If LLD has added scsi device (by calling scsi_add_device) before scheduling
async scsi_scan_host then scsi_finish_async_scan() will end up calling
scsi_sysfs_add_sdev for scsi device which was already added by LLD.
This patch fixes this issue by skipping the call to scsi_sysfs_add_sdev()
if it's already visible to rest of the kernel.
Signed-off-by: Subhash Jadavani <subhashj@codeaurora.org>
Signed-off-by: Dolev Raviv <draviv@codeaurora.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Some devices may respond with wrong type for well-known logical units.
This patch forces well-known type for devices which doesn't report it
correct.
Signed-off-by: Subhash Jadavani <subhashj@codeaurora.org>
Signed-off-by: Sujit Reddy Thumma <sthumma@codeaurora.org>
Signed-off-by: Dolev Raviv <draviv@codeaurora.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
The SCSI specification requires that the second Command Data Byte
should contain the LUN value in its high-order bits if the recipient
device reports SCSI level 2 or below. Nevertheless, some USB
mass-storage devices use those bits for other purposes in
vendor-specific commands. Currently Linux has no way to send such
commands, because the SCSI stack always overwrites the LUN bits.
Testing shows that Windows 7 and XP do not store the LUN bits in the
CDB when sending commands to a USB device. This doesn't matter if the
device uses the Bulk-Only or UAS transports (which virtually all
modern USB mass-storage devices do), as these have a separate
mechanism for sending the LUN value.
Therefore this patch introduces a flag in the Scsi_Host structure to
inform the SCSI midlayer that a transport does not require the LUN
bits to be stored in the CDB, and it makes usb-storage set this flag
for all devices using the Bulk-Only transport. (UAS is handled by a
separate driver, but it doesn't really matter because no SCSI-2 or
lower device is at all likely to use UAS.)
The patch also cleans up the code responsible for storing the LUN
value by adding a bitflag to the scsi_device structure. The test for
whether to stick the LUN value in the CDB can be made when the device
is probed, and stored for future use rather than being made over and
over in the fast path.
Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Reported-by: Tiziano Bacocco <tiziano.bacocco@gmail.com>
Acked-by: Martin K. Petersen <martin.petersen@oracle.com>
Acked-by: James Bottomley <James.Bottomley@HansenPartnership.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Some devices don't like REPORT SUPPORTED OPERATION CODES and will
simply timeout causing sd_mod init to take a very very long time.
Introduce BLIST_NO_RSOC scsi scan flag, that stops RSOC from being
issued. Add it to Promise Vtrak E610f entry in scsi scan
blacklist. Fixes bug #79901 reported at
https://bugzilla.kernel.org/show_bug.cgi?id=79901
Fixes: 98dcc2946a ("SCSI: sd: Update WRITE SAME heuristics")
Signed-off-by: Janusz Dziemidowicz <rraptorr@nails.eu.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Cc: stable@vger.kernel.org
Signed-off-by: Christoph Hellwig <hch@lst.de>
Despite supporting modern SCSI features some storage devices continue to
claim conformance to an older version of the SPC spec. This is done for
compatibility with legacy operating systems.
Linux by default will not attempt to read VPD pages on devices that
claim SPC-2 or older. Introduce a blacklist flag that can be used to
trigger VPD page inquiries on devices that are known to support them.
Reported-by: KY Srinivasan <kys@microsoft.com>
Tested-by: KY Srinivasan <kys@microsoft.com>
Reviewed-by: KY Srinivasan <kys@microsoft.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
CC: <stable@vger.kernel.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
We currently set the field in common code based on the device type,
but then only use it in the cdrom driver which also overrides the
value previously set in the generic code.
Just leave this entirely to the CDROM driver to make everyones life
simpler.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
This patch adds support for an alternate I/O path in the scsi midlayer
which uses the blk-mq infrastructure instead of the legacy request code.
Use of blk-mq is fully transparent to drivers, although for now a host
template field is provided to opt out of blk-mq usage in case any unforseen
incompatibilities arise.
In general replacing the legacy request code with blk-mq is a simple and
mostly mechanical transformation. The biggest exception is the new code
that deals with the fact the I/O submissions in blk-mq must happen from
process context, which slightly complicates the I/O completion handler.
The second biggest differences is that blk-mq is build around the concept
of preallocated requests that also include driver specific data, which
in SCSI context means the scsi_cmnd structure. This completely avoids
dynamic memory allocations for the fast path through I/O submission.
Due the preallocated requests the MQ code path exclusively uses the
host-wide shared tag allocator instead of a per-LUN one. This only
affects drivers actually using the block layer provided tag allocator
instead of their own. Unlike the old path blk-mq always provides a tag,
although drivers don't have to use it.
For now the blk-mq path is disable by defauly and must be enabled using
the "use_blk_mq" module parameter. Once the remaining work in the block
layer to make blk-mq more suitable for slow devices is complete I hope
to make it the default and eventually even remove the old code path.
Based on the earlier scsi-mq prototype by Nicholas Bellinger.
Thanks to Bart Van Assche and Robert Elliot for testing, benchmarking and
various sugestions and code contributions.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Webb Scales <webbnh@hp.com>
Acked-by: Jens Axboe <axboe@kernel.dk>
Tested-by: Bart Van Assche <bvanassche@acm.org>
Tested-by: Robert Elliott <elliott@hp.com>
Using dev_printk variants prefixes the logging message with
the originating device, which makes debugging easier.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
scsilun_to_int() has an error which prevents it from generating
correct LUN numbers for 64bit values.
Also we should remove the misleading comment about portions of
the LUN being ignored; the initiator should treat the LUN as
an opaque value.
And, finally, the example given should use the correct
prefix (here: extended flat space addressing scheme).
This patch includes the modifications suggested by
Bart van Assche.
Cc: Bart van Assche <bvanassche@acm.org>
Cc: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: James Bottomley <jbottomley@parallels.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Now that we're using 64-bit LUNs internally we need to increase
the size of max_luns to 64 bits, too.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Christoph Hellwig <hch@infradead.org>
Reviewed-by: Ewan Milne <emilne@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
The SCSI standard defines 64-bit values for LUNs, and large arrays
employing large or hierarchical LUN numbers become more and more
common.
So update the linux SCSI stack to use 64-bit LUN numbers.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Christoph Hellwig <hch@infradead.org>
Reviewed-by: Ewan Milne <emilne@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Sequential scan for more than 256 LUNs is very fragile as
LUNs might not be numbered sequentially after that point.
SAM revisions later than SCSI-3 impose a structure on
LUNs larger than 256, making LUN numbers between 256
and 16384 illegal.
SCSI-3, however allows for plain 64-bit numbers with
no internal structure.
So restrict sequential LUN scan to 256 LUNs and add a
new blacklist flag 'BLIST_SCSI3LUN' to scan up to
max_lun devices.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Ewan Milne <emilne@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Obsolete; either use 'max_lun' if the host supports only a
limited number of LUNs or BLIST_NOLUN if the target has
problems addressing more than one LUN.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Ewan Milne <emilne@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Pull async SCSI resume support from Dan Williams:
"Allow disks and other devices to resume in parallel.
This provides a tangible speed up for a non-esoteric use case (laptop
resume):
https://01.org/suspendresume/blogs/tebrandt/2013/hard-disk-resume-optimization-simpler-approach"
* 'async-scsi-resume' of git://git.kernel.org/pub/scm/linux/kernel/git/djbw/isci:
scsi: async sd resume
async_schedule() sd resume work to allow disks and other devices to
resume in parallel.
This moves the entirety of scsi_device resume to an async context to
ensure that scsi_device_resume() remains ordered with respect to the
completion of the start/stop command. For the duration of the resume,
new command submissions (that do not originate from the scsi-core) will
be deferred (BLKPREP_DEFER).
It adds a new ASYNC_DOMAIN_EXCLUSIVE(scsi_sd_pm_domain) as a container
of these operations. Like scsi_sd_probe_domain it is flushed at
sd_remove() time to ensure async ops do not continue past the
end-of-life of the sdev. The implementation explicitly refrains from
reusing scsi_sd_probe_domain directly for this purpose as it is flushed
at the end of dpm_resume(), potentially defeating some of the benefit.
Given sdevs are quiesced it is permissible for these resume operations
to bleed past the async_synchronize_full() calls made by the driver
core.
We defer the resolution of which pm callback to call until
scsi_dev_type_{suspend|resume} time and guarantee that the callback
parameter is never NULL. With this in place the type of resume
operation is encoded in the async function identifier.
There is a concern that async resume could trigger PSU overload. In the
enterprise, storage enclosures enforce staggered spin-up regardless of
what the kernel does making async scanning safe by default. Outside of
that context a user can disable asynchronous scanning via a kernel
command line or CONFIG_SCSI_SCAN_ASYNC. Honor that setting when
deciding whether to do resume asynchronously.
Inspired by Todd's analysis and initial proposal [2]:
https://01.org/suspendresume/blogs/tebrandt/2013/hard-disk-resume-optimization-simpler-approach
Cc: Len Brown <len.brown@intel.com>
Cc: Phillip Susi <psusi@ubuntu.com>
[alan: bug fix and clean up suggestion]
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Suggested-by: Todd Brandt <todd.e.brandt@linux.intel.com>
[djbw: kick all resume work to the async queue]
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
EVPD page 0x83 is used to uniquely identify the device.
So instead of having each and every program issue a separate
SG_IO call to retrieve this information it does make far more
sense to display it in sysfs.
Some older devices (most notably tapes) will only report reliable
information in page 0x80 (Unit Serial Number). So export this
in the sysfs attribute 'vpd_pg80'.
[jejb: checkpatch fix]
[hare: attach after transport configure]
[fengguang.wu@intel.com: spotted problems with the original now fixed]
Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
In the highly unusual case where two threads are running concurrently through
the scanning code scanning the same target, we run into the situation where
one may allocate the target while the other is still using it. In this case,
because the reap checks for STARGET_CREATED and kills the target without
reference counting, the second thread will do the wrong thing on reap.
Fix this by reference counting even creates and doing the STARGET_CREATED
check in the final put.
Tested-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
Cc: stable@vger.kernel.org # delay backport for 2 months for field testing
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
This patch eliminates the reap_ref and replaces it with a proper kref.
On last put of this kref, the target is removed from visibility in
sysfs. The final call to scsi_target_reap() for the device is done from
__scsi_remove_device() and only if the device was made visible. This
ensures that the target disappears as soon as the last device is gone
rather than waiting until final release of the device (which is often
too long).
Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
Tested-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
Cc: stable@vger.kernel.org # delay backport by 2 months for field testing
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Not all disks fill out the VPD pages correctly. Add a blacklist flag
that allows us ignore the SBC-3 VPD pages for a given device. The
BLIST_SKIP_VPD_PAGES flag triggers our existing skip_vpd_pages
scsi_device parameter to bypass VPD scanning.
Also blacklist the offending Seagate drive model.
Reported-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Introduce eh_timeout which can be used for error handling purposes. This
was previously hardcoded to 10 seconds in the SCSI error handling
code. However, for some fast-fail scenarios it is necessary to be able
to tune this as it can take several iterations (bus device, target, bus,
controller) before we give up.
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Hitachi Ultrastar 15K300 is quirky. Disable T10 PI (DIF).
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
This is a particularly nasty SCSI ATA Translation Layer (SATL) problem.
SAT-2 says (section 8.12.2)
if the device is in the stopped state as the result of
processing a START STOP UNIT command (see 9.11), then the SATL
shall terminate the TEST UNIT READY command with CHECK CONDITION
status with the sense key set to NOT READY and the additional
sense code of LOGICAL UNIT NOT READY, INITIALIZING COMMAND
REQUIRED;
mpt2sas internal SATL seems to implement this. The result is very confusing
standby behaviour (using hdparm -y). If you suspend a drive and then send
another command, usually it wakes up. However, if the next command is a TEST
UNIT READY, the SATL sees that the drive is suspended and proceeds to follow
the SATL rules for this, returning NOT READY to all subsequent commands. This
means that the ordering of TEST UNIT READY is crucial: if you send TUR and
then a command, you get a NOT READY to both back. If you send a command and
then a TUR, you get GOOD status because the preceeding command woke the drive.
This bit us badly because
commit 85ef06d1d2
Author: Tejun Heo <tj@kernel.org>
Date: Fri Jul 1 16:17:47 2011 +0200
block: flush MEDIA_CHANGE from drivers on close(2)
Changed our ordering on TEST UNIT READY commands meaning that SATA drives
connected to an mpt2sas now suspend and refuse to wake (because the mpt2sas
SATL sees the suspend *before* the drives get awoken by the next ATA command)
resulting in lots of failed commands.
The standard is completely nuts forcing this inconsistent behaviour, but we
have to work around it.
The fix for this is twofold:
1. Set the allow_restart flag so we wake the drive when we see it has been
suspended
2. Return all TEST UNIT READY status directly to the mid layer without any
further error handling which prevents us causing error handling which
may offline the device just because of a media check TUR.
Reported-by: Matthias Prager <linux@matthiasprager.de>
Cc: stable@vger.kernel.org
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
This reverts commit 43a8d39d01.
Commit 43a8d39d fixed the fact that wait_for_device_probe() was unable
to flush sd probe work. Now that sd probe work is once again flushable
via wait_for_device_probe() this workaround is no longer needed.
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Tested-by: Eldad Zack <eldad@fogrefinery.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Now that scsi registers its async scan work with the async subsystem,
wait_for_device_probe() is sufficient for ensuring all scanning is
complete.
[jejb: fix merge problems with eea03c20ae Make wait_for_device_probe() also do scsi_complete_async_scans()]
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Tested-by: Eldad Zack <eldad@fogrefinery.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
This is preparation to enable async_synchronize_full() to be used as a
replacement for scsi_complete_async_scans(), i.e. to stop leaking scsi
internal details where they are not needed.
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Tested-by: Eldad Zack <eldad@fogrefinery.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
The following crash results from cases where the end_device has been
removed before scsi_sysfs_add_sdev has had a chance to run.
BUG: unable to handle kernel NULL pointer dereference at 0000000000000098
IP: [<ffffffff8115e100>] sysfs_create_dir+0x32/0xb6
...
Call Trace:
[<ffffffff8125e4a8>] kobject_add_internal+0x120/0x1e3
[<ffffffff81075149>] ? trace_hardirqs_on+0xd/0xf
[<ffffffff8125e641>] kobject_add_varg+0x41/0x50
[<ffffffff8125e70b>] kobject_add+0x64/0x66
[<ffffffff8131122b>] device_add+0x12d/0x63a
[<ffffffff814b65ea>] ? _raw_spin_unlock_irqrestore+0x47/0x56
[<ffffffff8107de15>] ? module_refcount+0x89/0xa0
[<ffffffff8132f348>] scsi_sysfs_add_sdev+0x4e/0x28a
[<ffffffff8132dcbb>] do_scan_async+0x9c/0x145
...teach scsi_sysfs_add_devices() to check for deleted devices() before
trying to add them, and teach scsi_remove_target() how to remove targets
that have not been added via device_add().
Cc: <stable@vger.kernel.org>
Reported-by: Dariusz Majchrzak <dariusz.majchrzak@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Commit a7a20d1 "[SCSI] sd: limit the scope of the async probe domain"
moved sd probe work out of reach of wait_for_device_probe(). Allow it
to be synced via scsi_complete_async_scans().
Reported-by: Meelis Roos <mroos@linux.ee>
Tested-by: Meelis Roos <mroos@linux.ee>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
This resolves the conflict with drivers/usb/host/ehci-fsl.h that
happened with changes in Linus's and this branch at the same time.
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
In do_scan_async(), calling scsi_autopm_put_host(shost) may reference
freed shost, and cause Posison overwitten warning.
Yes, this case can happen, for example, an USB is disconnected just
when do_scan_async() thread starts to run, then scsi_host_put() called
in scsi_finish_async_scan() will lead to shost be freed(because the
refcount of shost->shost_gendev decreases to 1 after USB disconnects),
at this point, if references shost again, system will show following
warning msg.
To make scsi_autopm_put_host(shost) always reference a valid shost,
put it just before scsi_host_put() in function
scsi_finish_async_scan().
[ 299.281565] =============================================================================
[ 299.281634] BUG kmalloc-4096 (Tainted: G I ): Poison overwritten
[ 299.281682] -----------------------------------------------------------------------------
[ 299.281684]
[ 299.281752] INFO: 0xffff880056c305d0-0xffff880056c305d0. First byte
0x6a instead of 0x6b
[ 299.281816] INFO: Allocated in scsi_host_alloc+0x4a/0x490 age=1688
cpu=1 pid=2004
[ 299.281870] __slab_alloc+0x617/0x6c1
[ 299.281901] __kmalloc+0x28c/0x2e0
[ 299.281931] scsi_host_alloc+0x4a/0x490
[ 299.281966] usb_stor_probe1+0x5b/0xc40 [usb_storage]
[ 299.282010] storage_probe+0xa4/0xe0 [usb_storage]
[ 299.282062] usb_probe_interface+0x172/0x330 [usbcore]
[ 299.282105] driver_probe_device+0x257/0x3b0
[ 299.282138] __driver_attach+0x103/0x110
[ 299.282171] bus_for_each_dev+0x8e/0xe0
[ 299.282201] driver_attach+0x26/0x30
[ 299.282230] bus_add_driver+0x1c4/0x430
[ 299.282260] driver_register+0xb6/0x230
[ 299.282298] usb_register_driver+0xe5/0x270 [usbcore]
[ 299.282337] 0xffffffffa04ab03d
[ 299.282364] do_one_initcall+0x47/0x230
[ 299.282396] sys_init_module+0xa0f/0x1fe0
[ 299.282429] INFO: Freed in scsi_host_dev_release+0x18a/0x1d0 age=85
cpu=0 pid=2008
[ 299.282482] __slab_free+0x3c/0x2a1
[ 299.282510] kfree+0x296/0x310
[ 299.282536] scsi_host_dev_release+0x18a/0x1d0
[ 299.282574] device_release+0x74/0x100
[ 299.282606] kobject_release+0xc7/0x2a0
[ 299.282637] kobject_put+0x54/0xa0
[ 299.282668] put_device+0x27/0x40
[ 299.282694] scsi_host_put+0x1d/0x30
[ 299.282723] do_scan_async+0x1fc/0x2b0
[ 299.282753] kthread+0xdf/0xf0
[ 299.282782] kernel_thread_helper+0x4/0x10
[ 299.282817] INFO: Slab 0xffffea00015b0c00 objects=7 used=7 fp=0x
(null) flags=0x100000000004080
[ 299.282882] INFO: Object 0xffff880056c30000 @offset=0 fp=0x (null)
[ 299.282884]
...
Signed-off-by: Huajun Li <huajun.li.lee@gmail.com>
Cc: stable@kernel.org
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
This patch (as1507) adds a skip_vpd_pages flag to struct scsi_device
and a no_report_luns flag to struct scsi_target. The first is used to
control whether sd will look at VPD pages for information on block
provisioning, limits, and characteristics. The second prevents
scsi_report_lun_scan() from issuing a REPORT LUNS command.
The patch also modifies usb-storage to set the new flag bits for all
USB devices and targets, and to stop adjusting the scsi_level value.
Historically we have seen that USB mass-storage devices often don't
support VPD pages or REPORT LUNS properly. Until now we have avoided
these things by setting the scsi_level to SCSI_2 for all USB devices.
But this has the side effect of storing the LUN bits into the second
byte of each CDB, and now we have a report of a device which doesn't
like that. The best solution is to stop abusing scsi_level and
instead have separate flags for VPD pages and REPORT LUNS.
Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Reported-by: Perry Wagle <wagle@mac.com>
CC: Matthew Dharm <mdharm-usb@one-eyed-alien.net>
Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
* blk_get_queue() is peculiar in that it returns 0 on success and 1 on
failure instead of 0 / -errno or boolean. Update it such that it
returns %true on success and %false on failure.
* Make sure the caller checks for the return value.
* Separate out __blk_get_queue() which doesn't check whether @q is
dead and put it in blk.h. This will be used later.
This patch doesn't introduce any functional changes.
Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
When looking at memory consumption issues I noticed quite a
lot of memory in the kmalloc-2048 bucket:
OBJS ACTIVE USE OBJ SIZE SLABS OBJ/SLAB CACHE SIZE NAME
6561 6471 98% 2.30K 243 27 15552K kmalloc-2048
Over 15MB. slub debug shows that cfq is responsible for almost
all of it:
# sort -nr /sys/kernel/slab/kmalloc-2048/alloc_calls
6402 .cfq_init_queue+0xec/0x460 age=43423/43564/43655 pid=1 cpus=4,11,13
In scsi_alloc_sdev we do scsi_alloc_queue but if slave_alloc
fails we don't free it with scsi_free_queue.
The patch below fixes the issue:
OBJS ACTIVE USE OBJ SIZE SLABS OBJ/SLAB CACHE SIZE NAME
135 72 53% 2.30K 5 27 320K kmalloc-2048
# cat /sys/kernel/slab/kmalloc-2048/alloc_calls
3 .cfq_init_queue+0xec/0x460 age=3811/3876/3925 pid=1 cpus=4,11,13
Signed-off-by: Anton Blanchard <anton@samba.org>
Cc: <stable@kernel.org> #2.6.38+
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
In certain circumstances, we can get an oops from a torn down device.
Most notably this is from CD roms trying to call scsi_ioctl. The root
cause of the problem is the fact that after scsi_remove_device() has
been called, the queue is fully torn down. This is actually wrong
since the queue can be used until the sdev release function is called.
Therefore, we add an extra reference to the queue which is released in
sdev->release, so the queue always exists.
Reported-by: Parag Warudkar <parag.lkml@gmail.com>
Cc: stable@kernel.org
Signed-off-by: James Bottomley <jbottomley@parallels.com>
Commit c21e6beb removed our queue request_fn re-enter
protection, and defaulted to always running the queues from
kblockd to be safe. This was a known potential slow down,
but should be safe.
Unfortunately this is causing big performance regressions for
some, so we need to improve this logic. Looking into the details
of the re-enter, the real issue is on requeue of requests.
Requeue of requests upon seeing a BUSY condition from the device
ends up re-running the queue, causing traces like this:
scsi_request_fn()
scsi_dispatch_cmd()
scsi_queue_insert()
__scsi_queue_insert()
scsi_run_queue()
scsi_request_fn()
...
potentially causing the issue we want to avoid. So special
case the requeue re-run of the queue, but improve it to offload
the entire run of local queue and starved queue from a single
workqueue callback. This is a lot better than potentially
kicking off a workqueue run for each device seen.
This also fixes the issue of the local device going into recursion,
since the above mentioned commit never moved that queue run out
of line.
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
This patch removes the old CONFIG_SYSFS_DEPRECATED_V2 config option,
but it keeps the logic around to handle block devices in the old manner
as some people like to run new kernel versions on old (pre 2007/2008)
distros.
Signed-off-by: Kay Sievers <kay.sievers@vrfy.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Stephen Hemminger <shemminger@vyatta.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: "James E.J. Bottomley" <James.Bottomley@suse.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
Cc: Randy Dunlap <randy.dunlap@oracle.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jaroslav Kysela <perex@perex.cz>
Cc: Takashi Iwai <tiwai@suse.de>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: David Howells <dhowells@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
This patch (as1398b) adds runtime PM support to the SCSI layer. Only
the machanism is provided; use of it is up to the various high-level
drivers, and the patch doesn't change any of them. Except for sg --
the patch expicitly prevents a device from being runtime-suspended
while its sg device file is open.
The implementation is simplistic. In general, hosts and targets are
automatically suspended when all their children are asleep, but for
them the runtime-suspend code doesn't actually do anything. (A host's
runtime PM status is propagated up the device tree, though, so a
runtime-PM-aware lower-level driver could power down the host adapter
hardware at the appropriate times.) There are comments indicating
where a transport class might be notified or some other hooks added.
LUNs are runtime-suspended by calling the drivers' existing suspend
handlers (and likewise for runtime-resume). Somewhat arbitrarily, the
implementation delays for 100 ms before suspending an eligible LUN.
This is because there typically are occasions during bootup when the
same device file is opened and closed several times in quick
succession.
The way this all works is that the SCSI core increments a device's
PM-usage count when it is registered. If a high-level driver does
nothing then the device will not be eligible for runtime-suspend
because of the elevated usage count. If a high-level driver wants to
use runtime PM then it can call scsi_autopm_put_device() in its probe
routine to decrement the usage count and scsi_autopm_get_device() in
its remove routine to restore the original count.
Hosts, targets, and LUNs are not suspended while they are being probed
or removed, or while the error handler is running. In fact, a fairly
large part of the patch consists of code to make sure that things
aren't suspended at such times.
[jejb: fix up compile issues in PM config variations]
Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
* git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi-misc-2.6:
[SCSI] fix race in scsi_target_reap
[SCSI] aacraid: Eliminate use after free
[SCSI] arcmsr: Support HW reset for EH and polling scheme for scsi device
[SCSI] bfa: fix system crash when reading sysfs fc_host statistics
[SCSI] iscsi_tcp: remove sk_sleep check
[SCSI] ipr: improve interrupt service routine performance
[SCSI] ipr: set the data list length in the request control block
[SCSI] ipr: fix a register read to use the correct address for 64 bit adapters
[SCSI] ipr: include the resource path in the IOA status area structure
[SCSI] ipr: implement fixes for 64 bit adapter support
[SCSI] be2iscsi: correct return value in mgmt_invalidate_icds()
This patch (as1357) fixes a race in SCSI target allocation and
release. Putting a target in the STARGET_DEL state isn't protected by
the host lock, so an old target structure could be reused by a new
device even though it's about to be deleted. The cure is to change
the state while still holding the host lock.
Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
This patch (as1359) fixes a bug in scsi_alloc_target(). After a
device structure has been initialized (and especially after its name
has been set), it must not be freed directly. One has to call
put_device() instead.
Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
* 'for-2.6.34' of git://git.kernel.dk/linux-2.6-block: (38 commits)
block: don't access jiffies when initialising io_context
cfq: remove 8 bytes of padding from cfq_rb_root on 64 bit builds
block: fix for "Consolidate phys_segment and hw_segment limits"
cfq-iosched: quantum check tweak
blktrace: perform cleanup after setup error
blkdev: fix merge_bvec_fn return value checks
cfq-iosched: requests "in flight" vs "in driver" clarification
cciss: Fix problem with scatter gather elements in the scsi half of the driver
cciss: eliminate unnecessary pointer use in cciss scsi code
cciss: do not use void pointer for scsi hba data
cciss: factor out scatter gather chain block mapping code
cciss: fix scatter gather chain block dma direction kludge
cciss: simplify scatter gather code
cciss: factor out scatter gather chain block allocation and freeing
cciss: detect bad alignment of scsi commands at build time
cciss: clarify command list padding calculation
cfq-iosched: rethink seeky detection for SSDs
cfq-iosched: rework seeky detection
block: remove padding from io_context on 64bit builds
block: Consolidate phys_segment and hw_segment limits
...
The block layer calling convention is blk_queue_<limit name>.
blk_queue_max_sectors predates this practice, leading to some confusion.
Rename the function to appropriately reflect that its intended use is to
set max_hw_sectors.
Also introduce a temporary wrapper for backwards compability. This can
be removed after the merge window is closed.
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
This patch (as1334) fixes a bug in scsi_get_host_dev(). It
incorrectly calls get_device() on the new device's target.
Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
This patch (as1333) fixes a bug in scsi_report_lun_scan(). If a
newly-allocated device can't be used, it should be deleted.
Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
* git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi-misc-2.6: (222 commits)
[SCSI] zfcp: Remove flag ZFCP_STATUS_FSFREQ_TMFUNCNOTSUPP
[SCSI] zfcp: Activate fc4s attributes for zfcp in FC transport class
[SCSI] zfcp: Block scsi_eh thread for rport state BLOCKED
[SCSI] zfcp: Update FSF error reporting
[SCSI] zfcp: Improve ELS ADISC handling
[SCSI] zfcp: Simplify handling of ct and els requests
[SCSI] zfcp: Remove ZFCP_DID_MASK
[SCSI] zfcp: Move WKA port to zfcp FC code
[SCSI] zfcp: Use common code definitions for FC CT structs
[SCSI] zfcp: Use common code definitions for FC ELS structs
[SCSI] zfcp: Update FCP protocol related code
[SCSI] zfcp: Dont fail SCSI commands when transitioning to blocked fc_rport
[SCSI] zfcp: Assign scheduled work to driver queue
[SCSI] zfcp: Remove STATUS_COMMON_REMOVE flag as it is not required anymore
[SCSI] zfcp: Implement module unloading
[SCSI] zfcp: Merge trace code for fsf requests in one function
[SCSI] zfcp: Access ports and units with container_of in sysfs code
[SCSI] zfcp: Remove suspend callback
[SCSI] zfcp: Remove global config_mutex
[SCSI] zfcp: Replace local reference counting with common kref
...
Current FC HBA queue_depth ramp up code depends on last queue
full time. The sdev already has last_queue_full_time field to
track last queue full time but stored value is truncated by
last four bits.
So this patch updates last_queue_full_time without truncating
last 4 bits to store full value and then updates its only
current usages in scsi_track_queue_full to ignore last four bits
to keep current usages same while also use this field
in added ramp up code.
Adds scsi_handle_queue_ramp_up to ramp up queue_depth on
successful completion of IO. The scsi_handle_queue_ramp_up will
do ramp up on all luns of a target, just same as ramp down done
on all luns on a target.
The ramp up is skipped in case the change_queue_depth is not
supported by LLD or already reached to added max_queue_depth.
Updates added max_queue_depth on every new update to default
queue_depth value.
The ramp up is also skipped if lapsed time since either last
queue ramp up or down is less than LLD specified
queue_ramp_up_period.
Adds queue_ramp_up_period to sysfs but only if change_queue_depth
is supported since ramp up and queue_ramp_up_period is needed only
in case change_queue_depth is supported first.
Initializes queue_ramp_up_period to 120HZ jiffies as initial
default value, it is same as used in existing lpfc and qla2xxx.
-v2
Combined all ramp code into this single patch.
-v3
Moves max_queue_depth initialization after slave_configure is
called from after slave_alloc calling done. Also adjusted
max_queue_depth check to skip ramp up if current queue_depth
is >= max_queue_depth.
-v4
Changes sdev->queue_ramp_up_period unit to ms when using sysfs i/f
to store or show its value.
Signed-off-by: Vasu Dev <vasu.dev@intel.com>
Tested-by: Christof Schmitt <christof.schmitt@de.ibm.com>
Tested-by: Giridhar Malavali <giridhar.malavali@qlogic.com>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
Async scanning introduced a very wide window where the SCSI device is
up and running but has not yet been added to sysfs. We delay the
adding until all scans have completed to retain the same ordering as
sync scanning.
This delay in visibility causes an oops if a device is removed before
we make it visible because the SCSI removal routines have an inbuilt
assumption that if a device is in SDEV_RUNNING state, it must be
visible (which is not necessarily true in the async scanning case).
Fix this by introducing an additional is_visible flag which we can use
to condition the tear down so we do the right thing for running but
not yet made visible.
Reported-by: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
