ChangeSet@1.2387, 2005-01-13 09:01:51-08:00, paulus@samba.org
[PATCH] PPC64 Move thread_info flags to its own cache line
This patch fixes a problem I have been seeing since all the preempt
changes went in, which is that ppc64 SMP systems would livelock
randomly if preempt was enabled.
It turns out that what was happening was that one cpu was spinning in
spin_lock_irq (the version at line 215 of kernel/spinlock.c) madly
doing preempt_enable() and preempt_disable() calls. The other cpu had
the lock and was trying to set the TIF_NEED_RESCHED flag for the task
running on the first cpu. That is an atomic operation which has to be
retried if another cpu writes to the same cacheline between the load
and the store, which the other cpu was doing every time it did
preempt_enable() or preempt_disable().
I decided to move the thread_info flags field into the next cache
line, since it is the only field that would regularly be modified by
cpus other than the one running the task that owns the thread_info.
(OK possibly the `cpu' field would be on a rebalance; I don't know the
rebalancing code, but that should be pretty infrequent.) Thus, moving
the flags field seems like a good idea generally as well as solving the
immediate problem.
For the record I am pretty unhappy with the code we use for spin_lock
et al. with preemption turned on (the BUILD_LOCK_OPS stuff in
spinlock.c). For a start we do the atomic op (_raw_spin_trylock) each
time around the loop. That is going to be generating a lot of
unnecessary bus (or fabric) traffic. Instead, after we fail to get
the lock we should poll it with simple loads until we see that it is
clear and then retry the atomic op. Assuming a reasonable cache
design, the loads won't generate any bus traffic until another cpu
writes to the cacheline containing the lock.
Secondly we have lost the __spin_yield call that we had on ppc64,
which is an important optimization when we are running under the
hypervisor. I can't just put that in cpu_relax because I need to know
which (virtual) cpu is holding the lock, so that I can tell the
hypervisor which virtual cpu to give my time slice to. That
information is stored in the lock variable, which is why __spin_yield
needs the address of the lock.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
ChangeSet@1.2386, 2005-01-13 09:01:37-08:00, paulus@samba.org
[PATCH] PPC64 Add PREEMPT_BKL option
This patch adds the PREEMPT_BKL config option for PPC64, shamelessly
stolen from the i386 version. I have this turned on in the kernel on
my desktop G5 and it seems to be just fine.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
ChangeSet@1.2385, 2005-01-13 09:01:24-08:00, paulus@samba.org
[PATCH] PPC64 can do preempt debug too
This patch enables the DEBUG_PREEMPT config option for PPC64. I have
this turned on on my desktop G5 and it isn't finding any problems.
(It did find one problem, in flush_tlb_pending(), that I have just
sent a patch for.)
BTW, do we really need to restrict which architectures the config
option is available on?
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
ChangeSet@1.2384, 2005-01-13 09:01:10-08:00, paulus@samba.org
[PATCH] PPC64 Call preempt_schedule on exception exit
This patch mirrors the recent changes on x86 to call preempt_schedule
rather than schedule in the exception exit path, in the case where the
preempt_count is zero and the TIF_NEED_RESCHED bit is set.
I'm a little concerned that this means that we have a window where
interrupts are enabled and we are on our way into preempt_schedule,
but preempt_count is still zero. Ingo's proposed preempt_schedule_irq
would fix this, and I think something like that should go in.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
ChangeSet@1.2383, 2005-01-13 09:00:59-08:00, paulus@samba.org
[PATCH] PPC64 Disable preemption in flush_tlb_pending
The preempt debug stuff found a place where we were using
smp_processor_id() without having preemption disabled, in
flush_tlb_pending. This patch fixes it by using get_cpu_var and
put_cpu_var instead of the __get_cpu_var variant.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
ChangeSet@1.2382, 2005-01-13 09:00:45-08:00, axboe@suse.de
[PATCH] possible rq starvation on oom
I stumbled across this the other day. The block layer only uses a single
memory pool for request allocation, so it's very possible for eg writes
to have allocated them all at any point in time. If that is the case and
the machine is low on memory, a reader attempting to allocate a request
and failing in blk_alloc_request() can get stuck for a long time since
no one is there to wake it up.
The solution is either to add the extra mempool so both reads and writes
have one, or attempt to handle the situation. I chose the latter, to
save the extra memory required for the additional mempool with
BLKDEV_MIN_RQ statically allocated requests per-queue.
If a read allocation fails and we have no readers in flight for this
queue, mark us rq-starved so that the next write being freed will wake
up the sleeping reader(s). Same situation would happen for writes as
well of course, it's just a lot more unlikely.
Signed-off-by: Jens Axboe <axboe@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
ChangeSet@1.2381, 2005-01-13 09:00:32-08:00, axboe@suse.de
[PATCH] Don't enable ata over eth by default
"ATA over Ethernet support" should not default to 'm', it doesn't make
any sense for a special case driver to do so.
Signed-off-by: Jens Axboe <axboe@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
ChangeSet@1.2380, 2005-01-12 20:04:56-08:00, akropel1@rochester.rr.com
[PATCH] contort getdents64 to pacify gcc-2.96
A recent trivial fixup in sys_getdents64 gives gcc-2.96 indigestion in
the form of an ICE.
While upgrading to a sane gcc would be the preferred solution, rewriting
the change as follows eliminates the error for those who cannot do so.
Signed-off-by: Adam Kropelin <akropel1@rochester.rr.com>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
ChangeSet@1.2379, 2005-01-12 20:04:43-08:00, davej@redhat.com
[PATCH] matroxfb driver broken on non-x86.
This broke since the recent MODULE_PARAM conversion on
architectures that don't have CONFIG_MTRR
Signed-off-by: Dave Jones <davej@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
ChangeSet@1.2378, 2005-01-12 18:14:03-08:00, torvalds@ppc970.osdl.org
Merge bk://bk.arm.linux.org.uk/linux-2.6-rmk
into ppc970.osdl.org:/home/torvalds/v2.6/linux
ChangeSet@1.2280.2.11, 2005-01-12 21:03:45+00:00, nico@org.rmk.(none)
[ARM PATCH] 2204/1: bring {read|write}sw up to date with current reality
Patch from Nicolas Pitre
This patch adds support for all alignments to both endianness.
Signed-off-by: Nicolas Pitre
Signed-off-by: Russell King
ChangeSet@1.2280.2.10, 2005-01-12 20:55:37+00:00, nico@org.rmk.(none)
[ARM PATCH] 2391/1: remove obsolete help text
Patch from Nicolas Pitre
Now that MTD XIP support is merged this part is
not relevant anymore.
Signed-off-by: Nicolas Pitre
Signed-off-by: Russell King
ChangeSet@1.2215.1.12, 2005-01-12 19:52:49+00:00, rmk@flint.arm.linux.org.uk
[ARM] Add missing tlb_migrate_finish()
Signed-off-by: Russell King
ChangeSet@1.2377, 2005-01-12 10:08:53-08:00, torvalds@ppc970.osdl.org
Merge http://lia64.bkbits.net/linux-ia64-release-2.6.11
into ppc970.osdl.org:/home/torvalds/v2.6/linux
ChangeSet@1.2360.1.155, 2005-01-12 10:07:41-08:00, torvalds@ppc970.osdl.org
Merge bk://linux-scsi.bkbits.net/scsi-for-linus-2.6
into ppc970.osdl.org:/home/torvalds/v2.6/linux
ChangeSet@1.2376, 2005-01-12 09:14:26-08:00, davidm@hpl.hp.com
[IA64] add hpzx1_swiotlb machine-vector (new files)
This is really part of the earlier changeset from David to add the
new machine vector to support certain limited range DMA cards on
zx1. I just forgot to run "bk new" before the commit, so the newly
added files weren't checked into BK.
Signed-off-by: David Mosberger-Tang <davidm@hpl.hp.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
ChangeSet@1.2360.1.154, 2005-01-12 09:02:21-08:00, dwmw2@infradead.org
[PATCH] ppc: fix removed MMCR0_PMXE define
In ChangeSet 1.2370, 2005/01/11 17:41:32-08:00, tglx@linutronix.de wrote:
>
> [PATCH] ppc: remove duplicate define
>
> The MMCR0_PMXE is already defined in reg.h...
Er, no it's not. But perhaps it should be...
ChangeSet@1.2360.1.153, 2005-01-12 08:50:53-08:00, paulus@samba.org
[PATCH] PPC64 had _raw_read_trylock already
Ingo presumably didn't notice that ppc64 already had a functional
_raw_read_trylock when he added the #define to use the generic
version. This just removes the #define so we use the ppc64-specific
version again.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
ChangeSet@1.2360.1.152, 2005-01-12 08:50:39-08:00, axboe@suse.de
[PATCH] elevator: print default selection
Currently we only print the default io scheduler if the kernel chooses,
not if the user/bootloader has specified one. This patch saves the extra
line in dmesg but always notified of the default choice by appending
(default) to that line:
..
io scheduler noop registered
io scheduler anticipatory registered
io scheduler deadline registered
io scheduler cfq registered (default)
..
Patch originally from Srihari Vijayaraghavan, modified by me.
Signed-off-by: Jens Axboe <axboe@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
ChangeSet@1.2375, 2005-01-12 08:49:02-08:00, tony.luck@intel.com
[IA64] reorder functions to define ia64_pci_get_legacy_mem() before using it
Signed-off-by: Tony Luck <tony.luck@intel.com>
ChangeSet@1.2360.1.151, 2005-01-12 08:49:02-08:00, axboe@suse.de
[PATCH] cfq-iosched: fix scsi requeue accounting
The accounting can go bad in the requeue hook, it must check the
accounted flag to make sure it was previously considered in the driver.
Signed-off-by: Jens Axboe <axboe@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
ChangeSet@1.2360.1.150, 2005-01-12 08:48:49-08:00, kaos@sgi.com
[PATCH] ia64: export pcibios_resource_to_bus to match other architectures.
Signed-off-by: Keith Owens <kaos@sgi.com>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
ChangeSet@1.2360.1.149, 2005-01-12 08:48:35-08:00, ink@jurassic.park.msu.ru
[PATCH] Alpha: typos in io_trivial.h
This apparently explains some weird IO failures reported in last two months.
Only non-bwx (including generic) kernels were affected.
Acked-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
ChangeSet@1.2360.3.7, 2005-01-12 08:26:35-08:00, torvalds@ppc970.osdl.org
Make mm writelock testing less intrusive.
This enables it only for debug kernels, and also makes sure
that if some external module is still broken, we don't leave
the mmap-sem locked after warning about it.
ChangeSet@1.2360.3.6, 2005-01-12 08:12:09-08:00, marcelo.tosatti@cyclades.com
[PATCH] do_brk() needs mmap_sem write-locked
It seems to be general consensus that its safer to require all do_brk() callers
to grab mmap_sem, and have do_brk to warn otherwise. This is what the following
patch does.
Similar version has been changed to in v2.4.
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
ChangeSet@1.1938.1.176, 2005-01-12 10:09:46-06:00, jejb@mulgrave.(none)
FC Transport updates - additional fc host attributes
From: James.Smart@Emulex.Com
This patch adds 5 more FC transport host attributes in support of HBAAPI.
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
ChangeSet@1.2360.3.5, 2005-01-12 08:09:20-08:00, torvalds@ppc970.osdl.org
Handle two threads both trying to expand their stack simultaneously.
We had all the locking right, but we didn't check whether one of the
threads now no longer needed to expand, so we could incorrectly _shrink_
the stack in the other thread instead (not only causing segfaults, but
since we didn't do a proper unmap, we'd possibly leak pages too).
So re-check the need for expand after getting the lock.
Noticed by Paul Starzetz.
ChangeSet@1.1938.1.175, 2005-01-12 10:06:41-06:00, jejb@mulgrave.(none)
SCSI: add starget_for_each_device
From: James.Smart@Emulex.Com
This patch deprecates the use of device_for_each_child() with stargets.
The reasoning behind this is due to issues regarding:
Semaphores that device_for_each_child() takes
Implicit assumptions that each child is an sdev device.
The patch adds a new helper function, starget_for_each_device(), and
replaces all previous uses of device_for_each_child().
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
ChangeSet@1.2280.2.9, 2005-01-12 15:38:50+00:00, ben-linux@org.rmk.(none)
[ARM PATCH] 2390/1: Simtec Electronics MAINTAINERS file entries
Patch from Ben Dooks
MAINTAINERS entries for currently supported Simtec Electronics
development boards.
Signed-off-by: Ben Dooks
Signed-off-by: Russell King
ChangeSet@1.2360.3.4, 2005-01-12 07:36:34-08:00, ak@suse.de
[PATCH] [4/4] Fix numa=off command line parsing
Fix a long standing bug: numa=off only worked as last argument on
the command line.
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
ChangeSet@1.2360.3.3, 2005-01-12 07:36:17-08:00, ak@suse.de
[PATCH] [3/4] x86_64: Fix NUMA hash setup
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
ChangeSet@1.2360.3.2, 2005-01-12 07:36:02-08:00, ak@suse.de
[PATCH] x86_64: Fix K8 NUMA discovery
Fix K8 node discovery after nodemask changes.
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
ChangeSet@1.1938.1.174, 2005-01-12 09:35:52-06:00, akpm@osdl.org
[PATCH] use mmiowb in qla1280.c
From: Jesse Barnes <jbarnes@engr.sgi.com>
There are a few spots in qla1280.c that don't need a full PCI write flush
to the device, but rather a simple write ordering guarantee. This patch
changes some of the PIO reads that cause write flushes into mmiowb calls
instead, which is a lighter weight way of ensuring ordering.
Signed-off-by: Jeremy Higdon <jeremy@sgi.com>
Signed-off-by: Jesse Barnes <jbarnes@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
ChangeSet@1.2360.3.1, 2005-01-12 07:35:48-08:00, ak@suse.de
[PATCH] x86_64: Fix ACPI SRAT NUMA parsing
Fix fallout from the recent nodemask_t changes. The node ids assigned
in the SRAT parser were off by one.
I added a new first_unset_node() function to nodemask.h to allocate
IDs sanely.
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
ChangeSet@1.1938.1.173, 2005-01-12 09:29:50-06:00, akpm@osdl.org
[PATCH] SCSI aic7xxx: kill kernel 2.2 #ifdef's
From: Adrian Bunk <bunk@stusta.de>
The patch below kills kernel 2.2 #ifdef's from the SCSI aic7xxx driver.
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
ChangeSet@1.2280.2.8, 2005-01-12 15:19:25+00:00, catalin.marinas@com.rmk.(none)
[ARM PATCH] 2389/1: semaphore.c warning fixed
Patch from Catalin Marinas
The patch adds the "ax" attributes to the .sched.text section to
avoid a compiler warning.
Signed-off-by: Catalin Marinas
Signed-off-by: Russell King
ChangeSet@1.2280.2.7, 2005-01-12 15:14:51+00:00, rpurdie@net.rmk.(none)
[ARM PATCH] 2388/1: Add SSP control code for Sharp SL-C7xx Series (Corgi)
Patch from Richard Purdie
The Sharp SL-C7xx Series (Corgi) has 3 devices connected to the SSP
interface each needing different configurations of the port.
This code provides the necessary access and locking so drivers can
access these components. It uses the functions provided by the PXA
SSP driver to access the port.
It also adds some machine specific GPIO definitions used by this
code and adds some comments to existing definitions.
Signed-off-by: Richard Purdie
Signed-off-by: Russell King
ChangeSet@1.2280.2.6, 2005-01-12 14:01:58+00:00, rmk@flint.arm.linux.org.uk
[ARM] Remove <asm/atomic.h> include.
asm/processor.h doesn't use atomic operations nor types, so
there's no need to include asm/atomic.h.
Signed-off-by: Russell King <rmk@arm.linux.org.uk>
ChangeSet@1.2215.1.11, 2005-01-12 13:49:34+00:00, rmk@flint.arm.linux.org.uk
[ARM] Don't use __init for function prototypes.
ChangeSet@1.2360.2.1, 2005-01-12 00:30:07-05:00, fli@ati.com
[libata sata_sil] support ATI IXP300/IXP400 SATA
ChangeSet@1.2360.1.147, 2005-01-12 00:21:23-05:00, akpm@osdl.org
[PATCH] 3c515 warning fix
drivers/net/3c515.c: In function `__check_rx_copybreak':
drivers/net/3c515.c:406: warning: return discards qualifiers from pointer target type
drivers/net/3c515.c: At top level:
drivers/net/3c515.c:406: warning: initialization discards qualifiers from pointer target type
Signed-off-by: Andrew Morton <akpm@osdl.org>
ChangeSet@1.2360.1.146, 2005-01-12 00:21:09-05:00, akpm@osdl.org
[PATCH] ixgb whitespace fix
Signed-off-by: Andrew Morton <akpm@osdl.org>
ChangeSet@1.2360.1.145, 2005-01-12 00:20:57-05:00, akpm@osdl.org
[PATCH] eepro build fix
drivers/net/eepro.c:1799: initializer element is not constant
drivers/net/eepro.c:1799: (near initialization for `__param_arr_io.num')
drivers/net/eepro.c:1800: initializer element is not constant
drivers/net/eepro.c:1800: (near initialization for `__param_arr_irq.num')
drivers/net/eepro.c:1801: initializer element is not constant
drivers/net/eepro.c:1801: (near initialization for `__param_arr_mem.num')
Signed-off-by: Andrew Morton <akpm@osdl.org>
ChangeSet@1.2360.1.144, 2005-01-12 00:18:52-05:00, jgarzik@pobox.com
Merge pobox.com:/garz/repo/linux-2.6
into pobox.com:/garz/repo/net-drivers-2.6
ChangeSet@1.2360.1.143, 2005-01-11 19:48:12-08:00, torvalds@ppc970.osdl.org
Linux 2.6.11-rc1
TAG: v2.6.11-rc1