Commit Graph

234 Commits

Author SHA1 Message Date
Andrew Morton
394e3902c5 [PATCH] more for_each_cpu() conversions
When we stop allocating percpu memory for not-possible CPUs we must not touch
the percpu data for not-possible CPUs at all.  The correct way of doing this
is to test cpu_possible() or to use for_each_cpu().

This patch is a kernel-wide sweep of all instances of NR_CPUS.  I found very
few instances of this bug, if any.  But the patch converts lots of open-coded
test to use the preferred helper macros.

Cc: Mikael Starvik <starvik@axis.com>
Cc: David Howells <dhowells@redhat.com>
Acked-by: Kyle McMartin <kyle@parisc-linux.org>
Cc: Anton Blanchard <anton@samba.org>
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: William Lee Irwin III <wli@holomorphy.com>
Cc: Andi Kleen <ak@muc.de>
Cc: Christian Zankel <chris@zankel.net>
Cc: Philippe Elie <phil.el@wanadoo.fr>
Cc: Nathan Scott <nathans@sgi.com>
Cc: Jens Axboe <axboe@suse.de>
Cc: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-23 07:38:17 -08:00
Nick Piggin
0b2fcfdb8b [PATCH] atomic: add_unless cmpxchg optimise
Without branch hints, the very unlikely chance of the loop repeating due to
cmpxchg failure is unrolled with gcc-4 that I have tested.

Improve this for architectures with a native cas/cmpxchg.  llsc archs
should try to implement this natively.

Signed-off-by: Nick Piggin <npiggin@suse.de>
Cc: Andi Kleen <ak@muc.de>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Roman Zippel <zippel@linux-m68k.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-23 07:38:17 -08:00
Kyle McMartin
804f1594cc [PATCH] Move read_mostly definition to asm/cache.h
Seems like needless clutter having a bunch of #if defined(CONFIG_$ARCH) in
include/linux/cache.h.  Move the per architecture section definition to
asm/cache.h, and keep the if-not-defined dummy case in linux/cache.h to
catch architectures which don't implement the section.

Verified that symbols still go in .data.read_mostly on parisc,
and the compile doesn't break.

Signed-off-by: Kyle McMartin <kyle@parisc-linux.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-23 07:38:10 -08:00
David S. Miller
dcc1e8dd88 [SPARC64]: Add a secondary TSB for hugepage mappings.
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-22 01:15:14 -08:00
David S. Miller
f6b83f070e [SPARC64]: Fix 2 bugs in huge page support.
1) huge_pte_offset() did not check the page table hierarchy
   elements as being empty correctly, resulting in an OOPS

2) Need platform specific hugetlb_get_unmapped_area() to handle
   the top-down vs. bottom-up address space allocation strategies.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:17:17 -08:00
David S. Miller
bb8646d834 [SPARC64]: Optimized TSB table initialization.
We only need to write an invalid tag every 16 bytes,
so taking advantage of this can save many instructions
compared to the simple memset() call we make now.

A prefetching implementation is implemented for sun4u
and a block-init store version if implemented for Niagara.

The next trick is to be able to perform an init and
a copy_tsb() in parallel when growing a TSB table.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:16:41 -08:00
David S. Miller
d61e16df94 [SPARC64]: Increase top of 32-bit process stack.
Put it one page below the top of the 32-bit address space.
This gives us ~16MB more address space to work with.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:16:36 -08:00
David S. Miller
a91690ddd0 [SPARC64]: Top-down address space allocation for 32-bit tasks.
Currently allocations are very constrained for 32-bit processes.
It grows down-up from 0x70000000 to 0xf0000000 which gives about
2GB of stack + dynamic mmap() space.

So support the top-down method, and we need to override the
generic helper function in order to deal with D-cache coloring.

With these changes I was able to squeeze out a mmap() just over
3.6GB in size in a 32-bit process.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:16:35 -08:00
David S. Miller
7a1ac52641 [SPARC64]: Fix and re-enable dynamic TSB sizing.
This is good for up to %50 performance improvement of some test cases.
The problem has been the race conditions, and hopefully I've plugged
them all up here.

1) There was a serious race in switch_mm() wrt. lazy TLB
   switching to and from kernel threads.

   We could erroneously skip a tsb_context_switch() and thus
   use a stale TSB across a TSB grow event.

   There is a big comment now in that function describing
   exactly how it can happen.

2) All code paths that do something with the TSB need to be
   guarded with the mm->context.lock spinlock.  This makes
   page table flushing paths properly synchronize with both
   TSB growing and TLB context changes.

3) TSB growing events are moved to the end of successful fault
   processing.  Previously it was in update_mmu_cache() but
   that is deadlock prone.  At the end of do_sparc64_fault()
   we hold no spinlocks that could deadlock the TSB grow
   sequence.  We also have dropped the address space semaphore.

While we're here, add prefetching to the copy_tsb() routine
and put it in assembler into the tsb.S file.  This piece of
code is quite time critical.

There are some small negative side effects to this code which
can be improved upon.  In particular we grab the mm->context.lock
even for the tsb insert done by update_mmu_cache() now and that's
a bit excessive.  We can get rid of that locking, and the same
lock taking in flush_tsb_user(), by disabling PSTATE_IE around
the whole operation including the capturing of the tsb pointer
and tsb_nentries value.  That would work because anyone growing
the TSB won't free up the old TSB until all cpus respond to the
TSB change cross call.

I'm not quite so confident in that optimization to put it in
right now, but eventually we might be able to and the description
is here for reference.

This code seems very solid now.  It passes several parallel GCC
bootstrap builds, and our favorite "nut cruncher" stress test which is
a full "make -j8192" build of a "make allmodconfig" kernel.  That puts
about 256 processes on each cpu's run queue, makes lots of process cpu
migrations occur, causes lots of page table and TLB flushing activity,
incurs many context version number changes, and it swaps the machine
real far out to disk even though there is 16GB of ram on this test
system. :-)

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:16:33 -08:00
David S. Miller
90a6646bf6 [SPARC64]: Fix system type in /proc/cpuinfo and remove bogus OBP check.
Report 'sun4v' when appropriate in /proc/cpuinfo

Remove all the verifications of the OBP version string.  Just
make sure it's there, and report it raw in the bootup logs and
via /proc/cpuinfo.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:14:25 -08:00
David S. Miller
8935dced54 [SPARC64]: Add SMT scheduling support for Niagara.
The mapping is a simple "(cpuid >> 2) == core" for now.
Later we'll add more sophisticated code that will walk
the sun4v machine description and figure this out from
there.

We should also add core mappings for jaguar and panther
processors.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:14:24 -08:00
David S. Miller
d1112018b4 [SPARC64]: Move over to sparsemem.
This has been pending for a long time, and the fact
that we waste a ton of ram on some configurations
kind of pushed things over the edge.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:14:22 -08:00
David S. Miller
ee29074d3b [SPARC64]: Fix new context version SMP handling.
Don't piggy back the SMP receive signal code to do the
context version change handling.

Instead allocate another fixed PIL number for this
asynchronous cross-call.  We can't use smp_call_function()
because this thing is invoked with interrupts disabled
and a few spinlocks held.

Also, fix smp_call_function_mask() to count "cpus" correctly.
There is no guarentee that the local cpu is in the mask
yet that is exactly what this code was assuming.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:14:21 -08:00
David S. Miller
a77754b4d0 [SPARC64]: Bulletproof MMU context locking.
1) Always spin_lock_init() in init_context().  The caller essentially
   clears it out, or copies the mm info from the parent.  In both
   cases we need to explicitly initialize the spinlock.

2) Always do explicit IRQ disabling while taking mm->context.lock
   and ctx_alloc_lock.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:14:20 -08:00
David S. Miller
8bcd174116 [SPARC64]: Do not allow mapping pages within 4GB of 64-bit VA hole.
The UltraSPARC T1 manual recommends this because the chip
could instruction prefetch into the VA hole, and this would
also make decoding  certain kinds of memory access traps
more difficult (because the chip sign extends certain pieces
of trap state).

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:14:14 -08:00
David S. Miller
e22990451a [SPARC64]: Kill bogus function externs in asm/pgtable.h
These are all implemented inline earlier in the file.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:14:11 -08:00
David S. Miller
b830ab665a [SPARC64]: Fix bugs in SUN4V cpu mondo dispatch.
There were several bugs in the SUN4V cpu mondo dispatch code.

In fact, if we ever got a EWOULDBLOCK or other error from
the hypervisor call, we'd potentially send a cpu mondo multiple
times to the same cpu and even worse we could loop until the
timeout resending the same mondo over and over to such cpus.

So let's bulletproof this thing as follows:

1) Implement cpu_mondo_send() and cpu_state() hypervisor calls
   in arch/sparc64/kernel/entry.S, add prototypes to asm/hypervisor.h

2) Don't build and update the cpulist using inline functions, this
   was causing the cpu mask to not get updated in the caller.

3) Disable interrupts during the entire mondo send, otherwise our
   cpu list and/or mondo block could get overwritten if we take
   an interrupt and do a cpu mondo send on the current cpu.

4) Check for all possible error return types from the cpu_mondo_send()
   hypervisor call.  In particular:

   HV_EOK) Our work is done, all cpus have received the mondo.
   HV_CPUERROR) One or more of the cpus in the cpu list we passed
                to the hypervisor are in error state.  Use cpu_state()
                calls over the entries in the cpu list to see which
		ones.  Record them in "error_mask" and report this
		after we are done sending the mondo to cpus which are
		not in error state.
   HV_EWOULDBLOCK) We need to keep trying.

   Any other error we consider fatal, we report the event and exit
   immediately.

5) We only timeout if forward progress is not made.  Forward progress
   is defined as having at least one cpu get the mondo successfully
   in a given cpu_mondo_send() call.  Otherwise we bump a counter
   and delay a little.  If the counter hits a limit, we signal an
   error and report the event.

Also, smp_call_function_mask() error handling reports the number
of cpus incorrectly.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:14:09 -08:00
David S. Miller
97c4b6f95a [SPARC64]: Use 13-bit context size always.
We no longer have the problems that require using the smaller
sizes.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:14:06 -08:00
David S. Miller
3634476239 [SPARC64]: Niagara optimized XOR functions for RAID.
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:14:03 -08:00
David S. Miller
a0663a79ad [SPARC64]: Fix TLB context allocation with SMT style shared TLBs.
The context allocation scheme we use depends upon there being a 1<-->1
mapping from cpu to physical TLB for correctness.  Chips like Niagara
break this assumption.

So what we do is notify all cpus with a cross call when the context
version number changes, and if necessary this makes them allocate
a valid context for the address space they are running at the time.

Stress tested with make -j1024, make -j2048, and make -j4096 kernel
builds on a 32-strand, 8 core, T2000 with 16GB of ram.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:14:00 -08:00
David S. Miller
0f05da6d57 [SPARC64]: Fix %tstate ASI handling in start_thread{,32}()
Niagara helps us find a ancient bug in the sparc64 port :-)

The ASI_* values are plain constant defines, thus signed 32-bit
on sparc64.  To put shift this into the regs->tstate value we were
doing or'ing "(ASI_PNF << 24)" into there.

ASI_PNF is 0x82 and shifted left by 24 makes that topmost bit the
sign bit in a 32-bit value.  This would get sign extended to 64-bits
and thus corrupt the top-half of the reg->tstate value.

This never caused problems in pre-Niagara cpus because the only thing
up there were the condition code values.  But Niagara has the global
register level field, and this all 1's value is illegal there so
Niagara gives an illegal instruction trap due to this bug.

I'm pretty sure this bug is about as old as the sparc64 port itself.

This also points out that we weren't setting ASI_PNF for 32-bit tasks.
We should, so fix that while we're here.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:13:57 -08:00
David S. Miller
d7744a0950 [SPARC64]: Create a seperate kernel TSB for 4MB/256MB mappings.
It can map all of the linear kernel mappings with zero TSB hash
conflicts for systems with 16GB or less ram.  In such cases, on
SUN4V, once we load up this TSB the first time with all the
mappings, we never take a linear kernel mapping TLB miss ever
again, the hypervisor handles them all.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:13:56 -08:00
David S. Miller
6f5374c91f [SPARC64]: Add sun4v_cpu_yield().
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:13:52 -08:00
David S. Miller
1bd0cd74d1 [SPARC64]: Kill cpudata->idle_volume.
Set, but never used.

We used to use this for dynamic IRQ retargetting, but that
code died a long time ago.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:13:51 -08:00
David S. Miller
0f15952ac8 [SPARC64]: Export a PAGE_SHARED symbol.
For drivers/media/*, noticed by Fabbione.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:13:36 -08:00
Fabio M. Di Nitto
f6c1fe5292 [SPARC64] Fix build if CONFIG_HUGETLB_PAGE is not set
Signed-off-by: Fabio M. Di Nitto <fabbione@ubuntu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:13:35 -08:00
David S. Miller
8b23427441 [SPARC64]: More TLB/TSB handling fixes.
The SUN4V convention with non-shared TSBs is that the context
bit of the TAG is clear.  So we have to choose an "invalid"
bit and initialize new TSBs appropriately.  Otherwise a zero
TAG looks "valid".

Make sure, for the window fixup cases, that we use the right
global registers and that we don't potentially trample on
the live global registers in etrap/rtrap handling (%g2 and
%g6) and that we put the missing virtual address properly
in %g5.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:13:34 -08:00
David S. Miller
3763be32d5 [SPARC64]: Define ARCH_HAS_READ_CURRENT_TIMER.
This gives more consistent bogomips and delay() semantics,
especially on sun4v.  It gives weird looking values though...

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:13:29 -08:00
David S. Miller
c857e3fdbc [SPARC64]: __bzero_noasi --> __clear_user
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:13:28 -08:00
David S. Miller
97532f5982 [SPARC64]: Add HWCAP_SPARC_BLKINIT elf capability flag for Niagara.
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:13:26 -08:00
David S. Miller
ebd8c56c5a [SPARC64]: Fix uniprocessor IRQ targetting on SUN4V.
We need to use the real hardware processor ID when
targetting interrupts, not the "define to 0" thing
the uniprocessor build gives us.

Also, fill in the Node-ID and Agent-ID fields properly
on sun4u/Safari.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:13:24 -08:00
David S. Miller
72aff53f1f [SPARC64]: Get SUN4V SMP working.
The sibling cpu bringup is extremely fragile.  We can only
perform the most basic calls until we take over the trap
table from the firmware/hypervisor on the new cpu.

This means no accesses to %g4, %g5, %g6 since those can't be
TLB translated without our trap handlers.

In order to achieve this:

1) Change sun4v_init_mondo_queues() so that it can operate in
   several modes.

   It can allocate the queues, or install them in the current
   processor, or both.

   The boot cpu does both in it's call early on.

   Later, the boot cpu allocates the sibling cpu queue, starts
   the sibling cpu, then the sibling cpu loads them in.

2) init_cur_cpu_trap() is changed to take the current_thread_info()
   as an argument instead of reading %g6 directly on the current
   cpu.

3) Create a trampoline stack for the sibling cpus.  We do our basic
   kernel calls using this stack, which is locked into the kernel
   image, then go to our proper thread stack after taking over the
   trap table.

4) While we are in this delicate startup state, we put 0xdeadbeef
   into %g4/%g5/%g6 in order to catch accidental accesses.

5) On the final prom_set_trap_table*() call, we put &init_thread_union
   into %g6.  This is a hack to make prom_world(0) work.  All that
   wants to do is restore the %asi register using
   get_thread_current_ds().

Longer term we should just do the OBP calls to set the trap table by
hand just like we do for everything else.  This would avoid that silly
prom_world(0) issue, then we can remove the init_thread_union hack.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:13:22 -08:00
David S. Miller
4ff7ac417d [SPARC64]: Add GET_GL_GLOBAL() macro for SUN4V.
So we can read the %gl register for debugging.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:13:18 -08:00
David S. Miller
94f8762db9 [SPARC64]: Add sun4v_cpu_qconf() hypervisor call.
Call it from register_one_mondo().

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:13:16 -08:00
David S. Miller
bc45e32e0f [SPARC]: Kill off these __put_user_ret things.
They are bogus and haven't been referenced in years.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:13:15 -08:00
David S. Miller
9d29a3fafd [SPARC64]: Decode virtual-devices interrupts correctly.
Need to translate through the interrupt-map{,-mask] properties.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:13:05 -08:00
David S. Miller
7890f794e0 [SPARC64]: Add prom_{start,stop}cpu_cpuid().
Use prom_startcpu_cpuid() on SUN4V instead of prom_startcpu().

We should really test for "SUNW,start-cpu-by-cpuid" presence
and use it if present even on SUN4U.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:13:04 -08:00
David S. Miller
7c3514e450 [SPARC64]: Fixup TSTATE layout diagram in asm/pstate.h
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:13:02 -08:00
David S. Miller
50f4f23c3b [SPARC64]: Fix gcc-3.3.x warnings.
It doesn't like const variables being passed into
"i" constraing asm operations.  It's a bug, but
there is nothing we can really do but work around
it.

Based upon a report from Andrew Morton.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:12:53 -08:00
David S. Miller
c4bea28839 [SPARC64]: Make error codes available from sun4v_intr_get*().
And check for errors at call sites.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:12:51 -08:00
David S. Miller
5259d5bfaf [SPARC64]: Fix comment typo in asm/hypervisor.h
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:12:46 -08:00
David S. Miller
e77227eb4e [SPARC64]: Probe virtual-devices root node on sun4v.
This is where we learn how to get the interrupts
for things like the hypervisor console device.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:12:44 -08:00
David S. Miller
e3999574b4 [SPARC64]: Generic sun4v_build_irq().
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:12:40 -08:00
David S. Miller
6c0f402f6c [SPARC64]: Implement rest of generic interrupt hypervisor calls.
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:12:37 -08:00
David S. Miller
85dfa19ba9 [SPARC64]: Move devino_to_sysino out of pci_sun4v_asm.S
It is not PCI specific, it is for all system interrupts.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:12:36 -08:00
David S. Miller
cf627156c4 [SPARC64]: Use inline patching for critical PTE operations.
This handles the SUN4U vs SUN4V PTE layout differences
with near zero performance cost.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:12:32 -08:00
David S. Miller
ff02e0d26f [SPARC64]: Move PTE field definitions back into asm/pgtable.h
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:12:31 -08:00
David S. Miller
1a7a242c89 [SPARC64]: Recognize "virtual-console" as input and output console device.
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:12:28 -08:00
David S. Miller
c4bce90ea2 [SPARC64]: Deal with PTE layout differences in SUN4V.
Yes, you heard it right, they changed the PTE layout for
SUN4V.  Ho hum...

This is the simple and inefficient way to support this.
It'll get optimized, don't worry.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:12:25 -08:00
David S. Miller
490384e752 [SPARC64]: Register kernel TSB with hypervisor.
We do this right after we take over the trap table from OBP.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-20 01:12:23 -08:00