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>
Removing unused code as FW does not need any value in mbox-5.
Signed-off-by: Vikas Chaudhary <vikas.chaudhary@qlogic.com>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Issue:
While unloading driver MBOX 0x31 fail as DDB logout (MBOX 0x56)
operation is not completed.
Fix:
Wait for DDB Logout completion before MBOX 0x31
Signed-off-by: Vikas Chaudhary <vikas.chaudhary@qlogic.com>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Issue:
Driver holds rom-lock for too long during reset recovery.
During adapter reset testing, it was found that the driver
holds the rom-lock for too long, because of which other
drivers fail to acquire the rom-lock, leading to reset
failures.
The primary cause is, in the bootstrap code, while
holding the rom-lock, the driver checks if the peg is
halted, causing a 2 second contention.
Fix:
When a reset recovery starts, the driver deduces the cause, and
sets appropriate flags in watchdog & recover_adapter routines.
This flag should be used to determine if bootstrap is invoked
from probe or reset context, reducing the rom-lock footprint of
the drivers.
Signed-off-by: Vikas Chaudhary <vikas.chaudhary@qlogic.com>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Issue:
minidump data collection fails as driver reports data mismatch
Fix:
When the driver encounters a new entry type that it cannot process,
it should just skip the entry and adjust the total buffer size by
subtracting the skipped bytes from it. This is to ensure that there
is no data mismatch because of the new entries.
Signed-off-by: Tej Parkash <tej.parkash@qlogic.com>
Signed-off-by: Vikas Chaudhary <vikas.chaudhary@qlogic.com>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Issue:
Pending IO wait does not complete after triggering Graceful reset,
causing ack timeout and call traces.
Fix:
1. Reducing the IO command wait timeout before triggering reset,
as logically also timeout should be less than reset timeout (10sec).
2. Moving the abort IO after chip reset, because only after
chip reset, driver owns the IO otherwise it is with firmware and can
still revert back with response.
Signed-off-by: Tej Parkash <tej.parkash@qlogic.com>
Signed-off-by: Vikas Chaudhary <vikas.chaudhary@qlogic.com>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Issue:
While booting with kdump kernel, driver receive IOCB interrupts
for which it is not ready which results in processing them
before init_firmware during driver probe
Fix:
Two steps solution
1. Make driver ready to process the interrupt before interupts
handlers is registered.
2. Stop driver processing iocb interrupts if not generated as per
firmware protocol i.e R2H bit set
Signed-off-by: Tej Parkash <tej.parkash@qlogic.com>
Signed-off-by: Vikas Chaudhary <vikas.chaudhary@qlogic.com>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Issue:
Mailbox command 0x102 (IDC Time Extend) failure seen while applying
changes to iface using iscsiadm
Fix:
Added fix to extend IDC timeout only for ISP84xx when IDC ACK
needs to be posted and disable ACB mailbox command completion
is in intermediate state.
Signed-off-by: Vikas Chaudhary <vikas.chaudhary@qlogic.com>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Issue:
qla4xxx Unable to clear DDB indices when logout fails due to
failure of connection close mbox command.
Root cause:
If login to session fail, iscsiadm make call to destroy_session.
qla4xxx driver does not free ddb index map before free_ddb()
Fix:
Clear DDB Index map before free_ddb in "destroy_session"
in case of connection close mailbox command failure with 4005h.
Signed-off-by: Nilesh Javali <nilesh.javali@qlogic.com>
Signed-off-by: Vikas Chaudhary <vikas.chaudhary@qlogic.com>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
If waiting for signals was interrupted then the device was put to
FAILED state. Use msleep instead of msleep_interruptible to handle
this correctly.
Signed-off-by: Vikas Chaudhary <vikas.chaudhary@qlogic.com>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Removed AF_83XX_NO_FWDUMP flag and directly checking IDC_CTRL bit1
while taking minidump, to check for graceful reset.
Signed-off-by: Vikas Chaudhary <vikas.chaudhary@qlogic.com>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Issue:
For ISP8xxx, adapter initialization is not retried if
qla4xxx_initialize_adapter fails.
Fix:
If qla4xxx_initialize_adapter fails, first check if failure is due to IRQs not
attached in order to skip retrial, then free the IRQs and then retry
initializing the adapter.
Signed-off-by: Nilesh Javali <nilesh.javali@qlogic.com>
Signed-off-by: Vikas Chaudhary <vikas.chaudhary@qlogic.com>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Signed-off-by: John Soni Jose <sony.john-n@emulex.com>
Signed-off-by: Jayamohan Kallickal <jayamohan.kallickal@emulex.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
XinHong Zhu