Return value check of atomic_dec_if_positive is required as it returns
old value minus one. Without this fix, driver will send small ios to
firmware path and that will be a performance issue.
Not critical, but good to have r1_ldio_hint as default value in sdev
private.
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
When building with a dma_addr_t that is different from pointer size, we
get this warning:
drivers/scsi/megaraid/megaraid_sas_fusion.c: In function 'megasas_make_prp_nvme':
drivers/scsi/megaraid/megaraid_sas_fusion.c:1654:17: error: cast to pointer from integer of different size [-Werror=int-to-pointer-cast]
It's better to not pretend that the dma address is a pointer and instead
use a dma_addr_t consistently.
Fixes: 33203bc4d6 ("scsi: megaraid_sas: NVME fast path io support")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Sumit Saxena <sumit.saxena@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
For RAID1 FastPath writes, driver needs to allocate extra commands
internally to accommodate for the extra peer command being sent.
Currently driver is allocating 2 extra commands for each but only one
extra command is necessary. Set RAID_1_10_RMW_CMDS to 2 and also change
macro name to RAID_1_PEER_CMDS.
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Fix indentation issues and smatch warning reported by Dan Carpenter
for previous series as discussed below.
http://www.spinics.net/lists/linux-scsi/msg103635.htmlhttp://www.spinics.net/lists/linux-scsi/msg103603.html
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Sasikumar Chandrasekaran <sasikumar.pc@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Fix - increase internal command pool to 8.
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
FIX - Do not use random delay to synchronize with IRQ. Use kernel API.
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Code refactoring to build_mpt_mfi_pass_thru to return void.
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Error handling: If controller reset is not able to recover, kill HBA and
quit immediately.
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
FIX - firmware wants non-RW SYS PD IOs to avoid FastPath for better
tracking and other functionalities if the device is task management
capable.
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Fix to account for the reply_q_sz not exceeding the maximum commands
that the firmware can support, instance->max_fw_cmds is already
decremented in megasas_fusion_update_can_queue(). Remove the extra
decrement logic in code.
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Minor Optimization: No need to update HBA can_queue value if the current
max FW commands is equal to earlier value.
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Since maximum supported FW commands are all defined as u16, change
all local variables referring to max_cmd from u32 to u16.
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Fix endiannes fixes for Ventura specific.
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Fix if RDPQ mode enabled MR FW is deployed on big endian host machine,
driver does not setup reply address correctly.
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Change MR_TargetIdToLdGet return type from u8 to u16.
ld id range check is added at two places in this patch -
@megasas_build_ldio_fusion and @megasas_build_ld_nonrw_fusion. Previous
driver code used different data type for lds TargetId returned from
MR_TargetIdToLdGet. Prior to this change, above two functions was
safeguarded due to function always return u8 and maximum value of ld id
returned was 255.
In below check, fw_supported_vd_count as of today is 64 or 256 and valid
range to support is either 0-63 or 0-255. Ideally want to filter
accessing raid map for ld ids which are not valid. With the u16 change,
invalid ld id value is 0xFFFF and we will see kernel panic due to random
memory access in MR_LdRaidGet. The changes will ensure we do not call
MR_LdRaidGet if ld id is beyond size of ldSpanMap array.
if (ld < instance->fw_supported_vd_count)
>From firmware perspective,ld id 0xFF is invalid and even though current
driver code forward such command, firmware fails with target not
available.
ld target id issue occurs mainly whenever driver loops to populate raid
map (ea. MR_ValidateMapInfo). These are the only two places where we
may see out of range target ids and wants to protect raid map access
based on range provided by Firmware API.
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Currently fusion context has fixed array load_balance_info. Use dynamic
allocation. In few places, driver do not want physically contigious
memory. Attempt to use vmalloc if physical contiguous memory is not
available.
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Add additional logging from driver in OCR context.
Add debug logs for partial completion of IOs is iodone context.
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Fixing issue of not setting residual bytes correctly.
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Avoid Host side PCI bandwidth bottleneck and hint FW to do Write
buffering using RaidFlag MR_RAID_FLAGS_IO_SUB_TYPE_LDIO_BW_LIMIT. Once
IO is landed in FW with MR_RAID_FLAGS_IO_SUB_TYPE_LDIO_BW_LIMIT, it will
do single DMA from host and buffer the Write operation. On back end, FW
will DMA same buffer to the Mirror and Data Arm. This will improve
large block IO performance which bottleneck due to Host side PCI
bandwidth limitation.
Consistent ~4000MB T.P for 256K Block size is expected performance
numbers. IOPS for small Block size should be on par with Disk
performance. (E.g 42 SAS Disk in JBOD mode gives 3700MB T.P. Same
Drive used in R1 WT mode, should give ~1800MB T.P)
Using this patch 24 R1 VDs (HDD) gives below performance for Sequential
Write. Without this patch, we cannot reach above 3200MB (Throughput is
in MB.)
Block Size 50% 256K and 50% 4K 100% 256K
4K 3100 2030
8K 3140 2740
16K 3140 3140
32K 3400 3240
64K 3500 3700
128K 3870 3870
256K 3920 3920
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
This patch provide true fast path IO support. Driver creates PRP for
NVME drives and send Fast Path for performance. Certain h/w requirement
needs to be taken care in driver.
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Adding detection logic for NVME device attached behind Ventura
controller. Driver set HostPageSize in IOC_INIT frame to inform about
page size for NVME devices. Firmware reports NVME page size to the
driver. PD INFO DCMD provide new interface type NVME_PD. Driver set
property of NVME device.
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
With the changes to remove checks for a valid request descriptor,
issue_dcmd will now always return DCMD_SUCCESS. This patch changes
return type of issue_dcmd to void and change all callers appropriately.
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
No functional change. Code clean up. Removing error code which is not
valid scenario. In megasas_get_request_descriptor we can remove the
error handling which is not required. With fusion controllers, if there
is a valid message frame available, we are guaranteed to get a
corresponding request descriptor.
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Moving to use DID_REQUEUE return type for reliable unconditional
retries. Driver wants unconditional re-queue, so replace DID_RESET with
DID_REQUEUE
Discussed below -
https://www.spinics.net/lists/linux-scsi/msg102848.html
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
No functional change. Code refactor.
megasas_fire_cmd_fusion can always use 32 bit descriptor write for
ventura. No need to pass extra flag. Only IOC INIT required 64 bit
Descriptor write.
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
No functional change. Code refactor.
Remove function megasas_fpio_to_ldio as we never require to convert fpio
to ldio because of frame unavailability. Grab extra frame of raid 1
write fast path before it creates first frame as Fast Path. Removed
is_raid_1_fp_write flag as raid 1 write fast path command is decided
using r1_alt_dev_handle only. Move resetting megasas_cmd_fusion fields
at common function megasas_return_cmd_fusion.
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
No functional change. Code refactor.
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
This reverts commit "3e5eadb1a881" ("scsi: megaraid_sas: Enable or
Disable Fast path based on the PCI Threshold Bandwidth")
This patch was aimed to increase performance of R1 Write operation for
large IO size. Since this method used timer approach, it turn on/off
fast path did not work as expected. Patch 0013 describes new algorithm
and performance number.
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Update Linux driver to use new pdTargetId field for JBOD target ID
Signed-off-by: Sasikumar Chandrasekaran <sasikumar.pc@broadcom.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
ldio outstanding variable needs to be decremented in io completion path for
iMR dual queue depth
Signed-off-by: Sasikumar Chandrasekaran <sasikumar.pc@broadcom.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Large SEQ IO workload should sent as non fast path commands
Signed-off-by: Sasikumar Chandrasekaran <sasikumar.pc@broadcom.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
The Megaraid driver has to support the SAS3.5 Generic Megaraid Controllers Firmware functionality.
Signed-off-by: Sasikumar Chandrasekaran <sasikumar.pc@broadcom.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
SAS3.5 Generic Megaraid Controllers FW will support new dynamic RaidMap to have different
sizes for different number of supported VDs.
Signed-off-by: Sasikumar Chandrasekaran <sasikumar.pc@broadcom.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
To improve RAID 1/10 Write performance, OS drivers need to issue the
required Write IOs as Fast Path IOs (after the appropriate checks
allowing Fast Path to be used) to the appropriate physical drives
(translated from the OS logical IO) and wait for all Write IOs to complete.
Design: A write IO on RAID volume will be examined if it can be sent in
Fast Path based on IO size and starting LBA and ending LBA falling on to
a Physical Drive boundary. If the underlying RAID volume is a RAID 1/10,
driver issues two fast path write IOs one for each corresponding physical
drive after computing the corresponding start LBA for each physical drive.
Both write IOs will have the same payload and are posted to HW such that
replies land in the same reply queue.
If there are no resources available for sending two IOs, driver will send
the original IO from SCSI layer to RAID volume through the Firmware.
Based on PCI bandwidth and write payload, every second this feature is
enabled/disabled.
When both IOs are completed by HW, the resources will be released
and SCSI IO completion handler will be called.
Signed-off-by: Sasikumar Chandrasekaran <sasikumar.pc@broadcom.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Detect sequential Write IOs and pass the hint that it is part of sequential
stream to help HBA Firmware do the Full Stripe Writes. For read IOs on
certain RAID volumes like Read Ahead volumes,this will help driver to
send it to Firmware even if the IOs can potentially be sent to
hardware directly (called fast path) bypassing firmware.
Design: 8 streams are maintained per RAID volume as per the combined
firmware/driver design. When there is no stream detected the LRU stream
is used for next potential stream and LRU/MRU map is updated to make this
as MRU stream. Every time a stream is detected the MRU map
is updated to make the current stream as MRU stream.
Signed-off-by: Sasikumar Chandrasekaran <sasikumar.pc@broadcom.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
An UNMAP command on a PI formatted device will leave the Logical Block Application
Tag and Logical Block Reference Tag as all F's (for those LBAs that are unmapped).
To avoid IO errors if those LBAs are subsequently read before they are written with
valid tag fields, the MPI SCSI IO requests need to set the EEDPFlags element EEDP
Escape Mode field, Bits [7:6] appropriately. A value of 2 should be set to disable
all PI checks if the Logical Block Application Tag is 0xFFFF for PI types 1 and 2.
A value of 3 should be set to disable all PI checks if the Logical Block Application
Tag is 0xFFFF and the Logical Block Reference Tag is 0xFFFFFFFF for PI type 3.
Signed-off-by: Sasikumar Chandrasekaran <sasikumar.pc@broadcom.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
SAS3.5 Generic Megaraid based Controllers will have the support for 128 MSI-X vectors,
resulting in the need to support 128 reply queues
Signed-off-by: Sasikumar Chandrasekaran <sasikumar.pc@broadcom.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
This patch contains new pci device ids for SAS3.5 Generic Megaraid Controllers
Signed-off-by: Sasikumar Chandrasekaran <sasikumar.pc@broadcom.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
CC: stable@vger.kernel.org
Signed-off-by: Sumit Saxena <sumit.saxena@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Until now the megaraid_sas driver has reported successful completion on
SYNCHRONIZE_CACHE commands without sending them down to the controller.
The controller firmware has been responsible for taking care of flushing
disk caches for all drives that belong to a Virtual Disk at the time of
system reboot/shutdown.
There may have been a reason to avoid sending SYNCHRONIZE_CACHE to a VD
in the past but that no longer appears to be valid.
Older versions of MegaRaid firmware (Gen2 and Gen2.5) set the WCE bit
for Virtual Disks but the firmware does not report correct completion
status for a SYNCHRONIZE_CACHE command. As a result, we must use another
method to identify whether it is safe to send the command to the
controller. We use the canHandleSyncCache firmware flag in the scratch
pad register at offset 0xB4.
New SYNCHRONIZE_CACHE behavior:
IF 'JBOD'
Driver sends SYNCHRONIZE_CACHE command to the firmware
Firmware sends SYNCHRONIZE_CACHE to drive
Firmware obtains status from drive and returns same status back to driver
ELSEIF 'VirtualDisk'
IF firmware supports new API bit called canHandleSyncCache
Driver sends SYNCHRONIZE_CACHE command to the firmware
Firmware does not send SYNCHRONIZE_CACHE to drives
Firmware returns SUCCESS
ELSE
Driver does not send SYNCHRONIZE_CACHE command to the firmware
Driver return SUCCESS for that command
ENDIF
ENDIF
[mkp: edited patch description]
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Sumit Saxena <sumit.saxena@broadcom.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Ewan D. Milne <emilne@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
This patch addresses the issue of driver firing DCMDs in PCI
shutdown/detach path irrespective of firmware state. Driver will now
check whether firmware is in operational state or not before firing
DCMDs. If firmware is in unrecoverable state or does not become
operational within specfied time, driver will skip firing DCMDs.
[mkp: fixed typos]
Signed-off-by: Sumit Saxena <sumit.saxena@broadcom.com>
Signed-off-by: Shivasharan Srikanteshwara <shivasharan.srikanteshwara@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
For SRIOV enabled firmware, if there is a OCR(online controller reset)
possibility driver set the convert flag to 1, which is not happening if
there are outstanding commands even after 180 seconds. As driver does
not set convert flag to 1 and still making the OCR to run, VF(Virtual
function) driver is directly writing on to the register instead of
waiting for 30 seconds. Setting convert flag to 1 will cause VF driver
will wait for 30 secs before going for reset.
CC: stable@vger.kernel.org
Signed-off-by: Kiran Kumar Kasturi <kiran-kumar.kasturi@broadcom.com>
Signed-off-by: Sumit Saxena <sumit.saxena@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Found one megaraid_sas HBA probe fails,
[ 187.235190] scsi host2: Avago SAS based MegaRAID driver
[ 191.112365] megaraid_sas 0000:89:00.0: BAR 0: can't reserve [io 0x0000-0x00ff]
[ 191.120548] megaraid_sas 0000:89:00.0: IO memory region busy!
and the card has resource like,
[ 125.097714] pci 0000:89:00.0: [1000:005d] type 00 class 0x010400
[ 125.104446] pci 0000:89:00.0: reg 0x10: [io 0x0000-0x00ff]
[ 125.110686] pci 0000:89:00.0: reg 0x14: [mem 0xce400000-0xce40ffff 64bit]
[ 125.118286] pci 0000:89:00.0: reg 0x1c: [mem 0xce300000-0xce3fffff 64bit]
[ 125.125891] pci 0000:89:00.0: reg 0x30: [mem 0xce200000-0xce2fffff pref]
that does not io port resource allocated from BIOS, and kernel can not
assign one as io port shortage.
The driver is only looking for MEM, and should not fail.
It turns out megasas_init_fw() etc are using bar index as mask. index 1
is used as mask 1, so that pci_request_selected_regions() is trying to
request BAR0 instead of BAR1.
Fix all related reference.
Fixes: b6d5d8808b ("megaraid_sas: Use lowest memory bar for SR-IOV VF support")
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Acked-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
I actually read the error messages in my logs, and successful
initialization is not an error.
Arguably these log lines could be deleted entirely.
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Reviewed-by: Hannes Reinicke <hare@suse.de>
Acked-by: Sumit Saxena <sumit.saxena@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
In OCR path, before calling chip reset calls function
megasas_wait_for_outstanding_fusion to check reason for OCR. In case of
firmware FAULT initiated OCR and DCMD timeout initiated timeout, driver
will clear any outstanding reply (yet to be processed by driver) in
reply queues before going for chip reset. This code is added to handle a
scenario when IO timeout initiated adapter reset and management
application initiated adapter reset (by sending command to FAULT
firmware) happens simultaneously since adapter reset function is
safe-guarded by reset_mutex so only thread will be doing controller
reset. Consider IO timeout thread gets mutex and proceeds with adapter
reset process after disabling interrupts and by the time management
application has fired command to firmware to do adapter reset and the
same command is completed by firmware but since interrupts are disabled,
driver will not get completion and the same command will be in
outstanding/pending commands list of driver and refires same command
from IO timeout thread after chip reset which will again FAULT firmware
and eventually causes kill adapter.
Signed-off-by: Sumit Saxena <sumit.saxena@broadcom.com>
Reviewed-by: Hannes Reinicke <hare@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
This patch will reduce memory footprints of megaraid_sas driver when
booted in kdump mode. Driver will not allocate memory for optional and
perfromance oriented features. Below are key changes done in
megaraid_sas driver to do this:
1. Limit Controller's queue depth to 100 in kdump mode.
2. Do not allocate memory for system info buffer and PD info buffer.
3. Disable performance oriented features e.g. Disable RDPQ mode, disable
dual queue depth, restrict to single MSI-x vector.
Signed-off-by: Sumit Saxena <sumit.saxena@broadcom.com>
Reviewed-by: Hannes Reinicke <hare@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
A barrier should be added to ensure proper ordering of memory mapped
writes.
Signed-off-by: Tomas Henzl <thenzl@redhat.com>
Reviewed-by: Kashyap Desai <kashyap.desai@broadcom.com>
Acked-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Driver assumes that VFs always have peers present whenever they have
same LD IDs. But this is not the case. This patch handles the above
mentioned by explicitly checking for a peer before making HA/non-HA path
decision.
Signed-off-by: Uday Lingala <uday.lingala@avagotech.com>
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
This patch fixes online controller resets on SRIOV-enabled series of
Avago controllers.
1) Remove late detection heartbeat.
2) Change in the behavior if the FW found in READY/OPERATIONAL state.
Signed-off-by: Uday Lingala <uday.lingala@avagotech.com>
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
This patch will introduce module-parameter for SCSI command timeout
value and fix setting of resetwaittime beyond a value.
Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Make instance->adprecovery variable atomic and removes hba_lock spinlock
while accessing instance->adprecovery.
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
This patch will add capability in driver to tell firmware that it can
throttle IOs in case controller's queue depth is downgraded post OFU
(online firmware upgrade). This feature will ensure firmware can be
downgraded from higher queue depth to lower queue depth without needing
system reboot. Added throttling code in IO path of driver, in case OS
tries to send more IOs than post OFU firmware's queue depth.
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
1. For iMR controllers, firmware will report two queue depths:
- Controller-wide queue depth
- LDIO queue depth (240)
Controller-wide queue depth will be greater among the two. Using this
new feature, iMR can provide larger Queue depth(QD) for JBOD and limited
QD for Virtual Disk(VD).
2. megaraid_sas driver will throttle read/write LDIOs based on "LDIO
Queue Depth".
3. Dual queue depth can be enabled/disabled via module parameter. It is
enabled by default if the firmware supports it. Only specific firmware
builds will enable the feature.
4. Added sysfs parameter "ldio_outstanding" which permits querying the
number of outstanding LDIO requests at runtime.
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
build_and_issue_cmd should return SCSI_MLQUEUE_HOST_BUSY for a few error
cases instead of returning 1.
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
This patch will create a reply queue pool for each MSI-X index and will
provide an array of base addresses instead of the single address of
legacy mode. Using this new interface the driver can support higher
queue depths through scattered DMA pools.
If array mode is not supported driver will fall back to the legacy
method of reply pool allocation. This limits controller queue depth to
1K max. To enable a queue depth of more than 1K driver requires firmware
to support array mode and scratch_pad3 will provide the new queue depth
value.
When RDPQ is used, downgrading to an older firmware release should not
be permitted. This may cause firmware fault and is not supported.
Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Firmware will fill out per-LD data to tell driver whether a particular
LD supports region lock bypass. If yes, then driver will send non-FP
LDIO to region lock bypass FIFO. With this change in driver, firmware
will optimize certain code to improve performance.
Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
This patch adds task management for SCSI commands. Added functions are
task abort and target reset.
1. Currently, megaraid_sas driver performs controller reset when any IO
times out. With task management support added, task abort and target
reset will be tried to recover timed out IO. If task management fails,
then controller reset will be performaned. If the task management
request times out, fail the request and escalate to the next
level (controller reset).
2. mr_device_priv_data will be allocated for all generations of
controller, but is_tm_capable flag will never be set for
controllers (prior to Invader series) as firmware support is not
available for task management.
3. Task management capable firmware will set is_tm_capable flag in
firmware API.
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
This patch will do proper error handling for DCMD timeout failure cases
for Fusion adapters:
1. For MFI adapters, in case of DCMD timeout (DCMD which must return
SUCCESS) driver will call kill adapter.
2. What action needs to be taken in case of DCMD timeout is decided by
function dcmd_timeout_ocr_possible(). DCMD timeout causing OCR is
applicable to the following commands:
MR_DCMD_PD_LIST_QUERY
MR_DCMD_LD_GET_LIST
MR_DCMD_LD_LIST_QUERY
MR_DCMD_CTRL_SET_CRASH_DUMP_PARAMS
MR_DCMD_SYSTEM_PD_MAP_GET_INFO
MR_DCMD_LD_MAP_GET_INFO
3. If DCMD fails from driver init path there are certain DCMDs which
must return SUCCESS. If those DCMDs fail, driver bails out. For optional
DCMDs like pd_info etc., driver continues without executing certain
functionality.
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Remove PCI id based checks and use instance->ctrl_context to decide
whether controller is MFI-based or a Fusion adapter. Additionally,
Fusion adapters are divided into two categories: Thunderbolt and
Invader.
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Syncro firmware supports round robin I/O switching on dual path. Driver
uses validHandles to check for dual path. However, it is supposed to
check for values > 1 (not > 2).
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Fix the issue reported at:
http://marc.info/?l=linux-scsi&m=143694494104544&w=2
Try to do chip reset at driver load time. If firmware fails to reach
ready state, try chip reset using adp_reset() callback. For Fusion
adapters the call back was previously void. Provide a suitable reset
function.
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Driver will expose max sge = 256 (earlier it was 64) if firmware
supports extended IO size (1M).
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
Reviewed-by: Martin Petersen <martin.petersen@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Implemented JBOD map which will provide quick access for JBOD path and
also provide sequence number. This will help hardware to fail command
to the FW in case of any sequence mismatch.
Fast Path I/O for JBOD will refer JBOD map (which has sequence number
per JBOD device) instead of RAID map. Previously, the driver used RAID
map to get device handle for fast path I/O and this not have sequence
number information. Now, driver will use JBOD map instead. As part of
error handling, if JBOD map is failed/not supported by firmware, driver
will continue using legacy behavior.
Now there will be three IO paths for JBOD (syspd):
- JBOD map with sequence number (Fast Path)
- RAID map without sequence number (Fast Path)
- FW path via h/w exception queue deliberately setup devhandle
0xFFFF (FW path).
Relevant data structures:
- Driver send new DCMD MR_DCMD_SYSTEM_PD_MAP_GET_INFO for this purpose.
- struct MR_PD_CFG_SEQ- This structure represent map of single physical
device.
- struct MR_PD_CFG_SEQ_NUM_SYNC- This structure represent whole JBOD
map in general(size, count of sysPDs configured, struct MR_PD_CFG_SEQ
of syspD with 0 index).
- JBOD sequence map size is: sizeof(struct MR_PD_CFG_SEQ_NUM_SYNC)
+ (sizeof(struct MR_PD_CFG_SEQ) * (MAX_PHYSICAL_DEVICES - 1)) which
is allocated while setting up JBOD map at driver load time.
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
Reviewed-by: Martin Petersen <martin.petersen@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Use dev_printk() when possible to make messages more useful.
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Acked-by: Sumit Saxena <sumit.saxena@avagotech.com>
Signed-off-by: James Bottomley <JBottomley@Odin.com>
This is the usual grab bag of driver updates (lpfc, hpsa,
megaraid_sas, cxgbi, be2iscsi) plus an assortment of minor updates.
There are also one new driver: the Cisco snic; the advansys driver has
been rewritten to get rid of the warning about converting it to the
DMA API, the tape statistics patch got in and finally, there's a
resuffle of SCSI header files to separate more cleanly initiator from
target mode (and better share the common definitions).
Signed-off-by: James Bottomley <JBottomley@Odin.com>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2
iQEcBAABAgAGBQJViKWdAAoJEDeqqVYsXL0MAr8IAMmlA6HBVjMJJFCEOY9corHj
e70MNQa7LUgf+JCdOtzGcvHXTiFFd4IHZAwXUJAnsC4IU2QWEfi1bjUTErlqBIGk
LoZlXXpEHnFpmWot3OluOzzcGcxede8rVgPiKWVVdojIngBC2+LL/i2vPCJ84ri9
WCVlk6KBvWZXuU6JuOKAb2FO9HOX7Q61wuKAMast2Qc6RNc2ksgc7VbstsITqzZ9
FVEsjmQ5lqUj+xdxBpiUOdUpc22IJ4VcpBgQ2HrThvg6vf4aq937RJ/g4vi/g0SU
Utk0a3bUw1H/WnYAfJVFx83nVEsS/954Z7/ERDg1sjlfLYwQtQnpov0XIbPIbZU=
=k9IT
-----END PGP SIGNATURE-----
Merge tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi
Pull SCSI updates from James Bottomley:
"This is the usual grab bag of driver updates (lpfc, hpsa,
megaraid_sas, cxgbi, be2iscsi) plus an assortment of minor updates.
There is also one new driver: the Cisco snic. The advansys driver has
been rewritten to get rid of the warning about converting it to the
DMA API, the tape statistics patch got in and finally, there's a
resuffle of SCSI header files to separate more cleanly initiator from
target mode (and better share the common definitions)"
* tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi: (156 commits)
snic: driver for Cisco SCSI HBA
qla2xxx: Fix indentation
qla2xxx: Comment out unreachable code
fusion: remove dead MTRR code
advansys: fix compilation errors and warnings when CONFIG_PCI is not set
mptsas: fix depth param in scsi_track_queue_full
megaraid: fix irq setup process regression
lpfc: Update version to 10.7.0.0 for upstream patch set.
lpfc: Fix to drop PLOGIs from fabric node till LOGO processing completes
lpfc: Fix scsi task management error message.
lpfc: Fix cq_id masking problem.
lpfc: Fix scsi prep dma buf error.
lpfc: Add support for using block multi-queue
lpfc: Devices are not discovered during takeaway/giveback testing
lpfc: Fix vport deletion failure.
lpfc: Check for active portpeerbeacon.
lpfc: Update driver version for upstream patch set 10.6.0.1.
lpfc: Change buffer pool empty message to miscellaneous category
lpfc: Fix incorrect log message reported for empty FCF record.
lpfc: Fix rport leak.
...
This patch is rebased on top of recently sent 18 patches(submitted by me) for
megaraid_sas driver.
Change the return value of wait_and_poll() and megsas_issue_blocked_cmd()
based on MFI_STAT returned by firmware for that command. Earlier driver always
send return type based on command completion (but never check MFI_STAT_OK for
that command), so even if command is failed by firmware still driver will
return SUCCESS status from these functions wait_and_poll() and
megsas_issue_blocked_cmd() and if caller of these functions does not check
command status (MFI_STAT), then it may endup using invalid data returned in
DMA buffers(one of the example is megasas_ld_list_query DCMD). Best thing to
avoid this type of issue is do error handling and set proper return type from
caller function wait_and_poll() and megsas_issue_blocked_cmd().
The change proposed in this patch will fix the regression introduced in patch-
"90dc9d9 megaraid_sas : MFI MPT linked list corruption fix" inside function
megasas_ld_list_query(). Prior to this MFI MPT linked list corruption fix
patch, megasas_ld_list_query() function used to check DCMD status(returned by
firmware) but with this linked list corruption fix patch, DCMD status will not
be checked inside function megasas_ld_list_query() and introduced this issue
of wrong data being used by function megasas_ld_list_query().
Cc: <stable@vger.kernel.org>
Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: James Bottomley <JBottomley@Odin.com>
The fusion HBAs don't really use the instance template like the other
variants, as it branches off at a much higher level. So instead of
trying to squeeze megasas_fire_cmd_fusion into the wrong calling
convention call it locally with argument data types that match what
is passed.
[jejb: fix up 32 bit compile failure]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: James Bottomley <JBottomley@Odin.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: James Bottomley <JBottomley@Odin.com>
Add noop conversions for all ones to make sparse happy.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: James Bottomley <JBottomley@Odin.com>
This adds endianness annotations to all data structures, and a few
variables directly referencing them.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: James Bottomley <JBottomley@Odin.com>
This patch will add support for Single Server High Availability(SSHA) cluster
support. Here is the short decsription of changes done to add support for
SSHA-
1) Host will send system's Unique ID based on DMI_PRODUCT_UUID to firmware.
2) Toggle the devhandle in LDIO path for Remote LDs.
Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: James Bottomley <JBottomley@Odin.com>
megaraid_sas driver will use block layer provided tag for indexing internal
MPT frames to get any unique MPT frame tied with tag. Each IO request
submitted from SCSI mid layer will get associated MPT frame from MPT framepool
(retrieved and return back using spinlock inside megaraid_sas driver's
submission/completion call back). Getting MPT frame from MPT Frame pool is
very expensive operation because of associated spin lock operation (spinlock
overhead increase on multi NUMA node). This type of locking in driver is very
expensive call considering each IO request need - Acquire and Release of the
same lock.
With this support, in IO path driver will directly provide the unique command
index(which is based on block layer tag) and will get the MPT frame tied to
the tag and this way driver can get rid off lock, which synchronizes the
access to MPT frame pool while fetching and returning MPT frame from the pool.
This support in driver provides siginificant performance improvement(on multi
NUMA node system)on latest upstream with SCSI.MQ as well as on existing linux
distributions.
Here is the data for test executed at Avago-
- IO Tool- FIO
- 4 Socket SMC server. (4 NUMA node server)
- 12 SSDs in JBOD mode .
- 4K Rand READ, QD=32
- SCSI MQ x86_64 (Latest Upstream kernel)
- upto 300% Performance Improvement.
If IOs are running on single Node, perfromance gain is less, but as soon as
increase number of nodes, performance improvement is significant. IOs running
on all 4 NUMA nodes, with this patch applied IOPs observed was 1170K vs 344K
IOPs seen without this patch.
Logically, there are two parts of this patch- 1) Block layer tag support 2)
changes in calling convention of return_cmd. part 2 will revert the changes
done by patch- 90dc9d9 megaraid_sas : MFI MPT linked list corruption fix
because changes done in part 1 has fixed the problem of MFI MPT linked list
corruption. part 2 is very much dependent on part 1, so we decided to have
single patch for these two logical changes.
[jejb: remove chatty printk pointed out by hch]
Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: James Bottomley <JBottomley@Odin.com>
This patch will add separate function for refiring MFI commands in Fusion
adapters's OCR code.
Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: James Bottomley <JBottomley@Odin.com>
We only want to steer the I/O completion towards a queue, but don't
actually access any per-CPU data, so the raw_ version is fine to use
and avoids the warnings when using smp_processor_id().
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reported-by: Andy Lutomirski <luto@kernel.org>
Tested-by: Andy Lutomirski <luto@kernel.org>
Acked-by: Sumit Saxena <sumit.saxena@avagotech.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: James Bottomley <JBottomley@Odin.com>
1) For fusion adapters, limit reserved frames for non SCSI commands to 8
(3 for parallel IOCTLs + 5 for driver's internal DCMDs).
Earlier reserved commands for non SCSI IO frames was set to 32, so with
this implementation, increased per controller "can_queue".
Behavior of MFI controllers will remain unchanged.
2) Optimize the code related to per controller's 'can_queue' setting.
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Signed-off-by: Chaitra Basappa <chaitra.basappa@avagotech.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Driver calls megasas_complete_cmd() to call wake_up() for each MFI frame
that was issued through the ioctl() interface prior to the kill adapter.
This ensures userspace ioctl() system calls issued just before a kill
adapter don't get stuck in wait state and IOCTLs are returned to
the application.
Cc: <stable@vger.kernel.org>
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Signed-off-by: Chaitra Basappa <chaitra.basappa@avagotech.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Update driver "mask_interrupts" before enable/disable hardware interrupt
in order to avoid missing interrupts because of "mask_interrupts" still
set to 1 and hardware interrupts are enabled.
Cc: <stable@vger.kernel.org>
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Signed-off-by: Chaitra Basappa <chaitra.basappa@avagotech.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
This patch will address the issue of SCSI device created at OS level for
non existing VD. ldTgtIdtoLd[] array has size 256 for Extended VD firmware
and 128 for legacy firmware. Accessing indices beyond array size (OS will
send TUR, INQUIRY.. commands upto device index 255), may return valid LD
value and that particular SCSI command will be SUCCESS and creating SCSI
device for non existing target(VD).
For legacy firmware (64 VD firmware), invalidates LD (by setting LD value
to 0xff) in LdTgtIdtoLd[] array for device index beyond 127, so that
invalid LD(0xff) value should be returned beyond device index beyond 127.
Cc: <stable@vger.kernel.org>
Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
This patch adds support for Secure Encrypting Drives (SED) in JBOD mode:
1) If the firmware supports SED JBOD, all non read/write commands to JBODs
will be sent via firmware path, and read/write commands to JBODs will
be sent via fastpath.
2) If the firmware does not support SED JBOD, driver will fall back to the
old design, i.e. send all JBOD I/O via fastpath.
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Signed-off-by: Chaitra Basappa <chaitra.basappa@avagotech.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
This patch addresses below issues:
1) Few endianness bug fixes.
2) Break the iteration after (MAX_LOGICAL_DRIVES_EXT - 1)),
instead of MAX_LOGICAL_DRIVES_EXT.
3) Optimization in MFI INIT frame before firing.
4) MFI IO frame should be 256bytes aligned. Code is optimized to reduce
the size of frame for fusion adapters and make the MFI frame size
calculation a bit transparent and readable.
Cc: <stable@vger.kernel.org>
Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Signed-off-by: Chaitra Basappa <chaitra.basappa@avagotech.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
In OCR(Online Controller Reset) path, driver sets adapter state to
MEGASAS_HBA_OPERATIONAL before getting new RAID map. There will be a small
window where IO will come from OS with old RAID map. This patch will update
adapter state to MEGASAS_HBA_OPERATIONAL, only after driver has new RAID
map to avoid any IOs getting build using old RAID map.
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
In OCR (Online Controller Reset) path, driver sets adapter state to
MEGASAS_HBA_OPERATIONAL before getting new RAID map. There will be a small
window where IO will come from OS with old RAID map. This patch will
update adapter state to MEGASAS_HBA_OPERATIONAL, only after driver has new
RAID map to avoid any IOs getting build using old RAID map.
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Update MAINTAINERS list and copyright information for megaraid_sas driver.
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Resending the patch. Addressed the review comments from Tomas Henzl.
Added comment for to-do work.
Problem statement:
MFI link list in megaraid_sas driver is used from mfi-mpt pass-through commands.
This list can be corrupted due to many possible race conditions in driver and
eventually we may see kernel panic.
One example -
MFI frame is freed from calling process as driver send command via polling method and interrupt
for that command comes after driver free mfi frame (actually even after some other context reuse
the mfi frame). When driver receive MPT frame in ISR, driver will be using the index of MFI and
access that MFI frame and finally in-used MFI frame’s list will be corrupted.
High level description of new solution -
Free MFI and MPT command from same context.
Free both the command either from process (from where mfi-mpt pass-through was called) or from
ISR context. Do not split freeing of MFI and MPT, because it creates the race condition which
will do MFI/MPT list corruption.
Renamed the cmd_pool_lock which is used in instance as well as fusion with below name.
mfi_pool_lock and mpt_pool_lock to add more code readability.
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Resending the patch. Addressed the review comments from Tomas Henzl.
Current driver does fast path read load balancing between arm and mirror disk
for two Drive Raid-1 configuration only.
Now, Driver support fast path read load balancing for all (any number of disk) Raid-1 configuration.
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Resending the patch. Addressed the review comments from Tomas Henzl.
Round down the max sge to power of two.
Earlier max sge limit is 70 SGE, which will allow block layer to send 280K IO frame.
It is optimal to provide max IO size aligned to the smallest possible stripe size.
E.a
Consider that we have configured RAID Volumes which does not allow Fast Path across the stripe.
Raid volume with stripe size = 256K, will have peformance hit if we get io frame of size 280K.
Driver will not send IO frame large than stripe size to the Fast Path.
Also, FW will convert 280K frame into 256K + 24K. This is an additional overhead.
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Resending the patch. Addressed the review comments from Tomas Henzl.
reserved1 field(part of union) of Raid map struct was not required so it is removed.
Current MegaRAID firmware and hence the driver only supported 64VDs.
E.g: If the user wants to create more than 64VD on a controller,
it is not possible on current firmware/driver.
New feature and requirement to support upto 256VD, firmware/driver/apps need changes.
In addition to that there must be a backward compatibility of the new driver with the
older firmware and vice versa.
RAID map is the interface between Driver and FW to fetch all required
fields(attributes) for each Virtual Drives.
In the earlier design driver was using the FW copy of RAID map where as
in the new design the Driver will keep the RAID map copy of its own; on which
it will operate for any raid map access in fast path.
Local driver raid map copy will provide ease of access through out the code
and provide generic interface for future FW raid map changes.
For the backward compatibility driver will notify FW that it supports 256VD
to the FW in driver capability field.
Based on the controller properly returned by the FW, the Driver will know
whether it supports 256VD or not and will copy the RAID map accordingly.
At any given time, driver will always have old or new Raid map.
So with this changes, driver can also work in host lock less mode. Please
see next patch which enable host lock less mode for megaraid_sas driver.
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Resending the patch. Addressed the review comments from Tomas Henzl.
Move buff_offset inside spinlock, corrected loop at crash dump buffer free,
reset_devices check is added to disable fw crash dump feature in kdump kernel.
This feature will provide similar interface as kernel crash dump feature.
When megaraid firmware encounter any crash, driver will collect the firmware raw image and
dump it into pre-configured location.
Driver will allocate two different segment of memory.
#1 Non-DMA able large buffer (will be allocated on demand) to capture actual FW crash dump.
#2 DMA buffer (persistence allocation) just to do a arbitrator job.
Firmware will keep writing Crash dump data in chucks of DMA buffer size into #2,
which will be copy back by driver to the host memory as described in #1.
Driver-Firmware interface:
==================
A.) Host driver can allocate maximum 512MB Host memory to store crash dump data.
This memory will be internal to the host and will not be exposed to the Firmware.
Driver may not be able to allocate 512 MB. In that case, driver will do possible memory
(available at run time) allocation to store crash dump data.
Let’s call this buffer as Host Crash Buffer.
Host Crash buffer will not be contigious as a whole, but it will have multiple chunk of contigious memory.
This will be internal to driver and firmware/application are unaware of it.
Partial allocation of Host Crash buffer may have valid information to debug depending upon
what was collected in that buffer and depending on nature of failure.
Complete Crash dump is the best case, but we do want to capture partial buffer just to grab something rather than nothing.
Host Crash buffer will be allocated only when FW Crash dump data is available,
and will be deallocated once application copy Host Crash buffer to the file.
Host Crash buffer size can be anything between 1MB to 512MB. (It will be multiple of 1MBs)
B.) Irrespective of underlying Firmware capability of crash dump support,
driver will allocate DMA buffer at start of the day for each MR controllers.
Let’s call this buffer as “DMA Crash Buffer”.
For this feature, size of DMA crash buffer will be 1MB.
(We will not gain much even if DMA buffer size is increased.)
C.) Driver will now read Controller Info sending existing dcmd “MR_DCMD_CTRL_GET_INFO”.
Driver should extract the information from ctrl info provided by firmware and
figure out if firmware support crash dump feature or not.
Driver will enable crash dump feature only if
“Firmware support Crash dump” +
“Driver was able to create DMA Crash Buffer”.
If either one from above is not set, Crash dump feature should be disable in driver.
Firmware will enable crash dump feature only if “Driver Send DCMD- MR_DCMD_SET_CRASH_BUF_PARA with MR_CRASH_BUF_TURN_ON”
Helper application/script should use sysfs parameter fw_crash_xxx to actually copy data from
host memory to the filesystem.
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Shivasharan S