[PATCH] Directed yield: direct yield of spinlocks for s390.
Use the new diagnose 0x9c in the spinlock implementation for s390. It
yields the remaining timeslice of the virtual cpu that tries to acquire a
lock to the virtual cpu that is the current holder of the lock.
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
[PATCH] Directed yield: direct yield of spinlocks for powerpc
Powerpc already has a directed yield for CONFIG_PREEMPT="n". To make it
work with CONFIG_PREEMPT="y" as well the _raw_{spin,read,write}_relax
primitives need to be defined to call __spin_yield() for spinlocks and
__rw_yield() for rw-locks.
Acked-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
[PATCH] Directed yield: cpu_relax variants for spinlocks and rw-locks
On systems running with virtual cpus there is optimization potential in
regard to spinlocks and rw-locks. If the virtual cpu that has taken a lock
is known to a cpu that wants to acquire the same lock it is beneficial to
yield the timeslice of the virtual cpu in favour of the cpu that has the
lock (directed yield).
With CONFIG_PREEMPT="n" this can be implemented by the architecture without
common code changes. Powerpc already does this.
With CONFIG_PREEMPT="y" the lock loops are coded with _raw_spin_trylock,
_raw_read_trylock and _raw_write_trylock in kernel/spinlock.c. If the lock
could not be taken cpu_relax is called. A directed yield is not possible
because cpu_relax doesn't know anything about the lock. To be able to
yield the lock in favour of the current lock holder variants of cpu_relax
for spinlocks and rw-locks are needed. The new _raw_spin_relax,
_raw_read_relax and _raw_write_relax primitives differ from cpu_relax
insofar that they have an argument: a pointer to the lock structure.
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Haavard Skinnemoen <hskinnemoen@atmel.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Paul Collins [Sun, 1 Oct 2006 06:27:41 +0000 (23:27 -0700)]
[PATCH] leds: turn LED off when changing triggers
I was playing with LED triggers when I noticed that changing from heartbeat
(or ide-disk) to "none" at the right moment would leave the LED stuck on.
This is easy to reproduce by doing "find / >/dev/null" with the ide-disk
trigger enabled and then switching to "none".
Here is a patch that fixes the problem by explicitly turning the LED off
after removing the existing trigger.
Signed-off-by: Paul Collins <paul@ondioline.org> Acked-by: Richard Purdie <rpurdie@rpsys.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Alan Cox [Sun, 1 Oct 2006 06:27:29 +0000 (23:27 -0700)]
[PATCH] serverworks: Switch to pci refcounted interfaces
As we don't support hotplug we end up leaking an isa_dev reference which if
unload was ever added we would drop at the end of unloading. This is fine
because we do genuinely need the isa_dev pointer until unload.
Signed-off-by: Alan Cox <alan@redhat.com> Cc: Greg KH <greg@kroah.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Ross Biro [Sun, 1 Oct 2006 06:27:25 +0000 (23:27 -0700)]
[PATCH] allow /proc/config.gz to be built as a module
The driver for /proc/config.gz consumes rather a lot of memory and it is in
fact possible to build it as a module.
In some ways this is a bit risky, because the .config which is used for
compiling kernel/configs.c isn't necessarily the same as the .config which was
used to build vmlinux.
But OTOH the potential memory savings are decent, and it'd be fairly dumb to
build your configs.o with a different .config.
Signed-off-by: Andrew Morton <akpm@google.com> Cc: "Randy.Dunlap" <rdunlap@xenotime.net> Cc: Sam Ravnborg <sam@ravnborg.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Alan Cox [Sun, 1 Oct 2006 06:27:24 +0000 (23:27 -0700)]
[PATCH] serial: Fix up offenders peering at baud bits directly
Stop some other people peering into the baud bits on their own and make
them use the tty_get_baud_rate() helper as a preperation for the move to
the new termios. Corrected dependancy previous one had on new termios
structs
Signed-off-by: Alan Cox <alan@redhat.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
which is neat code except a programmer needs to write size twice. Which
sometimes leads to mistakes. If len passed to kmalloc is smaller that len
passed to memcpy, it's straight overwrite-beyond-end. If len passed to
memcpy is smaller than len passed to kmalloc, it's either a) legit
behaviour ;-), or b) cloned buffer will contain garbage in second half.
Slight trolling of commit lists shows several duplications bugs
done exactly because of diverged lenghts:
Takashi Iwai [Sun, 1 Oct 2006 06:27:19 +0000 (23:27 -0700)]
[PATCH] maximum latency tracking: ALSA support
Add maximum latency tracking to the ALSA subsystem for PCM playback. In
ALSA, the playback application controls the buffer size and thus indirectly
the period of latency that it can deal with. This patch uses 75% of the
total available latency as threshold to announce to the latency subsystem;
While 75% is a crude heuristic it's a quite reasonable one; the remaining
25% can be used for all driver processing for the next samples which is
also proportional to the size of the buffer.
With ogg123 a latency setting of about 4msec was seen (at 44Khz), while
with the "play" command a much longer maximum tolerable latency was seen.
Other, more multimedia oriented players as well as games, will have a lot
smaller buffers to allow better synchronization and those will actually get
into the latency domains where there is impact on the power management
rules.
Signed-off-by: Takashi Iwai <tiwai@suse.de> Signed-off-by: Arjan van de Ven <arjan@linux.intel.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Add infrastructure to track "maximum allowable latency" for power saving
policies.
The reason for adding this infrastructure is that power management in the
idle loop needs to make a tradeoff between latency and power savings
(deeper power save modes have a longer latency to running code again). The
code that today makes this tradeoff just does a rather simple algorithm;
however this is not good enough: There are devices and use cases where a
lower latency is required than that the higher power saving states provide.
An example would be audio playback, but another example is the ipw2100
wireless driver that right now has a very direct and ugly acpi hook to
disable some higher power states randomly when it gets certain types of
error.
The proposed solution is to have an interface where drivers can
* announce the maximum latency (in microseconds) that they can deal with
* modify this latency
* give up their constraint
and a function where the code that decides on power saving strategy can
query the current global desired maximum.
This patch has a user of each side: on the consumer side, ACPI is patched
to use this, on the producer side the ipw2100 driver is patched.
A generic maximum latency is also registered of 2 timer ticks (more and you
lose accurate time tracking after all).
While the existing users of the patch are x86 specific, the infrastructure
is not. I'd like to ask the arch maintainers of other architectures if the
infrastructure is generic enough for their use (assuming the architecture
has such a tradeoff as concept at all), and the sound/multimedia driver
owners to look at the driver facing API to see if this is something they
can use.
[akpm@osdl.org: cleanups] Signed-off-by: Arjan van de Ven <arjan@linux.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Acked-by: Jesse Barnes <jesse.barnes@intel.com> Cc: "Brown, Len" <len.brown@intel.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Keith Mannthey [Sun, 1 Oct 2006 06:27:09 +0000 (23:27 -0700)]
[PATCH] hot-add-mem x86_64: use CONFIG_MEMORY_HOTPLUG_RESERVE
The api for hot-add memory already has a construct for finding nodes based on
an address, memory_add_physaddr_to_nid. This patch allows the fucntion to do
something besides return 0. It uses the nodes_add infomation to lookup to
node info for a hot add event.
Signed-off-by: Keith Mannthey <kmannth@us.ibm.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Andi Kleen <ak@muc.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
In cases where the acpi memory-add event does not containe the pxm (node)
infomation allow the driver to look up node info based on the address. The
acpi_get_node call returns -1 if it can't decode the pxm info, this causes
add_memory to panic. acpi_get_node would have to decode the resource from the
handle (a lenghty proposition). This seems to be the cleanist point to
interject the hook.
The api for hot-add memory already has a construct for finding nodes based on
an address, memory_add_physaddr_to_nid. This patch allows the fucntion to do
something besides return 0. It uses the nodes_add infomation to lookup to
node info for a hot add event.
Signed-off-by: Keith Mannthey <kmannth@us.ibm.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Andi Kleen <ak@muc.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Keith Mannthey [Sun, 1 Oct 2006 06:27:05 +0000 (23:27 -0700)]
[PATCH] hot-add-mem x86_64: Enable SPARSEMEM in srat.c
Enable x86_64 srat.c to share code between both reserve and sparsemem based
add memory paths. Both paths need the hot-add area node locality infomration
(nodes_add). This code refactors the code path to allow this.
Signed-off-by: Keith Mannthey <kmannth@us.ibm.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Andi Kleen <ak@muc.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Keith Mannthey [Sun, 1 Oct 2006 06:27:05 +0000 (23:27 -0700)]
[PATCH] hot-add-mem x86_64: Kconfig changes
Create Kconfig namespace for MEMORY_HOTPLUG_RESERVE and MEMORY_HOTPLUG_SPARSE.
This is needed to create a disticiton between the 2 paths. Selecting the
high level opiton of MEMORY_HOTPLUG will get you MEMORY_HOTPLUG_SPARSE if you
have sparsemem enabled or MEMORY_HOTPLUG_RESERVE if you are x86_64 with
discontig and ACPI numa support.
Signed-off-by: Keith Mannthey <kmannth@us.ibm.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Andi Kleen <ak@muc.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Alan Cox [Sun, 1 Oct 2006 06:27:03 +0000 (23:27 -0700)]
[PATCH] PCI quirks update
This fixes two things
Firstly someone mistakenly used "errata" for the singular. This causes
Dave Woodhouse to emit diagnostics whenever the string is read, and so
should be fixed.
Secondly the AMD AGP tunnel has an erratum which causes hangs if you try
and do direct PCI to AGP transfers in some cases. We have a flag for
PCI/PCI failures but we need a different flag for this really as in this
case we don't want to stop PCI/PCI transfers using things like IOAT and the
new RAID offload work.
I'll post some updates to make proper use of the PCIAGP flag in the
media/video drivers to Mauro.
Signed-off-by: Alan Cox <alan@redhat.com> Cc: David Woodhouse <dwmw2@infradead.org> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
The ->flags in struct request was split into two variables, in a recent
changeset. The merge of this change forgot to update SCSI's libsas,
probably because libsas was a very recent merge.
Signed-off-by: Jeff Garzik <jeff@garzik.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
If we share the tag map between two or more queues, then we cannot
use __set_bit() to set the bit. In fact we need to make sure we
atomically acquire this tag, so loop using test_and_set_bit() to
protect from that.
David Howells [Tue, 29 Aug 2006 18:06:31 +0000 (19:06 +0100)]
[PATCH] BLOCK: Make USB storage depend on SCSI rather than selecting it [try #6]
This makes CONFIG_USB_STORAGE depend on CONFIG_SCSI rather than selecting it,
as selecting it makes CONFIG_USB_STORAGE override the dependencies of SCSI,
causing it to turn on even if they aren't all met.
Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
David Howells [Sat, 30 Sep 2006 18:45:40 +0000 (20:45 +0200)]
[PATCH] BLOCK: Make it possible to disable the block layer [try #6]
Make it possible to disable the block layer. Not all embedded devices require
it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require
the block layer to be present.
This patch does the following:
(*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev
support.
(*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls
an item that uses the block layer. This includes:
(*) Block I/O tracing.
(*) Disk partition code.
(*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS.
(*) The SCSI layer. As far as I can tell, even SCSI chardevs use the
block layer to do scheduling. Some drivers that use SCSI facilities -
such as USB storage - end up disabled indirectly from this.
(*) Various block-based device drivers, such as IDE and the old CDROM
drivers.
(*) MTD blockdev handling and FTL.
(*) JFFS - which uses set_bdev_super(), something it could avoid doing by
taking a leaf out of JFFS2's book.
(*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and
linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is,
however, still used in places, and so is still available.
(*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and
parts of linux/fs.h.
(*) Makes a number of files in fs/ contingent on CONFIG_BLOCK.
(*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK.
(*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK
is not enabled.
(*) fs/no-block.c is created to hold out-of-line stubs and things that are
required when CONFIG_BLOCK is not set:
(*) Default blockdev file operations (to give error ENODEV on opening).
(*) Makes some /proc changes:
(*) /proc/devices does not list any blockdevs.
(*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK.
(*) Makes some compat ioctl handling contingent on CONFIG_BLOCK.
(*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if
given command other than Q_SYNC or if a special device is specified.
(*) In init/do_mounts.c, no reference is made to the blockdev routines if
CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2.
(*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return
error ENOSYS by way of cond_syscall if so).
(*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if
CONFIG_BLOCK is not set, since they can't then happen.
Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
David Howells [Tue, 29 Aug 2006 18:06:18 +0000 (19:06 +0100)]
[PATCH] BLOCK: Move the ReiserFS device ioctl compat stuff to the ReiserFS driver [try #6]
Move the ReiserFS device ioctl compat stuff from fs/compat_ioctl.c to the
ReiserFS driver so that the ReiserFS header file doesn't need to be included.
Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
David Howells [Tue, 29 Aug 2006 18:06:09 +0000 (19:06 +0100)]
[PATCH] BLOCK: Dissociate generic_writepages() from mpage stuff [try #6]
Dissociate the generic_writepages() function from the mpage stuff, moving its
declaration to linux/mm.h and actually emitting a full implementation into
mm/page-writeback.c.
The implementation is a partial duplicate of mpage_writepages() with all BIO
references removed.
It is used by NFS to do writeback.
Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
Oleg Nesterov [Tue, 29 Aug 2006 07:15:14 +0000 (09:15 +0200)]
[PATCH] exit_io_context: don't disable irqs
We don't need to disable irqs to clear current->io_context, it is protected
by ->alloc_lock. Even IF it was possible to submit I/O from IRQ on behalf of
current this irq_disable() can't help: current_io_context() will re-instantiate
->io_context after irq_enable().
We don't need task_lock() or local_irq_disable() to clear ioc->task. This can't
prevent other CPUs from playing with our io_context anyway.
Merge branch 'drm-patches' of git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6
* 'drm-patches' of git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6: (36 commits)
drm: Use register writes instead of BITBLT_MULTI packets for buffer swap blits
drm: use radeon specific names for radeon flags
drm: add device/vendor id to drm_device_t for compat with FreeBSD drivers
drm: allow multiple addMaps with the same 32-bit map offsset.
drm: fd.o Bug #7595: Avoid u32 overflows in radeon_check_and_fixup_offset().
drm: Fix hashtab implementation leaking illegal error codes to user space.
drm: domain changes broke ppc r200
drm: fixup setversion return codes..
drm: fixup i915 error codes
drm: realign sosme radeon code with drm git tree
drm: realign via driver with drm git tree
drm: remove hash tables on drm exit
drm: cleanups
drm: i810_dma.c: fix pointer arithmetic for 64-bit target
drm: avoid kernel oops in some error paths calling drm_lastclose
drm: allow detection of new VIA chipsets
drm: fix i965 build bug
drm: remove FALSE/TRUE that snuck in with simple memory manager changes.
drm: Add support for Intel i965G chipsets.
drm: add better explanation for i830/i915
...
[PATCH] ll_rw_blk: allow more flexibility for read_ahead_kb store
It can make sense to set read-ahead larger than a single request.
We should not be enforcing such policy on the user. Additionally,
using the BLKRASET ioctl doesn't impose such a restriction. So
additionally we now expose identical behaviour through the two.
CFQ implements this on its own now, but it's really block layer
knowledge. Tells a device queue to start dispatching requests to
the driver, taking care to unplug if needed. Also fixes the issue
where as/cfq will invoke a stopped queue, which we really don't
want.
[PATCH] cfq-iosched: Kill O(N) runtime of cfq_resort_rr_list()
Currently it scales with number of processes in that priority group,
which is potentially not very nice as it's called quite often.
Basically we always need to do tail inserts, except for the case of a
new process. So just mark/detect a queue as such.
[PATCH] cfq-iosched: use new io context counting mechanism
It's ok if the read path is a lot more costly, as long as inc/dec is
really cheap. The inc/dec will happen for each created/freed io context,
while the reading only happens when a disk queue exits.
[PATCH] as-iosched: use new io context counting mechanism
It's ok if the read path is a lot more costly, as long as inc/dec is
really cheap. The inc/dec will happen for each created/freed io context,
while the reading only happens when a disk queue exits.
None of the in-kernel primitives for handling "atomic" counting seem
to be a good fit. We need something that is essentially free for
incrementing/decrementing, while the read side may be more expensive
as we only ever need to do that when a device is removed from the
kernel.
Use a per-cpu variable for maintaining a per-cpu ioc count and define
a reading mechanism that just sums up the values.
Jens Axboe [Tue, 29 Aug 2006 07:05:44 +0000 (09:05 +0200)]
[PATCH] cfq-iosched: kill cfq_exit_lock
cfq_exit_lock is protecting two things now:
- The per-ioc rbtree of cfq_io_contexts
- The per-cfqd linked list of cfq_io_contexts
The per-cfqd linked list can be protected by the queue lock, as it is (by
definition) per cfqd as the queue lock is.
The per-ioc rbtree is mainly used and updated by the process itself only.
The only outside use is the io priority changing. If we move the
priority changing to not browsing the rbtree, we can remove any locking
from the rbtree updates and lookup completely. Let the sys_ioprio syscall
just mark processes as having the iopriority changed and lazily update
the private cfq io contexts the next time io is queued, and we can
remove this locking as well.
[PATCH] cfq-iosched: cleanups, fixes, dead code removal
A collection of little fixes and cleanups:
- We don't use the 'queued' sysfs exported attribute, since the
may_queue() logic was rewritten. So kill it.
- Remove dead defines.
- cfq_set_active_queue() can be rewritten cleaner with else if conditions.
- Several places had cfq_exit_cfqq() like logic, abstract that out and
use that.
- Annotate the cfqq kmem_cache_alloc() so the allocator knows that this
is a repeat allocation if it fails with __GFP_WAIT set. Allows the
allocator to start freeing some memory, if needed. CFQ already loops for
this condition, so might as well pass the hint down.
- Remove cfqd->rq_starved logic. It's not needed anymore after we dropped
the crq allocation in cfq_set_request().
After Christophs SCSI change, the only usage left is RQ_ACTIVE
and RQ_INACTIVE. The block layer sets RQ_INACTIVE right before freeing
the request, so any check for RQ_INACTIVE in a driver is a bug and
indicates use-after-free.
So kill/clean the remaining users, straight forward.
Jens Axboe [Thu, 10 Aug 2006 06:59:11 +0000 (08:59 +0200)]
[PATCH] Remove struct request_list from struct request
It is always identical to &q->rq, and we only use it for detecting
whether this request came out of our mempool or not. So replace it
with an additional ->flags bit flag.
[PATCH] Remove ->waiting member from struct request
As the comments indicates in blkdev.h, we can fold it into ->end_io_data
usage as that is really what ->waiting is. Fixup the users of
blk_end_sync_rq().
projects / linux-2.6 / log