Performance enhancement. Remove spin_locks from the driver.
Reviewed-by: Scott Teel <scott.teel@pmcs.com>
Signed-off-by: Don Brace <don.brace@pmcs.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Empirically, this improves performance slightly (~2% max IOPS) by
allowing cmd_alloc to remember where it left off searching for
free commands between calls instead of always starting its search
at command 0.
Reviewed-by: Scott Teel <scott.teel@pmcs.com>
Signed-off-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Don Brace <don.brace@pmcs.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
This means changing the allocator to reference count commands.
The reference count is now the authoritative indicator of whether a
command is allocated or not. The h->cmd_pool_bits bitmap is now
only a heuristic hint to speed up the allocation process, it is no
longer the authoritative record of allocated commands.
Since we changed the command allocator to use reference counting
as the authoritative indicator of whether a command is allocated,
fail_all_outstanding_cmds needs to use the reference count not
h->cmd_pool_bits for this purpose.
Fix hpsa_drain_accel_commands to use the reference count as the
authoritative indicator of whether a command is allocated instead of
the h->cmd_pool_bits bitmap.
Reviewed-by: Scott Teel <scott.teel@pmcs.com>
Signed-off-by: Don Brace <don.brace@pmcs.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
When using the ioaccel submission methods, requests destined for RAID volumes
are sometimes diverted to physical devices. The OS has no or limited
knowledge of these physical devices, so it is up to the driver to avoid
pushing the device too hard. It is better to honor the physical device queue
limit rather than making the device spew zillions of TASK SET FULL responses.
This is so that hpsa based devices support /sys/block/sdNN/device/queue_type
of simple, which lets the SCSI midlayer automatically adjust the queue_depth
based on TASK SET FULL and GOOD status.
Adjust the queue depth for a new device after it is created based on the
maximum queue depths of the physical devices that constitute the
device. This drops the maximum queue depth from .can_queue of 1024 to
something like 174 for single-drive RAID-0, 348 for two-drive RAID-1, etc.
It also adjusts for the ratio of data to parity drives.
Reviewed-by: Scott Teel <scott.teel@pmcs.com>
Signed-off-by: Webb Scales <webbnh@hp.com>
Signed-off-by: Don Brace <don.brace@pmcs.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Instead of kicking the commands all the way back to the mid
layer, use a work queue. This enables having a mechanism for
the driver to be able to resubmit the commands down the "normal"
raid path without turning off the ioaccel feature entirely
whenever an error is encountered on the ioaccel path, and
prevent excessive rescanning of devices.
Reviewed-by: Scott Teel <scott.teel@pmcs.com>
Signed-off-by: Don Brace <don.brace@pmcs.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Factor out the bottom part of the queuecommand function
which is the part that builds commands for submitting down
the "normal' RAID stack path of a Smart Array.
Need to factor this out to improve how commands that
were initially sent down one of the "ioaccellerated"
paths but which have some sort of error condition are
retried down the "normal" path.
Reviewed-by: Scott Teel <scott.teel@pmcs.com>
Signed-off-by: Don Brace <don.brace@pmcs.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
The original reasoning behind doing this was faulty. An error
of some sort would be encountered, accelerated i/o would be
disabled for that logical drive, the command would be kicked
back out to the SCSI midlayer for a retry, and since i/o accelerator
mode was disabled, it would get retried down the RAID path.
However, something needs to turn ioaccellerator mode back on,
and this rescan request was what did that. However, it was racy,
and extremely bad for performance to rescan all devices, so,
don't do that.
Reviewed-by: Scott Teel <scott.teel@pmcs.com>
Signed-off-by: Don Brace <don.brace@pmcs.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
By not doing maintaining a list of queued commands, we can eliminate some spin
locking in the main i/o path and gain significant improvement in IOPS. Remove
the queuing code and the code that calls it; remove now-unused interrupt code;
remove DIRECT_LOOKUP_BIT.
Now that the passthru commands share the same command pool as
the main i/o path, and the total size of the pool is less than
or equal to the number of commands that will fit in the hardware
fifo, there is no need to check to see if we are exceeding the
hardware fifo's depth.
Reviewed-by: Scott Teel <scott.teel@pmcs.com>
Reviewed-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Don Brace <don.brace@pmcs.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
We have commands reserved for internal use.
This is laying the groundwork for removing the internal
queue of commands from the driver so that the locks that
protect that queue may be removed.
Reviewed-by: Scott Teel <scott.teel@pmcs.com>
Signed-off-by: Don Brace <don.brace@pmcs.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
We need to reserve some commands for device rescans,
aborts, and the pass through ioctls, etc. so we cannot
give them all to the scsi mid layer.
This is in preparation for removing cmd_special_alloc and
cmd_special_free so that we can stop queuing commands internally
in the driver so that we can remove the locks thta protect the
queue that we will no longer have.
Reviewed-by: Scott Teel <scott.teel@pmcs.com>
Signed-off-by: Don Brace <don.brace@pmcs.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
If hpsa_allocate_cmd_pool failed, we were calling two functions unnecessarily:
hpsa_free_sg_chain_blocks(h);
hpsa_free_cmd_pool(h);
This didn't cause any problem, as those functions can tolerate being called
when what they free hasn't been allocated (relevant pointers would be NULL)
but it is potentially confusing.
Reviewed-by: Scott Teel <scott.teel@pmcs.com>
Signed-off-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Don Brace <don.brace@pmcs.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Partial allocation failure wasn't handled correctly
Reviewed-by: Scott Teel <scott.teel@pmcs.com>
Signed-off-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Don Brace <don.brace@pmcs.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Scott Teel <scott.teel@pmcs.com>
Signed-off-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Don Brace <don.brace@pmcs.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Return the actual error code instead of a generic error code.
Reviewed-by: Scott Teel <scott.teel@pmcs.com>
Signed-off-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Don Brace <don.brace@pmcs.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Make the function name more descriptive. We use more than
one interrupt.
Reviewed-by: Scott Teel <scott.teel@pmcs.com>
Signed-off-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Don Brace <don.brace@pmcs.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Enhance error reporting.
Reviewed-by: Scott Teel <scott.teel@pmcs.com>
Signed-off-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Don Brace <don.brace@pmcs.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Cleanup comments to be more specific. Make messages more
informational.
Reviewed-by: Scott Teel <scott.teel@pmcs.com>
Signed-off-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Don Brace <don.brace@pmcs.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Encapsulate the conditional predicate which tests for legacy controllers
in a separate function and rework the code comments.
Reviewed-by: Scott Teel <scott.teel@pmcs.com>
Signed-off-by: Webb Scales <webbnh@hp.com>
Signed-off-by: Don Brace <don.brace@pmcs.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
There is nothing worrisome about the "Waiting for controller to
respond to no-op" print, so use dev_info rather than dev_warn.
Reviewed-by: Scott Teel <scott.teel@pmcs.com>
Signed-off-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Don Brace <don.brace@pmcs.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
If the board ID lookup function fails, return the return
code rather than return -ENODEV.
The only board ID failure reason right now is -ENODEV,
so this just provides more informative prints in kdump
and adapts to future changes.
Tested with error injection while booting with
reset_devices
on the kernel command line:
[ 62.804324] injecting error in inj_hpsa_lookup_board_id: 1 11
[ 62.804423] hpsa 0000:04:00.0: Board ID not found
(the pci probe layer does not print an additional
message if -ENODEV is the reason)
Reviewed-by: Scott Teel <scott.teel@pmcs.com>
Signed-off-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Don Brace <don.brace@pmcs.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Return the real reason for kdump_hard_reset failure rather
than change them all to -ENODEV.
Reviewed-by: Scott Teel <scott.teel@pmcs.com>
Signed-off-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Don Brace <don.brace@pmcs.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
The queue depth printed at startup is in decimal, so
shouldn't have a 0x prefix.
Reviewed-by: Scott Teel <scott.teel@pmcs.com>
Signed-off-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Don Brace <don.brace@pmcs.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
In MSI and MSI-X mode, where hpsa asks for more than one interrupt,
hpsa_request_irqs forgets if the first request_irq call failed
if later ones succeed.
It needs to exit the loop on any failure rather than continue,
freeing all irqs that were requested until that point.
Also, it needs to clear out the q numbers up to MAX_REPLY_QUEUES.
The same is true for the general hpsa_free_irqs function.
Tested with error injection of -ENOSYS on the 4th call:
[ 9.277691] injecting error in inj_request_irq: 1 4
[ 9.277780] hpsa 0000:02:00.0: failed to get irq 35 for hpsa1
[ 10.711623] scsi host1: Error handler scsi_eh_1 exiting
[ 10.739170] hpsa: probe of 0000:02:00.0 failed with error -38
Reviewed-by: Scott Teel <scott.teel@pmcs.com>
Signed-off-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Don Brace <don.brace@pmcs.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Remove unused variable in hpsa_free_cmd_pool.
Reviewed-by: Scott Teel <scott.teel@pmcs.com>
Signed-off-by: Fabian Frederick <fabf@skynet.be>
Acked-by: Don Brace <don.brace@pmcs.com>
Signed-off-by: Don Brace <don.brace@pmcs.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Change the function names to have hpsa prefix.
Reviewed-by: Scott Teel <scott.teel@pmcs.com>
Signed-off-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Don Brace <don.brace@pmcs.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
HP now uses RAID-6 rather than RAID-ADG (Advanced Data Guarding)
as the marketing name for our implementation of RAID-6.
The driver considers RAID-1 and RAID-1+0 to be the same level, and
considers RAID-1ADM and RAID-1+0ADM to be the same level. Parenthesis
can be used to reflect the optional +0 portion of both those RAID levels.
Rename: RAID-ADG to RAID-6
RAID-1(1+0) to RAID-1(+0)
RAID-1(ADM) to RAID-1(+0)ADM
Also, add another const after the pointer type as suggested
by checkpatch.pl so the array is:
static const char * const raid_label[]
Reviewed-by: Scott Teel <scott.teel@pmcs.com>
Signed-off-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Don Brace <don.brace@pmcs.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
We change drive queue depths to match drive reported queue depths.
The name of the SML function was changed from scsi_adjust_queue_depth
changed to scsi_change_queue_depth.
Reviewed-by: Scott Teel <scott.teel@pmcs.com>
Signed-off-by: Don Brace <don.brace@pmcs.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Change how SA controllers are reset by changing PCI power levels.
The hpsa driver was finding the PCI_PM_CTRL_STATE_MASK offset
then reading/writing a bitmask to change the power state. There
are kernel functions that do the same operations. Better to use
the kernel functions.
Signed-off-by: Don Brace <don.brace@pmcs.com>
Reviewed-by: Scott Teel <scott.teel@pmcs.com>
Reviewed-by: Webb Scales <webbnh@hp.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Sometimes when the card is restarted it may cause -
"irq 16: nobody cared (try booting with the "irqpoll" option)"
that is likely caused so, that the card, after the hard reset
finishes, pulls on the irq. Disabling the ints before or after
the hpsa_kdump_hard_reset_controller fixes it.
At this point we can't know in which state the card is,
so using SA5_INTR_OFF + SA5_REPLY_INTR_MASK_OFFSET defines directly,
instead of the function the drivers provides, seems to be apropriate.
Reviewed-by: Scott Teel <scott.teel@pmcs.com>
Signed-off-by: Don Brace <don.brace@pmcs.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
There is a potential memory leak in hpsa_kdump_hard_reset_controller.
Reviewed-by: Don Brace <don.brace@pmcs.com>
Reviewed-by: Scott Teel <scott.teel@pmcs.com>
Signed-off-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Don Brace <don.brace@pmcs.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Correct endiness issues reported by sparse. SA controllers are
little endian. This patch ensures endiness correctness.
Signed-off-by: Don Brace <don.brace@pmcs.com>
Reviewed-by: Scott Teel <scott.teel@pmcs.com>
Reviewed-by: Webb Scales <webbnh@hp.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
The following patch fixes an issue observed with 4k sector disks
where the max_hw_sectors attribute was getting set too large in
sd_revalidate_disk. Since sdkp->max_xfer_blocks is in units
of SCSI logical blocks and queue_max_hw_sectors is in units of
512 byte blocks, on a 4k sector disk, every time we went through
sd_revalidate_disk, we were taking the current value of
queue_max_hw_sectors and increasing it by a factor of 8. Fix
this by only shifting sdkp->max_xfer_blocks.
Cc: stable@vger.kernel.org
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
This fixes a regression caused by commit 1d5203 ("scsi: handle more device
handler setup/teardown in common code").
The bug is that the alua detach() callout will try to access the
sddev->scsi_dh_data, but we have already set it to NULL. This patch
moves the clearing of that field to after detach() is called.
Signed-off-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: Christoph Hellwig <hch@lst.de>
This patch fix is to use default firmware configuration files
present in the adapter incase if not available in standard
/lib/firmware/* dir. Additional cleanup is done to reuse flash
related defines from cxgb4 header file.
Please apply over net-next since it depends on previous commit.
Signed-off-by: Praveen Madhavan <praveenm@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts:
arch/arm/boot/dts/imx6sx-sdb.dts
net/sched/cls_bpf.c
Two simple sets of overlapping changes.
Signed-off-by: David S. Miller <davem@davemloft.net>
unloading: this broke with new atomic refcounting. The code is still
suspicious, but this solves the WARN_ON().
Thanks,
Rusty.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1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=JI7o
-----END PGP SIGNATURE-----
Merge tag 'fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux
Pull one more module fix from Rusty Russell:
"SCSI was using module_refcount() to figure out when the module was
unloading: this broke with new atomic refcounting. The code is still
suspicious, but this solves the WARN_ON()"
* tag 'fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux:
scsi: always increment reference count
Replace a magic number with a PCI #define symbol.
[bhelgaas: add parenthesis]
Signed-off-by: Rafał Miłecki <zajec5@gmail.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
This is the blk-mq part to support tag allocation policy. The default
allocation policy isn't changed (though it's not a strict FIFO). The new
policy is round-robin for libata. But it's a try-best implementation. If
multiple tasks are competing, the tags returned will be mixed (which is
unavoidable even with !mq, as requests from different tasks can be
mixed in queue)
Cc: Jens Axboe <axboe@fb.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
The libata tag allocation is using a round-robin policy. Next patch will
make libata use block generic tag allocation, so let's add a policy to
tag allocation.
Currently two policies: FIFO (default) and round-robin.
Cc: Jens Axboe <axboe@fb.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
James reported:
> After e513cc1 module: Remove stop_machine from module unloading,
> module_refcount() is returning (unsigned long)-1 when called from within
> a routine that runs in module_exit. This is confusing the scsi device
> put code which is coded to detect a module_refcount() of zero for
> running within a module exit routine and not try to do another
> module_put. The fix is to restore the original behaviour of
> module_refcount() and return zero if we're running inside an exit
> routine.
The correct fix is to turn try_module_get() into __module_get(), and
always do the module_put().
Acked-by: James Bottomley <James.Bottomley@HansenPartnership.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
cppcheck found the following issue:
(warning) Logical conjunction always evaluates to false:
alloc_len < 4 && alloc_len > 65535.
..the test should be instead:
if (alloc_len < 4 || alloc_len > 65536)
This error was introduced by recent commit 38d5c8336e
("scsi_debug: add Report supported opcodes+tmfs; Compare and write")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Acked-by: Douglas Gilbert <dgilbert@interlog.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Some devices might not implement config space access
(e.g. remoteproc used not to - before 3.9).
virtio/scsi needs config space access so make it
fail gracefully if not there.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
This change adds support for Qualcomm Technologies Inc platforms that
use UFS driver. for example, it adds :
- PM specific operations during hibern8, suspend, resume, clock setup
- qcom-ufs generic phy driver initialization, calibration,
power-on/off sequence, etc.
- UFS Controller specific configuration
- Rate, Gear, Mode negotiation between device and controller
Signed-off-by: Yaniv Gardi <ygardi@codeaurora.org>
Reviewed-by: Dov Levenglick <dovl@codeaurora.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
The midlayer scsi logging already logs the command and sense code
if the logging level is high enough, no need to duplicate that
in the sr driver.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: James Bottomley <JBottomley@Parallels.com>
Reviewed-by: Ewan D. Milne <emilne@redhat.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
The midlayer logging already prints the cdb details if the logging
level is high enough, no need to duplicate this in the ch driver.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: James Bottomley <JBottomley@Parallels.com>
Reviewed-by: Ewan D. Milne <emilne@redhat.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: James Bottomley <JBottomley@Parallels.com>
Reviewed-by: Ewan D. Milne <emilne@redhat.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
This can happen if a multipathed device uses DIX and another path is
added via an adapter that does not support it. Multipath should not
allow this path to be added, but we should not depend upon that to avoid
crashing.
Signed-off-by: Ewan D. Milne <emilne@redhat.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
We have decided not to productize FCoE on T4.
Hence file is removed.
Signed-off-by: Praveen Madhavan <praveenm@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We found a subtle issue with FCoE on T4 very late in the game
and decided not to productize FCoE on T4 and therefore there
are no customers that will be impacted by this change. Hence
T4 FCoE support is removed. FCoE supported only on T5 cards.
changes in v2:
- Make the commit message more clearer.
Signed-off-by: Praveen Madhavan <praveenm@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fixes a race condition in abort handling that was injected
when multiple interrupt support was added. When only a single
interrupt is present, the adapter guarantees it will send
responses for aborted commands prior to the response for the
abort command itself. With multiple interrupts, these responses
generally come back on different interrupts, so we need to
ensure the abort thread waits until the aborted command is
complete so we don't perform a double completion. This race
condition was being hit frequently in environments which
were triggering command timeouts, which was resulting in
a double completion causing a kernel oops.
Cc: <stable@vger.kernel.org>
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Reviewed-by: Wendy Xiong <wenxiong@linux.vnet.ibm.com>
Tested-by: Wendy Xiong <wenxiong@linux.vnet.ibm.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Contrary to common expectations for an "int" return, these functions
return only a positive value -- if used correctly they cannot even
return 0 because the message header will necessarily be in the skb.
This makes the very common pattern of
if (genlmsg_end(...) < 0) { ... }
be a whole bunch of dead code. Many places also simply do
return nlmsg_end(...);
and the caller is expected to deal with it.
This also commonly (at least for me) causes errors, because it is very
common to write
if (my_function(...))
/* error condition */
and if my_function() does "return nlmsg_end()" this is of course wrong.
Additionally, there's not a single place in the kernel that actually
needs the message length returned, and if anyone needs it later then
it'll be very easy to just use skb->len there.
Remove this, and make the functions void. This removes a bunch of dead
code as described above. The patch adds lines because I did
- return nlmsg_end(...);
+ nlmsg_end(...);
+ return 0;
I could have preserved all the function's return values by returning
skb->len, but instead I've audited all the places calling the affected
functions and found that none cared. A few places actually compared
the return value with <= 0 in dump functionality, but that could just
be changed to < 0 with no change in behaviour, so I opted for the more
efficient version.
One instance of the error I've made numerous times now is also present
in net/phonet/pn_netlink.c in the route_dumpit() function - it didn't
check for <0 or <=0 and thus broke out of the loop every single time.
I've preserved this since it will (I think) have caused the messages to
userspace to be formatted differently with just a single message for
every SKB returned to userspace. It's possible that this isn't needed
for the tools that actually use this, but I don't even know what they
are so couldn't test that changing this behaviour would be acceptable.
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Instead of pushing each byte via stack let's use custom specifier which allows
to print small buffers as a hex string.
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Get a reference on every ipv6 address we offload to hardware so that it cannot
be prematurely cleared out before cleanup.
Signed-off-by: Anish Bhatt <anish@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts:
drivers/net/xen-netfront.c
Minor overlapping changes in xen-netfront.c, mostly to do
with some buffer management changes alongside the split
of stats into TX and RX.
Signed-off-by: David S. Miller <davem@davemloft.net>
Bump mpt2sas driver version to 20.100.00.00.
Signed-off-by: Sreekanth Reddy <Sreekanth.Reddy@avagotech.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Added a support to set cpu affinity mask for each MSIX vector enabled
by the HBA. So that, running the irqbalancer will balance interrupts among
the cpus.
Change_set:
1. Added affinity_hint varable of type cpumask_var_t in adapter_reply_queue
structure. And allocated a memory for this varable by calling
alloc_cpumask_var.
2. Call the API irq_set_affinity_hint for each MSIx vector to affiniate it
with calculated cpus at driver inilization time.
3. While freeing the MSIX vector, call this same API to release the cpu
affinity mask for each MSIx vector by providing the NULL value in
cpumask argument.
4. then call the free_cpumask_var API to free the memory allocated in step 2.
Signed-off-by: Sreekanth Reddy <Sreekanth.Reddy@avagotech.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Copyright, Trademark & Confidentiality legal statements throughout the
source code changed from LSI to Avago.
Signed-off-by: Sreekanth Reddy <Sreekanth.Reddy@avagotech.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
For any SCSI command, if the driver receives IOC status =
SCSI_IOC_TERMINATED and log info = 0x32010081 then that command will be
completed with DID_RESET host status.
The definition of this log info value is "Virtual IO has failed and has
to be retried".
Firmware will provide this log info value with IOC Status
"SCSI_IOC_TERMINATED", whenever a drive (with is a part of a volume)
is pulled and pushed back within some minimal delay. With this log info
value, firmware informs the driver to retry the failed IO command
infinite times, so to provide some time for the firmware to discover
the reinserted drive successfully instated of just retrying failed
command for five times( doesn't giving enough time for firmware to
complete the drive discovery) and failing the IO permanently even
though drive came back successfully.
Signed-off-by: Sreekanth Reddy <Sreekanth.Reddy@avagotech.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Change Set:
1. Extended the upper boundary restriction for the module parameter
max_sgl_entries. Earlier, the max_sgl_entries was capped at the
SCSI_MAX_SG_SEGMENTS kernel definition. With this change, the user
would be able to set the max_sgl_entries to any value which is
greater than SCSI_MAX_SG_SEGMENTS and less than the minimum of
SCSI_MAX_SG_CHAIN_SEGMENTS & hardware limit (Calculated using
IOCFacts's MaxChainDepth).
2. Added a print for the message log whenever the user sets the
max_sgl_entries to a value greater than SCSI_MAX_SG_SEGMENTS to
warn about the kernel definition overriding.
Signed-off-by: Sreekanth Reddy <Sreekanth.Reddy@avagotech.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Change List in this MPI2 specification,
1. Added SSUTimeout field to MPI2_CONFIG_PAGE_BIOS_1,
and more defines for the BiosOptions field.
Signed-off-by: Sreekanth Reddy <Sreekanth.Reddy@avagotech.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Bump driver version to 19.100.00.00.
Signed-off-by: Sreekanth Reddy <Sreekanth.Reddy@avagotech.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
When a flaky disk is there in a topology then during driver load,
discovery related I/O times out; which results in SCSI error recovery
initiating host reset and then the controller won't see any disk.
In this patch, The driver would return FAILED status to the host reset
initiated due to discovery related I/O timeout if ioc->is_driver_loading
is set. This flag would be set until we exit out of scsih_scan_finished().
i.e.
During device discovery if one of the disk is flaky
(which responds to some discovery commands and doesn't respond to some)
the driver wouldn't perform host reset for discovery related I/O timeout.
Instead it would return Failure for the host reset resulting in the
flaky disk getting removed by the SCSI Mid layer,
so other disks would be added correctly.
Signed-off-by: Sreekanth Reddy <Sreekanth.Reddy@avagotech.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
This patch will log a message when driver receives "Temperature Threshold
exceeded" event from any temperature sensor.
The message will look similar to like:
mpt3sas0: Temperature Threshold flags a b c d exceeded for Sensor: x !!!
mpt3sas0: Current Temp In Celsius: y
where a b c d are threshold flags 0 1 2 3
Change_set:
1. Get the number of sensor count of this IOC by reading IO Unit page 8 at
driver initialization time.
2. Also unmask the Temperature Threshold Event at driver initialization
time
3. Whenever a MPI2_EVENT_TEMP_THRESHOLD event is received from the
firmware, then print the sensor number, the maximum threshold number it
has exceed and the current temperature of this sensor.
Signed-off-by: Sreekanth Reddy <Sreekanth.Reddy@avagotech.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
This patch cleanups all other macros/register define related to
CPL messages that are defined in t4_msg.h and the affected files
Signed-off-by: Anish Bhatt <anish@chelsio.com>
Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch cleanups all macros/register define related to connection management
CPL messages that are defined in t4_msg.h and the affected files
Signed-off-by: Anish Bhatt <anish@chelsio.com>
Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Below is the changeset from the MPI specification and 2.00.34 header
files:
1) Defined additional bits in the BiosOptions field of BIOS Page 1 to
allow for finer control of X86 BIOS and UEFI BSD.
2) For the Clean Tool, reserved bit 26 of the Flags field for product
specific use.
Signed-off-by: Sreekanth Reddy <Sreekanth.Reddy@avagotech.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
This patch fixes sparse warning reported by kbuild.
Apply this on net-next since it depends on previous commit.
drivers/scsi/csiostor/csio_hw.c:259:17: sparse: cast to restricted __le32
drivers/scsi/csiostor/csio_hw.c:536:31: sparse: incorrect type in assignment
(different base types)
drivers/scsi/csiostor/csio_hw.c:536:31: expected unsigned int [unsigned]
[usertype] <noident>
drivers/scsi/csiostor/csio_hw.c:536:31: got restricted __be32 [usertype]
<noident>
>> drivers/scsi/csiostor/csio_hw.c:2012:5: sparse: symbol 'csio_hw_prep_fw' was
not declared. Should it be static?
Signed-off-by: Praveen Madhavan <praveenm@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
struct fusion_context *fusion is already memset to '0', so remove a
redundant call to memmset "fusion->load_balance_info" to '0'.
Signed-off-by: Chaitra Basappa <chaitra.basappa@avagotech.com>
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
1) For fusion adapters, limit reserved frames for non SCSI commands to 8
(3 for parallel IOCTLs + 5 for driver's internal DCMDs).
Earlier reserved commands for non SCSI IO frames was set to 32, so with
this implementation, increased per controller "can_queue".
Behavior of MFI controllers will remain unchanged.
2) Optimize the code related to per controller's 'can_queue' setting.
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Signed-off-by: Chaitra Basappa <chaitra.basappa@avagotech.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Driver calls megasas_complete_cmd() to call wake_up() for each MFI frame
that was issued through the ioctl() interface prior to the kill adapter.
This ensures userspace ioctl() system calls issued just before a kill
adapter don't get stuck in wait state and IOCTLs are returned to
the application.
Cc: <stable@vger.kernel.org>
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Signed-off-by: Chaitra Basappa <chaitra.basappa@avagotech.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Update driver "mask_interrupts" before enable/disable hardware interrupt
in order to avoid missing interrupts because of "mask_interrupts" still
set to 1 and hardware interrupts are enabled.
Cc: <stable@vger.kernel.org>
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Signed-off-by: Chaitra Basappa <chaitra.basappa@avagotech.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
This patch will address the issue of SCSI device created at OS level for
non existing VD. ldTgtIdtoLd[] array has size 256 for Extended VD firmware
and 128 for legacy firmware. Accessing indices beyond array size (OS will
send TUR, INQUIRY.. commands upto device index 255), may return valid LD
value and that particular SCSI command will be SUCCESS and creating SCSI
device for non existing target(VD).
For legacy firmware (64 VD firmware), invalidates LD (by setting LD value
to 0xff) in LdTgtIdtoLd[] array for device index beyond 127, so that
invalid LD(0xff) value should be returned beyond device index beyond 127.
Cc: <stable@vger.kernel.org>
Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
This patch adds support for Secure Encrypting Drives (SED) in JBOD mode:
1) If the firmware supports SED JBOD, all non read/write commands to JBODs
will be sent via firmware path, and read/write commands to JBODs will
be sent via fastpath.
2) If the firmware does not support SED JBOD, driver will fall back to the
old design, i.e. send all JBOD I/O via fastpath.
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Signed-off-by: Chaitra Basappa <chaitra.basappa@avagotech.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
This patch addresses below issues:
1) Few endianness bug fixes.
2) Break the iteration after (MAX_LOGICAL_DRIVES_EXT - 1)),
instead of MAX_LOGICAL_DRIVES_EXT.
3) Optimization in MFI INIT frame before firing.
4) MFI IO frame should be 256bytes aligned. Code is optimized to reduce
the size of frame for fusion adapters and make the MFI frame size
calculation a bit transparent and readable.
Cc: <stable@vger.kernel.org>
Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Signed-off-by: Chaitra Basappa <chaitra.basappa@avagotech.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
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: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
scsi_log_send() would display buffer pointer for higher logging levels.
This is not only of questionable value but also exposes kernel pointer to
userspace, which is discouraged in some setups. So drop this message
altogether.
Tested-by: Robert Elliott <elliott@hp.com>
Reviewed-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Instead of having constants.c littered with ifdef statements we should
be moving dummy functions into the header and condintionally compile in
constants.c if selected. And update the Kconfig description to reflect
the actual size difference.
Suggested-by: Christoph Hellwig <hch@infradead.org>
Tested-by: Robert Elliott <elliott@hp.com>
Reviewed-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Convert scsi_print_result() to use the per-cpu buffer for decoding the
command result and disposition.
Tested-by: Robert Elliott <elliott@hp.com>
Reviewed-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Convert sense buffer logging to use the per-cpu buffer to avoid line
breakup.
Tested-by: Robert Elliott <elliott@hp.com>
Reviewed-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Use an external buffer for __scsi_print_command() and move command
logging over to use the per-cpu logging buffer. With that we can
guarantee the command always will always be formatted in one line.
So we can even print out a variable length command correctly across
several lines. Finally rename __scsi_print_command() to
__scsi_format_comment() to better reflect the functionality.
Tested-by: Robert Elliott <elliott@hp.com>
Reviewed-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
The request tag provides a concise identification of a SCSI
command, so we should be printing that out for scmd_printk().
Suggested-by: Christoph Hellwig <hch@lst.de>
Tested-by: Robert Elliott <elliott@hp.com>
Reviewed-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Implement a per-cpu buffer for formatting messages to avoid line breaks
up under high load. This patch implements scmd_printk() and
sdev_prefix_printk() using the per-cpu buffer and makes sdev_printk() a
wrapper for sdev_prefix_printk().
Tested-by: Robert Elliott <elliott@hp.com>
Reviewed-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
On win8 and win8 r2 hosts force SPC-3 compliance for MSFT virtual disks.
Ubuntu has been carrying a similar patch outside the tree for a while now.
Starting with win10, the host will support SPC-3 compliance. Based on all
the testing that has been done on win8 and win8 r2 hosts, we are comfortable
claiming SPC-3 compliance on these hosts as well. This will enable TRIM
support on these hosts.
Suggested by: James Bottomley <James.Bottomley@HansenPartnership.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Reviewed-by: Long Li <longli@microsoft.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Commit 4cd83ecdac changed the limits to
reflect the values on the host. It turns out that WS2008R2 cannot
correctly handle these new limits. Fix this bug by setting the limits
based on the host.
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Reviewed-by: Long Li <longli@microsoft.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
The host asks the guest to scan when a LUN is removed or added.
The only way a guest can identify the removed LUN is when an I/O is
attempted on a removed LUN - the SRB status code indicates that the LUN
is invalid. We currently handle this SRB status and remove the device.
Rather than waiting for an I/O to remove the device, force the discovery of
LUNs that may have been removed prior to discovering LUNs that may have
been added.
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Reviewed-by: Long Li <longli@microsoft.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
The virtual HBA that storvsc implements can support multiple channels and
targets. So, scan the host when the host notifies that a scan is needed.
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Reviewed-by: Long Li <longli@microsoft.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
STORVSC uses its own momory pool to manage device request data. However,
the SCSI layer already has a mechanisim for allocating additional memory
for each command issued to device driver. This patch removes the memory
pool in STORVSC and makes it use SCSI layer to allocate memory for device
request data.
Reviewed-by: Long Li <longli@microsoft.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
This patch, applicable to 8G/4G/2G adapters, adds a call that
resumes transmit operations after a link bounce. Without it, targets
that tried to suspend exchanges after a link bounce (such as tape devices
using sequence level error recovery) would never resume io operation,
causing scan failures, and eventually deadlocks if a device removal
request is made.
Signed-off-by: James Smart <james.smart@emulex.com>
Signed-off-by: Dick Kennedy <dick.kennedy@emulex.com>
Reviewed-by: Ewan D. Milne <emilne@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
'num_tags' is an unsigned char, so the check for 'ESP_MAX_TAGS'
(which is set to 256) is pointless.
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
The "issue_reset" can be used uninitialized. It should be set to false
at the start.
Also I cleaned up the types a little by using bool.
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Sreekanth Reddy <Sreekanth.Reddy@avagotech.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
The "issue_reset" variable can be used uninitialized. It should be set
to false at the start.
Also I cleaned up the types by using bool.
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Sreekanth Reddy <Sreekanth.Reddy@avagotech.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Replacing strncpy with strlcpy to avoid strings that lacks null terminate.
And use the sizeof on the to string rather than strlen on the from string.
Signed-off-by: Rickard Strandqvist <rickard_strandqvist@spectrumdigital.se>
Acked-by: Adam Radford <aradford@gmail.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Accept the WRITE BUFFER command and do nothing other than
set the appropriate "microcode has been changed" UA on the LU.
>From an earlier patch by Doug Gilbert.
Signed-off-by: Ewan D. Milne <emilne@redhat.com>
Acked-by: Douglas Gilbert <dgilbert@interlog.com>
Tested-by: Douglas Gilbert <dgilbert@interlog.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Generate a REPORTED LUNS DATA HAS CHANGED Unit Attention if
sysfs "max_luns" is used to change the number of scsi_debug LUNs.
This is only done if scsi_debug_scsi_level is SPC-3 or above.
Additionally, implement SPC-4 behavior which only generates
this Unit Attention on the first LUN on the target to receive
a command after the change. This condition is cleared when
a REPORT LUNS command is received.
Signed-off-by: Ewan D. Milne <emilne@redhat.com>
Acked-by: Douglas Gilbert <dgilbert@interlog.com>
Tested-by: Douglas Gilbert <dgilbert@interlog.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Add power_status to SES device slot, so we can power on/off the
HDDs behind the enclosure.
Check firmware status in ses_set_* before sending control pages to
firmware.
Signed-off-by: Song Liu <songliubraving@fb.com>
Acked-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Jens Axboe <axboe@fb.com>
Cc: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
The name provided by firmware is in a vendor specific format, publish
the slot number to have a reliable mechanism for identifying slots
across firmware implementations. If the enclosure does not provide a
slot number fallback to the component number which is guaranteed unique,
and usually mirrors the slot number.
Cleaned up the unused ses_component.desc in the process.
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Song Liu <songliubraving@fb.com>
Reviewed-by: Jens Axboe <axboe@fb.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>