- 29 Oct, 2009 40 commits
-
-
Kashyap, Desai authored
Bump version 3.04.13. Signed-off-by:
Kashyap Desai <kashyap.desai@lsi.com> Signed-off-by:
James Bottomley <James.Bottomley@suse.de>
-
Kashyap, Desai authored
Errata: Certain conditions on the scsi bus may casue the 53C1030 to incorrectly signal a SCSI_DATA_UNDERRUN to the host. Workaround 1: For an Errata on LSI53C1030 When the length of request data and transfer data are different with result of command (READ or VERIFY), DID_SOFT_ERROR is set. Workaround 2: For potential trouble on LSI53C1030. It is checked whether the length of request data is equal to the length of transfer and residual. MEDIUM_ERROR is set by incorrect data. Signed-off-by:
-
Kashyap, Desai authored
Signed-off-by:
-
Yang, Bo authored
Signed-off-by Bo Yang<bo.yang@lsi.com> Signed-off-by: -
Yang, Bo authored
use the constant MEGASAS_RESET_WAIT_TIME when waiting for firmware commands to complete (currently 3 minutes). Signed-off-by Bo Yang<bo.yang@lsi.com> Signed-off-by: -
Yang, Bo authored
The current sense pointer is cast to a u32 pointer, which can truncate on 64 bits. Fix by using unsigned long instead. Signed-off-by Bo Yang<bo.yang@lsi.com> Cc: stable@kernel.org Signed-off-by: -
Yang, Bo authored
Driver will update the OS devices after adding and deleting the device from FW. When driver receive add or delete AEN from FW, driver will send the DCMD cmd to get the System PD list from FW. Then driver will check if this device already in the OS: If add event and OS don't have the device (but it is in the list), driver add the device to OS, otherwise driver will not add. If remove event, driver will check the list, if is not in the list, but OS have the device, driver will remove the device. Signed-off-by Bo Yang<bo.yang@lsi.com> Signed-off-by: -
Yang, Bo authored
Add a lock to the skinny firmware initialisation sequence to prevent the two stage write being non atomic if multiple instances use it. Add a flag to the driver shutdown sequence to prevent aen ioctls being called after shutdown begins. Signed-off-by Bo Yang<bo.yang@lsi.com> Signed-off-by: -
Yang, Bo authored
To increase the performance, megaraid sas driver added the IEEE SGE support to support SAS2 controller. Signed-off-by Bo Yang<bo.yang@lsi.com> Signed-off-by: -
Yang, Bo authored
MegaRAID SAS2 controller ioctl can't use 32 cmd for applications. Driver need to divide different number of cmds to IO and application. Signed-off-by Bo Yang<bo.yang@lsi.com> Signed-off-by: -
Yang, Bo authored
When OS issue inquiry, it will check driver's internal pd_list. Signed-off-by Bo Yang<bo.yang@lsi.com> Signed-off-by: -
Yang, Bo authored
Add system PDs to OS. Driver implemented the get_pd_list function to get the system PD from FW. Signed-off-by Bo Yang<bo.yang@lsi.com> Signed-off-by: -
Yang, Bo authored
Add the new megaraid sas 2 controller to the driver. megaraid sas2 is LSI next generation SAS products. driver add the interface to support this product. Signed-off-by Bo Yang<bo.yang@lsi.com> Signed-off-by: -
Yang, Bo authored
update the sysfs parameter to tell application driver support AEN poll Signed-off-by Bo Yang<bo.yang@lsi.com> Signed-off-by: -
Yang, Bo authored
Add Poll_wait mechanism to SAS-2 MegaRAID SAS Linux driver. Driver will wakeup poll after the driver get event from MegaRAID SAS FW. Signed-off-by Bo Yang<bo.yang@lsi.com> Signed-off-by: -
Yang, Bo authored
Add the Tape drive fix to the megaraid_sas driver: If the command is for the tape device, set the FW pthru timeout to the os layer timeout value. Signed-off-by Bo Yang<bo.yang@lsi.com> Signed-off-by: -
Kashyap, Desai authored
Bump version to 03.100.03.00 Signed-off-by:
Eric Moore <Eric.moore@lsi.com> Signed-off-by:
-
Kashyap, Desai authored
(1) target resets are sending link change rate events with no link rate change -> thus said the driver was modified so when there is no link rate change, we don't need to call mpt2sas_transport_update_links nor _scsih_ublock_io_device. (2) There were changes made in _scsih_sas_topology_change_event_debug to change the debug strings so they are more clear. Also the link rate change information was added to display the new and previous link rate. for the MPI2_EVENT_SAS_TOPOLOGY_CHANGE_LIST event when the ExpStatus is set to zero, display "responding" instead of "unknown status". Signed-off-by:
-
Kashyap, Desai authored
(1) Added new function _scsih_ir_shutdown. This function will issue the MPI2_RAID_ACTION_SYSTEM_SHUTDOWN_INITIATED request via MPI2_FUNCTION_RAID_ACTION. The function will wait 10 seconds for reply message frame, then print out the ioc status and loginfo. This function is only called when there are raid volumes present. (2) Add shutdown callback in the struct pci_driver object scsih_driver. This will be called only when the system is shutting down. From this function, we will call _scsih_ir_shutdown mentioned above. (3) Add support in _scsih_remove to call _scsih_ir_shutdown. The function _scsih_remove will be called when the driver is unloaded (and system is still running). scsih internal command contex is added to send internal message frames from mpt2sas_scsih.c. Signed-off-by:
-
Kashyap, Desai authored
When receiving the MPI2_EVENT_SAS_DEV_STAT_RC_INTERNAL_DEVICE_RESET event, the driver will set the tm_busy flag in the sdev private host data, When tm_busy flag is set, the driver will return SCSI_MLQUEUE_DEVICE_BUSY, effectly freezing the IO to the device. The tm_busy flag is cleared with the MPI2_EVENT_SAS_DEV_STAT_RC_CMP_INTERNAL_DEV_RESET event. Signed-off-by:
-
Kashyap, Desai authored
(1) EEDP(End to End data protection) was not working. This was due to not setting EEDP BlockSize and Flags to little endian format in the message frame. (2) Some expander sysfs attributes were not getting set properly. The sas format was not getting set due to endian issues with sas_format field in the struct rep_manu_reply. Since sas_format was not set properly, the component_vendor_id, component_revision_id, and component_id were not set. (3) In _transport_smp_handler: we don't need to convert the smid from little endian to cpu prior to calling mpt2sas_base_free_smid, because its allready in cpu format. (4) Some loginfos and ioc status were not xonverted from little endian to cpu. Signed-off-by:
-
Kashyap, Desai authored
cpu_to_le64 when calculating the physical dma address. This will properly handle endianess on big endian systems. The return value of this function was changed from dma_addr_t to __le64. Remove the typecasting of u32 when setting the SenseBufferLowAddress, since its already in __le32 format. Signed-off-by:
-
Kashyap, Desai authored
[SCSI] mpt2sas: Return DID_TRANSPORT_DISRUPTED in nexus loss,SCSI_MLQUEUE_DEVICE_BUSY if device is busy 1 Its observed that the OS was sending request to the driver after it had been put into blocking state, so the driver was modified to return SCSI_MLQUEUE_DEVICE_BUSY. 2. Driver will return DID_TRANSPORT_DISRUPTED when sdev is haivng nexus loss. This occurrs when sdev is blocked, between the MPI2_EVENT_SAS_TOPO_RC_DELAY_NOT_RESPONDING and MPI2_EVENT_SAS_TOPO_RC_TARG_NOT_RESPONDING events. Signed-off-by:
-
Kashyap, Desai authored
The driver needs to retrieve the ioc facts prior to putting the controller into READY state. The current design is calling ioc facts after putting the controller into READY state, which means the driver is sending a diag reset instead of message unit reset becuase the capability information is not yet available. Signed-off-by:
-
Kashyap, Desai authored
(1) for the MPI2_EVENT_IR_OPERATION_STATUS event, add support to print "background init" or "make data consistent" for debugging purposes. If the RAIDOperation is set to a value not defined, then don't print anything (2) for the MPI2_EVENT_SAS_DEVICE_STATUS_CHANGE event, add support to print "expander reduced functionality" and "expander reduced functionality complete", which are new events. Signed-off-by:
-
Kashyap, Desai authored
Added sanity check in _scsih_change_queue_depth to limit the max_depth to 32 for SATA devices. This is only for physical devices not part of a volume. Signed-off-by:
-
Kashyap, Desai authored
Added support to set the TimeStamp when sending ioc_init. Signed-off-by:
-
Kashyap, Desai authored
Added tests for registry entries of EXBuffSize, EXImmed, and EXType to support the new Extended diag buffer type. Modified code where necessary to handle the new ExtendedType field in the F/W diagnostic Post and Release messages. Signed-off-by:
-
Kashyap, Desai authored
Added command line option diag_buffer_enable. When the command line option is set, the driver will automatically post diag buffers at driver load time. The command line option diag_buffer_enable is bitwise, so it's possible to enable both and/or snapshot + trace buffers. For trace, the driver will allocate 1MB buffer, whereas for snapshot its 2MB. The purpose for this is so the enduser doesn't have to manually use an application to setup diag buffers for debugging firmware related issues. Here is some examples trace: # insmod mpt2sas.ko diag_buffer_enable=1 snapshot: # insmod mpt2sas.ko diag_buffer_enable=2 both trace and snapshot: # insmod mpt2sas.ko diag_buffer_enable=3 Signed-off-by:
-
Kashyap, Desai authored
Fixed some of the comments sections for some of the function so "@ioc: pointer to scsi command object" was changed to "@ioc: per adapter object" Signed-off-by:
-
Kashyap, Desai authored
Added command line option and shost sysfs attribute called mpt2sas_fwfault_debug. When enduser writes a "1" to this parameter, this will enable support in the driver for debugging firmware timeout related issues. This handling was added in three areas (a) scsi error handling callback called task_abort, (b) IOCTL interface, and (c) other timeouts that result in diag resets, such as manufacturing config pages. When this support is enabled, the driver will provide dump_stack to console, halt controller firmware, and panic driver. The end user probably would want to setup serial console redirection so the dump stack can be seen. Here are the three methods for enable this support: (a) # insmod mpt2sas.ko mpt2sas_fwfault_debug=1 (b) # echo 1 > /sys/module/mpt2sas/parameters/mpt2sas_fwfault_debug (c) # echo 1 > /sys/class/scsi_host/host#/fwfault_debug (where # is the host number) Signed-off-by:
-
Kashyap, Desai authored
The new headers contain the following changes: (1) Added IO Unit Page 7. (2) Added new device ids for SAS2208. (3) Added SAS IO Unit Page 5. (4) Added partial and slumber power management capable flags to SAS Device Page 0 Flags field. (5) Added PhyInfo defines for power condition. (6) Added Ethernet configuration pages. Signed-off-by: -
Kashyap, Desai authored
Added device ids range for { 0x80 - 87 } , modified mpi/mpi2_cnfg.h containing MPI2_MFGPAGE_DEVID_SAS2208_X. Signed-off-by: -
Kashyap, Desai authored
Add support in the driver to check for valid response info in the scsi state, then check to see if the response code is MPI2_SCSITASKMGMT_RSP_INVALID_FRAME; when this condition occurrs, the driver will return DID_SOFT_ERROR. A return code of DID_SOFT_ERROR will result in a retry at the scsi-mid layer level. An additional change added to obtain the response code from the 1st byte of the response info instead of last. Signed-off-by:
-
Kashyap, Desai authored
This handles the case where driver receives a expander removal event while it is in the middle of processing an expander add event. The existing implementation will stop processing futher device adds when a expander delete arrives on top of add expander add. Due to a sanity check in the driver, the devices there were not added, were never handshaked to firmware with the device removal handshake protocal. Since the driver didnt' do the handshake, the controller never provide further add events. To fix this issue, the sanity check was removed so the driver will always do the device removal handshake protocal. Signed-off-by:
-
Kashyap, Desai authored
The device driver was not handling updating device handles in all cases across diag resets. To fix this issue, the driver is converted to using sas address instead of handle as a lookup reference to the parent expander or sas_host. Also, for both expanders and sas host, the phy handle will be one unique handle. In the sas host case, the phy handle can be different for every phy, so the change is to set the handle to the handle of the first phy; every phy will be one single sas address(phy 0) instead of a different sas address for every phy(previous implementation). So making one consistent sas address for all the direct attachedports to the sas host, will make it better user experience when using udev /dev/disk/by-path dev nodes Signed-off-by:
-
git://git.kernel.org/pub/scm/linux/kernel/git/davem/ide-2.6Linus Torvalds authored
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/ide-2.6: ide: Serialize CMD643 and CMD646 to fix a hardware bug with SSD
-
git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6Linus Torvalds authored
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6: (43 commits) net: Fix 'Re: PACKET_TX_RING: packet size is too long' netdev: usb: dm9601.c can drive a device not supported yet, add support for it qlge: Fix firmware mailbox command timeout. qlge: Fix EEH handling. AF_RAW: Augment raw_send_hdrinc to expand skb to fit iphdr->ihl (v2) bonding: fix a race condition in calls to slave MII ioctls virtio-net: fix data corruption with OOM sfc: Set ip_summed correctly for page buffers passed to GRO cnic: Fix L2CTX_STATUSB_NUM offset in context memory. MAINTAINERS: rt2x00 list is moderated airo: Reorder tests, check bounds before element mac80211: fix for incorrect sequence number on hostapd injected frames libertas spi: fix sparse errors mac80211: trivial: fix spelling in mesh_hwmp cfg80211: sme: deauthenticate on assoc failure mac80211: keep auth state when assoc fails mac80211: fix ibss joining b43: add 'struct b43_wl' missing declaration b43: Fix Bugzilla #14181 and the bug from the previous 'fix' rt2x00: Fix crypto in TX frame for rt2800usb ...
-
git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpuLinus Torvalds authored
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu: sched: move rq_weight data array out of .percpu percpu: allow pcpu_alloc() to be called with IRQs off
-
git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-param-fixesLinus Torvalds authored
* git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-param-fixes: param: fix setting arrays of bool param: fix NULL comparison on oom param: fix lots of bugs with writing charp params from sysfs, by leaking mem.
-
