The current medium access timeout counter will be increased for
each command, so if there are enough failed commands we'll hit
the medium access timeout for even a single device failure and
the following kernel message is displayed:

sd H:C:T:L: [sdXY] Medium access timeout failure. Offlining disk!

Fix this by making the timeout per EH run, ie the counter will
only be increased once per device and EH run.

Fixes: 18a4d0a2 ("[SCSI] Handle disk devices which can not process medium access commands")
Cc: Ewan Milne <emilne@redhat.com>
Cc: Lawrence Obermann <loberman@redhat.com>
Cc: Benjamin Block <bblock@linux.vnet.ibm.com>
Cc: Steffen Maier <maier@linux.vnet.ibm.com>
Signed-off-by: NHannes Reinecke <hare@suse.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NMartin K. Petersen <martin.petersen@oracle.com>

Instead define the timeout behavior purely based on the host_template
eh_timed_out method and wire up the existing transport implementations
in the host templates.  This also clears up the confusion that the
transport template method overrides the host template one, so some
drivers have to re-override the transport template one.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Reviewed-by: NTyrel Datwyler <tyreld@linux.vnet.ibm.com>
Signed-off-by: NMartin K. Petersen <martin.petersen@oracle.com>

Instead of keeping two levels of indirection for requests types, fold it
all into the operations.  The little caveat here is that previously
cmd_type only applied to struct request, while the request and bio op
fields were set to plain REQ_OP_READ/WRITE even for passthrough
operations.

Instead this patch adds new REQ_OP_* for SCSI passthrough and driver
private requests, althought it has to add two for each so that we
can communicate the data in/out nature of the request.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@fb.com>

This can be used to check for fs vs non-fs requests and basically
removes all knowledge of BLOCK_PC specific from the block layer,
as well as preparing for removing the cmd_type field in struct request.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@fb.com>

And require all drivers that want to support BLOCK_PC to allocate it
as the first thing of their private data.  To support this the legacy
IDE and BSG code is switched to set cmd_size on their queues to let
the block layer allocate the additional space.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@fb.com>

Rely on the new block layer functionality to allocate additional driver
specific data behind struct request instead of implementing it in SCSI
itѕelf.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Acked-by: NMartin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

A lot of the REQ_* flags are only used on struct requests, and only of
use to the block layer and a few drivers that dig into struct request
internals.

This patch adds a new req_flags_t rq_flags field to struct request for
them, and thus dramatically shrinks the number of common requests.  It
also removes the unfortunate situation where we have to fit the fields
from the same enum into 32 bits for struct bio and 64 bits for
struct request.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NShaun Tancheff <shaun.tancheff@seagate.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

sas_ata_strategy_handler() adds the works of the ata error handler to
system_unbound_wq. This workqueue asynchronously runs work items, so the
ata error handler will be performed concurrently on different CPUs. In
this case, ->host_failed will be decreased simultaneously in
scsi_eh_finish_cmd() on different CPUs, and become abnormal.

It will lead to permanently inequality between ->host_failed and
->host_busy, and scsi error handler thread won't start running. IO
errors after that won't be handled.

Since all scmds must have been handled in the strategy handler, just
remove the decrement in scsi_eh_finish_cmd() and zero ->host_busy after
the strategy handler to fix this race.

Fixes: 50824d6c ("[SCSI] libsas: async ata-eh")
Cc: stable@vger.kernel.org
Signed-off-by: NWei Fang <fangwei1@huawei.com>
Reviewed-by: NJames Bottomley <jejb@linux.vnet.ibm.com>
Signed-off-by: NMartin K. Petersen <martin.petersen@oracle.com>

Whenever a sense code is set it would need to be evaluated to
update the error mask.

tj: Cosmetic formatting updates.
Signed-off-by: NHannes Reinecke <hare@suse.de>
Signed-off-by: NTejun Heo <tj@kernel.org>

__GFP_WAIT was used to signal that the caller was in atomic context and
could not sleep.  Now it is possible to distinguish between true atomic
context and callers that are not willing to sleep.  The latter should
clear __GFP_DIRECT_RECLAIM so kswapd will still wake.  As clearing
__GFP_WAIT behaves differently, there is a risk that people will clear the
wrong flags.  This patch renames __GFP_WAIT to __GFP_RECLAIM to clearly
indicate what it does -- setting it allows all reclaim activity, clearing
them prevents it.

[akpm@linux-foundation.org: fix build]
[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: NMel Gorman <mgorman@techsingularity.net>
Acked-by: NMichal Hocko <mhocko@suse.com>
Acked-by: NVlastimil Babka <vbabka@suse.cz>
Acked-by: NJohannes Weiner <hannes@cmpxchg.org>
Cc: Christoph Lameter <cl@linux.com>
Acked-by: NDavid Rientjes <rientjes@google.com>
Cc: Vitaly Wool <vitalywool@gmail.com>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

b9d5c6b7 ("[SCSI] cleanup setting task state in
scsi_error_handler()") has introduced a race between scsi_error_handler
and scsi_host_dev_release resulting in the hang when the device goes
away because scsi_error_handler might miss a wake up:

CPU0					CPU1
scsi_error_handler			scsi_host_dev_release
  					  kthread_stop()
  kthread_should_stop()
    test_bit(KTHREAD_SHOULD_STOP)
					    set_bit(KTHREAD_SHOULD_STOP)
					    wake_up_process()
					    wait_for_completion()

  set_current_state(TASK_INTERRUPTIBLE)
  schedule()

The most straightforward solution seems to be to invert the ordering of
the set_current_state and kthread_should_stop.

The issue has been noticed during reboot test on a 3.0 based kernel but
the current code seems to be affected in the same way.

[jejb: additional comment added]
Cc: <stable@vger.kernel.org> # 3.6+
Reported-and-debugged-by: NMike Mayer <Mike.Meyer@teradata.com>
Signed-off-by: NMichal Hocko <mhocko@suse.com>
Reviewed-by: NDan Williams <dan.j.williams@intel.com>
Reviewed-by: NHannes Reinecke <hare@suse.de>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

Add a ->handler and a ->handler_data field to struct scsi_device and kill
this indirection.  Also move struct scsi_device_handler to scsi_dh.h so that
changes to it don't require rebuilding every SCSI LLDD.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NMartin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: NHannes Reinecke <hare@suse.de>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

scsi_error: should not get sense for timeout IO in scsi error handler

When an IO timeout occurs, the IO will be aborted in
scsi_abort_command() and SCSI_EH_ABORT_SCHEDULED will be set. Because
of that, the SCSI_EH_CANCEL_CMD will be clear in scsi_eh_scmd_add().
So when scsi error handler starts, it will get sense for this
timeout IO and the scmd of the IO request will be reused. In that
case, the scmd may be double released when racing with io_done(),
which will result in crash.
SO SCSI_EH_ABORT_SCHEDULED should also be checked when getting sense.
The bug maybe reproduced when the link between host and disk is
unstable.
Signed-off-by: NJiang Biao <jiang.biao2@zte.com.cn>
Signed-off-by: NLong Chun <long.chun@zte.com.cn>
Reviewed-by: NTan Hu <tan.hu@zte.com.cn>
Reviewed-by: NChen Donghai <chen.donghai@zte.com.cn>
Reviewed-by: NCai Qu <cai.qu@zte.com.cn>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

Log the ALUA state change unit attention correctly with
the message log and emit an event to allow user-space
tools to react to it.
Signed-off-by: NHannes Reinecke <hare@suse.de>
Reviewed-by: NEwan D. Milne <emilne@redhat.com>
Reviewed-by: NBart Van Assche <bart.vanassche@sandisk.com>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

This reverts commit a1524f22.

As implemented, ACS-4 sense reporting for ATA devices bypasses error
diagnosis and handling in libata degrading EH behavior significantly.
Revert the related changes for now.
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Hannes Reinecke <hare@suse.de>
Cc: stable@vger.kernel.org #v4.1+

Fix a memory leak with scsi-mq triggered by commands with large data
transfer length.

__sg_alloc_table() sets both table->nents and table->orig_nents to the
same value.  When the scatterlist is DMA-mapped, table->nents is
overwritten with the (possibly smaller) size of the DMA-mapped
scatterlist, while table->orig_nents retains the original size of the
allocated scatterlist.  scsi_free_sgtable() should therefore check
orig_nents instead of nents, and all code that initializes sdb->table
without calling __sg_alloc_table() should set both nents and orig_nents.

Fixes: d285203c ("scsi: add support for a blk-mq based I/O path.")
Cc: <stable@vger.kernel.org> # 3.17+
Signed-off-by: NTony Battersby <tonyb@cybernetics.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NEwan D. Milne <emilne@redhat.com>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

Sense data handling is also done in the target stack.
Hence, move sense handling routines to scsi_common so
the target will be able to use them as well.
Signed-off-by: NSagi Grimberg <sagig@mellanox.com>
Reviewed-by: NBart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NHannes Reinecke <hare@suse.de>
Reviewed-by: NMartin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

Move the functions that are used by both the initiator and target
subsystems into scsi_common.c/.h. This change will allow to remove
the initiator SCSI header include directives from most SCSI target
source files in a later patch.
Signed-off-by: NBart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: NHannes Reinecke <hare@suse.de>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

If NCQ autosense or the sense data reporting feature is enabled
the LBA of the offending command should be stored in the sense
data 'information' field.
Signed-off-by: NHannes Reinecke <hare@suse.de>
Signed-off-by: NTejun Heo <tj@kernel.org>

It is not good practice to display the kernel pointer in any message logs,
and it doesn't display any additional information. And as we know have
block-layer assigned tags we can use them to differentiate the messages.
So remove any pointer references from the displayed messages.
Signed-off-by: NHannes Reinecke <hare@suse.de>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

Fix kernel-doc warning in scsi_error.c:

Warning(..//drivers/scsi/scsi_error.c:887): No description found for parameter 'hostt'

Fixes: 883a030f
	(scsi: document scsi_try_to_abort_cmd)
Signed-off-by: NRandy Dunlap <rdunlap@infradead.org>
Reviewed-by: NHannes Reinecke <hare@suse.de>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

Commit ac61d195 (scsi: set correct completion code in
scsi_send_eh_cmnd()) introduced a bug.  It changed the stored return
value from a queuecommand call, but it didn't take into account that
the return value was used again later on.  This patch fixes the bug by
changing the later usage.

There is a big comment in the middle of scsi_send_eh_cmnd() which
does a good job of explaining how the routine works.  But it mentions
a "rtn = FAILURE" value that doesn't exist in the code.  This patch
adjusts the code to match the comment (I assume the comment is right
and the code is wrong).

This fixes Bugzilla #88341.
Signed-off-by: NAlan Stern <stern@rowland.harvard.edu>
Reported-by: NАндрей Аладьев <aladjev.andrew@gmail.com>
Tested-by: NАндрей Аладьев <aladjev.andrew@gmail.com>
Fixes: ac61d195Acked-by: NHannes Reinecke <hare@suse.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: NJames Bottomley <JBottomley@Parallels.com>

scsi_reset_provider already manually runs all queues for the given host,
so it doesn't need the scsi_run_queues call from it, and it doesn't need
a reference on the device because it's synchronous.

So let's just call scsi_put_command directly and avoid the device reference
dance to simplify the code.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NBart Van Assche <bvanassche@acm.org>
Reviewed-by: NHannes Reinecke <hare@suse.de>

Drop the now unused reason argument from the ->change_queue_depth method.
Also add a return value to scsi_adjust_queue_depth, and rename it to
scsi_change_queue_depth now that it can be used as the default
->change_queue_depth implementation.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NMike Christie <michaelc@cs.wisc.edu>
Reviewed-by: NHannes Reinecke <hare@suse.de>

All drivers use the implementation for ramping the queue up and down, so
instead of overloading the change_queue_depth method call the
implementation diretly if the driver opts into it by setting the
track_queue_depth flag in the host template.

Note that a few drivers validated the new queue depth in their
change_queue_depth method, but as we never go over the queue depth
set during slave_configure or the sysfs file this isn't nessecary
and can safely be removed.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NMike Christie <michaelc@cs.wisc.edu>
Reviewed-by: NHannes Reinecke <hare@suse.de>
Reviewed-by: NVenkatesh Srinivas <venkateshs@google.com>

Pull the common code from the two callers into the function,
and rename it to scsi_ioctl_reset.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NMartin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: NHannes Reinecke <hare@suse.de>

scsi_try_to_abort_cmd() should only return SUCCESS, FAILED, or
FAST_IO_FAIL. So document that in the function description and simplify
the logging message.
Signed-off-by: NHannes Reinecke <hare@suse.de>
Suggested-by: NChristoph Hellwig <hch@infradead.org>
Reviewed-by: NRobert Elliott <elliott@hp.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

The EH statistics are per host, so we should be using
shost_printk() here.
Signed-off-by: NHannes Reinecke <hare@suse.de>
Suggested-by: NRobert Elliott <elliott@hp.com>
Reviewed-by: NRobert Elliott <elliott@hp.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

Use the matching scope for logging messages to allow for
better command tracing.
Signed-off-by: NHannes Reinecke <hare@suse.de>
Suggested-by: NRobert Elliott <elliott@hp.com>
Reviewed-by: NRobert Elliott <elliott@hp.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

Convert scsi_normalize_sense() and friends to return 'bool'
instead of an integer.
Signed-off-by: NHannes Reinecke <hare@suse.de>
Reviewed-by: NRobert Elliott <elliott@hp.com>
Reviewed-by: NYoshihiro Yunomae <yoshihiro.yunomae.ez@hitachi.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

We should be using the standard dev_printk() variants for
sense code printing.

[hch: remove __scsi_print_sense call in xen-scsiback, Acked by Juergen]
[hch: folded bracing fix from Dan Carpenter]
Signed-off-by: NHannes Reinecke <hare@suse.de>
Reviewed-by: NRobert Elliott <elliott@hp.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

Further to a January 2013 thread titled: "[PATCH] SG_SCSI_RESET ioctl
should only perform requested operation" by Jeremy Linton a patch (v3)
is presented that expands the existing ioctl to include "no_escalate"
versions to the existing resets. This requires no changes to SCSI low
level drivers (LLDs); it adds several more finely tuned reset options
to the user space. For example:

   /* This call remains the same, with the same escalating semantics
    * if the device (LU) reset fail. That is: on failure to try a
    * target reset and if that fails, try a bus reset, and if that fails
    * try a host (i.e. LLD) reset. */
   val = SG_SCSI_RESET_DEVICE;
   res = ioctl(<sg_or_block_fd>, SG_SCSI_RESET, &val);

   /* What follows is a new option introduced by this patch series. Only
    * a device reset is attempted. If that fails then an appropriate
    * error code is provided. N.B. There is no reset escalation. */
   val = SG_SCSI_RESET_DEVICE | SG_SCSI_RESET_NO_ESCALATE;
   res = ioctl(<sg_or_block_fd>, SG_SCSI_RESET, &val);
Signed-off-by: NDouglas Gilbert <dgilbert@interlog.com>
Reviewed-by: NJeremy Linton <jlinton@tributary.com>
Reviewed-by: NHannes Reinecke <hare@suse.de>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

Multipath devices using the TUR path checker need to see the sense
code for a failed TUR command in their device handler.  Since commit
14216561 we always return success for mid
layer issued TUR commands before calling the device handler, which
stopped the TUR path checker from working.

Move the call to the device handler check sense method before the early
return for TUR commands to give the device handler a chance to intercept
them.
Signed-off-by: NChristoph Hellwig <hch@infradead.org>
Tested-by: NWen Xiong <wenxiong@linux.vnet.ibm.com>
Reviewed-by: NHannes Reinecke <hare@suse.de>

Setups that use the blk-mq I/O path can lock up if a host with a single
device that has its door locked enters EH.  Make sure to only send the
command to re-lock the door to devices that actually were reset and thus
might have lost their state.  Otherwise the EH code might be get blocked
on blk_get_request as all requests for non-reset devices might be in use.

Cc: stable@vger.kernel.org
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reported-by: NMeelis Roos <meelis.roos@ut.ee>
Tested-by: NMeelis Roos <meelis.roos@ut.ee>
Reviewed-by: NMartin K. Petersen <martin.petersen@oracle.com>

Convert spaces to tabs in kernel-doc notation.
Correct duplicated (copy-paste) kernel-doc comments that are incorrect.
Fix kernel-doc warning:

Warning(..//drivers/scsi/scsi_error.c:1647): No description found for parameter 'shost'
Signed-off-by: NRandy Dunlap <rdunlap@infradead.org>
Reviewed-by: NEwan D. Milne <emilne@redhat.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

The blk_get_request function may fail in low-memory conditions or during
device removal (even if __GFP_WAIT is set). To distinguish between these
errors, modify the blk_get_request call stack to return the appropriate
ERR_PTR. Verify that all callers check the return status and consider
IS_ERR instead of a simple NULL pointer check.

For consistency, make a similar change to the blk_mq_alloc_request leg
of blk_get_request.  It may fail if the queue is dead, or the caller was
unwilling to wait.
Signed-off-by: NJoe Lawrence <joe.lawrence@stratus.com>
Acked-by: Jiri Kosina <jkosina@suse.cz> [for pktdvd]
Acked-by: Boaz Harrosh <bharrosh@panasas.com> [for osd]
Reviewed-by: NJeff Moyer <jmoyer@redhat.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

The blk-core dead queue checks introduce an error scenario to
blk_get_request that returns NULL if the request queue has been
shutdown. This affects the behavior for __GFP_WAIT callers, who should
verify the return value before dereferencing.
Signed-off-by: NJoe Lawrence <joe.lawrence@stratus.com>
Acked-by: Jiri Kosina <jkosina@suse.cz> [for pktdvd]
Reviewed-by: NJeff Moyer <jmoyer@redhat.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

Avoid taking the host-wide host_lock to check the per-host queue limit.
Instead we do an atomic_inc_return early on to grab our slot in the queue,
and if necessary decrement it after finishing all checks.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NMartin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: NHannes Reinecke <hare@suse.de>
Reviewed-by: NWebb Scales <webbnh@hp.com>
Acked-by: NJens Axboe <axboe@kernel.dk>
Tested-by: NBart Van Assche <bvanassche@acm.org>
Tested-by: NRobert Elliott <elliott@hp.com>

Using dev_printk variants prefixes the logging message with
the originating device, which makes debugging easier.
Signed-off-by: NHannes Reinecke <hare@suse.de>
Reviewed-by: NMartin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

scsi_put_command() is either invoked before blk_start_request() or
after block layer processing has completed.  scsi_cmnd.abort_work
is scheduled from inside the SCSI timeout handler.  The block layer
guarantees that either the regular completion handler
(softirq_done_fn()) or the timeout handler (rq_timed_out_fn()) is
invoked but not both. This means that scsi_put_command() is never
invoked while abort_work is scheduled.  Hence remove the
cancel_delayed_work() call from scsi_put_command().

Similarly, scsi_abort_command() is only invoked from the SCSI
timeout handler. If scsi_abort_command() is invoked for a SCSI
command with the SCSI_EH_ABORT_SCHEDULED flag set this means that
scmd_eh_abort_handler() has already invoked scsi_queue_insert() and
hence that scsi_cmnd.abort_work is no longer pending. Hence also
remove the cancel_delayed_work() call from scsi_abort_command().
Signed-off-by: NBart Van Assche <bvanassche@acm.org>
Reviewed-by: NHannes Reinecke <hare@suse.de>
Signed-off-by: NChristoph Hellwig <hch@lst.de>