19 Feb, 2008
10 commits
-
Clear drain buffer before chaining if the command in question is a
write.Signed-off-by: Tejun Heo
Signed-off-by: Jens Axboe -
Draining shouldn't be done for commands where overflow may indicate
data integrity issues. Add dma_drain_needed callback to
request_queue. Drain buffer is appened iff this function returns
non-zero.Signed-off-by: Tejun Heo
Cc: James Bottomley
Signed-off-by: Jens Axboe -
With padding and draining moved into it, block layer now may extend
requests as directed by queue parameters, so now a request has two
sizes - the original request size and the extended size which matches
the size of area pointed to by bios and later by sgs. The latter size
is what lower layers are primarily interested in when allocating,
filling up DMA tables and setting up the controller.Both padding and draining extend the data area to accomodate
controller characteristics. As any controller which speaks SCSI can
handle underflows, feeding larger data area is safe.So, this patch makes the primary data length field, request->data_len,
indicate the size of full data area and add a separate length field,
request->raw_data_len, for the unmodified request size. The latter is
used to report to higher layer (userland) and where the original
request size should be fed to the controller or device.Signed-off-by: Tejun Heo
Cc: James Bottomley
Signed-off-by: Jens Axboe -
DMA start address and transfer size alignment for PC requests are
achieved using bio_copy_user() instead of bio_map_user(). This works
because bio_copy_user() always uses full pages and block DMA alignment
isn't allowed to go over PAGE_SIZE.However, the implementation didn't update the last bio of the request
to make this padding visible to lower layers. This patch makes
blk_rq_map_user() extend the last bio such that it includes the
padding area and the size of area pointed to by the request is
properly aligned.Signed-off-by: Tejun Heo
Cc: James Bottomley
Signed-off-by: Jens Axboe -
Currently we fail if someone requests a valid io scheduler, but it's
modular and not currently loaded. That can happen from a driver init
asking for a different scheduler, or online switching through sysfs
as requested by a user.This patch makes elevator_get() request_module() to attempt to load
the appropriate module, instead of requiring that done manually.Signed-off-by: Jens Axboe
-
It's cumbersome to browse a radix tree from start to finish, especially
since we modify keys when a process exits. So add a hlist for the single
purpose of browsing over all known cfq_io_contexts, used for exit,
io prio change, etc.This fixes http://bugzilla.kernel.org/show_bug.cgi?id=9948
Signed-off-by: Jens Axboe
-
That way the interface is symmetric, and calling blk_rq_unmap_user()
on the request wont oops.Signed-off-by: Jens Axboe
-
blk_settings_init() can become static.
Signed-off-by: Adrian Bunk
Signed-off-by: Jens Axboe -
blk_ioc_init() can become static.
Signed-off-by: Adrian Bunk
Signed-off-by: Jens Axboe -
request_cachep needlessly became global.
Signed-off-by: Adrian Bunk
Signed-off-by: Jens Axboe
08 Feb, 2008
4 commits
-
Removes the now unused old partition statistic code.
Signed-off-by: Jerome Marchand
Signed-off-by: Jens Axboe -
Reports enhanced partition statistics in /proc/diskstats.
Signed-off-by: Jerome Marchand
-
Updates the enhanced partition statistics in generic block layer
besides the disk statistics.Signed-off-by: Jerome Marchand
Signed-off-by: Jens Axboe -
Rearrange fields in cache order and initialize some fields that
we didn't previously init. Remove init of ->completion_data, it's
part of a union with ->hash. Luckily clearing the rb node is the same
as setting it to null!Signed-off-by: Jens Axboe
01 Feb, 2008
6 commits
-
It blindly copies everything in the io_context, including the lock.
That doesn't work so well for either lock ordering or lockdep.There seems zero point in swapping io contexts on a request to request
merge, so the best point of action is to just remove it.Signed-off-by: Jens Axboe
-
Since it's acquired from irq context, all locking must be of the
irq safe variant. Most are already inside the queue lock (which
already disables interrupts), but the io scheduler rmmod path
always has irqs enabled and the put_io_context() path may legally
be called with irqs enabled (even if it isn't usually). So fixup
those two.Signed-off-by: Jens Axboe
-
Signed-off-by: Jens Axboe
-
Signed-off-by: Jens Axboe
-
Signed-off-by: Jens Axboe
-
No point in passing signed integers as the byte count, they can never
be negative.Signed-off-by: Jens Axboe
31 Jan, 2008
1 commit
-
This fixes a problem in SCSI where we use the (previously
uninitialised) cmd_type via blk_pc_request() to set up the transfer in
scsi_init_sgtable().Acked-by: FUJITA Tomonori
Signed-off-by: James Bottomley
30 Jan, 2008
9 commits
-
If the two requests belong to the same io context, we will attempt
to lock the same lock twice. But swapping contexts is pointless in
that case, so just check for rioc == nioc before doing the double
lock and copy.Tested-by: Olof Johansson
Signed-off-by: Jens Axboe -
Signed-off-by: Jan Engelhardt
Signed-off-by: Jens Axboe -
Expose hardware sector size in sysfs queue directory.
Signed-off-by: Martin K. Petersen
Signed-off-by: Jens Axboe -
Signed-off-by: Jens Axboe
-
Signed-off-by: Jens Axboe
-
Signed-off-by: Jens Axboe
-
Adds files for barrier handling, rq execution, io context handling,
mapping data to requests, and queue settings.Signed-off-by: Jens Axboe
-
Seperates the tag and sysfs handling from ll_rw_blk.
Signed-off-by: Jens Axboe
-
Then we retain history in blk-core.c
Signed-off-by: Jens Axboe
29 Jan, 2008
2 commits
-
* 'for-2.6.25' of git://git.kernel.dk/linux-2.6-block:
block: implement drain buffers
__bio_clone: don't calculate hw/phys segment counts
block: allow queue dma_alignment of zero
blktrace: Add blktrace ioctls to SCSI generic devices -
* 'blk-end-request' of git://git.kernel.dk/linux-2.6-block: (30 commits)
blk_end_request: changing xsysace (take 4)
blk_end_request: changing ub (take 4)
blk_end_request: cleanup of request completion (take 4)
blk_end_request: cleanup 'uptodate' related code (take 4)
blk_end_request: remove/unexport end_that_request_* (take 4)
blk_end_request: changing scsi (take 4)
blk_end_request: add bidi completion interface (take 4)
blk_end_request: changing ide-cd (take 4)
blk_end_request: add callback feature (take 4)
blk_end_request: changing ide normal caller (take 4)
blk_end_request: changing cpqarray (take 4)
blk_end_request: changing cciss (take 4)
blk_end_request: changing ide-scsi (take 4)
blk_end_request: changing s390 (take 4)
blk_end_request: changing mmc (take 4)
blk_end_request: changing i2o_block (take 4)
blk_end_request: changing viocd (take 4)
blk_end_request: changing xen-blkfront (take 4)
blk_end_request: changing viodasd (take 4)
blk_end_request: changing sx8 (take 4)
...
28 Jan, 2008
8 commits
-
Use of inlines were a bit over the top, trim them down a bit.
Signed-off-by: Jens Axboe
-
Currently you must be root to set idle io prio class on a process. This
is due to the fact that the idle class is implemented as a true idle
class, meaning that it will not make progress if someone else is
requesting disk access. Unfortunately this means that it opens DOS
opportunities by locking down file system resources, hence it is root
only at the moment.This patch relaxes the idle class a little, by removing the truly idle
part (which entals a grace period with associated timer). The
modifications make the idle class as close to zero impact as can be done
while still guarenteeing progress. This means we can relax the root only
criteria as well.Signed-off-by: Jens Axboe
-
These DMA drain buffer implementations in drivers are pretty horrible
to do in terms of manipulating the scatterlist. Plus they're being
done at least in drivers/ide and drivers/ata, so we now have code
duplication.The one use case for this, as I understand it is AHCI controllers doing
PIO mode to mmc devices but translating this to DMA at the controller
level.So, what about adding a callback to the block layer that permits the
adding of the drain buffer for the problem devices. The idea is that
you'd do this in slave_configure after you find one of these devices.The beauty of doing it in the block layer is that it quietly adds the
drain buffer to the end of the sg list, so it automatically gets mapped
(and unmapped) without anything unusual having to be done to the
scatterlist in driver/scsi or drivers/ata and without any alteration to
the transfer length.Signed-off-by: James Bottomley
Signed-off-by: Jens Axboe -
changes to anticipatory io scheduler for io_context sharing
Signed-off-by: Jens Axboe
-
The io context sharing introduced a per-ioc spinlock, that would protect
the cfq io context lookup. That is a regression from the original, since
we never needed any locking there because the ioc/cic were process private.The cic lookup is changed from an rbtree construct to a radix tree, which
we can then use RCU to make the reader side lockless. That is the performance
critical path, modifying the radix tree is only done on process creation
(when that process first does IO, actually) and on process exit (if that
process has done IO).As it so happens, radix trees are also much faster for this type of
lookup where the key is a pointer. It's a very sparse tree.Signed-off-by: Jens Axboe
-
changes in the cfq for io_context sharing
Signed-off-by: Jens Axboe
-
Detach task state from ioc, instead keep track of how many processes
are accessing the ioc.Signed-off-by: Jens Axboe
-
This is where it belongs and then it doesn't take up space for a
process that doesn't do IO.Signed-off-by: Jens Axboe
