Defer copying of ptes until fault time when it is possible to reconstruct
the pte from backing store. Idea from Andi Kleen and Nick Piggin.

Thanks to input from Rik van Riel and Linus and to Hugh for correcting
my blundering.

Ray Fucillo <fucillo@intersystems.com> reports:

  "I applied this latest patch to a 2.6.12 kernel and found that it does
   resolve the problem.  Prior to the patch on this machine, I was
   seeing about 23ms spent in fork for ever 100MB of shared memory
   segment.

   After applying the patch, fork is taking about 1ms regardless of the
   shared memory size."
Signed-off-by: NNick Piggin <npiggin@suse.de>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

It appears that a memory barrier soon after a mispredicted
branch, not just in the delay slot, can cause the hang
condition of this cpu errata.

So move them out-of-line, and explicitly put them into
a "branch always, predict taken" delay slot which should
fully kill this problem.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When the spinlock routines were moved out of line into
kernel/spinlock.c this made it so that the debugging
spinlocks record lock acquisition program counts in the
kernel/spinlock.c functions not in their callers.
This makes the debugging info kind of useless.

So record the correct caller's program counter and
now this feature is useful once more.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Removed sparc architecture specific users of asm/segment.h and
asm-sparc/segment.h itself
Signed-off-by: NKumar Gala <kumar.gala@freescale.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Removed sparc64 architecture specific users of asm/segment.h and
asm-sparc64/segment.h itself
Signed-off-by: NKumar Gala <kumar.gala@freescale.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Current uncorrectable error handling was poor enough
that the processor could just loop taking the same
trap over and over again.  Fix things up so that we
at least get a log message and perhaps even some register
state.

In the process, much consolidation became possible,
particularly with the correctable error handler.

Prefix assembler and C function names with "spitfire"
to indicate that these are for Ultra-I/II/IIi/IIe only.

More work is needed to make these routines robust and
featureful to the level of the Ultra-III error handlers.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Verify we really are taking a data access exception trap, at TL1, from
one of the window spill/fill handlers.

Else call a new function, data_access_exception_tl1, to log the error.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

1) Read ASI_IMMU SFSR not ASI_DMMU.
2) IMMU has no SFAR, read TPC instead
3) Delete old and incorrect comment about the DTLB protection
   trap having a dependency on the SFSR contents in order to
   function correctly
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NAl Viro <viro@parcelfarce.linux.theplanet.co.uk>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Signed-off-by: NAl Viro <viro@parcelfarce.linux.theplanet.co.uk>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

 * ieee1394_device_id has kernel_ulong_t field after an odd number of
   __u32 ones.  Since mod_devicetable.h is included both from kernel and
   from host build helper, we may be in trouble if we are building on
   32bit host for 64bit target - userland sees unsigned long long,
   kernel sees unsigned long and while their sizes match, alignments
   might not.  Fixed by forcing alignment.  Fortunately, almost nobody
   else needs that - the rest of such fields is naturally aligned as it
   is.

 * of_device_id has void * in it.  Host userland helpers need
   kernel_ulong_t instead, since their void * might have nothing to do
   with the kernel one.  Fixed in the same way it's done for similar
   problems in pcmcia_device_id (ifdef __KERNEL__).

 * pcmcia_device_id has the same problem as ieee1394_device_id.  Fixed
   the same way.
Signed-off-by: NAl Viro <viro@parcelfarce.linux.theplanet.co.uk>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

We've had Woozy Numbat for a while now.  Here's an updated name care of
Jeff Garzik and myself.
Signed-off-by: NBenjamin LaHaise <bcrl@linux.intel.com>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

It has been reported that the way Linux handles NODEFER for signals is
not consistent with the way other Unix boxes handle it.  I've written a
program to test the behavior of how this flag affects signals and had
several reports from people who ran this on various Unix boxes,
confirming that Linux seems to be unique on the way this is handled.

The way NODEFER affects signals on other Unix boxes is as follows:

1) If NODEFER is set, other signals in sa_mask are still blocked.

2) If NODEFER is set and the signal is in sa_mask, then the signal is
still blocked. (Note: this is the behavior of all tested but Linux _and_
NetBSD 2.0 *).

The way NODEFER affects signals on Linux:

1) If NODEFER is set, other signals are _not_ blocked regardless of
sa_mask (Even NetBSD doesn't do this).

2) If NODEFER is set and the signal is in sa_mask, then the signal being
handled is not blocked.

The patch converts signal handling in all current Linux architectures to
the way most Unix boxes work.

Unix boxes that were tested:  DU4, AIX 5.2, Irix 6.5, NetBSD 2.0, SFU
3.5 on WinXP, AIX 5.3, Mac OSX, and of course Linux 2.6.13-rcX.

* NetBSD was the only other Unix to behave like Linux on point #2. The
main concern was brought up by point #1 which even NetBSD isn't like
Linux.  So with this patch, we leave NetBSD as the lonely one that
behaves differently here with #2.
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Paulus, I think this is now a reasonable candidate for the post-2.6.13
queue.

Relax address restrictions for hugepages on ppc64

Presently, 64-bit applications on ppc64 may only use hugepages in the
address region from 1-1.5T.  Furthermore, if hugepages are enabled in
the kernel config, they may only use hugepages and never normal pages
in this area.  This patch relaxes this restriction, allowing any
address to be used with hugepages, but with a 1TB granularity.  That
is if you map a hugepage anywhere in the region 1TB-2TB, that entire
area will be reserved exclusively for hugepages for the remainder of
the process's lifetime.  This works analagously to hugepages in 32-bit
applications, where hugepages can be mapped anywhere, but with 256MB
(mmu segment) granularity.

This patch applies on top of the four level pagetable patch
(http://patchwork.ozlabs.org/linuxppc64/patch?id=1936).
Signed-off-by: NDavid Gibson <dwg@au1.ibm.com>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

You can't call get_property() on a NULL node, so check if of_chosen is set
in check_for_initrd().
Signed-off-by: NMichael Ellerman <michael@ellerman.id.au>

 arch/ppc64/kernel/setup.c |   20 ++++++++++++--------
 1 files changed, 12 insertions(+), 8 deletions(-)
Signed-off-by: NPaul Mackerras <paulus@samba.org>

unflatten_device_tree() doesn't check if lmb_alloc() succeeds or not, it
should. All it can do is panic, but at least there's an error message
(assuming you have some sort of console at that point).
Signed-off-by: NMichael Ellerman <michael@ellerman.id.au>

 arch/ppc64/kernel/prom.c |    9 +++++++--
 1 files changed, 7 insertions(+), 2 deletions(-)
Signed-off-by: NPaul Mackerras <paulus@samba.org>

When unflatten_dt_node() fails to find an OF_DT_END_NODE tag it prints
"Weird tag at start of node", this should be "Weird tag at end of node".
Signed-off-by: NMichael Ellerman <michael@ellerman.id.au>

 arch/ppc64/kernel/prom.c |    2 +-
 1 files changed, 1 insertion(+), 1 deletion(-)
Signed-off-by: NPaul Mackerras <paulus@samba.org>

This patch moves power4_enable_pmcs() to arch/ppc64/kernel/pmc.c.

I've tested it on P5 LPAR and P4. It does what it used to.
Signed-off-by: NMichael Ellerman <michael@ellerman.id.au>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

If both CONFIG_XMON and CONFIG_XMON_DEFAULT is enabled in the .config,
there is no way to disable xmon again. setup_system calls first xmon_init,
later parse_early_param. So a new 'xmon=off' cmdline option will do the right
thing.
Signed-off-by: NOlaf Hering <olh@suse.de>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

We can now remove CONFIG_MSCHUNKS as it doesn't do anything interesting
anymore.

The only macro in abs_addr.h which is called by non-iSeries code is
phys_to_abs(), so remove the other dummy implementations, and we add a
firmware feature check to phys_to_abs().
Signed-off-by: NMichael Ellerman <michael@ellerman.id.au>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

lmb_phys_mem_size() can always return lmb.memory.size, as long as it's called
after lmb_analyze(), which it is. There's no need to recalculate the size on
every call.

lmb_analyze() was calculating a few things we then threw away, so just don't
calculate them to start with.
Signed-off-by: NMichael Ellerman <michael@ellerman.id.au>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

We no longer need the lmb code to know about abs and phys addresses, so
remove the physbase variable from the lmb_property struct.
Signed-off-by: NMichael Ellerman <michael@ellerman.id.au>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

abs_to_phys() is a macro that turns out to do nothing, and also has the
unfortunate property that it's not the inverse of phys_to_abs() on iSeries.

The following is for my benefit as much as everyone else.

With CONFIG_MSCHUNKS enabled, the lmb code is changed such that it keeps
a physbase variable for each lmb region. This is used to take the possibly
discontiguous lmb regions and present them as a contiguous address space
beginning from zero.

In this context each lmb region's base address is its "absolute" base
address, and its physbase is it's "physical" address (from Linux's point of
view). The abs_to_phys() macro does the mapping from "absolute" to "physical".

Note: This is not related to the iSeries mapping of physical to absolute
(ie. Hypervisor) addresses which is maintained with the msChunks structure.
And the msChunks structure is not controlled via CONFIG_MSCHUNKS.

Once upon a time you could compile for non-iSeries with CONFIG_MSCHUNKS
enabled. But these days CONFIG_MSCHUNKS depends on CONFIG_PPC_ISERIES, so
for non-iSeries code abs_to_phys() is a no-op.

On iSeries we always have one lmb region which spans from 0 to
systemcfg->physicalMemorySize (arch/ppc64/kernel/iSeries_setup.c line 383).
This region has a base (ie. absolute) address of 0, and a physbase address
of 0 (as calculated in lmb_analyze() (arch/ppc64/kernel/lmb.c line 144)).

On iSeries, abs_to_phys(aa) is defined as lmb_abs_to_phys(aa), which finds
the lmb region containing aa (and there's only one, ie. 0), and then does:

 return lmb.memory.region[0].physbase + (aa - lmb.memory.region[0].base)

physbase == base == 0, so you're left with "return aa".

So remove abs_to_phys(), and lmb_abs_to_phys() which is the implementation
of abs_to_phys() for iSeries.
Signed-off-by: NMichael Ellerman <michael@ellerman.id.au>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

The lmb code is all written to use a pointer to an lmb struct. But it's always
the same lmb struct, called "lmb". So we take the address of lmb, call it
_lmb and then start using _lmb->foo everywhere, which is silly.

This patch removes the _lmb pointers and replaces them with direct references
to the one "lmb" struct. We do the same for some _mem and _rsv pointers which
point to lmb.memory and lmb.reserved respectively.

This patch looks quite busy, but it's basically just:
s/_lmb->/lmb./g
s/_mem->/lmb.memory./g
s/_rsv->/lmb.reserved./g
s/_rsv/&lmb.reserved/g
s/mem->/lmb.memory./g
Signed-off-by: NMichael Ellerman <michael@ellerman.id.au>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

physRpn_to_absRpn is a no-op on non-iSeries platforms, remove the two
redundant calls.

There's only one caller on iSeries so fold the logic in there so we can get
rid of it completely.
Signed-off-by: NMichael Ellerman <michael@ellerman.id.au>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

The only caller of chunk_offset() and abs_chunk() is phys_to_abs(), so
fold the former two into the latter.
Signed-off-by: NMichael Ellerman <michael@ellerman.id.au>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

Rename the msChunks struct to get rid of the StUdlY caps and make it a bit
clearer what it's for.
Signed-off-by: NMichael Ellerman <michael@ellerman.id.au>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

Chunks are 256KB, so use constants for the size/shift/mask, rather than
getting them from the msChunks struct. The iSeries debugger (??) might still
need access to the values in the msChunks struct, so we keep them around
for now, but set them from the constant values.

Replace msChunks_entry typedef with regular u32.

Simplify msChunks_alloc() to manipulate klimit directly, rather than via
a parameter.

Move msChunks_alloc() and msChunks into iSeries_setup.c, as that's where
they're used.
Signed-off-by: NMichael Ellerman <michael@ellerman.id.au>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

The msChunks code was written to work on pSeries, but now it's only used on
iSeries. This means there's no need to do PTRRELOC anymore, so remove it all.

A few places were getting "extern reloc_offset()" from abs_addr.h, move it
into system.h instead.
Signed-off-by: NMichael Ellerman <michael@ellerman.id.au>
Signed-off-by: NPaul Mackerras <paulus@samba.org>