| Age | Commit message (Collapse) | Author |
|---|
|
Add the primary datastructures needed to implement VMID in the lpfc
driver. Maintain the capability, current state, and hash table for the
vmid/appid along with other information. This implementation supports the
two versions of vmid implementation (app header and priority tagging).
Link: https://lore.kernel.org/r/20210608043556.274139-5-muneendra.kumar@broadcom.com
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Gaurav Srivastava <gaurav.srivastava@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Muneendra Kumar <muneendra.kumar@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
FC-LS-5 specifies that a received RDF implies a possible change to fabric
supported diagnostic functions. Endpoints are to re-perform the RDF
exchange with the fabric to enable possible new features or adapt to
changes in values.
This patch adds the logic to RDF receive to re-perform the RDF exchange
with the switch.
Link: https://lore.kernel.org/r/20210514195559.119853-11-jsmart2021@gmail.com
Co-developed-by: Justin Tee <justin.tee@broadcom.com>
Signed-off-by: Justin Tee <justin.tee@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
Default behavior for the driver, when aborting an I/O, is to terminate the
I/O with the adapter. The adapter will initiate an ABTS to terminate the
exchange on the link and mark the exchange is terminated so that no further
use of the sgl or any traffic for the exchange is worked on. Completion on
the Abort is then posted to the driver, which as the I/O is terminated can
complete the I/O to the OS. This completion may occur prior to the ABTS
handshake completing on the wire. The ABTS handshake can take a long time
to complete with timeouts and retries reaching 60+ seconds. Note: if
retries fail, LOGO occurs.
Some devices want to ensure that the ABTS handshake fully completes (this
device has fully ack'd it) before the I/O completion is posted back to the
OS, where a failed I/O may be retried via a different path.
To support this behavior, an option was added to the driver to change I/O
completion from the Abort cmd completion to the Exchange termination (aka
ABTS) completion.
Link: https://lore.kernel.org/r/20210514195559.119853-10-jsmart2021@gmail.com
Co-developed-by: Justin Tee <justin.tee@broadcom.com>
Signed-off-by: Justin Tee <justin.tee@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
For the files modified in 2021 via the 12.8.0.7 and 12.8.0.8 patch sets,
update the copyright for 2021.
Link: https://lore.kernel.org/r/20210301171821.3427-23-jsmart2021@gmail.com
Co-developed-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
When connected in pt2pt mode, there is a scenario where the remote port
significantly delays sending a response to our FLOGI, but acts on the FLOGI
it sent us and proceeds to PLOGI/PRLI. The FLOGI ends up timing out and
kicks off recovery logic. End result is a lot of unnecessary state changes
and lots of discovery messages being logged.
Fix by terminating the FLOGI and noop'ing its completion if we have already
accepted the remote ports FLOGI and are now processing PLOGI.
Link: https://lore.kernel.org/r/20210301171821.3427-13-jsmart2021@gmail.com
Co-developed-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
Several errors have occurred where the adapter stops or fails but does not
raise the register values for the driver to detect failure. Thus driver is
unaware of the failure. The failure typically results in I/O timeouts, the
I/O timeout handler failing (after several seconds), and the error handler
escalating recovery policy and resulting in more errors. Eventually, the
driver is in a position where things have spiraled and it can't do recovery
because other recovery ops are still outstanding and it becomes unusable.
Resolve the situation by having the I/O timeout handler (actually a els,
SCSI I/O, NVMe ls, or NVMe I/O timeout), in addition to aborting the I/O,
perform a mailbox command and look for a response from the hardware. If
the mailbox command fails, it will mark the adapter offline and then invoke
the adapter reset handler to clean up.
The new I/O timeout test will be limited to a test every 5s. If there are
multiple I/O timeouts concurrently, only the 1st I/O timeout will generate
the mailbox command. Further testing will only occur once a timeout occurs
after a 5s delay from the last mailbox command has expired.
Link: https://lore.kernel.org/r/20210104180240.46824-14-jsmart2021@gmail.com
Co-developed-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
A very long time ago, there was a feature: auto sli mode. It gave the user
the ability to auto select the SLI mode (SLI2 or SLI3) to run the port in,
or even force SLI2 mode if configured. Because of the convoluted logic,
the CONFIG_PORT mbox command ends up being called 2 or 3 times. It should
have been called only once. Additionally, the driver no longer supports
SLI-2, so only SLI-3 mode should be allowed.
The following changes were made:
- Force module parameter to SLI3 only.
- Rip out redundant CONFIG_PORT mbox commands.
- Force CONFIG_PORT mbox command to be in beginning of enable ISR routine.
- Added changes for offline to online behavior
Link: https://lore.kernel.org/r/20210104180240.46824-3-jsmart2021@gmail.com
Co-developed-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
This patch converts the SCSI I/O path from the iocb-centric interfaces to
the common I/O submission path which supports native SLI-4 WQEs.
A wrapper routine is put in place to distinguish SLI-3 from SLI. If SLI-3,
the same iocb-centric paths are used, perhaps with refactored code that is
explicitly for SLI-3. For SLI-4, any iocb-related formatting is replaced
by wqe-based formatting, although much of that is addressed by the common
wqe templates in the SLI-4 path.
Link: https://lore.kernel.org/r/20201115192646.12977-14-james.smart@broadcom.com
Co-developed-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
To set up common use by the SCSI and NVMe I/O paths, create a new routine
that issues FCP I/O commands which can be used by either protocol. The new
routine addresses SLI-3 vs SLI-4 differences within its implementation.
Replace the (SLI-3 centric) iocb routine in the SCSI path with this new
WQE-centric common routine.
Link: https://lore.kernel.org/r/20201115192646.12977-13-james.smart@broadcom.com
Co-developed-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
Currently the discovery layers within the driver use the SCSI midlayer
host_lock to access node-specific structures. This can contend with the I/O
path and is too coarse of a lock.
Rework the driver so that it uses a lock specific to the remote port node
structure when accessing the structure contents. A few of the changes
brought out spots were some slightly reorganized routines worked better.
Link: https://lore.kernel.org/r/20201115192646.12977-6-james.smart@broadcom.com
Co-developed-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
Created new attribute lpfc_enable_mi, which by default is enabled.
Add command definition bits for SLI-4 parameters that recognize whether the
adapter has MIB information support and what revision of MIB data. Using
the adapter information, register vendor-specific MIB support with FDMI.
The registration will be done every link up.
During FDMI registration, encountered a couple of errors when reverting to
FDMI rev1. Code needed to exist once reverting. Fixed these.
Link: https://lore.kernel.org/r/20201020202719.54726-8-james.smart@broadcom.com
Co-developed-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
The following call trace was seen during HBA reset testing:
BUG: scheduling while atomic: swapper/2/0/0x10000100
...
Call Trace:
dump_stack+0x19/0x1b
__schedule_bug+0x64/0x72
__schedule+0x782/0x840
__cond_resched+0x26/0x30
_cond_resched+0x3a/0x50
mempool_alloc+0xa0/0x170
lpfc_unreg_rpi+0x151/0x630 [lpfc]
lpfc_sli_abts_recover_port+0x171/0x190 [lpfc]
lpfc_sli4_abts_err_handler+0xb2/0x1f0 [lpfc]
lpfc_sli4_io_xri_aborted+0x256/0x300 [lpfc]
lpfc_sli4_sp_handle_abort_xri_wcqe.isra.51+0xa3/0x190 [lpfc]
lpfc_sli4_fp_handle_cqe+0x89/0x4d0 [lpfc]
__lpfc_sli4_process_cq+0xdb/0x2e0 [lpfc]
__lpfc_sli4_hba_process_cq+0x41/0x100 [lpfc]
lpfc_cq_poll_hdler+0x1a/0x30 [lpfc]
irq_poll_softirq+0xc7/0x100
__do_softirq+0xf5/0x280
call_softirq+0x1c/0x30
do_softirq+0x65/0xa0
irq_exit+0x105/0x110
do_IRQ+0x56/0xf0
common_interrupt+0x16a/0x16a
With the conversion to blk_io_poll for better interrupt latency in normal
cases, it introduced this code path, executed when I/O aborts or logouts
are seen, which attempts to allocate memory for a mailbox command to be
issued. The allocation is GFP_KERNEL, thus it could attempt to sleep.
Fix by creating a work element that performs the event handling for the
remote port. This will have the mailbox commands and other items performed
in the work element, not the irq. A much better method as the "irq" routine
does not stall while performing all this deep handling code.
Ensure that allocation failures are handled and send LOGO on failure.
Additionally, enlarge the mailbox memory pool to reduce the possibility of
additional allocation in this path.
Link: https://lore.kernel.org/r/20201020202719.54726-3-james.smart@broadcom.com
Fixes: 317aeb83c92b ("scsi: lpfc: Add blk_io_poll support for latency improvment")
Cc: <stable@vger.kernel.org> # v5.9+
Co-developed-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
The current logging methods typically end up requesting a reproduction with
a different logging level set to figure out what happened. This was mainly
by design to not clutter the kernel log messages with things that were
typically not interesting and the messages themselves could cause other
issues.
When looking to make a better system, it was seen that in many cases when
more data was wanted was when another message, usually at KERN_ERR level,
was logged. And in most cases, what the additional logging that was then
enabled was typically. Most of these areas fell into the discovery machine.
Based on this summary, the following design has been put in place: The
driver will maintain an internal log (256 elements of 256 bytes). The
"additional logging" messages that are usually enabled in a reproduction
will be changed to now log all the time to the internal log. A new logging
level is defined - LOG_TRACE_EVENT. When this level is set (it is not by
default) and a message marked as KERN_ERR is logged, all the messages in
the internal log will be dumped to the kernel log before the KERN_ERR
message is logged.
There is a timestamp on each message added to the internal log. However,
this timestamp is not converted to wall time when logged. The value of the
timestamp is solely to give a crude time reference for the messages.
Link: https://lore.kernel.org/r/20200630215001.70793-14-jsmart2021@gmail.com
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
Although the existing implementation is very good at high I/O load, on
tests involving light load, especially on only a few hardware queues,
latency was a little higher than it can be due to using workqueue
scheduling. Other tasks in the system can delay handling.
Change the lower level to use irq_poll by default which uses a softirq for
I/O completion. This gives better latency as variance in when the cq is
processed is reduced over the workqueue interface. However, as high load is
better served by not being in softirq when the CPU is loaded, work queues
are still used under high I/O load.
Link: https://lore.kernel.org/r/20200630215001.70793-13-jsmart2021@gmail.com
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
Pull SCSI updates from James Bottomley:
:This series consists of the usual driver updates (qla2xxx, ufs, zfcp,
target, scsi_debug, lpfc, qedi, qedf, hisi_sas, mpt3sas) plus a host
of other minor updates.
There are no major core changes in this series apart from a
refactoring in scsi_lib.c"
* tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi: (207 commits)
scsi: ufs: ti-j721e-ufs: Fix unwinding of pm_runtime changes
scsi: cxgb3i: Fix some leaks in init_act_open()
scsi: ibmvscsi: Make some functions static
scsi: iscsi: Fix deadlock on recovery path during GFP_IO reclaim
scsi: ufs: Fix WriteBooster flush during runtime suspend
scsi: ufs: Fix index of attributes query for WriteBooster feature
scsi: ufs: Allow WriteBooster on UFS 2.2 devices
scsi: ufs: Remove unnecessary memset for dev_info
scsi: ufs-qcom: Fix scheduling while atomic issue
scsi: mpt3sas: Fix reply queue count in non RDPQ mode
scsi: lpfc: Fix lpfc_nodelist leak when processing unsolicited event
scsi: target: tcmu: Fix a use after free in tcmu_check_expired_queue_cmd()
scsi: vhost: Notify TCM about the maximum sg entries supported per command
scsi: qla2xxx: Remove return value from qla_nvme_ls()
scsi: qla2xxx: Remove an unused function
scsi: iscsi: Register sysfs for iscsi workqueue
scsi: scsi_debug: Parser tables and code interaction
scsi: core: Refactor scsi_mq_setup_tags function
scsi: core: Fix incorrect usage of shost_for_each_device
scsi: qla2xxx: Fix endianness annotations in source files
...
|
|
To support FC-NVME-2 support (actually FC-NVME (rev 1) with Ammendment 1),
both the nvme (host) and nvmet (controller/target) sides will need to be
able to receive LS requests. Currently, this support is in the nvmet side
only. To prepare for both sides supporting LS receive, rename
lpfc_nvmet_rcv_ctx to lpfc_async_xchg_ctx and commonize the definition.
Signed-off-by: Paul Ely <paul.ely@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
By default, the driver attempts to allocate a hdwq per logical cpu in order
to provide good cpu affinity. Some systems have extremely high cpu counts
and this can significantly raise memory consumption.
In testing on x86 platforms (non-AMD) it is found that sharing of a hdwq by
a physical cpu and its HT cpu can occur with little performance
degredation. By sharing, the hdwq count can be halved, significantly
reducing the memory overhead.
Change the default behavior of the driver on non-AMD x86 platforms to
share a hdwq by the cpu and its HT cpu.
Link: https://lore.kernel.org/r/20200501214310.91713-6-jsmart2021@gmail.com
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
During code review, identified dss feature that was a prototype only and
was never productized in SLI3. They shouldn't be there and prevents reuse
of the command areas.
Remove any code in the driver to deal with dss, including code to deal with
fips, which is associated with the dss feature.
Link: https://lore.kernel.org/r/20200322181304.37655-12-jsmart2021@gmail.com
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
Currently driver ktime stats, measuring code paths, is NVME-specific.
Convert the stats routines such that the code paths are generic, providing
status for NVME and SCSI. Added ktime stat calls in SCSI queuecommand and
cmpl routines.
Link: https://lore.kernel.org/r/20200322181304.37655-11-jsmart2021@gmail.com
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
The cpu io statistics were capped by a hard define limit of 128. This
effectively was a max number of CPUs, not an actual CPU count, nor actual
CPU numbers which can be even larger than both of those values. This made
stats off/misleading and on large CPU count systems, wrong.
Fix the stats so that all CPUs can have a stats struct. Fix the looping
such that it loops by hdwq, finds CPUs that used the hdwq, and sum the
stats, then display.
Link: https://lore.kernel.org/r/20200322181304.37655-9-jsmart2021@gmail.com
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
SCSI layer sends driver IOs with more s/g segments than driver can handle.
This results in "Too many sg segments from dma_map_sg. Config 64, seg_cnt
219" error messages from the lpfc_scsi_prep_dma_buf_s3() routine.
The was due to use the driver using individual templates for pport and
vport, host reset enabled or not, nvme vs scsi, etc. In the end, there was
a combination for a vport that didn't match the pport.
Rather than enumerating more templates and more discretionary assignments,
revert to a base template that is copied to a template specific to the
pport/vport. Then, based on role, attributes and sli type, modify the
fields that are different for that port. Added a log message to
lpfc_create_port to validate values.
Link: https://lore.kernel.org/r/20200322181304.37655-5-jsmart2021@gmail.com
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
This patch modifies lpfc to register for Link Integrity events via the use
of an RDF ELS and to perform Link Integrity FPIN logging.
Specifically, the driver was modified to:
- Format and issue the RDF ELS immediately following SCR registration.
This registers the ability of the driver to receive FPIN ELS.
- Adds decoding of the FPIN els into the received descriptors, with
logging of the Link Integrity event information. After decoding, the ELS
is delivered to the scsi fc transport to be delivered to any user-space
applications.
- To aid in logging, simple helpers were added to create enum to name
string lookup functions that utilize the initialization helpers from the
fc_els.h header.
- Note: base header definitions for the ELS's don't populate the
descriptor payloads. As such, lpfc creates it's own version of the
structures, using the base definitions (mostly headers) and additionally
declaring the descriptors that will complete the population of the ELS.
Link: https://lore.kernel.org/r/20200210173155.547-3-jsmart2021@gmail.com
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
Update copyrights to 2020 for files modified in the 12.6.0.4 patch set.
Link: https://lore.kernel.org/r/20200128002312.16346-13-jsmart2021@gmail.com
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
There was report of an odd "Fix me..." log message, which was tracked down
to the lpfc_els_rcv_rps() routine. This was in handling of a very old and
obsolete ELS - Read Port Status. The RPS ELS was defined in FC-LS-1, but
deprecated in FC-LS-2, and removed from all later FC-LS revisions. It was
replaced by the Read Diagnostic Parameters (RDP) ELS and the Link Error
Status Block descriptor.
There should be no support for the RSP ELS. Remove support from driver.
Link: https://lore.kernel.org/r/20200128002312.16346-9-jsmart2021@gmail.com
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
When driver is set to enable bb credit recovery, the switch displayed the
setting as inactive. If the link bounces, it switches to Active.
During link up processing, the driver currently does a MBX_READ_SPARAM
followed by a MBX_CONFIG_LINK. These mbox commands are queued to be
executed, one at a time and the completion is processed by the worker
thread. Since the MBX_READ_SPARAM is done BEFORE the MBX_CONFIG_LINK, the
BB_SC_N bit is never set the the returned values. BB Credit recovery status
only gets set after the driver requests the feature in CONFIG_LINK, which
is done after the link up. Thus the ordering of READ_SPARAM needs to follow
the CONFIG_LINK.
Fix by reordering so that READ_SPARAM is done after CONFIG_LINK. Added a
HBA_DEFER_FLOGI flag so that any FLOGI handling waits until after the
READ_SPARAM is done so that the proper BB credit value is set in the FLOGI
payload.
Fixes: 6bfb16208298 ("scsi: lpfc: Fix configuration of BB credit recovery in service parameters")
Cc: <stable@vger.kernel.org> # v5.4+
Link: https://lore.kernel.org/r/20200128002312.16346-4-jsmart2021@gmail.com
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
There are reports of multiple ports on the same system displaying different
hostnames in fabric FDMI displays.
Currently, the driver registers the hostname at initialization and obtains
the hostname via init_utsname()->nodename queried at the time the FC link
comes up. Unfortunately, if the machine hostname is updated after
initialization, such as via DHCP or admin command, the value registered
initially will be incorrect.
Fix by having the driver save the hostname that was registered with FDMI.
The driver then runs a heartbeat action that will check the hostname. If
the name changes, reregister the FMDI data.
The hostname is used in RSNN_NN, FDMI RPA and FDMI RHBA.
Link: https://lore.kernel.org/r/20191218235808.31922-5-jsmart2021@gmail.com
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
The current driver attempts to allocate an interrupt vector per cpu using
the systems managed IRQ allocator (flag PCI_IRQ_AFFINITY). The system IRQ
allocator will either provide the per-cpu vector, or return fewer
vectors. When fewer vectors, they are evenly spread between the numa nodes
on the system. When run on an AMD architecture, if interrupts occur to a
cpu that is not in the same numa node as the adapter generating the
interrupt, there are extreme costs and overheads in performance. Thus, if
1:1 vector allocation is used, or the "balanced" vectors in the other numa
nodes, performance can be hit significantly.
A much more performant model is to allocate interrupts only on the cpus
that are in the numa node where the adapter resides. I/O completion is
still performed by the cpu where the I/O was generated. Unfortunately,
there is no flag to request the managed IRQ subsystem allocate vectors only
for the CPUs in the numa node as the adapter.
On AMD architecture, revert the irq allocation to the normal style
(non-managed) and then use irq_set_affinity_hint() to set the cpu
affinity and disable user-space rebalancing.
Tie the support into CPU offline/online. If the cpu being offlined owns a
vector, the vector is re-affinitized to one of the other CPUs on the same
numa node. If there are no more CPUs on the numa node, the vector has all
affinity removed and lets the system determine where it's serviced.
Similarly, when the cpu that owned a vector comes online, the vector is
reaffinitized to the cpu.
Link: https://lore.kernel.org/r/20191105005708.7399-10-jsmart2021@gmail.com
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
The recent affinitization didn't address cpu offlining/onlining. If an
interrupt vector is shared and the low order cpu owning the vector is
offlined, as interrupts are managed, the vector is taken offline. This
causes the other CPUs sharing the vector will hang as they can't get io
completions.
Correct by registering callbacks with the system for Offline/Online
events. When a cpu is taken offline, its eq, which is tied to an interrupt
vector is found. If the cpu is the "owner" of the vector and if the
eq/vector is shared by other CPUs, the eq is placed into a polled mode.
Additionally, code paths that perform io submission on the "sharing CPUs"
will check the eq state and poll for completion after submission of new io
to a wq that uses the eq.
Similarly, when a cpu comes back online and owns an offlined vector, the eq
is taken out of polled mode and rearmed to start driving interrupts for eq.
Link: https://lore.kernel.org/r/20191105005708.7399-9-jsmart2021@gmail.com
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
In the past, the lpe32000 models, based their main support being for 32G,
and as FC-AL is not supported in the FC standards past 8G, did not support
FC-AL operation.
This patch adds private-loop FC-AL support for the LPE32000 adapters
when a link is 8G or below. To avoid conditions where link rate may
change, which would cause non-connectivity to the AL device, FC-AL
mode must become a persistent setting and the link kept at a speed
supporting FC-AL.
The patch:
- Adds a pls attribute indicating whether the adapter properly supports
FC-AL.
- Adds support for the adapter to indicate that topology should be fixed
and the topology types to be configured.
- Adds a pt attribute to report the persistent topology if present.
Link: https://lore.kernel.org/r/20191018211832.7917-15-jsmart2021@gmail.com
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
Currently, the FW logging facility is a load/boot time parameter which
requires the driver to be unloaded/reloaded or the system rebooted in order
to change its configuration.
Convert the logging facility to allow dynamic enablement and configuration.
Specifically:
- Convert the feature so that it can be enabled dynamically via an
attribute. Additionally, the size of the buffer can be configured
dynamically.
- Add locks around states that now may be changing.
- Tie the feature into debugfs so that the logs can be read at any time.
Link: https://lore.kernel.org/r/20191018211832.7917-12-jsmart2021@gmail.com
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
Lower IOps performance with write operations. Perf tool shows lock
contention in dma_pool_alloc and dma_pool_free related to the
txrdy_payload_pool.
The allocations are for dma buffers for XFER_RDY's, which actually are not
needed for the FCP_TRECEIVE command as the command contents are used by the
adapter to generate the IU.
Remove the allocations and the associated buffer pool. Rather than leaving
NULLs in buffer pointer locations, set command and sgl to indicate skipped
SGLE indexes.
Link: https://lore.kernel.org/r/20191018211832.7917-10-jsmart2021@gmail.com
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
The nvme-fc transport may call to abort an io on controller reset. If the
driver is out of resources to issue an abort command, it just gives up and
does nothing. The transport expects the lldd to always be able to terminate
an io it has issued. At that point, the controller hangs waiting for
aborted ios to be returned. Note: flaged by "6136" and "6176" error
messages.
Root issue was the adapter mis-allocated the number resources it allocated
for command entries for the adapter.
Convert the driver to allocate command resources based on the number of
xris supported by the FC port - 1 resource for the original command and 1
resource for the abort request.
Link: https://lore.kernel.org/r/20190922035906.10977-5-jsmart2021@gmail.com
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
Pull SCSI updates from James Bottomley:
"This is mostly update of the usual drivers: qla2xxx, ufs, smartpqi,
lpfc, hisi_sas, qedf, mpt3sas; plus a whole load of minor updates. The
only core change this time around is the addition of request batching
for virtio. Since batching requires an additional flag to use, it
should be invisible to the rest of the drivers"
* tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi: (264 commits)
scsi: hisi_sas: Fix the conflict between device gone and host reset
scsi: hisi_sas: Add BIST support for phy loopback
scsi: hisi_sas: Add hisi_sas_debugfs_alloc() to centralise allocation
scsi: hisi_sas: Remove some unused function arguments
scsi: hisi_sas: Remove redundant work declaration
scsi: hisi_sas: Remove hisi_sas_hw.slot_complete
scsi: hisi_sas: Assign NCQ tag for all NCQ commands
scsi: hisi_sas: Update all the registers after suspend and resume
scsi: hisi_sas: Retry 3 times TMF IO for SAS disks when init device
scsi: hisi_sas: Remove sleep after issue phy reset if sas_smp_phy_control() fails
scsi: hisi_sas: Directly return when running I_T_nexus reset if phy disabled
scsi: hisi_sas: Use true/false as input parameter of sas_phy_reset()
scsi: hisi_sas: add debugfs auto-trigger for internal abort time out
scsi: virtio_scsi: unplug LUNs when events missed
scsi: scsi_dh_rdac: zero cdb in send_mode_select()
scsi: fcoe: fix null-ptr-deref Read in fc_release_transport
scsi: ufs-hisi: use devm_platform_ioremap_resource() to simplify code
scsi: ufshcd: use devm_platform_ioremap_resource() to simplify code
scsi: hisi_sas: use devm_platform_ioremap_resource() to simplify code
scsi: ufs: Use kmemdup in ufshcd_read_string_desc()
...
|
|
Capturing and downloading dif command data and dif data was done a dozen
years ago and no longer being used. Also creates a potential security hole.
Remove the debugfs buffer for dif debugging.
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
CC: KyleMahlkuch <kmahlkuc@linux.vnet.ibm.com>
CC: Hannes Reinecke <hare@suse.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
Currently, each hardware queue, typically allocated per-cpu, consists of a
WQ/CQ pair per protocol. Meaning if both SCSI and NVMe are supported 2
WQ/CQ pairs will exist for the hardware queue. Separate queues are
unnecessary. The current implementation wastes memory backing the 2nd set
of queues, and the use of double the SLI-4 WQ/CQ's means less hardware
queues can be supported which means there may not always be enough to have
a pair per cpu. If there is only 1 pair per cpu, more cpu's may get their
own WQ/CQ.
Rework the implementation to use a single WQ/CQ pair by both protocols.
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
FC-NVMe-2 added support for sequence level error recovery in the FC-NVME
protocol. This allows for the detection of errors and lost frames and
immediate retransmission of data to avoid exchange termination, which
escalates into NVMeoFC connection and association failures. A significant
RAS improvement.
The driver is modified to indicate support for SLER in the NVMe PRLI is
issues and to check for support in the PRLI response. When both sides
support it, the driver will set a bit in the WQE to enable the recovery
behavior on the exchange. The adapter will take care of all detection and
retransmission.
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
Typical SLI-4 hardware supports up to 2 4KB pages to be registered per XRI
to contain the exchanges Scatter/Gather List. This caps the number of SGL
elements that can be in the SGL. There are not extensions to extend the
list out of the 2 pages.
The G7 hardware adds a SGE type that allows the SGL to be vectored to a
different scatter/gather list segment. And that segment can contain a SGE
to go to another segment and so on. The initial segment must still be
pre-registered for the XRI, but it can be a much smaller amount (256Bytes)
as it can now be dynamically grown. This much smaller allocation can
handle the SG list for most normal I/O, and the dynamic aspect allows it to
support many MB's if needed.
The implementation creates a pool which contains "segments" and which is
initially sized to hold the initial small segment per xri. If an I/O
requires additional segments, they are allocated from the pool. If the
pool has no more segments, the pool is grown based on what is now
needed. After the I/O completes, the additional segments are returned to
the pool for use by other I/Os. Once allocated, the additional segments are
not released under the assumption of "if needed once, it will be needed
again". Pools are kept on a per-hardware queue basis, which is typically
1:1 per cpu, but may be shared by multiple cpus.
The switch to the smaller initial allocation significantly reduces the
memory footprint of the driver (which only grows if large ios are
issued). Based on the several K of XRIs for the adapter, the 8KB->256B
reduction can conserve 32MBs or more.
It has been observed with per-cpu resource pools that allocating a resource
on CPU A, may be put back on CPU B. While the get routines are distributed
evenly, only a limited subset of CPUs may be handling the put routines.
This can put a strain on the lpfc_put_cmd_rsp_buf_per_cpu routine because
all the resources are being put on a limited subset of CPUs.
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
When SCSI-MQ is enabled, the SCSI-MQ layers will do pre-allocation of MQ
resources based on shost values set by the driver. In newer cases of the
driver, which attempts to set nr_hw_queues to the cpu count, the
multipliers become excessive, with a single shost having SCSI-MQ
pre-allocation reaching into the multiple GBytes range. NPIV, which
creates additional shosts, only multiply this overhead. On lower-memory
systems, this can exhaust system memory very quickly, resulting in a system
crash or failures in the driver or elsewhere due to low memory conditions.
After testing several scenarios, the situation can be mitigated by limiting
the value set in shost->nr_hw_queues to 4. Although the shost values were
changed, the driver still had per-cpu hardware queues of its own that
allowed parallelization per-cpu. Testing revealed that even with the
smallish number for nr_hw_queues for SCSI-MQ, performance levels remained
near maximum with the within-driver affiinitization.
A module parameter was created to allow the value set for the nr_hw_queues
to be tunable.
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Ewan D. Milne <emilne@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
To support scenarios which aren't bound to nvmetcli add port scenarios,
which is currently where the nvmet_fc transport invokes the discovery
event callbacks, a syfs attribute is added to lpfc which can be written
to cause an RSCN to be generated for the nport.
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Arun Easi <aeasi@marvell.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
|
|
This patch adds general RSCN support:
- The ability to transmit an RSCN to the port on the other end of
the link (regular port if pt2pt, or fabric controller if fabric).
- And general recognition of an RSCN ELS when an ELS is received.
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Arun Easi <aeasi@marvell.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
|
|
The driver is currently reporting the firmware revision not the actual boot
bios version in FDMI data.
Modify the driver to obtain the boot bios version from the adapter and use
that data in the FMDI data sent to the switch.
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
For files modified as part of 12.2.0.0 patches, update copyright to 2019
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
When the transport calls into the lpfc target to release an IO job
structure, which corresponds to an exchange, and if the driver was waiting
for an exchange in order to post a previously received command to the
transport, the driver immediately takes the IO job and reuses the context
for the prior command and calls nvmet_fc_rcv_fcp_req() to tell the
transport about a newly received command.
Problem is, the execution of the IO job release may be in the context of
the back end driver and its bio completion handlers, thus it may be in a
irq context and protection code kicks in in the bio and request layers that
are subsequently called.
Rework lpfc so that instead of immediately upcalling, queue it to a
deferred work thread and have the thread make the upcall.
Took advantage of this change to remove duplicated code with the normal
command receive path that preps the IO job and upcalls nvmet_fc. Created a
common routine both paths use.
Also corrected some errors that were found during review of the context
freeing and reuse - basically unlocked operations and a somewhat disjoint
set of calls to release associated job elements. Cleaned up this path and
added locks for coherency.
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
The conversion to enable SCSI and NVME fc4 support ran into an issue with
NPIV support. With NVME, NPIV is not currently supported, but with SCSI it
was. The driver reverted to its lowest setting meaning NPIV with SCSI was
not allowed.
Convert the NPIV checks and implementation so that SCSI can continue to
allow NPIV support.
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
When driving high iop counts, auto_imax coalescing kicks in and drives the
performance to extremely small iops levels.
There are two issues:
1) auto_imax is enabled by default. The auto algorithm, when iops gets
high, divides the iops by the hdwq count and uses that value to
calculate EQ_Delay. The EQ_Delay is set uniformly on all EQs whether
they have load or not. The EQ_delay is only manipulated every 5s (a
long time). Thus there were large 5s swings of no interrupt delay
followed by large/maximum delay, before repeating.
2) When processing a CQ, the driver got mixed up on the rate of when
to ring the doorbell to keep the chip appraised of the eqe or cqe
consumption as well as how how long to sit in the thread and
process queue entries. Currently, the driver capped its work at
64 entries (very small) and exited/rearmed the CQ. Thus, on heavy
loads, additional overheads were taken to exit and re-enter the
interrupt handler. Worse, if in the large/maximum coalescing
windows,k it could be a while before getting back to servicing.
The issues are corrected by the following:
- A change in defaults. Auto_imax is turned OFF and fcp_imax is set
to 0. Thus all interrupts are immediate.
- Cleanup of field names and their meanings. Existing names were
non-intuitive or used for duplicate things.
- Added max_proc_limit field, to control the length of time the
handlers would service completions.
- Reworked EQ handling:
Added common routine that walks eq, applying notify interval and max
processing limits. Use queue_claimed to claim ownership of the queue
while processing. Always rearm the queue whenever the common routine
is called.
Rework queue element processing, namely to eliminate hba_index vs
host_index. Only one index is necessary. The queue entry can be
marked invalid and the host_index updated immediately after eqe
processing.
After rework, xx_release routines are now DB write functions. Renamed
the routines as such.
Moved lpfc_sli4_eq_flush(), which does similar action, to same area.
Replaced the 2 individual loops that walk an eq with a call to the
common routine.
Slightly revised lpfc_sli4_hba_handle_eqe() calling syntax.
Added per-cpu counters to detect interrupt rates and scale
interrupt coalescing values.
- Reworked CQ handling:
Added common routine that walks cq, applying notify interval and max
processing limits. Use queue_claimed to claim ownership of the queue
while processing. Always rearm the queue whenever the common routine
is called.
Rework queue element processing, namely to eliminate hba_index vs
host_index. Only one index is necessary. The queue entry can be
marked invalid and the host_index updated immediately after cqe
processing.
After rework, xx_release routines are now DB write functions. Renamed
the routines as such.
Replaced the 3 individual loops that walk a cq with a call to the
common routine.
Redefined lpfc_sli4_sp_handle_mcqe() to commong handler definition with
queue reference. Add increment for mbox completion to handler.
- Added a new module/sysfs attribute: lpfc_cq_max_proc_limit To allow
dynamic changing of the CQ max_proc_limit value being used.
Although this leaves an EQ as an immediate interrupt, that interrupt will
only occur if a CQ bound to it is in an armed state and has cqe's to
process. By staying in the cq processing routine longer, high loads will
avoid generating more interrupts as they will only rearm as the processing
thread exits. The immediately interrupt is also beneficial to idle or
lower-processing CQ's as they get serviced immediately without being
penalized by sharing an EQ with a more loaded CQ.
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
So far MSIX vector allocation assumed it would be 1:1 with hardware
queues. However, there are several reasons why fewer MSIX vectors may be
allocated than hardware queues such as the platform being out of vectors or
adapter limits being less than cpu count.
This patch reworks the MSIX/EQ relationships with the per-cpu hardware
queues so they can function independently. MSIX vectors will be equitably
split been cpu sockets/cores and then the per-cpu hardware queues will be
mapped to the vectors most efficient for them.
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
The XRI get/put lists were partitioned per hardware queue. However, the
adapter rarely had sufficient resources to give a large number of resources
per queue. As such, it became common for a cpu to encounter a lack of XRI
resource and request the upper io stack to retry after returning a BUSY
condition. This occurred even though other cpus were idle and not using
their resources.
Create as efficient a scheme as possible to move resources to the cpus that
need them. Each cpu maintains a small private pool which it allocates from
for io. There is a watermark that the cpu attempts to keep in the private
pool. The private pool, when empty, pulls from a global pool from the
cpu. When the cpu's global pool is empty it will pull from other cpu's
global pool. As there many cpu global pools (1 per cpu or hardware queue
count) and as each cpu selects what cpu to pull from at different rates and
at different times, it creates a radomizing effect that minimizes the
number of cpu's that will contend with each other when the steal XRI's from
another cpu's global pool.
On io completion, a cpu will push the XRI back on to its private pool. A
watermark level is maintained for the private pool such that when it is
exceeded it will move XRI's to the CPU global pool so that other cpu's may
allocate them.
On NVME, as heartbeat commands are critical to get placed on the wire, a
single expedite pool is maintained. When a heartbeat is to be sent, it will
allocate an XRI from the expedite pool rather than the normal cpu
private/global pools. On any io completion, if a reduction in the expedite
pools is seen, it will be replenished before the XRI is placed on the cpu
private pool.
Statistics are added to aid understanding the XRI levels on each cpu and
their behaviors.
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
Now that the lower half has much better per-cpu parallelization using the
hardware queues, the SCSI MQ support needs to be tied into it.
The involves the following mods:
- Use the hardware queue info from the midlayer to help select the
hardware queue to utilize. This required change to the get_scsi-buf_xxx
routines.
- Remove lpfc_sli4_scmd_to_wqidx_distr() routine. No longer needed.
- Includes fix for SLI-3 that does not have multi queue parallelization.
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
Many io statistics were being sampled and saved using adapter-based data
structures. This was creating a lot of contention and cache thrashing in
the I/O path.
Move the statistics to the hardware queue data structures. Given the
per-queue data structures, use of atomic types is lessened.
Add new sysfs and debugfs stat routines to collate the per hardware queue
values and report at an adapter level.
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
Similar to the io execution path that reports cpu context information, the
debugfs routines for cpu information needs to be aligned with new hardware
queue implementation.
Convert debugfs cnd nvme cpucheck statistics to report information per
Hardware Queue.
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
