-of-bounds test
* 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc:
powerpc: Fix PCI ROM access
powerpc/pseries: Really fix the oprofile CPU type on pseries
serial/nwpserial: Fix wrong register read address and add interrupt acknowledge.
powerpc/cell: Make ptcal more reliable
powerpc: Allow mem=x cmdline to work with 4G+
powerpc/mpic: Fix incorrect allocation of interrupt rev-map
powerpc: Fix oprofile sampling of marked events on POWER7
powerpc/iseries: Fix pci breakage due to bad dma_data initialization
powerpc: Fix mktree build error on Mac OS X host
powerpc/virtex: Fix duplicate level irq events.
powerpc/virtex: Add uImage to the default images list
powerpc/boot: add simpleImage.* to clean-files list
powerpc/8xx: Update defconfigs
powerpc/embedded6xx: Update defconfigs
powerpc/86xx: Update defconfigs
powerpc/85xx: Update defconfigs
powerpc/83xx: Update defconfigs
powerpc/fsl_soc: Remove mpc83xx_wdt_init, again
The treatment of the SP register is different on x86_64 and i386.
This is a regression fix that lived outside the mainline kernel from
2.6.27 to now. The regression was a result of the original merge
consolidation of the i386 and x86_64 archs to x86.
The incorrectly reported SP on i386 prevented stack tracebacks from
working correctly in gdb.
Signed-off-by: Jason Wessel <jason.wessel@windriver.com>
This is a build fix, resyncing the DaVinci EVM ASoC board code
with the version in the DaVinci tree. That resync includes
support for the DM355 EVM, although that board isn't yet in
mainline.
(NOTE: also includes a bugfix to the platform_add_resources
call, recently sent by Chaithrika U S <chaithrika@ti.com> but
not yet merged into the DaVinci tree.)
Signed-off-by: David Brownell <dbrownell@users.sourceforge.net>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
A couple of issues crept in since about 2.6.27 related to accessing PCI
device ROMs on various powerpc machines.
First, historically, we don't allocate the ROM resource in the resource
tree. I'm not entirely certain of why, I susepct they often contained
garbage on x86 but it's hard to tell. This causes the current generic
code to always call pci_assign_resource() when trying to access the said
ROM from sysfs, which will try to re-assign some new address regardless
of what the ROM BAR was already set to at boot time. This can be a
problem on hypervisor platforms like pSeries where we aren't supposed
to move PCI devices around (and in fact probably can't).
Second, our code that generates the PCI tree from the OF device-tree
(instead of doing config space probing) which we mostly use on pseries
at the moment, didn't set the (new) flag IORESOURCE_SIZEALIGN on any
resource. That means that any attempt at re-assigning such a resource
with pci_assign_resource() would fail due to resource_alignment()
returning 0.
This fixes this by doing these two things:
- The code that calculates resource flags based on the OF device-node
is improved to set IORESOURCE_SIZEALIGN on any valid BAR, and while at
it also set IORESOURCE_READONLY for ROMs since we were lacking that too
- We now allocate ROM resources as part of the resource tree. However
to limit the chances of nasty conflicts due to busted firmwares, we
only do it on the second pass of our two-passes allocation scheme,
so that all valid and enabled BARs get precedence.
This brings pSeries back the ability to access PCI ROMs via sysfs (and
thus initialize various video cards from X etc...).
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
My previous pach for fixing the oprofile CPU type got somewhat mismerged
(by my fault) when it collided with another related patch. This should
finally (fingers crossed) fix the whole thing.
We make sure we keep the -old- oprofile type and CPU type whenever
one of them was specified in the first pass through the function.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
There have been a series of checkstops on QS21 related to
ptcal being set up incorrectly. On systems that only
have memory on a single node, ptcal fails when it gets
a pointer to memory on the remote node.
Moreover, agressive prefetching in memcpy and other
functions may accidentally touch the first cache line
of the page that we reserve for ptcal, which causes
an ECC checkstop.
We now allocate pages only from the specified node, moves the
ptcal area into the middle of the allocated page to avoid
potential prefetch problems and prints the address of the
ptcal area to facilitate diagnostics.
Signed-off-by: Gerhard Stenzel <gerhard.stenzel@de.ibm.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
We're currently choking on mem=4g (and above) due to memory_limit
being specified as an unsigned long. Make memory_limit
phys_addr_t to fix this.
Signed-off-by: Becky Bruce <beckyb@kernel.crashing.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Before when we were setting up the irq host map for mpic we passed in
just isu_size for the size of the linear map. However, for a number of
mpic implementations we have no isu (thus pass in 0) and will end up
with a no linear map (size = 0). This causes us to always call
irq_find_mapping() from mpic_get_irq().
By moving the allocation of the host map to after we've determined the
number of sources we can actually benefit from having a linear map for
the non-isu users that covers all the interrupt sources.
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Description
-----------
Change ppc64 oprofile kernel driver to use the SLOT bits (MMCRA[37:39]only on
older processors where those bits are defined.
Background
----------
The performance monitor unit of the 64-bit POWER processor family has the
ability to collect accurate instruction-level samples when profiling on marked
events (i.e., "PM_MRK_<event-name>"). In processors prior to POWER6, the MMCRA
register contained "slot information" that the oprofile kernel driver used to
adjust the value latched in the SIAR at the time of a PMU interrupt. But as of
POWER6, these slot bits in MMCRA are no longer necessary for oprofile to use,
since the SIAR itself holds the accurate sampled instruction address. With
POWER6, these MMCRA slot bits were zero'ed out by hardware so oprofile's use of
these slot bits was, in effect, a NOP. But with POWER7, these bits are no
longer zero'ed out; however, they serve some other purpose rather than slot
information. Thus, using these bits on POWER7 to adjust the SIAR value results
in samples being attributed to the wrong instructions. The attached patch
changes the oprofile kernel driver to ignore these slot bits on all newer
processors starting with POWER6.
Signed-off-by: Maynard Johnson <maynardj@us.ibm.com>
Signed-off-by: Michael Wolf <mjw@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Commit 4fc665b88a "powerpc: Merge 32 and
64-bit dma code" made changes to the PCI initialisation code that added
an assignment to archdata.dma_data but only for 32 bit code. Commit
7eef440a54 "powerpc/pci: Cosmetic cleanups
of pci-common.c" removed the conditional compilation. Unfortunately,
the iSeries code setup the archdata.dma_data before that assignment was
done - effectively overwriting the dma_data with NULL.
Fix this up by moving the iSeries setup of dma_data into a
pci_dma_dev_setup callback.
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
The mktree utility defines some variables as "uint", although this is not a
standard C type, and so cross-compiling on Mac OS X fails. Change this to
"unsigned int".
Signed-off-by: Timur Tabi <timur@freescale.com>
Acked-by: Josh Boyer <jwboyer@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
The interrupt controller was not handling level interrupts correctly
such that duplicate interrupts were happening. This fixes the problem
and adds edge type interrupts which are needed in Xilinx hardware.
Signed-off-by: John Linn <john.linn@xilinx.com>
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
It is common to use U-Boot on Xilinx Virtex platforms. This patch
ensures that CONFIG_DEFAULT_UIMAGE is selected for virtex
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
Locking of irq_desc is now done in irq_set_affinity; don't lock it again
in chip specific set_affinity function.
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
When init is started it is SIGNAL_UNKILLABLE. If it were to get an
address error, we would try to send it SIGBUS, but it would be ignored
and the faulting instruction restarted. This results in an endless
loop.
We need to use force_sig() instead so it will actually die and give us
some useful information.
Reported-by: Florian Fainelli <florian@openwrt.org>
Signed-off-by: David Daney <ddaney@caviumnetworks.com>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
This patch modifies parameter of octeon_cvmcount_read() from 'void' to
'struct clocksource *cs', which fixes compile warning for incompatible
parameter type.
Signed-off-by: Coly Li <coly.li@suse.de>
Cc: David Daney <ddaney@caviumnetworks.com>
Cc: Ingo Molnar <mingo@elte.hu>
Reviewed-by: David Daney <ddaney@caviumnetworks.com>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
The inline assembler used on 32-bit kernels was using the "h" constraint
which was considered dangerous and removed for gcc 4.4.0.
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Commit 351336929c (kernel.org) rsp.
b3594a089f1c17ff919f8f78505c3f20e1f6f8ce (linux-mips.org):
> From: Chris Dearman <chris@mips.com>
> Date: Wed, 19 Sep 2007 00:58:24 +0100
> Subject: [PATCH] [MIPS] Allow setting of the cache attribute at run time.
>
> Slightly tacky, but there is a precedent in the sparc archirecture code.
introduces the variable _page_cachable_default, which defaults to zero and.
is used to create the prototype PTE for __kmap_atomic in
arch/mips/mm/init.c:kmap_init before initialization in
arch/mips/mm/c-r4k.c:coherency_setup, so the default value of 0 will be
used as the CCA of kmap atomic pages which on many processors is not a
defined CCA value and may result in writes to kmap_atomic pages getting
corrupted. Debugged by Jon Fraser (jfraser@broadcom.com).
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
The RAMROOT function was a successful but non-portable attempt to append
the root filesystem to the end of the kernel image. The preferred and
portable solution is to use an initramfs instead.
Signed-off-by: Shane McDonald <mcdonald.shane@gmail.com>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
I don't think that in 15 years of Linux/MIPS the zero division checking
code generated by gcc by default has ever caught anything.
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
There have been a number of compile problems with the msp71xx configuration
ever since it was included in the linux-mips.org repository. This patch
resolves compilation problems with attempting to reset the board using
non-existent GPIO routines.
This patch has been compile-tested against the current HEAD.
Signed-off-by: Shane McDonald <mcdonald.shane@gmail.com>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
There have been a number of compile problems with the msp71xx configuration
ever since it was included in the linux-mips.org repository. This patch
resolves the "multiple definition of plat_timer_setup" problem, and creates
the required get_c0_compare_int function.
This patch has been compile-tested against the current HEAD.
Signed-off-by: Shane McDonald <mcdonald.shane@gmail.com>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
There was already a define for NMI_OFFSET in asm/sn/addr.h, which now
clashes with linux/hardirq.h. Rename the one in sn/addr.h to fix IP27
builds..
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
