linux-toradex.git/include/linux, branch v2.6.16

[TG3]: 40-bit DMA workaround part 2

2006-03-19T21:21:12+00:00

The 40-bit DMA workaround recently implemented for 5714, 5715, and
5780 needs to be expanded because there may be other tg3 devices
behind the EPB Express to PCIX bridge in the 5780 class device.

For example, some 4-port card or mother board designs have 5704 behind
the 5714.

All devices behind the EPB require the 40-bit DMA workaround.

Thanks to Chris Elmquist again for reporting the problem and testing
the patch.

Signed-off-by: Michael Chan 
Signed-off-by: David S. Miller

[PATCH] remove __put_task_struct_cb export again

2006-03-11T17:19:34+00:00

The patch '[PATCH] RCU signal handling' [1] added an export for
__put_task_struct_cb, a put_task_struct helper newly introduced in that
patch.  But the put_task_struct couldn't be used modular previously as
__put_task_struct wasn't exported.  There are not callers of it in modular
code, and it shouldn't be exported because we don't want drivers to hold
references to task_structs.

This patch removes the export and folds __put_task_struct into
__put_task_struct_cb as there's no other caller.

[1] http://www2.kernel.org/git/gitweb.cgi?p=linux/kernel/git/torvalds/linux-2.6.git;a=commit;h=e56d090310d7625ecb43a1eeebd479f04affb48b

Signed-off-by: Christoph Hellwig 
Acked-by: Paul E. McKenney 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

[PATCH] ext3: ext3_symlink should use GFP_NOFS allocations inside

2006-03-11T17:19:34+00:00

This patch fixes illegal __GFP_FS allocation inside ext3 transaction in
ext3_symlink().  Such allocation may re-enter ext3 code from
try_to_free_pages.  But JBD/ext3 code keeps a pointer to current journal
handle in task_struct and, hence, is not reentrable.

This bug led to "Assertion failure in journal_dirty_metadata()" messages.

http://bugzilla.openvz.org/show_bug.cgi?id=115

Signed-off-by: Andrey Savochkin 
Signed-off-by: Kirill Korotaev 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

[PATCH] slab: Node rotor for freeing alien caches and remote per cpu pages.

2006-03-10T03:47:38+00:00

The cache reaper currently tries to free all alien caches and all remote
per cpu pages in each pass of cache_reap.  For a machines with large number
of nodes (such as Altix) this may lead to sporadic delays of around ~10ms.
Interrupts are disabled while reclaiming creating unacceptable delays.

This patch changes that behavior by adding a per cpu reap_node variable.
Instead of attempting to free all caches, we free only one alien cache and
the per cpu pages from one remote node.  That reduces the time spend in
cache_reap.  However, doing so will lengthen the time it takes to
completely drain all remote per cpu pagesets and all alien caches.  The
time needed will grow with the number of nodes in the system.  All caches
are drained when they overflow their respective capacity.  So the drawback
here is only that a bit of memory may be wasted for awhile longer.

Details:

1. Rename drain_remote_pages to drain_node_pages to allow the specification
   of the node to drain of pcp pages.

2. Add additional functions init_reap_node, next_reap_node for NUMA
   that manage a per cpu reap_node counter.

3. Add a reap_alien function that reaps only from the current reap_node.

For us this seems to be a critical issue.  Holdoffs of an average of ~7ms
cause some HPC benchmarks to slow down significantly.  F.e.  NAS parallel
slows down dramatically.  NAS parallel has a 12-16 seconds runtime w/o rotor
compared to 5.8 secs with the rotor patches.  It gets down to 5.05 secs with
the additional interrupt holdoff reductions.

Signed-off-by: Christoph Lameter 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

[PATCH] mtd: 64 bit fixes

2006-03-10T03:47:37+00:00

Fix some bugs in mtd/jffs2 on 64bit platform.

The MEMGETBADBLOCK/MEMSETBADBLOCK ioctl are not listed in compat_ioctl.h.

And some variables in jffs2 are declared as uint32_t but used to hold
size_t values.

Signed-off-by: Atsushi Nemoto 
Cc: Thomas Gleixner 
Acked-by: David Woodhouse 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

[PATCH] fix file counting

2006-03-08T22:14:01+00:00

I have benchmarked this on an x86_64 NUMA system and see no significant
performance difference on kernbench.  Tested on both x86_64 and powerpc.

The way we do file struct accounting is not very suitable for batched
freeing.  For scalability reasons, file accounting was
constructor/destructor based.  This meant that nr_files was decremented
only when the object was removed from the slab cache.  This is susceptible
to slab fragmentation.  With RCU based file structure, consequent batched
freeing and a test program like Serge's, we just speed this up and end up
with a very fragmented slab -

llm22:~ # cat /proc/sys/fs/file-nr
587730  0       758844

At the same time, I see only a 2000+ objects in filp cache.  The following
patch I fixes this problem.

This patch changes the file counting by removing the filp_count_lock.
Instead we use a separate percpu counter, nr_files, for now and all
accesses to it are through get_nr_files() api.  In the sysctl handler for
nr_files, we populate files_stat.nr_files before returning to user.

Counting files as an when they are created and destroyed (as opposed to
inside slab) allows us to correctly count open files with RCU.

Signed-off-by: Dipankar Sarma 
Cc: "Paul E. McKenney" 
Cc: "David S. Miller" 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

[PATCH] rcu batch tuning

2006-03-08T22:14:01+00:00

This patch adds new tunables for RCU queue and finished batches.  There are
two types of controls - number of completed RCU updates invoked in a batch
(blimit) and monitoring for high rate of incoming RCUs on a cpu (qhimark,
qlowmark).

By default, the per-cpu batch limit is set to a small value.  If the input
RCU rate exceeds the high watermark, we do two things - force quiescent
state on all cpus and set the batch limit of the CPU to INTMAX.  Setting
batch limit to INTMAX forces all finished RCUs to be processed in one shot.
 If we have more than INTMAX RCUs queued up, then we have bigger problems
anyway.  Once the incoming queued RCUs fall below the low watermark, the
batch limit is set to the default.

Signed-off-by: Dipankar Sarma 
Cc: "Paul E. McKenney" 
Cc: "David S. Miller" 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

[PATCH] percpu_counter_sum()

2006-03-08T22:14:01+00:00

Implement percpu_counter_sum().  This is a more accurate but slower version of
percpu_counter_read_positive().

We need this for Alex's speedup-ext3_statfs patch and for the nr_file
accounting fix.  Otherwise these things would be too inaccurate on large CPU
counts.

Cc: Ravikiran G Thirumalai 
Cc: Alex Tomas 
Cc: "David S. Miller" 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

Mark the pipe file operations static

2006-03-08T22:03:09+00:00

They aren't used (nor even really usable) outside of pipe.c anyway

Signed-off-by: Linus Torvalds

[PATCH] Increase max kmalloc size for very large systems

2006-03-07T02:40:44+00:00

Systems with extemely large numbers of nodes or cpus need to kmalloc
structures larger than is currently supported.  This patch increases the
maximum supported size for very large systems.

This patch should have no effect on current systems.

(akpm: why not just use alloc_pages() for sysfs_cpus?)

Signed-off-by: Jack Steiner 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds