Pull SCSI updates from James Bottomley:
"This is mostly updates of the usual suspects: lpfc, qla2xxx, hisi_sas,
megaraid_sas, pm80xx, mpt3sas, be2iscsi, hpsa. and a host of minor
updates.
There's no major behaviour change or additions to the core in all of
this, so the potential for regressions should be small (biggest
potential being in the scsi error handler changes)"
* tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi: (203 commits)
scsi: lpfc: Fix hard lock up NMI in els timeout handling.
scsi: mpt3sas: remove a stray KERN_INFO
scsi: mpt3sas: cleanup _scsih_pcie_enumeration_event()
scsi: aacraid: use timespec64 instead of timeval
scsi: scsi_transport_fc: add 64GBIT and 128GBIT port speed definitions
scsi: qla2xxx: Suppress a kernel complaint in qla_init_base_qpair()
scsi: mpt3sas: fix dma_addr_t casts
scsi: be2iscsi: Use kasprintf
scsi: storvsc: Avoid excessive host scan on controller change
scsi: lpfc: fix kzalloc-simple.cocci warnings
scsi: mpt3sas: Update mpt3sas driver version.
scsi: mpt3sas: Fix sparse warnings
scsi: mpt3sas: Fix nvme drives checking for tlr.
scsi: mpt3sas: NVMe drive support for BTDHMAPPING ioctl command and log info
scsi: mpt3sas: Add-Task-management-debug-info-for-NVMe-drives.
scsi: mpt3sas: scan and add nvme device after controller reset
scsi: mpt3sas: Set NVMe device queue depth as 128
scsi: mpt3sas: Handle NVMe PCIe device related events generated from firmware.
scsi: mpt3sas: API's to remove nvme drive from sml
scsi: mpt3sas: API 's to support NVMe drive addition to SML
...
The latest MegaRAID Firmware (for Invader series) has support for 64bit
DMA for both streaming and consistent DMA buffers. All Ventura series
controller FW always support 64 bit consistent DMA. Also, on a few
architectures 32bit DMA is not supported.
Current driver always prefers 32bit for consistent DMA and 64bit for
streaming DMA. This behavior was unintentional and carried forwarded
from legacy controller FW. Need to enhance the driver to support 64bit
consistent DMA buffers based on the firmware capability.
Below is the DMA setting strategy in driver with this patch. For
Ventura series, always try to set 64bit DMA mask. If it fails fall back
to 32bit DMA mask. For Invader series and earlier generation
controllers, first try to set to 32bit consistent DMA mask irrespective
of FW capability. This is needed to ensure firmware downgrades do not
break. If 32bit DMA setting fails, check FW capability and try seting to
64bit DMA mask.
There are certain restrictions in the hardware for having all sense
buffers and all reply descriptors to be in the same 4GB memory region.
This limitation is h/w dependent and can not be changed in firmware.
This limitation needs to be taken care in driver while allocating the
buffers. There was a discussion regarding this - find details at below
link. https://www.spinics.net/lists/linux-scsi/msg108251.html
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Driver load fails if memory allocation for request frame pool fails due
to the higher queue_depth requirement. The driver now allows dynamically
reducing queue_depth if memory allocations fail rather than failing
load. With this, there is no need to limit queue_depth to 1K.
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
In certain cases, the host memory is limited and with FW supporting
higher queue depths there are increasing chances of IO request frame
allocation failures that we are seeing. In case of request frame
allocation failures, retry allocation with reduced queue depth (in steps
of 64) to continue to configure the controller with a reduced
performance rather than failing load.
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Older firmware version unconditionally pulls 4k frame for IOC INIT MFA
frame. But driver allocates 1k or 4k max_chain_frame_sz based on FW
capability. During boot time, this results in DMA read errors.
Workaround fix in driver by allocating separate ioc_init frame of 4k
size to support older firmware.
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Cc: stable@vger.kernel.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
fusion_context structure is very large around 180kB and most of the size
is contributed by log_to_span array. Move log_to_span out of fusion
context and have separate allocation for log_to_span. And use kmalloc to
allocate fusion_context. Currently kmemleak reports 1000s of false
positives for fusion->cmd_list[]. kmemleak does not track page
allocation for fusion_context. This change will also fix the false
positives reported by kmemleak.
Ref: https://marc.info/?l=linux-scsi&m=150545293900917
Reported-by: Shu Wang <shuwang@redhat.com>
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
megasas_wait_for_outstanding_fusion checks for pending commands every 1
second. But megasas_complete_cmd_dpc_fusion is only called every 5
seconds. If the commands are already completed by firmware, there is an
additional delay of 5 seconds before driver will process completion for
these commands.
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>
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 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>
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>
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>
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>
