31 Oct, 2011
14 commits
-
PCI Express devices will return "XPRS" host bus type during BIOS EDD
call. "XPRS" should be treated just like "PCI" so that the proper
pci_dev symlink will be created. Scripts such as fcoe_edd.sh will
then work correctly.Signed-off-by: Michael Chan
Reviewed-by: Matt Domsch
Signed-off-by: Yi Zou
Signed-off-by: James Bottomley -
Fixes bug where max_concurr_spinup oem parameter should be
overriden by max_concurr_spinup user parameter. Override should
happen only when max_concurr_spinup user parameter is specified
in command line (greater than 0). Also this fix shortens variables
representing max_conxurr_spinup for oem and user parameters.Signed-off-by: Andrzej Jakowski
Signed-off-by: Dan Williams
Signed-off-by: James Bottomley -
The initial bcn filtering implementation was validated on a kernel
baseline that predated the switch to new libata error handling. Also,
prior to that conversion we borrowed the mvsas MVS_DEV_EH approach to
prevent the unwanted extra ap->ops->phy_reset(ap) that occurred in the
ata_bus_probe() path.After the conversion to new libata eh resets at discovery are more
frequent and get filtered prematurely by IDEV_EH. The result is that
our bcn filtering has been blocked from running and at discovery and it
appears to stall discovery completion to the point of triggering hung
task timeouts. So, revert the implementation for now. When it returns
it will go into libsas proper.The domain rediscovery that takes place due to ->lldd_I_T_nexus_reset()
events should now be properly waited for by the ata_port_wait_eh() call
in ata_port_probe(). So the hard coded delay in the isci
->lldd_I_T_nexus_reset() and other libsas drivers should help debounce
the libsas thread from seeing temporary device removals.Signed-off-by: Dan Williams
Signed-off-by: James Bottomley -
A hard reset can timeout before or after the last phy in the
port goes away. If after, then notify the OS that the last
phy has failed.The recovery for the failed hard reset has been removed.
This recovery code was unecessary in that the link would
recover from the failure normally by a new link reset sequence
or hotplug of the remote device.Signed-off-by: Jeff Skirvin
Signed-off-by: Dan Williams
Signed-off-by: James Bottomley -
The lldd does not need to look at or manage the pending device
reset bit in pending sas_tasks.Signed-off-by: Jeff Skirvin
Signed-off-by: Dan Williams
Signed-off-by: James Bottomley -
Use the existing IREQ_TMF flag as a request type indicator.
Signed-off-by: Jeff Skirvin
Signed-off-by: Dan Williams
Signed-off-by: James Bottomley -
libsas uses the LLDD abort task interface to handle I/O timeouts
in the SATA/STP and SMP discovery paths, so this change will terminate
STP/SMP requests. Also, if the device is gone, the lldd will prevent
libsas from further escalations in the error handler.Signed-off-by: Jeff Skirvin
Signed-off-by: Dan Williams
Signed-off-by: James Bottomley -
libsas will cleanup pending sas_tasks after error handler
path functions are called; do not call task_done callbacks.Signed-off-by: Jeff Skirvin
Signed-off-by: Dan Williams
Signed-off-by: James Bottomley -
In the case where "task" requests timeout (note that this class of
requests can also include SATA/STP soft reset FIS transmissions),
handle the case where the task was being managed by some call to
terminate the task request by completing both the tmf and the aborting
process.Signed-off-by: Jeff Skirvin
Signed-off-by: Dan Williams
Signed-off-by: James Bottomley -
Make sure terminated requests and completed task tags are freed.
Signed-off-by: Jeff Skirvin
Signed-off-by: Dan Williams
Signed-off-by: James Bottomley -
In the case where an I/O fails to start in isci_request_execute,
only allow retries if the device is not already gone.Signed-off-by: Jeff Skirvin
Signed-off-by: Dan Williams
Signed-off-by: James Bottomley -
The LLDD needs to obtain a reference to the device through the request
itself and not through the domain_device, because the
domain_device.lldd_dev is set to NULL early in the lldd_dev_gone call.
This relies on the fact that the isci_remote_device object is keeping a
seperate reference count of outstanding requests. TODO: unify the
request count tracking with the isci_remote_device kref.The failure signature of this condition looks like the following
log, where the important bits are the call to lldd_dev_gone followed
by a crash in isci_terminate_request_core:[ 229.151541] isci 0000:0b:00.0: isci_remote_device_gone: domain_device = ffff8801492d4800, isci_device = ffff880143c657d0, isci_port = ffff880143c63658
[ 229.166007] isci 0000:0b:00.0: isci_remote_device_stop: isci_device = ffff880143c657d0
[ 229.175317] isci 0000:0b:00.0: isci_terminate_pending_requests: idev=ffff880143c657d0 request=ffff88014741f000; task=ffff8801470f46c0 old_state=2
[ 229.189702] isci 0000:0b:00.0: isci_terminate_request_core: device = ffff880143c657d0; request = ffff88014741f000
[ 229.201339] isci 0000:0b:00.0: isci_terminate_request_core: before completion wait (ffff88014741f000/ffff880149715ad0)
[ 229.213414] isci 0000:0b:00.0: sci_controller_process_completions: completion queue entry:0x8000a0e9
[ 229.214401] BUG: unable to handle kernel NULL pointer dereference at 0000000000000228
[ 229.214401] IP:jdskirvi-testlbo [] sci_request_completed_state_enter+0x50/0xafb [isci]
[ 229.214401] PGD 13d19e067 PUD 13d104067 PMD 0
[ 229.214401] Oops: 0000 [#1] SMP
[ 229.214401] CPU 0 x kernel: [ 226
[ 229.214401] Modules linked in: ipv6 dm_multipath uinput nouveau snd_hda_codec_realtek snd_hda_intel ttm drm_kms_helper drm snd_hda_codec snd_hwdep snd_pcm snd_timer i2c_algo_bit isci snd libsas ioatdma mxm_wmi iTCO_wdt soundcore snd_page_alloc scsi_transport_sas iTCO_vendor_support wmi dca video i2c_i801 i2c_core [last unloaded: speedstep_lib]
[ 229.214401]
[ 229.214401] Pid: 5, comm: kworker/u:0 Not tainted 3.0.0-isci-11.7.29+ #30.353196] Buffer Intel Corporation Stoakley/Pearlcity Workstation
[ 229.214401] RIP: 0010:[] I/O error on dev [] sci_request_completed_state_enter+0x50/0xafb [isci]
[ 229.214401] RSP: 0018:ffff88014fc03d20 EFLAGS: 00010046
[ 229.214401] RAX: 0000000000000000 RBX: ffff88014741f000 RCX: 0000000000000000
[ 229.214401] RDX: ffffffffa00b2c90 RSI: 0000000000000017 RDI: ffff88014741f0a0
[ 229.214401] RBP: ffff88014fc03d90 R08: 0000000000000018 R09: 0000000000000000
[ 229.214401] R10: 0000000000000000 R11: ffffffff81a17d98 R12: 000000000000001d
[ 229.214401] R13: ffff8801470f46c0 R14: 0000000000000000 R15: 0000000000008000
[ 229.214401] FS: 0000000000000000(0000) GS:ffff88014fc00000(0000) knlGS:0000000000000000
[ 229.214401] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[ 229.214401] CR2: 0000000000000228 CR3: 000000013ceaa000 CR4: 00000000000406f0
[ 229.214401] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 229.214401] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
[ 229.214401] Process kworker/u:0 (pid: 5, threadinfo ffff880149714000, task ffff880149718000)
[ 229.214401] Call Trace:
[ 229.214401]
[ 229.214401] [] sci_change_state+0x4a/0x4f [isci]
[ 229.214401] [] sci_io_request_tc_completion+0x79c/0x7a0 [isci]
[ 229.214401] [] sci_controller_process_completions+0x14f/0x396 [isci]
[ 229.214401] [] ? spin_lock_irq+0xe/0x10 [isci]
[ 229.214401] [] isci_host_completion_routine+0x71/0x2be [isci]
[ 229.214401] [] ? mark_held_locks+0x52/0x70
[ 229.214401] [] tasklet_action+0x90/0xf1
[ 229.214401] [] __do_softirq+0xe5/0x1bf
[ 229.214401] [] ? hrtimer_interrupt+0x129/0x1bb
[ 229.214401] [] call_softirq+0x1c/0x30
[ 229.214401] [] do_softirq+0x4b/0xa3
[ 229.214401] [] irq_exit+0x53/0xb4
[ 229.214401] [] smp_apic_timer_interrupt+0x83/0x91
[ 229.214401] [] apic_timer_interrupt+0x13/0x20
[ 229.214401]
[ 229.214401] [] ? retint_restore_args+0x13/0x13
[ 229.214401] [] ? trace_hardirqs_off+0xd/0xf
[ 229.214401] [] ? vprintk+0x40b/0x452
[ 229.214401] [] printk+0x41/0x47
[ 229.214401] [] __dev_printk+0x78/0x7a
[ 229.214401] [] dev_printk+0x45/0x47
[ 229.214401] [] isci_terminate_request_core+0x15d/0x317 [isci]
[ 229.214401] [] isci_terminate_pending_requests+0x1a4/0x204 [isci]
[ 229.214401] [] ? sas_phye_oob_error+0xc3/0xc3 [libsas]
[ 229.214401] [] isci_remote_device_nuke_requests+0xa6/0xff [isci]
[ 229.214401] [] isci_remote_device_stop+0x7c/0x166 [isci]
[ 229.214401] [] ? sas_phye_oob_error+0xc3/0xc3 [libsas]
[ 229.214401] [] isci_remote_device_gone+0x76/0x7e [isci]
[ 229.214401] [] sas_notify_lldd_dev_gone+0x34/0x36 [libsas]
[ 229.214401] [] sas_unregister_dev+0x57/0x9c [libsas]
[ 229.214401] [] sas_unregister_domain_devices+0x36/0x65 [libsas]
[ 229.214401] [] sas_deform_port+0x72/0x1ac [libsas]
[ 229.214401] [] ? sas_phye_oob_error+0xc3/0xc3 [libsas]
[ 229.214401] [] sas_phye_loss_of_signal+0x3e/0x42 [libsas]Signed-off-by: Jeff Skirvin
Signed-off-by: Dan Williams
Signed-off-by: James Bottomley -
Add the appropriate definition and table entry for an additional adapter.
Signed-off-by: Wayne Boyer
Acked-by: Brian King
Signed-off-by: James Bottomley -
This patch validates sdev pointer in scsi_dh_activate before proceeding further.
Without this check we might see the panic as below. I have seen this
panic multiple times..Call trace:
#0 [ffff88007d647b50] machine_kexec at ffffffff81020902
#1 [ffff88007d647ba0] crash_kexec at ffffffff810875b0
#2 [ffff88007d647c70] oops_end at ffffffff8139c650
#3 [ffff88007d647c90] __bad_area_nosemaphore at ffffffff8102dd15
#4 [ffff88007d647d50] page_fault at ffffffff8139b8cf
[exception RIP: scsi_dh_activate+0x82]
RIP: ffffffffa0041922 RSP: ffff88007d647e00 RFLAGS: 00010046
RAX: 0000000000000000 RBX: 0000000000000000 RCX: 00000000000093c5
RDX: 00000000000093c5 RSI: ffffffffa02e6640 RDI: ffff88007cc88988
RBP: 000000000000000f R8: ffff88007d646000 R9: 0000000000000000
R10: ffff880082293790 R11: 00000000ffffffff R12: ffff88007cc88988
R13: 0000000000000000 R14: 0000000000000286 R15: ffff880037b845e0
ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0000
#5 [ffff88007d647e38] run_workqueue at ffffffff81060268
#6 [ffff88007d647e78] worker_thread at ffffffff81060386
#7 [ffff88007d647ee8] kthread at ffffffff81064436
#8 [ffff88007d647f48] kernel_thread at ffffffff81003fbaSigned-off-by: Babu Moger
Cc: stable@kernel.org
Signed-off-by: James Bottomley
30 Oct, 2011
24 commits
-
When controller lockup condition is detected,
we should fail all outstanding commands and disable
the controller. This will enable multipath solutions
to recover gracefully.Signed-off-by: Stephen M. Cameron
Signed-off-by: James Bottomley -
We weren't filling in the transfer length of the
flush cache command (it transfers 4 bytes of zeroes).
Firmware didn't seem to be bothered by this, but it
should be fixed.Signed-off-by: Stephen M. Cameron
Signed-off-by: James Bottomley -
The currentsd[] array in hpsa_update_scsi_devices had room for
256 devices. The code was iterating over however many physical
and logical devices plus an additional number of possible external
MSA2XXX controllers, which together could potentially exceed 256.We increased the size of the currentsd array to 1024 + 1024 + 32 + 1
elements to reflect a reasonable maximum possible number of devices
which might be encountered. We also don't just walk off the end
of the array if the array controller reports more devices than we
are prepared to handle, we just ignore the excessive devices.Signed-off-by: Scott Teel
Signed-off-by: Stephen M. Cameron
Signed-off-by: James Bottomley -
Rename HPSA_MAX_SCSI_DEVS_PER_HBA to HPSA_MAX_DEVICES
Signed-off-by: Scott Teel
Signed-off-by: Stephen M. Cameron
Signed-off-by: James Bottomley -
Signed-off-by: Stephen M. Cameron
Signed-off-by: James Bottomley -
Set the max hardware sectors in the SCSI host template to 8192
to allow for larger i/o's (8192 is the same limit the cciss
driver currently has.)Signed-off-by: Stephen M. Cameron
Signed-off-by: James Bottomley -
During heavy I/O (CPU-affinity mode enabled) and CLI/Agent
interactions, the driver would report periodic mailbox command
timeout statuses. Within the CPU-affinity ISR handler, the
driver should check the 'disable-msix-handshake' flag in deciding
whether or not to clear HCCRX_CLR_RISC_INT. The mode is not
specific to a dedicated queue, instead, applies to the current
'ha' context.Signed-off-by: Andrew Vasquez
Signed-off-by: Chad Dupuis
Signed-off-by: James Bottomley -
Size is 1st arg, not second.
Signed-off-by: Dave Jones
Signed-off-by: James Bottomley -
Signed-off-by: Bhanu Prakash Gollapudi
Signed-off-by: James Bottomley -
When SRR LS_ACC is dropped, the driver was not issuing ABTS for SRR when it
times out. Since the target received SRR, it was able to send the XFER_RDY and
the the original IO request completed successfully. In this condition ABTS was
not sent during bnx2fc_srr_compl(). Fix this by first checking for ELS timeout
and issue ABTS before checking if original IO request is complete.Signed-off-by: Bhanu Prakash Gollapudi
Signed-off-by: James Bottomley -
If the IO and the corresponding ABTS are not responded by a target, cleanup the
IO and issue explicit logout when ulp timer expires while waiting for ABTS to
complete. Wait for the session to be ready before returning to the SCSI layer.
If the session is not ready let the SCSI-ml escalate the error recovery.Signed-off-by: Bhanu Prakash Gollapudi
Signed-off-by: James Bottomley -
The call to complete() in st_scsi_execute_end() wakes up sleeping thread
in write_behind_check(), which frees the st_request, thus invalidating
the pointer to the associated bio structure, which is then passed to the
blk_rq_unmap_user(). Fix by storing pointer to bio structure into
temporary local variable.This bug is present since at least linux-2.6.32.
CC: stable@kernel.org
Signed-off-by: Petr Uzel
Reported-by: Juergen Groß
Reviewed-by: Jan Kara
Acked-by: Kai Mäkisara
Signed-off-by: James Bottomley -
Make sure that SCSI device removal via scsi_remove_host() does finish
all pending SCSI commands. Currently that's not the case and hence
removal of a SCSI host during I/O can cause a deadlock. See also
"blkdev_issue_discard() hangs forever if underlying storage device is
removed" (http://bugzilla.kernel.org/show_bug.cgi?id=40472). See also
http://lkml.org/lkml/2011/8/27/6.Signed-off-by: Bart Van Assche
Cc:
Signed-off-by: James Bottomley -
There is no reason to limit the SCSI disk namespace to sdXXX.
Add new error messages to sd_probe() in the unlikely event that either
ida_get_new() or sd_format_disk_name() fail.Signed-off-by: Dave Kleikamp
Signed-off-by: James Bottomley -
Bump driver vesion to 10.100.00.00
Signed-off-by: Nagalakshmi Nandigama
Signed-off-by: James Bottomley -
The driver was setting the action to MPI2_CONFIG_ACTION_PAGE_READ_CURRENT,
which only returns active volumes. In order to get info on inactive volumes,
the driver needs to change the action to
MPI2_RAID_PGAD_FORM_GET_NEXT_CONFIGNUM, and traverse each config till the
iocstatus is MPI2_IOCSTATUS_CONFIG_INVALID_PAGE returned.
Added a change in the driver to remove the instance of
sas_device object when the driver returns "1" from the slave_configure callback.
Also fixed code to report the hot spares to the operating system with a /dev/sg
assigned.Signed-off-by: Nagalakshmi Nandigama
Cc: stable@kernel.org
Signed-off-by: James Bottomley -
…lete while issued during creating a volume
This is due to the slave_configuration routine is getting called when
host reset is active, and config page reads are failing, and driver
attempts to added device with stale config data.To fix the issue, added error checking in slave_configure to check
for configuration pages failing, and return "1" so the device is
not configured. The config pages are failing if raid volume is
configured while issuing a host reset, thus driver is reading stale
data and proceeding to attempt to add. The fix is to return error
so the volume is not configured.Signed-off-by: Nagalakshmi Nandigama <nagalakshmi.nandigama@lsi.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com> -
This is due to driver reporting a device missing to the OS then the OS sending
a SYNC_CACHE request to driver while the IO queues are locked due to host reset.To fix the issue, the driver will be waking up the port enable context
immediately when the driver receives the reply message, instead of waiting
on the hot plug worker threads.Signed-off-by: Nagalakshmi Nandigama
Signed-off-by: James Bottomley -
Fix for dead lock occurring between host_lock and sas_device_lock.
The deadlock is between two spin locks, between the shost->host_lock
and driver ioc->sas_device_lock.The fix is to rearrange the code in the FW/Driver device removal
handshake so the ioc->sas_device_lock is not occurring when the
shost->host_lock is taken.[jejb: zero initialise sas_address to fix spurious compiler warning]
Signed-off-by: Nagalakshmi Nandigama
Signed-off-by: James Bottomley -
…while host reset is active
The fix is in the driver-firmware handshake device removal code. We
need to read the controller ioc_state to see if controller is OPERATIONAL
prior to sending target reset and OP_REMOVE. Previously it was checking
the flag ioc->shost_recovery flag, which is always set when host reset is
active, thus preventing drives from getting properly deleted.Signed-off-by: Nagalakshmi Nandigama <nagalakshmi.nandigama@lsi.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com> -
The fix is to inhibit the warning message in _scsih_get_sas_address
when the MPI2_IOCSTATUS_CONFIG_INVALID_PAGE ioc status is returned.Signed-off-by: Nagalakshmi Nandigama
Signed-off-by: James Bottomley -
Fix for issue : While discovery is in progress, hot unplug and hot plug of
enclosure connected to the controller card is causing system to hang.When a device is in the process of being detected at driver load time then
if it is removed, the device that is no longer present will not be added
to the list. So the code in _scsih_probe_sas() is rearranged as such so
the devices that failed to be detected are not added to the list.Signed-off-by: Nagalakshmi Nandigama
Cc: stable@kernel.org
Signed-off-by: James Bottomley -
New feature Fast Load Support.
(1)Asynchronous SCSI scanning: This will allow the drivers to scan
for devices in parallel while other device drivers are loading at
the same time. This will improve the amount of time it takes for the
OS to load.(2) Reporting Devices while port enable is active: This feature will
allow devices to be reported to OS immediately while port enable is
active. The previous implementation waits for port enable to complete,
and then report devices. This feature is only enabled on IT firmware
configurations when there are no boot device configured in BIOS Configuration
Utility, else the driver will wait till port enable completes reporting
devices. For IR firmware, this feature is turned off. This feature is to
address large SAS topologies (>100 drives) when the boot OS is using onboard
SATA device, in other words, the boot devices is not
connected to our controller.(3) Scanning for devices after diagnostic reset completes: A new routine
_scsih_scan_start is added. This will scan the expander pages, IR pages,
and sas device pages, then reporting new devices to SCSI Mid layer. It
seems the driver is not supporting adding devices while diagnostic reset
is active. Apparently this is due to the sanity checks on
ioc->shost_recovery flag throughout the context of kernel work thread FIFO,
and the mpt2sas_fw_work.Signed-off-by: Nagalakshmi Nandigama
Signed-off-by: James Bottomley -
1)Added ProxyVF_ID field to Configuration Request message.
2)Added IO Unit Page 8, IO Unit Page 9,and IO Unit Page 10.
3)Added SASNotifyPrimitiveMasks field to IOC Page 7.
4)Added SAS NOTIFY Primitive event.
5)Added Temperature Threshold Event.
6)Added Host Message Event.
7)Added Send Host Message request and reply.Signed-off-by: Nagalakshmi Nandigama
Signed-off-by: James Bottomley
29 Oct, 2011
2 commits
-
* git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi-misc-2.6: (204 commits)
[SCSI] qla4xxx: export address/port of connection (fix udev disk names)
[SCSI] ipr: Fix BUG on adapter dump timeout
[SCSI] megaraid_sas: Fix instance access in megasas_reset_timer
[SCSI] hpsa: change confusing message to be more clear
[SCSI] iscsi class: fix vlan configuration
[SCSI] qla4xxx: fix data alignment and use nl helpers
[SCSI] iscsi class: fix link local mispelling
[SCSI] iscsi class: Replace iscsi_get_next_target_id with IDA
[SCSI] aacraid: use lower snprintf() limit
[SCSI] lpfc 8.3.27: Change driver version to 8.3.27
[SCSI] lpfc 8.3.27: T10 additions for SLI4
[SCSI] lpfc 8.3.27: Fix queue allocation failure recovery
[SCSI] lpfc 8.3.27: Change algorithm for getting physical port name
[SCSI] lpfc 8.3.27: Changed worst case mailbox timeout
[SCSI] lpfc 8.3.27: Miscellanous logic and interface fixes
[SCSI] megaraid_sas: Changelog and version update
[SCSI] megaraid_sas: Add driver workaround for PERC5/1068 kdump kernel panic
[SCSI] megaraid_sas: Add multiple MSI-X vector/multiple reply queue support
[SCSI] megaraid_sas: Add support for MegaRAID 9360/9380 12GB/s controllers
[SCSI] megaraid_sas: Clear FUSION_IN_RESET before enabling interrupts
... -
* 'for-linus' of git://ceph.newdream.net/git/ceph-client:
libceph: fix double-free of page vector
ceph: fix 32-bit ino numbers
libceph: force resend of osd requests if we skip an osdmap
ceph: use kernel DNS resolver
ceph: fix ceph_monc_init memory leak
ceph: let the set_layout ioctl set single traits
Revert "ceph: don't truncate dirty pages in invalidate work thread"
ceph: replace leading spaces with tabs
libceph: warn on msg allocation failures
libceph: don't complain on msgpool alloc failures
libceph: always preallocate mon connection
libceph: create messenger with client
ceph: document ioctls
ceph: implement (optional) max read size
ceph: rename rsize -> rasize
ceph: make readpages fully async
