the current implementation does the following to 'give up' the CPU:

   - it decreases its priority by 1 until it reaches the lowest level
   - it queues the task to the end of the priority queue

  this scheme works fine in most cases, but if sched_yield()-active tasks
  are mixed with CPU-using processes then it's quite likely that the
  CPU-using process is in the expired array. In that case the yield()-ing
  process only requeues itself in the active array - a true context-switch
  to the expired process will only occur once the timeslice of the
  yield()-ing process has expired: in ~150 msecs. This leads to the
  yield()-ing and CPU-using process to use up rougly the same amount of
  CPU-time, which is arguably deficient.

  i've fixed this problem by extending sched_yield() the following way:

  +        * There are three levels of how a yielding task will give up
  +        * the current CPU:
  +        *
  +        *  #1 - it decreases its priority by one. This priority loss is
  +        *       temporary, it's recovered once the current timeslice
  +        *       expires.
  +        *
  +        *  #2 - once it has reached the lowest priority level,
  +        *       it will give up timeslices one by one. (We do not
  +        *       want to give them up all at once, it's gradual,
  +        *       to protect the casual yield()er.)
  +        *
  +        *  #3 - once all timeslices are gone we put the process into
  +        *       the expired array.
  +        *
  +        *  (special rule: RT tasks do not lose any priority, they just
  +        *  roundrobin on their current priority level.)
  +        */

This was done by inspection, is it OK Anton?  It's very simple:

into home.transmeta.com:/home/torvalds/v2.5/linux

This patch removes the concept of "logical" CPU numbers, in
preparation for CPU hotplugging.

Summary: 2.5.17 broke initrd on x86. Fix below.

Why: Kai's patch in 2.5.17 to move x86-specific options from
Makefile to arch/i386/boot/Makefile unfortunately lost the fact
that the orginal "#export RAMDISK = -DRAMDISK=512" statement
was commented out. (I suspect a typo.) RAMDISK is obsolete since
1.3.something, and uncommenting it has "interesting" effects
since the ram_size field has a very different meaning now.

The patch below reverts the statement to its pre-2.5.17 state.
Perhaps it should be removed altogether?

into home.transmeta.com:/home/torvalds/v2.5/linux

This patch splits fput into fput and __fput.  __fput is needed by aio to
construct a mechanism for performing a deferred fput during io
completion, which typically occurs during interrupt context.

This adds support for wait queue function callbacks, which are used by
aio to build async read / write operations on top of existing wait
queues at points that would normally block a process.

This patch switches SCSI from a bottom half to a tasklet.  It's been
reviewed, tested & approved by Andrew Morton, James Bottomley & Doug
Gilbert.

I took a quick look at why 2.5.21 hung at boot detecting partitions,
because a 2.5.22 did the exact same thing on my test box today... The
tcq locking is completely screwed now, and as I said before the weekend
I think the entire locking is just getting worse now.

Anyways, this patch at least attempts to make tcq follow the channel
lock usage to make it work for me.

Attached patch brings over the sane bits from 2.4-ac: i.e. if Linus
merges this and Alan merges your patch minus my complaints, the two
trees will be in sync...

 - Finally unify task_in_intr and task_mulin_intr. One crucial code path less to
   watch out, but a quite dangerous step in itself. PIO reading is functional
   again. The next step will be the unification of the write path of course.

 - Introduce a small helper for the execution of task file commands which
   basically just send a simple command down to the drive.

 - Add a buffer parameter to ide_raw_taskfile allowing to unify the handling of
   ioctl and normal ide_raw_taskfile request.

 - Fix some small function pointer type mismatches.

Apply more host chip controller clenups by Bartlomiej:

     - move setting drive->current_speed from *_tune_chipset()
       to ide_config_drive_speed()

    cmd64x.c:
	- convert cmd64x_tuneproc() to use ata-timing library
	- clean cmd64x_tune_chipset() and cmd680_tune_chipset()

    hpt366.c:
	- remove empty timings table

    it8172.c:
	- kill prototypes
	- update to new udma_setup() scheme

    - misc cleanups

  Set up CardBus cards correctly: initialize them fully
  before calling device_register(), and make sure to tell
  the world that it's a PCI-like bus.

This kills Sysrq-D support (did not work anyway, and complicated
code).

Adds resume support to i8259A (otherwise interrupts will not work
after S3).

HAVE_NEW_DEVICE_MODEL is always true in 2.5, so we should define
it. S3 can't work properly without that. Also limit toshiba workaround
to S1. (This hide lack of i8259A support for me).

Fixes compilation, and kills <asm/suspend.h> being included
twice with ugly hacks around.

- (leak) memory allocated in dscc4_found1() isn't freed by caller in error path.
  dscc4_free1() is now in charge of this duty.
- (style) code factored in dscc4_remove_one after use of dscc4_free1().

- (compilation fix) plain old typo in struct member naming.

- (compilation fix) missing init.h include;
- (compilation fix) multiple pointers can't be set to NULL in one line if their
  type differ.

Courtesy of Kevin Curtis <kevin.curtis@farsite.co.uk>, posted
on l-k the 2002/04/15.

Description
- (compilation fix) removal of deprecated fields in net_device;
- (bug) early pci_enable_device.

Below a patch removing the list of sense codes from usb/storage/debug.h
since the same list is already found in scsi/constants.c.
This also brings this list up to date with SCSI-3.

The patch below cleans up some SCSI stuff.

The main purpose is to avoid trying to read the partition table
of a removable disk when the drive has told us that no media
are present. (Right now we try to read a 4K block and fail and
retry and fail, and give an I/O error on the first sector,
then try to read the second sector and fail and retry ...)

Unused fields  sector_bit_size  and  sector_bit_shift  in
struct scsi_disk were removed. The field  has_part_table
(that has nothing to do with partition tables) was
renamed to  has_been_registered . The field  ready  was
renamed to  media_present .
The overly long  sd_init_onedisk()  was split up.

When we notice that no media are present anymore, the
partitions are removed from /proc/partitions, but the
drive remains, with size 0.

A future patch will remove the field  capacity  - there are
all too many places where capacities are stored - but the
present patch is large enough already.

There is also a quite independent patch in scsi_error.c
(yesterday someone had an infinite loop retrying to read
bad media) - this patch honours the SCpnt->retries.
In case you applied this already, just ignore the scsi_error.c part.

Also some "Overrides for Emacs" were removed.

into home.transmeta.com:/home/torvalds/v2.5/linux

into home.transmeta.com:/home/torvalds/v2.5/linux

into home.transmeta.com:/home/torvalds/v2.5/linux

into home.transmeta.com:/home/torvalds/v2.5/linux

	- remove call to check_region 
	- check the result of request_region
	- call release_region if something goes wrong afterwards during driver initialisation.

I don't have this hardware so I can't verify if it works (compilation checked only).