With a NR_CPUS==128 kernel with CPU hotplug enabled we would waste 4MB
on per CPU data of all possible CPUs. The reason was that HOTPLUG
always set up possible map to NR_CPUS cpus and then we need to allocate
that much (each per CPU data is roughly ~32k now)
The underlying problem is that ACPI didn't tell us how many hotplug CPUs
the platform supports. So the old code just assumed all, which would
lead to this memory wastage.
This implements some new heuristics:
- If the BIOS specified disabled CPUs in the ACPI/mptables assume they
can be enabled later (this is bending the ACPI specification a bit,
but seems like a obvious extension)
- The user can overwrite it with a new additionals_cpus=NUM option
- Otherwise use half of the available CPUs or 2, whatever is more.
Cc: ashok.raj@intel.com
Cc: len.brown@intel.com
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Adding __initdata_* to asm-generic/sections.h
Replaces a lot of open coded externs in arch/x86_64/*
I had to change __bss_end to __bss_stop to match the other architectures.
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
It is for physical addresses, not for PFNs.
Pointed out by Tejun Heo.
Cc: htejun@gmail.com
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
We should zap the low mappings, as soon as possible, so that we can catch
kernel bugs more effectively. Previously early boot had NULL mapped
and didn't trap on NULL references.
This patch introduces boot_level4_pgt, which will always have low identity
addresses mapped. Druing boot, all the processors will use this as their
level4 pgt. On BP, we will switch to init_level4_pgt as soon as we enter C
code and zap the low mappings as soon as we are done with the usage of
identity low mapped addresses. On AP's we will zap the low mappings as
soon as we jump to C code.
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Ashok Raj <ashok.raj@intel.com>
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Not go from the CPU number to an mapping array.
Mode number is often used now in fast paths.
This also adds a generic numa_node_id to all the topology includes
Suggested by Eric Dumazet
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Has been introduced for x86-64 at some point to save memory
in struct page, but has been obsolete for some time. Just
remove it.
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
pfn_to_page really requires pfn_valid to be true now, no question.
Some people stumbled over it, but it was misleading and wrong.
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Here's a patch that builds on Natalie Protasevich's IRQ compression
patch and tries to work for MPS boots as well as ACPI. It is meant for
a 4-node IBM x460 NUMA box, which was dying because it had interrupt
pins with GSI numbers > NR_IRQS and thus overflowed irq_desc.
The problem is that this system has 270 GSIs (which are 1:1 mapped with
I/O APIC RTEs) and an 8-node box would have 540. This is much bigger
than NR_IRQS (224 for both i386 and x86_64). Also, there aren't enough
vectors to go around. There are about 190 usable vectors, not counting
the reserved ones and the unused vectors at 0x20 to 0x2F. So, my patch
attempts to compress the GSI range and share vectors by sharing IRQs.
Cc: "Protasevich, Natalie" <Natalie.Protasevich@unisys.com>
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
MC4_MISC - DRAM Errors Threshold Register realized under AMD K8 Rev F.
This register is used to count correctable and uncorrectable ECC errors that occur during DRAM read operations.
The user may interface through sysfs files in order to change the threshold configuration.
bank%d/error_count - reads current error count, write to clear.
bank%d/interrupt_enable - set/clear interrupt enable.
bank%d/threshold_limit - read/write the threshold limit.
APIC vector 0xF9 in hw_irq.h.
5 software defined bank ids in mce.h.
new apic.c function to setup threshold apic lvt.
defaults to interrupt off, count enabled, and threshold limit max.
sysfs interface created on /sys/devices/system/threshold.
AK: added some ifdefs to make it compile on UP
Signed-off-by: Jacob Shin <jacob.shin@amd.com>
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Add a new 4GB GFP_DMA32 zone between the GFP_DMA and GFP_NORMAL zones.
As a bit of historical background: when the x86-64 port
was originally designed we had some discussion if we should
use a 16MB DMA zone like i386 or a 4GB DMA zone like IA64 or
both. Both was ruled out at this point because it was in early
2.4 when VM is still quite shakey and had bad troubles even
dealing with one DMA zone. We settled on the 16MB DMA zone mainly
because we worried about older soundcards and the floppy.
But this has always caused problems since then because
device drivers had trouble getting enough DMA able memory. These days
the VM works much better and the wide use of NUMA has proven
it can deal with many zones successfully.
So this patch adds both zones.
This helps drivers who need a lot of memory below 4GB because
their hardware is not accessing more (graphic drivers - proprietary
and free ones, video frame buffer drivers, sound drivers etc.).
Previously they could only use IOMMU+16MB GFP_DMA, which
was not enough memory.
Another common problem is that hardware who has full memory
addressing for >4GB misses it for some control structures in memory
(like transmit rings or other metadata). They tended to allocate memory
in the 16MB GFP_DMA or the IOMMU/swiotlb then using pci_alloc_consistent,
but that can tie up a lot of precious 16MB GFPDMA/IOMMU/swiotlb memory
(even on AMD systems the IOMMU tends to be quite small) especially if you have
many devices. With the new zone pci_alloc_consistent can just put
this stuff into memory below 4GB which works better.
One argument was still if the zone should be 4GB or 2GB. The main
motivation for 2GB would be an unnamed not so unpopular hardware
raid controller (mostly found in older machines from a particular four letter
company) who has a strange 2GB restriction in firmware. But
that one works ok with swiotlb/IOMMU anyways, so it doesn't really
need GFP_DMA32. I chose 4GB to be compatible with IA64 and because
it seems to be the most common restriction.
The new zone is so far added only for x86-64.
For other architectures who don't set up this
new zone nothing changes. Architectures can set a compatibility
define in Kconfig CONFIG_DMA_IS_DMA32 that will define GFP_DMA32
as GFP_DMA. Otherwise it's a nop because on 32bit architectures
it's normally not needed because GFP_NORMAL (=0) is DMA able
enough.
One problem is still that GFP_DMA means different things on different
architectures. e.g. some drivers used to have #ifdef ia64 use GFP_DMA
(trusting it to be 4GB) #elif __x86_64__ (use other hacks like
the swiotlb because 16MB is not enough) ... . This was quite
ugly and is now obsolete.
These should be now converted to use GFP_DMA32 unconditionally. I haven't done
this yet. Or best only use pci_alloc_consistent/dma_alloc_coherent
which will use GFP_DMA32 transparently.
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Use ata_pad_{alloc,free} in two drivers, to factor out common code.
Add ata_pad_{alloc,free} to two other drivers, which needed the padding
but had not been updated.
This adds support for the Nvidia Geforce 7800 series of cards to the
nvidiafb framebuffer driver. All it does is add the PCI device id for
the 7800, 7800 GTX, 7800 GO, and 7800 GTX GO cards to the module device
table for the nvidiafb.ko driver, so that nvidiafb.ko will actually work
on these cards.
I also added the relevant PCI device ids to linux/pci_ids.h
I tested it on my 7800 GTX here and it works like a charm. I now can
get framebuffer support on this card! Woo hoo!! Nothing like 200x75 text
mode to make your eyes BLEED. ;)
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This also moves setup_cpu_maps to setup-common.c (calling it
smp_setup_cpu_maps) and uses it on both 32-bit and 64-bit.
Signed-off-by: Paul Mackerras <paulus@samba.org>
RFC 3530 states that for OPEN_DOWNGRADE "The share_access and share_deny
bits specified must be exactly equal to the union of the share_access and
share_deny bits specified for some subset of the OPENs in effect for
current openowner on the current file.
Setattr is currently violating the NFSv4 rules for OPEN_DOWNGRADE in that
it may cause a downgrade from OPEN4_SHARE_ACCESS_BOTH to
OPEN4_SHARE_ACCESS_WRITE despite the fact that there exists no open file
with O_WRONLY access mode.
Fix the problem by replacing nfs4_find_state() with a modified version of
nfs_find_open_context().
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Patch from Dave Jiang
This provides support for IXP2xxx error interrupt handling. Previously there was a patch to remove this (although the original stuff was broken). Well, now the error bits are needed again. These are used extensively by the micro-engine drivers according to Deepak and also we will need it for the new EDAC code that Alan Cox is trying to push into the main kernel.
Re-submit of 3072/1, generated against git tree pulled today. AFAICT, this git tree pulled in all the ARM changes that's in arm.diff. Please let me know if there are additional changes. Thx!
Signed-off-by: Dave Jiang <djiang@mvista.com>
Signed-off-by: Deepak Saxena <dsaxena@plexity.net>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
The merged verison of ELF_CORE_COPY_REGS is basically the PPC64 version, with
a memset that came from PPC and a few types abstracted out into #defines. But
it's not _quite_ right.
The first problem is we calculate the number of registers with:
nregs = sizeof(struct pt_regs) / sizeof(ELF_GREG_TYPE)
For a 32-bit process on a 64-bit kernel that's bogus because the registers are
64 bits, but ELF_GREG_TYPE is u32, so nregs == 88 which is wrong.
The other problem is the memset, which assumes a struct pt_regs is smaller
than a struct elf_regs. For a 32-bit process on a 64-bit kernel that's false.
The fix is to calculate the number of regs using sizeof(unsigned long), which
should always be right, and just memset the whole damn thing _before_ copying
the registers in.
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
There's no reason for smp_release_cpus() to be asm, and most people can make
more sense of C code. Add an extern declaration to smp.h and remove the custom
one in machine_kexec.c
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Since we do not invalidate TLBs/caches on MM switches, we should not
clear the cpu_vm_mask for the CPU.
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
register_vpa() doesn't actually do a VPA register call it just uses the flags
you pass it, so rename it to vpa_call() to be clearer.
We can then define register_vpa() and unregister_vpa() which are both simple
wrappers around vpa_call(). (we'll need unregister_vpa() for kexec soon)
We can then cleanup vpa_init(), and because vpa_init() is only called from
platforms/pseries we remove the definition in asm-ppc64/smp.h.
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
There's a few places already, and soon will be more, where we synthesise
branch instructions at runtime. Rather than doing it by hand in each case,
it would make sense to have one implementation.
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Oops, replacing the two u64s in struct ipc64_perm with __u32s changed
the alignment of that structure, which could mess up userspace.
Revert to using two unsigned long longs (which is what ppc32 had
originally). ppc64 orignally had two unsigned longs, but long long is
the same size on 64 bit, so this should be ok there too.
Signed-off-by: David Gibson <dwg@au1.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Merge include/asm-ppc/kexec.h and include/asm-ppc64/kexec.h.
The only thing that's really changed is that we now allocate crash_notes
properly on PPC32. It's address is exported via sysfs, so it's not correct
for it to be a pointer.
I've also removed some of the "we don't use this" comments, because they're
wrong (or perhaps were referring only to arch code).
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Move plpar_wrappers.h into arch/powerpc/platforms/pseries, fixup white space,
and update callers.
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Move pSeries specific code in set_dabr() into a ppc_md function, this will
allow us to keep plpar_wrappers.h private to platforms/pseries.
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
This moves rtas-proc.c and rtas_flash.c into arch/powerpc/kernel, since
cell wants them as well as pseries (and chrp can use rtas-proc.c too,
at least in principle). rtas_fw.c is gone, with its bits moved into
rtas_flash.c and rtas.c.
Signed-off-by: Paul Mackerras <paulus@samba.org>