When porting blktrace to tracepoints, we changed to trace/block.h
for trace prober declarations.
Signed-off-by: NLi Zefan <lizf@cn.fujitsu.com>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

eec94620 fold mg_disk.h into mg_disk.c,
but mg_disk platform driver needs private data for operation. This also
make mg_disk.c as machine independent. Seperate only needed structure and
defines to mg_disk.h
Signed-off-by: Nunsik Kim <donari75@gmail.com>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

.ko is normally not included in Kconfig help, make it consistent.
Signed-off-by: NPavel Machek <pavel@ucw.cz>
Signed-off-by: NJiri Kosina <jkosina@suse.cz>

The remove member of the virtio_driver structure uses __devexit_p(), so
the remove function itself should be marked with __devexit.  And where
there be __devexit on the remove, so is there __devinit on the probe.
Signed-off-by: NMike Frysinger <vapier@gentoo.org>
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>

This replaces find_vq/del_vq with find_vqs/del_vqs virtio operations,
and updates all drivers. This is needed for MSI support, because MSI
needs to know the total number of vectors upfront.
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> (+ lguest/9p compile fixes)

Add a linked list of all virtqueues for a virtio device: this helps for
debugging and is also needed for upcoming interface change.

Also, add a "name" field for clearer debug messages.
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>

Based on Ingo Molnar's patch from 2006, this makes the floppy work after
resume from hibernation, at least on my machine.

This fix resets the floppy controller on resume.  It was experimentally
determined to bring the controller back to life - we don't really know why
it works.

floppy_init() does the same thing at boot/modprobe time.
Signed-off-by: NOndrej Zary <linux@rainbow-software.org>
Cc: "Rafael J. Wysocki" <rjw@sisk.pl>
Cc: Ingo Molnar <mingo@elte.hu>
Acked-by: NPavel Machek <pavel@ucw.cz>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

The "ramdisk" parameter was removed from the defunct rd.c file quite some
time ago, in favour of the more specific "ramdisk_size" parameter so, for
consistency, the same should be done here.
Signed-off-by: NRobert P. J. Day <rpjday@crashcourse.ca>
Acked-by: NNick Piggin <nickpiggin@yahoo.com.au>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

This patch extracts the opaque data from pci i/o
region 0 via the added VIRTIO_BLK_F_IDENTIFY
field.  By convention this data takes the form of
that returned by an ATA IDENTIFY DEVICE command,
however the driver (except for structure size)
makes no interpretation of the data.  The structure
data is copied wholesale to userspace via a
HDIO_GET_IDENTITY ioctl command (eg: hdparm -i <dev>).
Signed-off-by: Njohn cooper <john.cooper@redhat.com>
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Make SCSI reset error handler decode unit attention ASC
and after a target reset wait for a unit attention that indicates
a reset occurred rather than just for any old unit attention.
Signed-off-by: NStephen M. Cameron <scameron@beardog.cca.cpqcorp.net>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Now that the cciss SCSI error handling routines operate with interrupts
enabled, we no longer need to maintain the list of command completions that
sendcmd() might inadvertantly scoop up, since now it only runs at driver init
time, and there won't be any other commands for it to scoop up.  So we
can remove that list and the code that adds to it and processes it.
Signed-off-by: NStephen M. Cameron <scameron@beardog.cca.cpqcorp.net>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Change cciss scsi error handling routines to work with interrupts enabled.
Signed-off-by: NStephen M. Cameron <scameron@beardog.cca.cpqcorp.net>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Separate the error processing from sendcmd_withirq_core from the code
which retries commands.  The rationale for this is that the SCSI error
handling code can then be made to use sendcmd_withirq_core, but avoid
retrying commands.
Signed-off-by: NStephen M. Cameron <scameron@beardog.cca.cpqcorp.net>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Factor out code to process target status of completed commands in sendcmd()
and sendcmd_withirq_core(), and fix problem that bad target status was ignored in
sendcmd_withirq_core.
Signed-off-by: NStephen M. Cameron <scameron@beardog.cca.cpqcorp.net>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Simplify interfaces of sendcmd() and sendcmd_withirq() so that they
provide only one way to address commands instead of three ways.
Signed-off-by: NStephen M. Cameron <scameron@beardog.cca.cpqcorp.net>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Factor the core of sendcmd_withirq out to provide a simpler interface
which provides access to full error information.
Signed-off-by: NStephen M. Cameron <scameron@beardog.cca.cpqcorp.net>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Use schedule_timeout_uninterruptible instead of schedule_timeout in the
scsi error handling code when waiting between TUR polls since we are not
interested in nor want to be interrupted by signals.
Signed-off-by: NStephen M. Cameron <scameron@beardog.cca.cpqcorp.net>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Use schedule_timeout_interruptible() instead of open-coding the set and
schedule parts.

Cc: Mike Miller <mikem@beardog.cca.cpqcorp.net>
Cc: Stephen M. Cameron <scameron@beardog.cca.cpqcorp.net>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Add sysfs entries to the cciss driver needed for the dm/multipath tools.

A file for vendor, model, rev, and unique_id is added for each logical
drive under directory /sys/bus/pci/devices/<dev>/ccissX/cXdY.  Where X =
the controller (or host) number and Y is the logical drive number.

A link from /sys/bus/pci/devices/<dev>/ccissX/cXdY/block:cciss!cXdY to
/sys/block/cciss!cXdY/device is also created.  A bus is created in
/sys/bus/cciss.  A link is created from the pci ccissX entry to
/sys/bus/cciss/devices/ccissX.  Please consider this for inclusion.
Signed-off-by: NMike Miller <mike.miller@hp.com>
Cc: Stephen M. Cameron <scameron@beardog.cca.cpqcorp.net>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Fix the SCSI reset error handler to send a working, properly addressed
reset message to the target device and add code to wait for the target
device to become ready by polling it with Test Unit Ready.

The existing reset code was broken in that it didn't bother to set the
8-byte LUN address to anything besides zero, so the command was addressed
to the controller, which pretended to the driver that the command
succeeded, while doing nothing.  Ages ago I tested this code, but
unbeknownst to me, my test was flawed, and what I thought was a tape drive
getting reset was actually nothing of the sort.  Unfortunately, there is
still lots of Smartarray firmware that doesn't handle doing target resets
right, and this code won't help in those cases, but it also shouldn't make
things worse in those cases than they already are.
Signed-off-by: NStephen M. Cameron <scameron@beardog.cca.cpqcorp.net>
Cc: Mike Miller <mikem@beardog.cca.cpqcorp.net>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Factor out the core of sendcmd() to provide a simpler interface which
exposes all the error information to the caller and make the original
sendcmd use this new function.  Rationale: The SCSI error handling
routines need to send commands with interrupts turned off, but they also
need access to the full error information.
Signed-off-by: NStephen M. Cameron <scameron@beardog.cca.cpqcorp.net>
Cc: Mike Miller <mikem@beardog.cca.cpqcorp.net>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

This code uses alloc_skb() which clears them out for us.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Convert all external users of queue limits to using wrapper functions
instead of poking the request queue variables directly.
Signed-off-by: NMartin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Until now we have had a 1:1 mapping between storage device physical
block size and the logical block sized used when addressing the device.
With SATA 4KB drives coming out that will no longer be the case.  The
sector size will be 4KB but the logical block size will remain
512-bytes.  Hence we need to distinguish between the physical block size
and the logical ditto.

This patch renames hardsect_size to logical_block_size.
Signed-off-by: NMartin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Do not go beyond ARRAY_SIZE of info->shadow
Signed-off-by: NRoel Kluin <roel.kluin@gmail.com>
Acked-by: NJeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Signed-off-by: NMichal Simek <monstr@monstr.eu>

In commit c3a4d78c, while introducing
rq->resid_len, the default value of residue count was changed from
full count to zero.  The conversion was done under the assumption that
when a request fails residue count wasn't defined.  However, Boaz and
James pointed out that this wasn't true and the residue count should
be preserved for failed requests too.

This patchset restores the original behavior by setting rq->resid_len
to blk_rq_bytes(rq) on request start and restoring explicit clearing
in affected drivers.  While at it, take advantage of the fact that
rq->resid_len is set to full count where applicable.

* ide-cd: rq->resid_len cleared on pc success

* mptsas: req->resid_len cleared on success

* sas_expander: rsp/req->resid_len cleared on success

* mpt2sas_transport: req->resid_len cleared on success

* ide-cd, ide-tape, mptsas, sas_host_smp, mpt2sas_transport, ub: take
  advantage of initial full count to simplify code

Boaz Harrosh spotted bug in resid_len initialization.  Fixed as
suggested.
Signed-off-by: NTejun Heo <tj@kernel.org>
Acked-by: NBorislav Petkov <petkovbb@googlemail.com>
Cc: Boaz Harrosh <bharrosh@panasas.com>
Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
Cc: Pete Zaitcev <zaitcev@redhat.com>
Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Cc: Eric Moore <Eric.Moore@lsi.com>
Cc: Darrick J. Wong <djwong@us.ibm.com>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

ub_end_rq() always tries to complete full request.  The @cmd_len
parameter was there because rq->data_len used to be overwritten with
residue count.  Drop @cmd_len and use __blk_end_request_all().
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Pete Zaitcev <zaitcev@redhat.com>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Currently blkfront gives a warning when hot unplugging due to calling
del_gendisk() with interrupts disabled (due to blkif_io_lock).

WARNING: at kernel/softirq.c:124 local_bh_enable+0x36/0x84()
Modules linked in: xenfs xen_netfront ext3 jbd mbcache xen_blkfront
Pid: 13, comm: xenwatch Not tainted 2.6.29-xs5.5.0.13 #3
Call Trace:
 [<c012611c>] warn_slowpath+0x80/0xb6
 [<c0104cf1>] xen_sched_clock+0x16/0x63
 [<c0104710>] xen_force_evtchn_callback+0xc/0x10
 [<c0104e32>] check_events+0x8/0xe
 [<c0104d9b>] xen_restore_fl_direct_end+0x0/0x1
 [<c0103749>] xen_mc_flush+0x10a/0x13f
 [<c0105bd2>] __switch_to+0x114/0x14e
 [<c011d92b>] dequeue_task+0x62/0x70
 [<c0123b6f>] finish_task_switch+0x2b/0x84
 [<c0299877>] schedule+0x66d/0x6e7
 [<c0104710>] xen_force_evtchn_callback+0xc/0x10
 [<c0104710>] xen_force_evtchn_callback+0xc/0x10
 [<c012a642>] local_bh_enable+0x36/0x84
 [<c022f9a7>] sk_filter+0x57/0x5c
 [<c0233dae>] netlink_broadcast+0x1d5/0x315
 [<c01c6371>] kobject_uevent_env+0x28d/0x331
 [<c01e7ead>] device_del+0x10f/0x120
 [<c01e7ec6>] device_unregister+0x8/0x10
 [<c015f86d>] bdi_unregister+0x2d/0x39
 [<c01bf6f4>] unlink_gendisk+0x23/0x3e
 [<c01ac946>] del_gendisk+0x7b/0xe7
 [<d0828c19>] blkfront_closing+0x28/0x6e [xen_blkfront]
 [<d082900c>] backend_changed+0x3ad/0x41d [xen_blkfront]

We can fix this by calling del_gendisk() later in blkfront_closing, after
releasing blkif_io_lock. Since the queue is stopped during the interrupts
disabled phase I don't think there is any danger of an event occuring between
releasing the blkif_io_lock and deleting the disk.
Signed-off-by: NIan Campbell <ian.campbell@citrix.com>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

This situation can occur when attempting to attach a block device whose
backend is an empty physical CD-ROM driver. The backend in this case
will go directly from the Initialising state to Closing->Closed.
Previously this would result in a NULL pointer deref on info->gd
(xenbus_dev_fatal does not return as a1a15ac5 seems to expect)

Cc: stable@kernel.org
Signed-off-by: NIan Campbell <ian.campbell@citrix.com>
Acked-by: NJeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

drivers/block/virtio_blk.c: In function 'blk_done':
drivers/block/virtio_blk.c:53: warning: unused variable 'nr_bytes'

Leftover from commit 1cde26f9Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Add support for SG_IO passthru to virtio_blk.  We add the scsi command
block after the normal outhdr, and the scsi inhdr with full status
information aswell as the sense buffer before the regular inhdr.

[hch: forward ported, added the VIRTIO_BLK_F_SCSI flags, some comments
 and tested the whole beast]
[axboe: updated to use ->resid and not dual-path the byte count]
Signed-off-by: NHannes Reinecke <hare@suse.de>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> (+ checkpatch.pl tweak)
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

request->rq_disk is only set for FS requests or BLOCK_PC requests
originating from the generic block layer scsi ioctls.  It's not set
for requests origination from other soures or internal cache flush
commands implemented by the patch I'll send after this.

So instead of using it to get at the private data in do_virtblk_request
setup queue->queuedata and use it.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

If f_op->splice_read() is not implemented, fall back to a plain read.
Use vfs_readv() to read into previously allocated pages.

This will allow splice and functions using splice, such as the loop
device, to work on all filesystems.  This includes "direct_io" files
in fuse which bypass the page cache.
Signed-off-by: NMiklos Szeredi <mszeredi@suse.cz>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Till now block layer allowed two separate modes of request execution.
A request is always acquired from the request queue via
elv_next_request().  After that, drivers are free to either dequeue it
or process it without dequeueing.  Dequeue allows elv_next_request()
to return the next request so that multiple requests can be in flight.

Executing requests without dequeueing has its merits mostly in
allowing drivers for simpler devices which can't do sg to deal with
segments only without considering request boundary.  However, the
benefit this brings is dubious and declining while the cost of the API
ambiguity is increasing.  Segment based drivers are usually for very
old or limited devices and as converting to dequeueing model isn't
difficult, it doesn't justify the API overhead it puts on block layer
and its more modern users.

Previous patches converted all block low level drivers to dequeueing
model.  This patch completes the API transition by...

* renaming elv_next_request() to blk_peek_request()

* renaming blkdev_dequeue_request() to blk_start_request()

* adding blk_fetch_request() which is combination of peek and start

* disallowing completion of queued (not started) requests

* applying new API to all LLDs

Renamings are for consistency and to break out of tree code so that
it's apparent that out of tree drivers need updating.

[ Impact: block request issue API cleanup, no functional change ]
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
Cc: Mike Miller <mike.miller@hp.com>
Cc: unsik Kim <donari75@gmail.com>
Cc: Paul Clements <paul.clements@steeleye.com>
Cc: Tim Waugh <tim@cyberelk.net>
Cc: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Laurent Vivier <Laurent@lvivier.info>
Cc: Jeff Garzik <jgarzik@pobox.com>
Cc: Jeremy Fitzhardinge <jeremy@xensource.com>
Cc: Grant Likely <grant.likely@secretlab.ca>
Cc: Adrian McMenamin <adrian@mcmen.demon.co.uk>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
Cc: Borislav Petkov <petkovbb@googlemail.com>
Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Cc: Alex Dubov <oakad@yahoo.com>
Cc: Pierre Ossman <drzeus@drzeus.cx>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Markus Lidel <Markus.Lidel@shadowconnect.com>
Cc: Stefan Weinhuber <wein@de.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Pete Zaitcev <zaitcev@redhat.com>
Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

plat-omap/mailbox, floppy, viocd, mspro_block, i2o_block and
mmc/card/queue are already pretty close to dequeueing model and can be
converted with simple changes.  Convert them.

While at it,

* xen-blkfront: !fs check moved downwards to share dequeue call with
  normal path.

* mspro_block: __blk_end_request(..., blk_rq_cur_byte()) converted to
  __blk_end_request_cur()

* mmc/card/queue: loop of __blk_end_request() converted to
  __blk_end_request_all()

[ Impact: dequeue in-flight request ]
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Jeremy Fitzhardinge <jeremy@xensource.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Alex Dubov <oakad@yahoo.com>
Cc: Markus Lidel <Markus.Lidel@shadowconnect.com>
Cc: Pierre Ossman <drzeus@drzeus.cx>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

z2ram processes requests one-by-one synchronously and can be easily
converted to dequeueing model.  Convert it.

[ Impact: dequeue in-flight request ]
Signed-off-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

xd processes requests one-by-one synchronously and can be easily
converted to dequeueing model.  Convert it.

While at it, use rq_cur_bytes instead of rq_bytes when checking for
sector overflow.  This is for for consistency and better behavior for
merged requests.

[ Impact: dequeue in-flight request ]
Signed-off-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

swim processes requests one-by-one synchronously and can easily be
converted to dequeuing model.  Convert it.

[ Impact: dequeue in-flight request ]
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Laurent Vivier <Laurent@lvivier.info>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Request processing in amiflop is done sequentially in
redo_fd_request() proper and redo_fd_request() can easily be converted
to track in-flight request.  Remove CURRENT, track in-flight request
directly and dequeue it when processing starts.

[ Impact: dequeue in-flight request ]
Signed-off-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>