- 28 7月, 2010 11 次提交
-
-
由 Kashyap, Desai 提交于
Add support to display additional debug info for SCSI_IO and RAID_SCSI_IO_PASSTHROUGH sent from the normal entry queued entry point, as well as internal generated commands, and IOCTLS. The additional debug info included the phy number, as well as the sas address, enclosure logical id, and slot number. This debug info has to be enabled thru the logging_level command line option, by default this will not be displayed. Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
由 Kashyap, Desai 提交于
Converting print level from MPT2SAS_DEBUG_FMT to MPT2SAS_INFO_FMT. Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
由 Kashyap, Desai 提交于
Added support so the diag ring buffer can be pulled via sysfs Added three new shost attributes: host_trace_buffer, host_trace_buffer_enable, and host_trace_buffer_size. The host_trace_buffer_enable attribute is used to either post or release the trace buffers. The host_trace_buffer_size attribute contains the size of the trace buffer. The host_trace_buffer atttribute contains a maximum 4KB window of the buffer. In order to read the entire host buffer, you will need to write the offset to host_trace_buffer prior to reading it. release the host buffer, then write the entire host buffer contents to a file. In addition to this enhancement, we moved the automatic posting of host buffers at driver load time to be called prior to port_enable, instead of after. That way discovery is available in the host buffer. Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
由 Kashyap, Desai 提交于
Updating MPI header version N. Removed mpi_history.txt. Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
由 Kashyap, Desai 提交于
Added a new sysfs shost attribute called ioc_reset_count. This will keep count of host resets (both diagnostic and message unit). Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
由 Kashyap, Desai 提交于
Added support to send link resets, hard resets, enable/disable phys, and changing link rates for for expanders. This will be exported to attributes within the sas transport layer. A new wrapper function was added for sending SMP passthru to expanders for phy control. Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
由 Kashyap, Desai 提交于
Added support to retrieve the invalid_dword_count, running_disparity_error_count, loss_of_dword_sync_count, and phy_reset_problem_count for expanders. This will be exported to attributes within the sas transport layer. A new wrapper function was added for sending SMP passthru to retrieve the expander phy error log. Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
由 Kashyap, Desai 提交于
Added command line option called disable_discovery. When enabled on the command line, the driver will not send a port_enable when loaded for the first time. If port_enable is not called, then there is no discovery of devices, as well as the sas topology. Then later if one desires to invoke discovery, then they will need to issue a diagnostic reset. A diagnostic reset can be issued various ways. One of the way is throught sysfs. Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
由 Kashyap, Desai 提交于
Driver should not allow multiple host reset when already host reset is in progress. It is possible that host reset was sent by scsi mid layer while there was already an host reset active, either issued via IOCTL interface or internaly, like a config page timeout. Since there was a host reset active, the driver would return a FAILED response to the scsi mid layer. The solution is make sure pending host resets will wait for the active host reset to complete before returning control back up the call stack. Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
由 Kashyap, Desai 提交于
[SCSI] mpt2sas: Fix to use sas device list instead of enclosure list for _transpor_get_enclosure_identifier. Enclosure_identifier not being returned by mpt2sas The driver exports callback function to the sas transport layer for obtaining the enclosure logical id. This function is called _transport_get_enclosure_identifier. The driver was searching the wrong list for the enclosure_identifier. The driver should be searching the sas device list instead of enclosure list. The sas address that is passed to the driver is for the end device, not enclosure. Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
由 Eric Moore 提交于
Adding DIF Type 2 protection support, as well as turning on 32 byte cdb's, and setting the cdb length for > 16 byte in the SCSI_IO->control parameter. Signed-off-by: NMartin Petersen <martin.petersen@oracle.com> Signed-off-by: NEric Moore <eric.moore@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
- 25 5月, 2010 1 次提交
-
-
由 Alexey Dobriyan 提交于
- C99 knows about USHRT_MAX/SHRT_MAX/SHRT_MIN, not USHORT_MAX/SHORT_MAX/SHORT_MIN. - Make SHRT_MIN of type s16, not int, for consistency. [akpm@linux-foundation.org: fix drivers/dma/timb_dma.c] [akpm@linux-foundation.org: fix security/keys/keyring.c] Signed-off-by: NAlexey Dobriyan <adobriyan@gmail.com> Acked-by: NWANG Cong <xiyou.wangcong@gmail.com> Signed-off-by: NAndrew Morton <akpm@linux-foundation.org> Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
-
- 12 4月, 2010 9 次提交
-
-
由 Kashyap, Desai 提交于
Upgrade version to 05.100.00.02 Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
由 Kashyap, Desai 提交于
Fix a oops in _scsih_sas_device_remove. The driver was attempting to delete a object from the sas_device link list when the object was not present. Added sanity check for sas_device NULL dereference. before deleting sas_device now driver will search device in list then only it will follow device removal. Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
由 Kashyap, Desai 提交于
we added support to set the deleted flag prior to device scan, then clear the flag for responding devices, leaving the deleted flag only set for missing devices. The problem is for internal generated host resets, IO queues are not blocked at scsi mid layer level. IO will be continued sent to driver, and driver will return SCSI_MLQUEUE_HOST_BUSY. The problem is the driver checks for the deleted flag before it checks for the controller being in reset, so there is a window where the driver would be returning DID_NO_CONNECT for responding devices. This occurs during the time between calling _scsih_prep_device_scan, and _scsih_mark_responding_sas_device & _scsih_mark_responding_raid_device. Fix the queuecommand entry point so ioc->shost_recovery flag sanity check is given higher presidence then the device "deleted flag" check. Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
由 Kashyap, Desai 提交于
Upgraded version string. Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
由 Kashyap, Desai 提交于
Added check before free_pages just to make sure ioc->scsi_lookup is not NULL. Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
由 Kashyap, Desai 提交于
Added support in the driver to support EEH and PCIe Advanced Error Recovery. This involves adding new pci_error_handler interface for recovering the controller from PCI Bus errors, such as SERR and PERR. Some tools are available for simulating PCI errors in order to validate this interface: http://www.kernel.org/pub/linux/utils/pci/aer-injectSigned-off-by: NKashyap Desai <kashyap.desai@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
由 Kashyap, Desai 提交于
RAID_SCSI_IO_PASSTHROUGH: Driver needs to be sending the default descriptor for RAID Passthru, currently its sending SCSI_IO descriptor. Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
由 Kashyap, Desai 提交于
There are few special cases which needs to be handled deleting old port. CASE1: In topology you need cascaded expanders. Through sysfs just make sure topology is up. Erase the manufacturing image of the cascaded expander and reset the board. In some cases Adapter will receive Exapnder Add event before expander delete. In such a case, driver needs to delete duplicate port before adding new port. CASE2: Enable Device Missing delay of HBA through lsiutils. If expander or end device is hotswapped with different device before DMD timer expires, driver will get device add for new device first and then device deletion event for the original devices will arrive later at DMD timer expires. In this case also driver need to delete duplicate port before adding port for new device. Added new function which will make sure when new port is added, that its not claiming the same phy resources already in use by another port. If it does, then it will delete the other port before adding the new port. Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
由 Kashyap, Desai 提交于
After Host Reset firmware will have new list of device handles for the target. Device handle refresh in driver is part of Rescan topology logic. (See functions like *_search_responding_*). This needs to be done from Host Reset context before making shost_recovery to 0. Currently it is done in Firwmare event context, which may leads IO to a wrong device. Now handler refresh is moved to HBA reset context. Apart from this, Now driver will stop IOs for all device setting deleted flag to 1 at the time of HBA Reset through _scsih_prep_device_scan. It will only unblock devices, if devices has been found as part of RESCAN. This way it will make more safe IO blocking at the time of HBA reset at mpt2sas driver layer. Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
- 11 4月, 2010 18 次提交
-
-
由 Kashyap, Desai 提交于
Upgraded version string. Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
由 Kashyap, Desai 提交于
Copyright changes for year 2010. Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
由 Kashyap, Desai 提交于
RAID_SCSI_IO_PASSTHROUGH: Driver needs to be send the default descriptor for RAID Passthru, currently its sending SCSI_IO descriptor. Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
由 Kashyap, Desai 提交于
Added proper return type values in case memory allocation failed. Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
由 Kashyap, Desai 提交于
Removed all the mutex's for ioc->tm_cmds.mutex, then created one single mutex inside the function mpt2sas_scsih_issue_tm. This is the single function used when sending task management. Also the sanity checks required for scsi mid layer escalation were moved to inside the same function because these checks need to be done while the mutex is held. The ioc->tm_cmds.mutex inside the IOCTL branch is really not required since there is another mutex in this code called for ctl_cmds handling this sync. Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
由 Kashyap, Desai 提交于
1. Fixes for little endian issues. 2. Now Debug info for Discovery event is more readable. Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
由 Kashyap, Desai 提交于
Now Driver will not treat NEEDS_INIT as failure. In addition to this, the driver will now display message to describe the the access flags when bits are set, so the end user can better understand failures. Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
由 Kashyap, Desai 提交于
Aded checks for shost_recovery flag for early return from function. Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
由 Kashyap, Desai 提交于
use the get_free_pages API for larger contigious physical memory chunk. Also, the ioc->chain_depth need to be changed from a 16bit to 32bit variable because the number of chains will exceed 64k when the queue depth is large. Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
由 Kashyap, Desai 提交于
bug fix in the handling of the internal device reset event The reason code check in scsih_sas_device_status_change_event never evaluates as true for internal device reset, hence driver never quiesce s IO when firmware is sending a device reset. The fix is to change the evaluate to: if (event_data->ReasonCode != MPI2_EVENT_SAS_DEV_STAT_RC_INTERNAL_DEVICE_RESET && event_data->ReasonCode != MPI2_EVENT_SAS_DEV_STAT_RC_CMP_INTERNAL_DEV_RESET) return; Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
由 Kashyap, Desai 提交于
incorrect timestamp on 32 bit platforms: The upper 32 bit of the timestamp was getting truncated when converting seconds to milliseconds, which was due to the variable being long. To fix the problem, the variable needs to be u64. Also the microseconds conversion to milliseconds was incorrect; it should be divide by 1000 instead of divide by 8. Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
由 Kashyap, Desai 提交于
[SCSI] mpt2sas : Do not reset handle before calling _scsih_remove_device in RESCAN task after HBA RESET Setting handle to zero is not required before _scsih_remove_device. Driver uses sas_device->handle reference in _scsih_remove_device. Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
由 Richard A Lary 提交于
This patch replaces incorrect base address space flag with correct IO resource flag. Also, performs check of memory resource to validate resource before using. Signed-off-by: NRichard A Lary <rlary@linux.vnet.ibm.com> Acked-by: N"Desai, Kashyap" <Kashyap.Desai@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
由 Kashyap, Desai 提交于
external host not connecting after controller reboot: The problem is : devices are not coming back after having the cable disconnected then reconnected. The problem is because the driver/firmware device removal handshake is failing. Due to this failure, the controller firmware is not sending out device add events when the target is reconnected. This is root caused to a race in the driver/firmware device removal algorithm. There is duplicate code in both interrupt and user context; where target reset is being issue from user context path while sas_iounit_control(OP_REMOVE) is being sent from interrupt context. An active target_reset will fail the OP_REMOVE. To fix this problem, the duplicate code has been removed from user context path. Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
由 Kashyap, Desai 提交于
Upgraded version string. Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com> Reviewed-by: NEric Moore <eric.moore@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
由 Kashyap, Desai 提交于
modified _scsih_sas_device_find_by_handle so to handle the search on both list(device list and device_init_list) Also, we moved the priority of the search so the ioc->sas_device_list is done first. The "sas_device_init_list" is only used during the 1st port enable, so its unlikely there’s devices on it. Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com> Reviewed-by: NEric Moore <eric.moore@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
由 Kashyap, Desai 提交于
Add the cancel_pending_work flag from the fw_event_work structure, and then to set the flag during host reset, check the flag later from work threads context and if cancel_pending_work_flag is set ingore those events. Now Rescan after host reset is changed. Added special task MPT2SAS_RESCAN_AFTER_HOST_RESET. This task will be queued at the time of HBA reset. this task is treated as barrier. All work after MPT2SAS_RESCAN_AFTER_HOST_RESET will be treated as new work and will be server by callback handle. If host_recovery is going on while running RESCAN task, it will wait for shos_recovery_done completion which will be called from HBA reset DONE context. Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com> Reviewed-by: NEric Moore <eric.moore@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
由 FUJITA Tomonori 提交于
scsi_dma_map() returns -1 if an error occurred (zero means that the command has no data). So the following current code can't catch an error: sges_left = scsi_dma_map(scmd); if (!sges_left) { sdev_printk(KERN_ERR, scmd->device, "pci_map_sg" " failed: request for %d bytes!\n", scsi_bufflen(scmd)); return -ENOMEM; } Signed-off-by: NFUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Acked-by: N"Desai, Kashyap" <Kashyap.Desai@lsi.com> Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>
-
- 30 3月, 2010 1 次提交
-
-
由 Tejun Heo 提交于
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: NTejun Heo <tj@kernel.org> Guess-its-ok-by: NChristoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
-