This patch removes extended delay bit on GSCSI reads/writes ops, the
performance will be significanly better.
Signed-off-by: Wen Xiong <wenxiong@linux.vnet.ibm.com>
Acked-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
This adds a module parameter to enable clustering.
Without enabling clustering support, the transfer length for read and
write scsi commands is limited upto 8MB when page size is 4KB and
sg_tablesize is 2048 (= SCSI_MAX_SG_CHAIN_SEGMENTS). I would like to
test commands with more than that transfer length.
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Reviewed-by: Douglas Gilbert <dgilbert@interlog.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
This change ensures that concurrent device access including ramdisk
storage, protection info, and provisioning map by read, write, and
unmap commands are protected with atomic_rw spinlock.
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Reviewed-by: Douglas Gilbert <dgilbert@interlog.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Currently, clustering support for scsi_debug is disabled. This is
because there are for_each_sg() loops which assume that each sg list
element is consisted with a single page. But enabling clustering
support, each sg list element for scsi commands can be consisted with
multiple pages.
This replaces these for_each_sg() loops with sg mapping iterator which
is capable of handling each sg list element is consisted with multiple
pages.
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Reviewed-by: Douglas Gilbert <dgilbert@interlog.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
When resp_xdwriteread() can't allocate temporary buffer, it returns -1.
But the return value is used as scsi status code and -1 is not
interpreted as correct code.
target_core_mod has similar xdwriteread emulation code. So this mimics
what target_core_mod does for xdwriteread when running out of memory.
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Reviewed-by: Douglas Gilbert <dgilbert@interlog.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
It is unnecessary to increase dif_errors in dif_verify(), because the
caller will increment it when dif_verify() detects failure.
This bug was introduced by commit beb40ea42b ("[SCSI] scsi_debug:
reduce duplication between prot_verify_read and prot_verify_write")
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Acked-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Douglas Gilbert <dgilbert@interlog.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
As pseudo_primary is only used in scsi_debug.c, it should be static.
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Reviewed-by: Douglas Gilbert <dgilbert@interlog.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Reading partially unwritten sectors generates a false positive logical
block reference tag check failure when DIF is enabled.
This bug is caused by missing ei_lba increment in loop of dif_verify()
when unwritten sector is skipped.
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Acked-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Douglas Gilbert <dgilbert@interlog.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Avoid a spurious device get/put pair by cleaning up scsi_requeue_command
and folding scsi_unprep_request into it.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Eliminate a get_device() / put_device() pair from scsi_next_command().
Both are atomic operations hence removing these slightly improves
performance.
[hch: slight changes due to different context]
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
SCSI devices may only be removed by calling scsi_remove_device().
That function must invoke blk_cleanup_queue() before the final put
of sdev->sdev_gendev. Since blk_cleanup_queue() waits for the
block queue to drain and then tears it down, scsi_request_fn cannot
be active anymore after blk_cleanup_queue() has returned and hence
the get_device()/put_device() pair in scsi_request_fn is unnecessary.
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Many callers won't need this and we can optimize them away. In addition
the handling in the __-prefixed variants was inconsistant to start with.
Based on an earlier patch from Bart Van Assche.
[jejb: fix kerneldoc probelm picked up by Fengguang Wu]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
If we don't have starved devices we don't need to take the host lock
to iterate over them. Also split the function up to be more clear.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Avoid hitting the host-wide free_list lock unless we need to put a command
back onto the freelist.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Structure was already memset to zero at the top
of hpsa_scsi_ioaccel2_queue_command
Signed-off-by: Stephen M. Cameron <scameron@beardog.cce.hp.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
This allows exposing physical disks behind Smart
Array controllers to the OS (if the controller
has the right firmware and is in "hba" mode)
Signed-off-by: Joe Handzik <joseph.t.handzik@hp.com>
Signed-off-by: Stephen M. Cameron <scameron@beardog.cce.hp.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
rc is set in the loop, and it isn't set back to zero anywhere
this patch fixes it
Signed-off-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Do not expose drives that are undergoing a format immediately
to the OS, instead wait until they are ready before bringing
them online. This is so that logical drives created with
"rapid parity initialization" do not get immediately kicked
off the system for being unresponsive.
Signed-off-by: Stephen M. Cameron <scameron@beardog.cce.hp.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Evidently some wacky USB-ATA bridges don't recognize the SYNCHRONIZE
CACHE command, as shown in this email thread:
http://marc.info/?t=138978356200002&r=1&w=2
The fact that we can't tell them to drain their caches shouldn't
prevent the system from going into suspend. Therefore sd_sync_cache()
shouldn't return an error if the device replies with an Invalid
Command ASC.
Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Reported-by: Sven Neumann <s.neumann@raumfeld.com>
Tested-by: Daniel Mack <zonque@gmail.com>
CC: <stable@vger.kernel.org>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
If a phy device is removed, the device can get error of I/O and HBA maybe
receieve IO_OPEN_CNX_ERROR_IT_NEXUS_LOSS of event which causes pm8001_work_fn
to reset the phy device but in pm8001_task_exec we don't assign a value for
the device field of the ccb and in other case a ccb used have device field
set, when ccb is freed the field device of the ccb don't be set NULL.So there
is possibility of getting another device reset in function mpi_ssp_completion.
Signed-off-by: zhuxh <zxh3737@163.com>
Acked-by: Lindar Liu <lindar_liu@usish.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
In function pm8001_dev_gone_notify we consume a tag from bitmap resource and
later don't free that tag resource, so the tag resource will never be
freed. In the function we don't need to use any tag to issue command for
unregistering the device .
Signed-off-by: XinHong Zhu <zxh3737@163.com>
Acked-by: Lindar Liu <lindar_liu@usish.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
The following patch for megaraid_sas updates the driver version to
v06.803.01.00-rc1, and updates Documentation/scsi/ChangeLog.megaraid_sas.
Signed-off-by: Adam Radford <aradford@gmail.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
The following patch for megaraid_sas adds Dell PowerEdge VRTS SR-IOV VF
support (Device ID 0x002f).
This patch has some > 80 column lines that need to be left in place
for code readability purposes.
Signed-off-by: Adam Radford <aradford@gmail.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
The following patch for megaraid_sas will return leaked MPT frames from any
polled DCMD's that timeout to the MPT frame pool.
Signed-off-by: Adam Radford <aradford@gmail.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
The following patch for megaraid_sas fixes the megasas_ioc_init_fusion
function to use a local stack variable for the IOCinit frame physical address
instead of clobbering the first request descriptor.
Signed-off-by: Adam Radford <aradford@gmail.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
The following patch for megaraid_sas loads the correct raid context timeout
value for multpathing and clustering.
Signed-off-by: Adam Radford <aradford@gmail.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Host lock is added back around queuecommand. Host lock removal can create race
conditon between ISR path(when RAID map update interrupt is raised) and IO
build path of driver, since IO build path is making use of RAID map, and in
case of RAID map update interrupt, old RAID map copy is memset to zero, which
some IOs may be referencing in build IO path. Changes done for performance
boost- 1) Added code to set SMP IRQ affinity per CPU. 2) Pass MSI-x index,
while issuing sysPD IO.
Signed-off-by: Kashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: Sumit Saxena <sumit.saxena@lsi.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
If consistent DMA mask is set to 64 bit, fall back to 32bit DMA mask and 32bit consistent DMA mask.
64bit consistent DMA mask may be set on some 64bit DMA slot, which causes DMA offset "10000000000000" and
MFI_INIT and IOCTL frames will have high memory addresses, leads to firmware FAULT.
Signed-off-by: Kashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: Sumit Saxena <sumit.saxena@lsi.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Don't wait forever for firmware response for internal DCMDs sent from driver
firmware. Such DCMDs will be posted to firmware with timeout. Timeout is also
introduced for DCMD sent to abort the commands. DCMD sent via IOCTL path will
still be always blocking to keep the IOCTL design intact.
Signed-off-by: Sumit Saxena <sumit.saxena@lsi.com>
Signed-off-by: Kashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
The original code always set the upper 32 bits to zero because it was
doing a shift of the wrong variable.
Fixes: 1a4f550a09 ('[SCSI] arcmsr: 1.20.00.15: add SATA RAID plus other fixes')
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Currently, scsi error handling in scsi_io_completion() tries to
unconditionally requeue scsi command when device keeps some error state.
For example, UNIT_ATTENTION causes infinite retry with
action == ACTION_RETRY.
This is because retryable errors are thought to be temporary and the scsi
device will soon recover from those errors. Normally, such retry policy is
appropriate because the device will soon recover from temporary error state.
But there is no guarantee that device is able to recover from error state
immediately. Some hardware error can prevent device from recovering.
This patch adds timeout in scsi_io_completion() to avoid infinite command
retry in scsi_io_completion(). Once scsi command retry time is longer than
this timeout, the command is treated as failure.
Signed-off-by: Eiichi Tsukata <eiichi.tsukata.xh@hitachi.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Check that the session is setup before accessing its
connection. This fixes a oops where userspace tries
to get the ip address before the session is bound to
a host.
Signed-off-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Load and unload iscsi_ibft module will cause kernel memory leak, fix it
in scsi/iscsi_boot_sysfs.c iscsi_boot_destroy_kset().
Signed-off-by: Ethan Zhao <ethan.kernel@gmail.com>
Signed-off-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
iscsi_queuecommand will only take in commands that can fit in the
current window. So, if a command is on the cmdqueue then it can
fit in the current window. If a command is on the mgmtqueue, then
we are setting the immediate bit so they will also fit in the
window. As a result, we never need to to do a iscsi_conn_queue_work
when the maxCmdSn is increased.
What should happen is that a command will complete the window will
be increased, then the scsi layer will send us more commands by
running the scsi_device queues.
Signed-off-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Replace the session lock with two locks, a forward lock and
a backwards lock named frwd_lock and back_lock respectively.
The forward lock protects resources that change while sending a
request to the target, such as cmdsn, queued_cmdsn, and allocating
task from the commands' pool with kfifo_out.
The backward lock protects resources that change while processing
a response or in error path, such as cmdsn_exp, cmdsn_max, and
returning tasks to the commands' pool with kfifo_in.
Under a steady state fast-path situation, that is when one
or more processes/threads submit IO to an iscsi device and
a single kernel upcall (e.g softirq) is dealing with processing
of responses without errors, this patch eliminates the contention
between the queuecommand()/request response/scsi_done() flows
associated with iscsi sessions.
Between the forward and the backward locks exists a strict locking
hierarchy. The mutual exclusion zone protected by the forward lock can
enclose the mutual exclusion zone protected by the backward lock but not
vice versa.
For example, in iscsi_conn_teardown or in iscsi_xmit_data when there is
a failure and __iscsi_put_task is called, the backward lock is taken while
the forward lock is still taken. On the other hand, if in the RX path a nop
is to be sent, for example in iscsi_handle_reject or __iscsi_complete_pdu
than the forward lock is released and the backward lock is taken for the
duration of iscsi_send_nopout, later the backward lock is released and the
forward lock is retaken.
libiscsi_tcp uses two kernel fifos the r2t pool and the r2t queue.
The insertion and deletion from these queues didn't corespond to the
assumption taken by the new forward/backwards session locking paradigm.
That is, in iscsi_tcp_clenup_task which belongs to the RX (backwards)
path, r2t is taken out from r2t queue and inserted to the r2t pool.
In iscsi_tcp_get_curr_r2t which belong to the TX (forward) path, r2t
is also inserted to the r2t pool and another r2t is pulled from r2t
queue.
Only in iscsi_tcp_r2t_rsp which is called in the RX path but can requeue
to the TX path, r2t is taken from the r2t pool and inserted to the r2t
queue.
In order to cope with this situation, two spin locks were added,
pool2queue and queue2pool. The former protects extracting from the
r2t pool and inserting to the r2t queue, and the later protects the
extracing from the r2t queue and inserting to the r2t pool.
Signed-off-by: Shlomo Pongratz <shlomop@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
[minor fix up to apply cleanly and compile fix]
Signed-off-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Restructure the iscsi_tcp_r2t_rsp routine in order to avoid allocating
r2t from r2tpool.queue and returning it back in case the parameters
rhdr->data_length and or rhdr->data_offset prohibit the requing.
Since the values of these parameters are known prior to the allocation,
we can pre-check and thus avoid futile allocations.
[jejb: checkpatch fixes]
Signed-off-by: Shlomo Pongratz <shlomop@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Fixed calculates wrong tuple values on T5 adapter: switch to use the exported
API cxgb4_select_ntuple() from cxgb4 base driver.
Signed-off-by: Karen Xie <kxie@chelsio.com>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
When megasas_get_pd_list() fails we cannot detect any drives,
so we should be checking the return value accordingly.
[jejb: checkpatch fix]
Signed-off-by: Hannes Reinecke <hare@suse.de>
Acked-by: Kashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
When no HBA is found we should be returning '-ENXIO' to be consistent
with the other return values.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Acked-by: Kashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
The pointer to the queue info structure is potentially
a 64-bit value, so we should be using the correct macros
to set the values in the init frame.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Acked-by: Kashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
The version of isci driver has not been updated for 2 years.
It was 83 isci commits ago. Suspend/resume support has been implemented
and many bugs have been fixed since 1.1. Now update the version to 1.2.
Signed-off-by: Lukasz Dorau <lukasz.dorau@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Maciej Patelczyk <maciej.patelczyk@intel.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
For various error conditions the bfa driver just returns
'DID_ERROR', which carries no information at all about the
actual source of error.
This patch updates the error handling to return a correct
error code, depending on the type of error occurred.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Acked-by: Vijaya Mohan Guvva <vmohan@brocade.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
