GitHub/LineageOS/android_kernel_motorola_exynos9610.git
18 years ago[PATCH] x86_64: When cpu_up fails clean up page allocator properly
Andi Kleen [Sat, 5 Nov 2005 16:25:53 +0000 (17:25 +0100)]
[PATCH] x86_64: When cpu_up fails clean up page allocator properly

Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
18 years ago[PATCH] x86_64: Make i386 compile again with fourth DMA32 zone
Andi Kleen [Sat, 5 Nov 2005 16:25:53 +0000 (17:25 +0100)]
[PATCH] x86_64: Make i386 compile again with fourth DMA32 zone

The code should deal with an additional empty zone, so fix up the
#error.

Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
18 years ago[PATCH] x86_64: Set compatibility flag for 4GB zone on IA64
Andi Kleen [Sat, 5 Nov 2005 16:25:53 +0000 (17:25 +0100)]
[PATCH] x86_64: Set compatibility flag for 4GB zone on IA64

IA64 traditionally had a 4GB DMA32 zone. Set the compatibility flag
to keep old drivers working.

For new drivers it would be better to use ZONE_DMA32 now.

Cc: tony.luck@intel.com
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
18 years ago[PATCH] x86_64: Add 4GB DMA32 zone
Andi Kleen [Sat, 5 Nov 2005 16:25:53 +0000 (17:25 +0100)]
[PATCH] x86_64: Add 4GB DMA32 zone

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>
18 years ago[PATCH] x86_64: Update defconfig
Andi Kleen [Sat, 5 Nov 2005 16:25:53 +0000 (17:25 +0100)]
[PATCH] x86_64: Update defconfig

Rerun and enable autofs 4, relayfs and softdog

Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
19 years ago[libata] ATAPI pad allocation fixes/cleanup
Jeff Garzik [Sat, 5 Nov 2005 03:08:00 +0000 (22:08 -0500)]
[libata] ATAPI pad allocation fixes/cleanup

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.

19 years agoMerge branch 'master'
Jeff Garzik [Sat, 5 Nov 2005 02:39:31 +0000 (21:39 -0500)]
Merge branch 'master'

19 years ago[PATCH] nvidiafb: Geforce 7800 series support added
Calin A. Culianu [Sat, 5 Nov 2005 01:38:04 +0000 (20:38 -0500)]
[PATCH] nvidiafb: Geforce 7800 series support added

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>
19 years agoMerge branch 'srp' of master.kernel.org:/pub/scm/linux/kernel/git/roland/infiniband
Linus Torvalds [Sat, 5 Nov 2005 00:32:36 +0000 (16:32 -0800)]
Merge branch 'srp' of /linux/kernel/git/roland/infiniband

19 years agoMerge branch 'for-linus' of master.kernel.org:/pub/scm/linux/kernel/git/roland/infiniband
Linus Torvalds [Sat, 5 Nov 2005 00:31:54 +0000 (16:31 -0800)]
Merge branch 'for-linus' of /linux/kernel/git/roland/infiniband

19 years agoMerge master.kernel.org:/pub/scm/linux/kernel/git/paulus/powerpc-merge
Linus Torvalds [Sat, 5 Nov 2005 00:27:50 +0000 (16:27 -0800)]
Merge /linux/kernel/git/paulus/powerpc-merge

19 years agopowerpc: Fix vmlinux.lds.S for 32-bit
Paul Mackerras [Fri, 4 Nov 2005 23:36:59 +0000 (10:36 +1100)]
powerpc: Fix vmlinux.lds.S for 32-bit

We can't currently use asm-ppc/page.h in vmlinux.lds.S, so until
we have a merged page.h, define PAGE_SIZE and KERNELBASE locally.
Also gets rid of some dynamic executable cruft that we had for
32-bit.  With -Ttext=$(KERNELBASE) this didn't cause any problem,
but when we changed to putting . = KERNELBASE in the vmlinux.lds.S
this cruft caused the text to get linked at 0xa0 instead of
0xc0000000.  Oops.

Signed-off-by: Paul Mackerras <paulus@samba.org>
19 years agopowerpc: Merge smp.c and smp.h
Paul Mackerras [Fri, 4 Nov 2005 23:33:55 +0000 (10:33 +1100)]
powerpc: Merge smp.c and smp.h

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>
19 years agoNFS,SUNRPC,NLM: fix unused variable warnings when CONFIG_SYSCTL is disabled
Chuck Lever [Tue, 1 Nov 2005 21:53:32 +0000 (16:53 -0500)]
NFS,SUNRPC,NLM: fix unused variable warnings when CONFIG_SYSCTL is disabled

 Fix some dprintk's so that NLM, NFS client, and RPC client compile
 cleanly if CONFIG_SYSCTL is disabled.

 Test plan:
 Compile kernel with CONFIG_NFS enabled and CONFIG_SYSCTL disabled.

Signed-off-by: Chuck Lever <cel@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
19 years agoSUNRPC: allow sunrpc.o to link when CONFIG_SYSCTL is disabled
Chuck Lever [Tue, 1 Nov 2005 17:24:48 +0000 (12:24 -0500)]
SUNRPC: allow sunrpc.o to link when CONFIG_SYSCTL is disabled

 The sunrpc module should build properly even when CONFIG_SYSCTL is
 disabled.

 Reported by Jan-Benedict Glaw.

 Test plan:
 Compile kernel with CONFIG_NFS as a module and built-in, and CONFIG_SYSCTL
 enabled and disabled.

Signed-off-by: Chuck Lever <cel@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
19 years agoNFSv4: Teach NFSv4 to cache locks when we hold a delegation
Trond Myklebust [Fri, 4 Nov 2005 20:39:36 +0000 (15:39 -0500)]
NFSv4: Teach NFSv4 to cache locks when we hold a delegation

 Now that we have a method of dealing with delegation recalls, actually
 enable the caching of posix and BSD locks.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
19 years agoNFSv4: Recover locks too when returning a delegation
Trond Myklebust [Fri, 4 Nov 2005 20:38:11 +0000 (15:38 -0500)]
NFSv4: Recover locks too when returning a delegation

 Delegations allow us to cache posix and BSD locks, however when the
 delegation is recalled, we need to "flush the cache" and send
 the cached LOCK requests to the server.

 This patch sets up the mechanism for doing so.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
19 years agoNFSv4: Fix recovery of flock() locks.
Trond Myklebust [Fri, 4 Nov 2005 20:35:30 +0000 (15:35 -0500)]
NFSv4: Fix recovery of flock() locks.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
19 years agoNFSv4: Return any delegations before sillyrenaming the file
Trond Myklebust [Fri, 4 Nov 2005 20:35:02 +0000 (15:35 -0500)]
NFSv4: Return any delegations before sillyrenaming the file

 I missed this one... Any form of rename will result in a delegation
 recall, so it is more efficient to return the one we hold before
 trying the rename.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
19 years agoNFSv4: Fix the handling of the error NFS4ERR_OLD_STATEID
Trond Myklebust [Fri, 4 Nov 2005 20:33:50 +0000 (15:33 -0500)]
NFSv4: Fix the handling of the error NFS4ERR_OLD_STATEID

 Ensure that we retry the failed operation...

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
19 years agoNFSv4: Fix problem with OPEN_DOWNGRADE
Trond Myklebust [Fri, 4 Nov 2005 20:33:38 +0000 (15:33 -0500)]
NFSv4: Fix problem with OPEN_DOWNGRADE

 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>
19 years agoNFSv4: Fix a race between open() and close()
Trond Myklebust [Fri, 4 Nov 2005 20:32:58 +0000 (15:32 -0500)]
NFSv4: Fix a race between open() and close()

 We must not remove the nfs4_state structure from the inode open lists
 before we are in sequence lock.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
19 years ago[USB]: Make early handoff a final fixup instead of a header one.
David S. Miller [Fri, 4 Nov 2005 19:17:24 +0000 (11:17 -0800)]
[USB]: Make early handoff a final fixup instead of a header one.

At header fixup time, it is not yet legal to ioremap() PCI
device registers, yet that is what this quirk code needs to
do.

Signed-off-by: David S. Miller <davem@davemloft.net>
19 years ago[PATCH] improve scheduler fairness a bit
Oleg Nesterov [Fri, 4 Nov 2005 15:54:30 +0000 (18:54 +0300)]
[PATCH] improve scheduler fairness a bit

Do not transfer remaining time slice to another cpu on process exit.

Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
19 years agoMerge master.kernel.org:/home/rmk/linux-2.6-serial
Linus Torvalds [Fri, 4 Nov 2005 18:42:53 +0000 (10:42 -0800)]
Merge master.kernel.org:/home/rmk/linux-2.6-serial

19 years agoMerge master.kernel.org:/home/rmk/linux-2.6-arm
Linus Torvalds [Fri, 4 Nov 2005 18:40:11 +0000 (10:40 -0800)]
Merge master.kernel.org:/home/rmk/linux-2.6-arm

19 years agoMerge master.kernel.org:/pub/scm/linux/kernel/git/acme/net-2.6
Linus Torvalds [Fri, 4 Nov 2005 18:39:28 +0000 (10:39 -0800)]
Merge /pub/scm/linux/kernel/git/acme/net-2.6

19 years ago[PATCH] ARM: Reverted 2918/1: [update] Base port of Comdial MP1000 platfrom
Russell King [Fri, 4 Nov 2005 17:28:34 +0000 (17:28 +0000)]
[PATCH] ARM: Reverted 2918/1: [update] Base port of Comdial MP1000 platfrom

No longer maintained

19 years ago[PATCH] ARM: Reverted 2921/1: Support for the RTC / nvram on the Comdial MP1000
Russell King [Fri, 4 Nov 2005 17:26:57 +0000 (17:26 +0000)]
[PATCH] ARM: Reverted 2921/1: Support for the RTC / nvram on the Comdial MP1000

No longer maintained

19 years ago[PATCH] ARM: Reverted 2919/1: CS8900A ethernet driver modifications for the Comdial...
Russell King [Fri, 4 Nov 2005 17:26:56 +0000 (17:26 +0000)]
[PATCH] ARM: Reverted 2919/1: CS8900A ethernet driver modifications for the Comdial MP1000

No longer maintained

19 years ago[ARM] 3097/1: change library link ordering
Nicolas Pitre [Fri, 4 Nov 2005 17:17:30 +0000 (17:17 +0000)]
[ARM] 3097/1: change library link ordering

Patch from Nicolas Pitre

We have an optimized sha1 routine (arch/arm/lib/sha1.S) meant to
override the generic one in lib/sha1.c.

Unfortunately lib/lib.a is listed _before_ arch/arm/lib/lib.a in the
link argument list and therefore the architecture specific lib functions
are not picked up before the generic versions.

This patch is a quick fix to change that ordering for ARM.  Here's what
the kbuild maintainer had to say about it (was also CC'd on lkml):

On Wed, 2 Nov 2005, Sam Ravnborg wrote:
> This looks like an obvious way to achive correct ordering.
> We could change it so arch defines always took precedence but
> the above is so simple that it is not worth the effort.

Signed-off-by: Nicolas Pitre <nico@cam.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
19 years ago[ARM] 3087/1: PXA2xx flash platform device conversion
Todd Poynor [Fri, 4 Nov 2005 17:15:45 +0000 (17:15 +0000)]
[ARM] 3087/1: PXA2xx flash platform device conversion

Patch from Todd Poynor

Add platform devices for flash to Lubbock and Mainstone board files.
Once in place, the two existing mtd map drivers for the boards will be
converted to use a single pxa2xx map driver in the linux-mtd tree.
Take 4: flash_platform_data .map_name vs. .name cleaned up, resync with
merged irda patch context.

Signed-off-by: Todd Poynor <tpoynor@mvista.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
19 years ago[ARM] 3086/1: ixp2xxx error irq handling
Dave Jiang [Fri, 4 Nov 2005 17:15:44 +0000 (17:15 +0000)]
[ARM] 3086/1: ixp2xxx error irq handling

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>
19 years ago[ARM] 3094/1: remove PLD stuff from old uaccess code
Nicolas Pitre [Fri, 4 Nov 2005 17:15:43 +0000 (17:15 +0000)]
[ARM] 3094/1: remove PLD stuff from old uaccess code

Patch from Nicolas Pitre

ARM processors that have pld instructions are not using those copy_user
implementation anymore.  Let's remove the useless PLD lines which were
half wrong anyway.

Signed-off-by: Nicolas Pitre <nico@cam.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
19 years agoMerge git://oak/home/sfr/kernels/iseries/work
Paul Mackerras [Fri, 4 Nov 2005 06:03:39 +0000 (17:03 +1100)]
Merge git://oak/home/sfr/kernels/iseries/work

19 years agopowerpc: merge tlbflush.h
Stephen Rothwell [Fri, 4 Nov 2005 05:58:59 +0000 (16:58 +1100)]
powerpc: merge tlbflush.h

Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
19 years agoMerge branch 'for-paulus' of git://kernel/home/michael/src/work/
Paul Mackerras [Fri, 4 Nov 2005 05:17:32 +0000 (16:17 +1100)]
Merge branch 'for-paulus' of git://kernel/home/michael/src/work/

19 years agopowerpc: Merge smp-tbsync.c (the generic timebase sync routine)
Paul Mackerras [Fri, 4 Nov 2005 02:28:58 +0000 (13:28 +1100)]
powerpc: Merge smp-tbsync.c (the generic timebase sync routine)

Signed-off-by: Paul Mackerras <paulus@samba.org>
19 years agoMerge with Paulus
Michael Ellerman [Fri, 4 Nov 2005 01:12:52 +0000 (12:12 +1100)]
Merge with Paulus

19 years agopowerpc: Fix random memory corruption in merged elf.h
Michael Ellerman [Thu, 3 Nov 2005 10:10:48 +0000 (21:10 +1100)]
powerpc: Fix random memory corruption in merged elf.h

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>
19 years agopowerpc: Implement smp_release_cpus() in C not asm
Michael Ellerman [Fri, 4 Nov 2005 01:09:42 +0000 (12:09 +1100)]
powerpc: Implement smp_release_cpus() in C not asm

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>
19 years agoMerge git://oss.sgi.com:8090/oss/git/xfs-2.6
Linus Torvalds [Fri, 4 Nov 2005 00:25:58 +0000 (16:25 -0800)]
Merge git://oss.sgi.com:8090/oss/git/xfs-2.6

19 years ago[XFS] Remove no-longer-used qsort source.
Nathan Scott [Thu, 3 Nov 2005 23:51:01 +0000 (10:51 +1100)]
[XFS] Remove no-longer-used qsort source.

Signed-off-by: Nathan Scott <nathans@sgi.com>
19 years agopowerpc: merge tlb.h
Stephen Rothwell [Thu, 3 Nov 2005 23:20:27 +0000 (10:20 +1100)]
powerpc: merge tlb.h

Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
19 years ago[IB] mthca: check P_Key index in modify QP
Jack Morgenstein [Thu, 3 Nov 2005 22:58:33 +0000 (14:58 -0800)]
[IB] mthca: check P_Key index in modify QP

Make sure that the P_Key index passed into mthca_modify_qp() is
within the device's P_Key table.

Signed-off-by: Jack Morgenstein <jackm@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
19 years ago[XFS] Fix an inode32 regression - if no options are presented, must still
Nathan Scott [Thu, 3 Nov 2005 22:49:07 +0000 (09:49 +1100)]
[XFS] Fix an inode32 regression - if no options are presented, must still
set default flags.

SGI-PV: 945242
SGI-Modid: xfs-linux-melb:xfs-kern:24292a

Signed-off-by: Nathan Scott <nathans@sgi.com>
19 years ago[SERIAL] 8250_early.c passing 0 instead of NULL
Ben Dooks [Thu, 3 Nov 2005 21:07:37 +0000 (21:07 +0000)]
[SERIAL] 8250_early.c passing 0 instead of NULL

Fix sparse warning about passing `0` to  simple_strtoul()

Signed-off-by: Ben Dooks <ben-linux@fluff.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
19 years ago[ARM] Fix IXDP2x01 config files
Deepak Saxena [Thu, 3 Nov 2005 21:05:39 +0000 (21:05 +0000)]
[ARM] Fix IXDP2x01 config files

IXDP2401 config file has wrong baudrate and both boards have 3 UARTs.

Signed-off-by: Deepak Saxena <dsaxena@plexity.net>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
19 years ago[ARM] Merge SMP tree
Russell King [Thu, 3 Nov 2005 21:02:39 +0000 (21:02 +0000)]
[ARM] Merge SMP tree

19 years ago[ARM] 3092/1: remove excessive print format padding
Nicolas Pitre [Thu, 3 Nov 2005 20:40:50 +0000 (20:40 +0000)]
[ARM] 3092/1: remove excessive print format padding

Patch from Nicolas Pitre

Using a llx format to print addresses that might possibly be (only) 36
bits wide make sense.  However making it a zero padded 16 char wide
field is a bit excessive and useless.

Signed-off-by: Nicolas Pitre <nico@cam.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
19 years ago[ARM SMP] Do not clear cpu_vm_mask for VIPT caches
Russell King [Thu, 3 Nov 2005 20:32:45 +0000 (20:32 +0000)]
[ARM SMP] Do not clear cpu_vm_mask for VIPT caches

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>
19 years ago[IB] umad: fix hot remove of IB devices
Roland Dreier [Thu, 3 Nov 2005 20:01:18 +0000 (12:01 -0800)]
[IB] umad: fix hot remove of IB devices

Fix hotplug of devices for ib_umad module: when a device goes away,
kill off all MAD agents for open files associated with that device,
and make sure that the device is not touched again after ib_umad
returns from its remove_one function.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
19 years ago[ARM SMP] Add configuration option for ARMv6K processors
Russell King [Thu, 3 Nov 2005 15:48:21 +0000 (15:48 +0000)]
[ARM SMP] Add configuration option for ARMv6K processors

The 'K' extension adds several new instructions to the ARMv6 ISA
which are primerily useful for SMP.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
19 years ago[ARM] Fix another build error with IOP3xx platforms
Russell King [Thu, 3 Nov 2005 11:04:53 +0000 (11:04 +0000)]
[ARM] Fix another build error with IOP3xx platforms

ld doesn't like comments starting with // in its scripts

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
19 years ago[ARM] Add Realview default configuration file
Russell King [Thu, 3 Nov 2005 10:17:44 +0000 (10:17 +0000)]
[ARM] Add Realview default configuration file

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
19 years ago[ARM] Fix more 3016/1 breakage
Russell King [Thu, 3 Nov 2005 10:06:35 +0000 (10:06 +0000)]
[ARM] Fix more 3016/1 breakage

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
19 years agopowerpc: Cleanup vpa code
Michael Ellerman [Thu, 3 Nov 2005 08:34:38 +0000 (19:34 +1100)]
powerpc: Cleanup vpa code

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>
19 years ago[IB] mthca: fix format of FW version
Roland Dreier [Thu, 3 Nov 2005 06:59:37 +0000 (22:59 -0800)]
[IB] mthca: fix format of FW version

Mellanox has decided that the components of the firmware version are
really meant to be displayed in decimal, e.g. 0x000400070190 is
version 4.7.400.  Change the format we use from "%x.%x.%x" to
"%d.%d.%d" to match this convention.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
19 years agopowerpc: Add helper functions for synthesising instructions at runtime
Michael Ellerman [Thu, 3 Nov 2005 06:57:53 +0000 (17:57 +1100)]
powerpc: Add helper functions for synthesising instructions at runtime

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>
19 years agoMerge git://oak/home/sfr/kernels/iseries/work
Paul Mackerras [Thu, 3 Nov 2005 06:04:08 +0000 (17:04 +1100)]
Merge git://oak/home/sfr/kernels/iseries/work

19 years agopowerpc: merge ucontext.h
Stephen Rothwell [Thu, 3 Nov 2005 05:59:17 +0000 (16:59 +1100)]
powerpc: merge ucontext.h

Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
19 years ago[PATCH] powerpc: Keep fixing merged ipcbuf.h
David Gibson [Wed, 2 Nov 2005 23:13:58 +0000 (10:13 +1100)]
[PATCH] powerpc: Keep fixing merged ipcbuf.h

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>
19 years ago[PATCH] ppc32: Fixed warning in m8xx_setup.c
Vitaly Bordug [Wed, 2 Nov 2005 19:55:14 +0000 (22:55 +0300)]
[PATCH] ppc32: Fixed warning in m8xx_setup.c

This adds missing header and thus fix the warning issued by ming prototype.

Signed-off-by: Vitaly Bordug <vbordug@ru.mvista.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
19 years ago[PATCH] ppc32 8xx: fix cpm_dpalloc() comment
Marcelo Tosatti [Wed, 2 Nov 2005 14:42:16 +0000 (12:42 -0200)]
[PATCH] ppc32 8xx: fix cpm_dpalloc() comment

Current comment on top of m8xx_cpm_dpinit is wrong.

Signed-off-by: Marcelo Tosatti <marcelo.tosatti@cyclades.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
19 years ago[PATCH] ppc32 8xx: Fix harmless warning in 8xx_io/commproc.c
Marcelo Tosatti [Wed, 2 Nov 2005 14:46:28 +0000 (12:46 -0200)]
[PATCH] ppc32 8xx: Fix harmless warning in 8xx_io/commproc.c

Signed-off-by: Paul Mackerras <paulus@samba.org>
19 years ago[PATCH] ppc32 8xx: export symbols required for modular IDE
Marcelo Tosatti [Wed, 2 Nov 2005 14:44:16 +0000 (12:44 -0200)]
[PATCH] ppc32 8xx: export symbols required for modular IDE

This fixes these warnings:

      Building modules, stage 2.
      MODPOST
    *** Warning: "__ide_mm_insl" [drivers/ide/ide-core.ko] undefined!
    *** Warning: "__ide_mm_outsw" [drivers/ide/ide-core.ko] undefined!
    *** Warning: "__ide_mm_insw" [drivers/ide/ide-core.ko] undefined!
    *** Warning: "__ide_mm_outsl" [drivers/ide/ide-core.ko] undefined!

Signed-off-by: Paul Mackerras <paulus@samba.org>
19 years ago[PATCH] powerpc: always init nvram on 64-bit powermac
David Woodhouse [Wed, 2 Nov 2005 16:54:46 +0000 (16:54 +0000)]
[PATCH] powerpc: always init nvram on 64-bit powermac

Currently there is no Kconfig symbol to indicate that we want nvram
support on 64-bit kernels; it's assumed we always want it, so make
the powermac setup code always initialize the pmac nvram code if
64-bit.

Signed-off-by: Paul Mackerras <paulus@samba.org>
19 years ago[PATCH] ppc: Fix build warnings in arch/ppc/kernel/traps.c
Becky Bruce [Wed, 2 Nov 2005 16:52:52 +0000 (10:52 -0600)]
[PATCH] ppc: Fix build warnings in arch/ppc/kernel/traps.c

The latest updates to bug.h generate build warnings in traps.c in
arch/ppc.  Fix print format specifiers to account for change of line type
to long from int.

Signed-off-by: Becky Bruce <becky.bruce@freescale.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
19 years ago[PATCH] ppc64: Fix add notifier crashes
John Rose [Wed, 2 Nov 2005 16:29:55 +0000 (10:29 -0600)]
[PATCH] ppc64: Fix add notifier crashes

The extraction of PCI stuff from struct device_node left some false
assumptions in notifier code.  As a result, dynamic add crashes when
non-PCI nodes are added.  This patch fixes these assumptions.

Signed-off-by: John Rose <johnrose@austin.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
19 years ago[XFS] Remove several no-longer-used files.
Nathan Scott [Thu, 3 Nov 2005 05:50:07 +0000 (16:50 +1100)]
[XFS] Remove several no-longer-used files.

Signed-off-by: Nathan Scott <nathans@sgi.com>
19 years agopowerpc: merge sigcontext.h
Stephen Rothwell [Thu, 3 Nov 2005 05:24:25 +0000 (16:24 +1100)]
powerpc: merge sigcontext.h

Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
19 years ago[XFS] Cleanup cosmetic differences between source trees.
Nathan Scott [Thu, 3 Nov 2005 05:14:31 +0000 (16:14 +1100)]
[XFS] Cleanup cosmetic differences between source trees.

Signed-off-by: Nathan Scott <nathans@sgi.com>
19 years agopowerpc: move include/asm-ppc64/ppc32.h to arch/powerpc/kernel
Stephen Rothwell [Thu, 3 Nov 2005 04:32:07 +0000 (15:32 +1100)]
powerpc: move include/asm-ppc64/ppc32.h to arch/powerpc/kernel

It is only included by signal_32.c

Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
19 years agopowerpc: move ppc64/kernel/signal.c to arch/powerpc
Stephen Rothwell [Thu, 3 Nov 2005 04:26:23 +0000 (15:26 +1100)]
powerpc: move ppc64/kernel/signal.c to arch/powerpc

Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
19 years agopowerpc: merge ptrace.h
Stephen Rothwell [Thu, 3 Nov 2005 04:14:36 +0000 (15:14 +1100)]
powerpc: merge ptrace.h

Move struct ptregs32 into asm-ppc64/ppc32.h

Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
19 years agopowerpc: Set entry point and text address in linker script
Michael Ellerman [Thu, 3 Nov 2005 05:03:06 +0000 (16:03 +1100)]
powerpc: Set entry point and text address in linker script

Currently we set the kernel entry point and the address of the text
section in the Makefile, using CONFIG_KERNEL_START.

But we've already got <asm/page.h> in the linker script, so we can just
use KERNELBASE directly. That means if we ever change KERNELBASE there's
one less place to change it.

And we can set the entry point with ENTRY().

There are zero differences from "readelf -a vmlinux" with or without this
patch.

Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
19 years agopowerpc: merge stat.h
Stephen Rothwell [Thu, 3 Nov 2005 05:02:23 +0000 (16:02 +1100)]
powerpc: merge stat.h

Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
19 years ago[IPoIB] don't compile debug code if debugging isn't enabled
Roland Dreier [Thu, 3 Nov 2005 04:51:01 +0000 (20:51 -0800)]
[IPoIB] don't compile debug code if debugging isn't enabled

Don't build ipoib_mcast_iter_ functions if CONFIG_INFINIBAND_IPOIB_DEBUG
is not enabled -- their only callers will not be built either.

Also move the prototype for ipoib_open() to ipoib.h to fix a sparse warning.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
19 years agopowerpc: Make early debugging fit on 80 character terminal
Michael Ellerman [Thu, 3 Nov 2005 04:39:09 +0000 (15:39 +1100)]
powerpc: Make early debugging fit on 80 character terminal

There's some debugging in prom.c that wraps nastly on 80 character
terminals, reformat it to fit.

Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
19 years agopowerpc: Merge asm-ppc/kexec.h and asm-ppc64/kexec.h
Michael Ellerman [Thu, 3 Nov 2005 04:35:45 +0000 (15:35 +1100)]
powerpc: Merge asm-ppc/kexec.h and asm-ppc64/kexec.h

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>
19 years agopowerpc: Move plpar_wrappers.h into arch/powerpc/platforms/pseries
Michael Ellerman [Thu, 3 Nov 2005 04:33:31 +0000 (15:33 +1100)]
powerpc: Move plpar_wrappers.h into arch/powerpc/platforms/pseries

Move plpar_wrappers.h into arch/powerpc/platforms/pseries, fixup white space,
and update callers.

Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
19 years agopowerpc: Make set_dabr() a ppc_md function
Michael Ellerman [Thu, 3 Nov 2005 04:30:49 +0000 (15:30 +1100)]
powerpc: Make set_dabr() a ppc_md function

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>
19 years ago[PKT_SCHED]: Rework QoS and/or fair queueing configuration
Thomas Graf [Tue, 1 Nov 2005 14:13:02 +0000 (15:13 +0100)]
[PKT_SCHED]: Rework QoS and/or fair queueing configuration

Make "QoS and/or fair queueing" have its own menu, it's too big to be
inlined into "Network options". Remove the obsolete NET_QOS option.
Automatically select NET_CLS if needed. Do the same for NET_ESTIMATOR
but allow it to be selected manually for statistical purposes. Add
comments to separate queueing from classification. Fix dependencies
and ordering of classifiers. Improve descriptions/help texts and
remove outdated pieces.

Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
19 years agopowerpc: Copy default configs into arch/powerpc/configs
Michael Ellerman [Thu, 3 Nov 2005 04:24:57 +0000 (15:24 +1100)]
powerpc: Copy default configs into arch/powerpc/configs

Copy default configs into arch/powerpc/configs, rename bpa_defconfig to
cell_defconfig while we're at it.

Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
19 years ago[PATCH] x86-64: bitops fix for -Os
Alexandre Oliva [Mon, 31 Oct 2005 20:29:36 +0000 (18:29 -0200)]
[PATCH] x86-64: bitops fix for -Os

This fixes the x86-64 find_[first|next]_zero_bit() function for the
end-of-range case.  It didn't test for a zero size, and the "rep scas"
would do entirely the wrong thing.

Signed-off-by: Alexandre Oliva <oliva@lsd.ic.unicamp.br>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
19 years agopowerpc: Merge remaining RTAS code
Paul Mackerras [Thu, 3 Nov 2005 03:41:19 +0000 (14:41 +1100)]
powerpc: Merge remaining RTAS code

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>
19 years ago[IPV6]: inet6_ifinfo_notify should use RTM_DELLINK in addrconf_ifdown
Yan Zheng [Fri, 14 Oct 2005 10:31:15 +0000 (18:31 +0800)]
[IPV6]: inet6_ifinfo_notify should use RTM_DELLINK in addrconf_ifdown

Signed-off-by: Yan Zheng <yanzheng@21cn.com>
Acked-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
19 years ago[XFS] fix XFS quota for modular XFS builds
Nathan Scott [Thu, 3 Nov 2005 02:55:06 +0000 (13:55 +1100)]
[XFS] fix XFS quota for modular XFS builds

Cannot build XFS filesystem support as module with quota support.  It
works only when the XFS filesystem support is compiled into the kernel.
Menuconfig prevents from setting CONFIG_XFS_FS=m and CONFIG_XFS_QUOTA=y.

How to reproduce: configure the XFS filesystem with quota support as
module.  The resulting kernel won't have quota support compiled into
xfs.ko.

Fix: Changing the fs/xfs/Kconfig file from tristate to bool lets you
configure the quota support to be compiled into the XFS module.  The
Makefile-linux-2.6 checks only for CONFIG_XFS_QUOTA=y.

Signed-off-by: Dimitri Puzin <tristan-777@ddkom-online.de>
Signed-off-by: Adrian Bunk <bunk@stusta.de>
signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Nathan Scott <nathans@sgi.com>
19 years ago[XFS] Add a mechanism for XFS to use the generic quota sync method.
Nathan Scott [Thu, 3 Nov 2005 02:53:34 +0000 (13:53 +1100)]
[XFS] Add a mechanism for XFS to use the generic quota sync method.
This is now used to issue a delayed allocation flush before reporting
quota, which allows the used space quota report to match reality.

Signed-off-by: Nathan Scott <nathans@sgi.com>
19 years ago[XFS] Add the project quota type into the XFS quota header.
Nathan Scott [Thu, 3 Nov 2005 02:51:23 +0000 (13:51 +1100)]
[XFS] Add the project quota type into the XFS quota header.

Signed-off-by: Nathan Scott <nathans@sgi.com>
19 years ago[XFS] Update XFS quota header license to match the SGI boilerplate.
Nathan Scott [Thu, 3 Nov 2005 02:50:05 +0000 (13:50 +1100)]
[XFS] Update XFS quota header license to match the SGI boilerplate.

Signed-off-by: Nathan Scott <nathans@sgi.com>
19 years ago[XFS] Update XFS documentation.
Nathan Scott [Thu, 3 Nov 2005 02:46:43 +0000 (13:46 +1100)]
[XFS] Update XFS documentation.

Signed-off-by: Nathan Scott <nathans@sgi.com>
19 years agoMerge master.kernel.org:/home/rmk/linux-2.6-arm
Linus Torvalds [Thu, 3 Nov 2005 02:38:22 +0000 (18:38 -0800)]
Merge master.kernel.org:/home/rmk/linux-2.6-arm

19 years agoMerge branch 'swiotlb' of git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux-2.6
Linus Torvalds [Thu, 3 Nov 2005 02:36:15 +0000 (18:36 -0800)]
Merge branch 'swiotlb' of git://git./linux/kernel/git/aegl/linux-2.6

19 years ago[NET]: Fix zero-size datagram reception
Herbert Xu [Wed, 2 Nov 2005 07:55:00 +0000 (18:55 +1100)]
[NET]: Fix zero-size datagram reception

The recent rewrite of skb_copy_datagram_iovec broke the reception of
zero-size datagrams.  This patch fixes it.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
19 years ago[ETHERNET]: Add ether stuff to docbook
Stephen Hemminger [Wed, 2 Nov 2005 01:05:09 +0000 (17:05 -0800)]
[ETHERNET]: Add ether stuff to docbook

Fix up etherdevice docbook comments and make them (and other networking stuff)
get dragged into the kernel-api. Delete the old 8390 stuff, it really isn't
interesting anymore.

Signed-off-by: Stephen Hemminger <shemminger@osdl.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
19 years ago[ETHERNET]: Optimize is_broadcast_ether_addr
Stephen Hemminger [Wed, 2 Nov 2005 00:52:11 +0000 (16:52 -0800)]
[ETHERNET]: Optimize is_broadcast_ether_addr

Optimize the match for broadcast address by using bit operations instead
of comparison. This saves a number of conditional branches, and generates
smaller code.

Signed-off-by: Stephen Hemminger <shemminger@osdl.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
19 years ago[XFS] Fixed the inconsistency between attribute b-tree intermidiate node
Yingping Lu [Wed, 2 Nov 2005 23:31:47 +0000 (10:31 +1100)]
[XFS] Fixed the inconsistency between attribute b-tree intermidiate node
and leaf blocks. The problem cam from xfsqa test 117.

SGI-PV: 940655
SGI-Modid: xfs-linux:xfs-kern:201527a

Signed-off-by: Yingping Lu <yingping@sgi.com>
Signed-off-by: Nathan Scott <nathans@sgi.com>
19 years ago[TCP]: BIC max increment too large
Stephen Hemminger [Tue, 1 Nov 2005 23:26:45 +0000 (15:26 -0800)]
[TCP]: BIC max increment too large

The max growth of BIC TCP is too large. Original code was based on
BIC 1.0 and the default there was 32. Later code (2.6.13) included
compensation for delayed acks, and should have reduced the default
value to 16; since normally TCP gets one ack for every two packets sent.

The current value of 32 makes BIC too aggressive and unfair to other
flows.

Submitted-by: Injong Rhee <rhee@eos.ncsu.edu>
Signed-off-by: Stephen Hemminger <shemminger@osdl.org>
Acked-by: Ian McDonald <imcdnzl@gmail.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
19 years ago[MCAST]: ip[6]_mc_add_src should be called when number of sources is zero
Yan Zheng [Fri, 28 Oct 2005 00:02:08 +0000 (08:02 +0800)]
[MCAST]: ip[6]_mc_add_src should be called when number of sources is zero

And filter mode is exclude.

Further explanation by David Stevens:

Multicast source filters aren't widely used yet, and that's really the only
feature that's affected if an application actually exercises this bug, as far
as I can tell. An ordinary filter-less multicast join should still work, and
only forwarded multicast traffic making use of filters and doing empty-source
filters with the MSFILTER ioctl would be at risk of not getting multicast
traffic forwarded to them because the reports generated would not be based on
the correct counts.

Signed-off-by: Yan Zheng <yanzheng@21cn.com
Acked-by: David L Stevens <dlstevens@us.ibm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>