Pull rdma updates from Doug Ledford:
"This is a big pull request.
Of note is that I'm sending you the new ioctl API for the rdma
subsystem. We put it up on linux-api@, but didn't get much response.
The API is complex, but it solves two different problems in one go:
1) The bi-directional nature of the RDMA file write calls, which
created the security hole we had to handle (and for which the fix
is now causing problems for systems in production, we were a bit
over zealous in the fix and the ability to open a device, then
fork, then create new queue pairs on the device and use them is
broken).
2) The bloat caused by different vendors implementing extensions to
the base verbs API. Each vendor's hardware is slightly different,
and the hardware might be suitable for one extension but not
another.
By the time we add generic extensions for all the different ways
that the different hardware can offload things, the API becomes
bloated. Things like our completion structs have started to exceed
a cache line in size because of all the elements needed to support
this. That in turn shows up heavily in the performance graphs with
a noticable drop in performance on 100Gigabit links as our
completion structs go from occupying one cache line to 1+.
This API makes things like the completion structs modular in a
very similar way to netlink so that your structs can only include
the items needed for the offloads/features you are actually using
on a given queue pair. In that way we support everything, but only
use what we need, and our structs stay smaller.
The ioctl API is better explained by the posting on linux-api@ than I
can explain it here, so I'll just leave it at that.
The rest of the pull request is typical stuff.
Updates for 4.14 kernel merge window
- Lots of hfi1 driver updates (mixed with a few qib and core updates
as well)
- rxe updates
- various mlx updates
- Set default roce type to RoCEv2
- Several larger fixes for bnxt_re that were too big for -rc
- Several larger fixes for qedr that, likewise, were too big for -rc
- Misc core changes
- Make the hns_roce driver compilable on arches other than aarch64 so
we can more easily debug build issues related to it
- Add rdma-netlink infrastructure updates
- Add automatic IRQ affinity infrastructure
- Add 32bit lid support
- Lots of misc fixes across the subsystem from random people
- Autoloading of RDMA netlink modules
- PCI pool cleanups from Romain Perier
- mlx5 driver feature additions and fixes
- Hardware tag matchine feature
- Fix sleeping in atomic when resolving roce ah
- Add experimental ioctl interface as posted to linux-api@"
* tag 'for-linus-ioctl' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (328 commits)
IB/core: Expose ioctl interface through experimental Kconfig
IB/core: Assign root to all drivers
IB/core: Add completion queue (cq) object actions
IB/core: Add legacy driver's user-data
IB/core: Export ioctl enum types to user-space
IB/core: Explicitly destroy an object while keeping uobject
IB/core: Add macros for declaring methods and attributes
IB/core: Add uverbs merge trees functionality
IB/core: Add DEVICE object and root tree structure
IB/core: Declare an object instead of declaring only type attributes
IB/core: Add new ioctl interface
RDMA/vmw_pvrdma: Fix a signedness
RDMA/vmw_pvrdma: Report network header type in WC
IB/core: Add might_sleep() annotation to ib_init_ah_from_wc()
IB/cm: Fix sleeping in atomic when RoCE is used
IB/core: Add support to finalize objects in one transaction
IB/core: Add a generic way to execute an operation on a uobject
Documentation: Hardware tag matching
IB/mlx5: Support IB_SRQT_TM
net/mlx5: Add XRQ support
...
Due to various page sizes in the system (IOMMU/device/kernel), we
set the fabrics controller page size to 4k and block layer boundaries
accordinglly. In architectures that uses different kernel page size
we'll have a mismatch to the MR page size that may cause a mapping error.
Update the MR page size to correspond to the core ctrl settings.
Signed-off-by: Max Gurtovoy <maxg@mellanox.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
This patch slightly improves performance (mainly for small block sizes).
Signed-off-by: Max Gurtovoy <maxg@mellanox.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
To make the nvme_rdma_configure_admin_queue generic in preparation of
moving it to common code.
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
No need to queue an extra work to indirect controller removal, just call the
ctrl remove routine.
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
This should pair with nvme_rdma_stop_queue. While this is not a complete
inverse, it still pairs up pretty well because in fabrics we don't have a
disconnect capsule (yet) but we simply teardown the transport association.
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Give it a name symmetric to nvme_rdma_free_queue. Also pass in the ctrl
sqsize+1 and not the opts queue_size. And suppress a superflous
failure message.
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
If we move the queues from LIVE state, we might as well stop them (drain
for rdma). Do it after we stop the request queues to prevent a stray
request sneaking in .queue_rq after we stop the queue.
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Mimic the pci driver as a controller disable might be more lightweight
than a shutdown.
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
We always pair tagset allocation with rdma device reference and it shares
some code, centralize it with an argument if its an admin or IO tagset.
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
We will call it from other places so avoid having to forward declare it.
Also move it next to nvme_rdma_destroy_admin_queue.
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
NVME_RDMA_MAX_SEGMENT_SIZE is not used anywhere, zap it.
Signed-off-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Max Gurtovoy <maxg@mellanox.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Conflicts:
drivers/infiniband/core/iwcm.c - The rdma_netlink patches in
HEAD and the iwarp cm workqueue fix (don't use WQ_MEM_RECLAIM,
we aren't safe for that context) touched the same code.
Signed-off-by: Doug Ledford <dledford@redhat.com>
Since blk_mq_ops.reinit_request is only called from inside
blk_mq_reinit_tagset(), make this function pointer an argument of
blk_mq_reinit_tagset() instead of a member of struct blk_mq_ops.
This patch does not change any functionality but makes
blk_mq_reinit_tagset() calls easier to read and to analyze.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Sagi Grimberg <sagi@grimberg.me>
Cc: James Smart <james.smart@broadcom.com>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Use the generic block layer affinity mapping helper. Also,
limit nr_hw_queues to the rdma device number of irq vectors
as we don't really need more.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Doug Ledford <dledford@redhat.com>
When our RDMA queue-pair is torn down with high load
of I/O traffic, we have no way of knowing if the
memory region was actually registered by the reg_mr
work request as it completion flushes with error (hw
might have done it or not).
So in order to not deal with all this uncertanty, we
simply recycle the MR in reinit_request.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Usually before we teardown the controller we want to:
1. complete/cancel any ctrl inflight works
2. remove ctrl namespaces (only for removal though, resets
shouldn't remove any namespaces).
but we do not want to destroy the controller device as
we might use it for logging during the teardown stage.
This patch adds nvme_start_ctrl() which queues inflight
controller works (aen, ns scan, queue start and keep-alive
if kato is set) and nvme_stop_ctrl() which cancels the works
namespace removal is left to the callers to handle.
Move nvme_uninit_ctrl after we are done with the
controller device.
Reviewed-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
unlike blk_mq_stop_hw_queues and blk_mq_start_stopped_hw_queues
quiescing/unquiescing respects the submission path rcu grace.
Also make sure to kick the requeue list when appropriate.
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
This patch improves the way the RDMA IB signalling is done by using atomic
operations for the signalling variable. This avoids race conditions on
sig_count.
The signalling interval changes slightly and is now the largest power of
two not larger than queue depth / 2.
ilog() usage idea by Bart Van Assche.
Signed-off-by: Marta Rybczynska <marta.rybczynska@kalray.eu>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Cc: stable@vger.kernel.org
We might have more/less queues once we reconnect/reset. For
example due to cpu going online/offline or controller constraints.
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
All transports use either a private cache of controller cap or an on-stack
copy, move it to the generic struct nvme_ctrl. In the future it will also
be maintained by the core.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Max Gurtovoy <maxg@mellanox.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
All all transports use the queue_count in exactly the same, so move it to
the generic struct nvme_ctrl. In the future it will also be maintained by
the core.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-By: James Smart <james.smart@broadcom.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Max Gurtovoy <maxg@mellanox.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
NVMe 1.2.1 or later requires controllers to provide a subsystem NQN in the
Identify controller data structures. Use this NQN for the subsysnqn
sysfs attribute by storing it in the nvme_ctrl structure after verifying
it. For older controllers we generate a "fake" NQN per non-normative
text in the NVMe 1.3 spec.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This moves the nvme_reset function from the PCIe driver to common code,
renaming it to nvme_reset_ctrl in the process. Additionally a new
helper nvme_reset_ctrl_sync is added for the case where we want to
wait for the reset. To facilitate that the reset_work work structure is
move to the common nvme_ctrl structure and the ->reset_ctrl method is
removed. For now the drivers initialize the reset_work with their own
callback, but longer term we should move to callouts for specific
parts of the reset process and move even more code to the core.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Now that we get the tagset passed we can have a single implementation for
the I/O and admin queues.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Max Gurtovoy <maxg@mellanox.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
We accidentally return ERR_PTR(0) which is NULL. The caller isn't
explicitly checking for that but I couldn't immediately spot whether
this would lead to a NULL dereference. Anyway, we can fix add an
error code easily enough.
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
It is not a user option but rather a variable controller
attribute.
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Instead of each transport using it's own workqueue, export
a single nvme-core workqueue and use that instead.
In the future, this will help us moving towards some unification
if controller setup/teardown flows.
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
We only care about if the queue is LIVE for request submission,
so no need for CONNECTED.
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Instead of introducing a flag for if the queue is allocated,
simply free the rdma resources when we get the error.
We allocate the queue rdma resources when we have an address
resolution, their we allocate (or take a reference on) our device
so we should free it when we have error after the address resolution
namely:
1. route resolution error
2. connect reject
3. connect error
4. peer unreachable error
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
We put the reference on the device in the destroy routine
so we should lookup and take the reference in the create
routine.
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
We don't need it as the core polling context will take
are of rearming the completion queue.
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
The merge of 4.12-rc5 into the for-4.13/block tree didn't handle the queue
ready case correctly. Fix this by propagating blk_status_t into
nvme_rdma_queue_is_ready.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
We've already got a few conflicts and upcoming work depends on some of the
changes that have gone into mainline as regression fixes for this series.
Pull in 4.12-rc5 to resolve these conflicts and make it easier on down stream
trees to continue working on 4.13 changes.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Use the same values for use for request completion errors as the return
value from ->queue_rq. BLK_STS_RESOURCE is special cased to cause
a requeue, and all the others are completed as-is.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
When we encounter an transport/controller errors, error recovery
kicks in which performs:
1. stops io/admin queues
2. moves transport queues out of LIVE state
3. fast fail pending io
4. schedule periodic reconnects.
But we also need to fast fail incoming IO taht enters after we
already scheduled. Given that our queue is not LIVE anymore, simply
restart the request queues to fail in .queue_rq
Reported-by: Alex Turin <alex@vastdata.com>
Reported-by: shahar.salzman <shahar.salzman@gmail.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Cc: stable@vger.kernel.org
So that we can have more flags for transport-specific behavior.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <keith.busch@intel.com>
In the case of small NVMe-oF queue size (<32) we may enter a deadlock
caused by the fact that the IB completions aren't sent waiting for 32
and the send queue will fill up.
The error is seen as (using mlx5):
[ 2048.693355] mlx5_0:mlx5_ib_post_send:3765:(pid 7273):
[ 2048.693360] nvme nvme1: nvme_rdma_post_send failed with error code -12
This patch changes the way the signaling is done so that it depends on
the queue depth now. The magic define has been removed completely.
Cc: stable@vger.kernel.org
Signed-off-by: Marta Rybczynska <marta.rybczynska@kalray.eu>
Signed-off-by: Samuel Jones <sjones@kalray.eu>
Acked-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Remove the request_idx parameter, which can't be used safely now that we
support I/O schedulers with blk-mq. Except for a superflous check in
mtip32xx it was unused anyway.
Also pass the tag_set instead of just the driver data - this allows drivers
to avoid some code duplication in a follow on cleanup.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
Pull block layer updates from Jens Axboe:
- Add BFQ IO scheduler under the new blk-mq scheduling framework. BFQ
was initially a fork of CFQ, but subsequently changed to implement
fairness based on B-WF2Q+, a modified variant of WF2Q. BFQ is meant
to be used on desktop type single drives, providing good fairness.
From Paolo.
- Add Kyber IO scheduler. This is a full multiqueue aware scheduler,
using a scalable token based algorithm that throttles IO based on
live completion IO stats, similary to blk-wbt. From Omar.
- A series from Jan, moving users to separately allocated backing
devices. This continues the work of separating backing device life
times, solving various problems with hot removal.
- A series of updates for lightnvm, mostly from Javier. Includes a
'pblk' target that exposes an open channel SSD as a physical block
device.
- A series of fixes and improvements for nbd from Josef.
- A series from Omar, removing queue sharing between devices on mostly
legacy drivers. This helps us clean up other bits, if we know that a
queue only has a single device backing. This has been overdue for
more than a decade.
- Fixes for the blk-stats, and improvements to unify the stats and user
windows. This both improves blk-wbt, and enables other users to
register a need to receive IO stats for a device. From Omar.
- blk-throttle improvements from Shaohua. This provides a scalable
framework for implementing scalable priotization - particularly for
blk-mq, but applicable to any type of block device. The interface is
marked experimental for now.
- Bucketized IO stats for IO polling from Stephen Bates. This improves
efficiency of polled workloads in the presence of mixed block size
IO.
- A few fixes for opal, from Scott.
- A few pulls for NVMe, including a lot of fixes for NVMe-over-fabrics.
From a variety of folks, mostly Sagi and James Smart.
- A series from Bart, improving our exposed info and capabilities from
the blk-mq debugfs support.
- A series from Christoph, cleaning up how handle WRITE_ZEROES.
- A series from Christoph, cleaning up the block layer handling of how
we track errors in a request. On top of being a nice cleanup, it also
shrinks the size of struct request a bit.
- Removal of mg_disk and hd (sorry Linus) by Christoph. The former was
never used by platforms, and the latter has outlived it's usefulness.
- Various little bug fixes and cleanups from a wide variety of folks.
* 'for-4.12/block' of git://git.kernel.dk/linux-block: (329 commits)
block: hide badblocks attribute by default
blk-mq: unify hctx delay_work and run_work
block: add kblock_mod_delayed_work_on()
blk-mq: unify hctx delayed_run_work and run_work
nbd: fix use after free on module unload
MAINTAINERS: bfq: Add Paolo as maintainer for the BFQ I/O scheduler
blk-mq-sched: alloate reserved tags out of normal pool
mtip32xx: use runtime tag to initialize command header
scsi: Implement blk_mq_ops.show_rq()
blk-mq: Add blk_mq_ops.show_rq()
blk-mq: Show operation, cmd_flags and rq_flags names
blk-mq: Make blk_flags_show() callers append a newline character
blk-mq: Move the "state" debugfs attribute one level down
blk-mq: Unregister debugfs attributes earlier
blk-mq: Only unregister hctxs for which registration succeeded
blk-mq-debugfs: Rename functions for registering and unregistering the mq directory
blk-mq: Let blk_mq_debugfs_register() look up the queue name
blk-mq: Register <dev>/queue/mq after having registered <dev>/queue
ide-pm: always pass 0 error to ide_complete_rq in ide_do_devset
ide-pm: always pass 0 error to __blk_end_request_all
..
We want our own clearly defined error field for NVMe passthrough commands,
and the request errors field is going away in its current form.
Just store the status and result field in the nvme_request field from
hardirq completion context (using a new helper) and then generate a
Linux errno for the block layer only when we actually need it.
Because we can't overload the status value with a negative error code
for cancelled command we now have a flags filed in struct nvme_request
that contains a bit for this condition.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
