At very high queue depths, bdev modules may not have enough
internal resources to track all of the incoming I/O. For example,
we allocate a finite number of nvme_request objects per allocated
queue pair. Currently if these resources are exhausted, the
bdev module will return failure (with no indication why) which
gets propagated all the way back to the application.
So instead, add SPDK_BDEV_IO_STATUS_NOMEM to allow bdev modules
to indicate this type of failure. Also add handling for this
status type in the generic bdev layer, involving queuing these
I/O for later retry after other I/O on the failing channel have
completed.
This does place an expectation on the bdev module that these
internal resources are allocated per io_channel. Otherwise we
cannot guarantee forward progress solely on reception of
completions. For example, without this guarantee, a bdev
module could theoretically return ENOMEM even if there were
no I/O oustanding for that io_channel. nvme, aio, rbd,
virtio and null drivers comply with this expectation already.
malloc only complies though when not using copy offload.
This patch will fix malloc w/ copy engine to at least
return ENOMEM when no copy descriptors are available. If the
condition above occurs, I/O waiting for resources will get
failed as part of a subsequent reset which matches the
behavior it has today.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Iea7cd51a611af8abe882794d0b2361fdbb74e84e
Reviewed-on: https://review.gerrithub.io/378853
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Use SPDK bdev subsystem to allow basic IO to pmem pool
using pmemblk_* calls.
New pmem bdev can be constructed using RPC call
construct_pmem_bdev PMEM_FILE
Signed-off-by: Piotr Pelplinski <piotr.pelplinski@intel.com>
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: If5ca94161fe53644b8fccd3b77de5479da1b2e55
Reviewed-on: https://review.gerrithub.io/376973
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
A few small tweaks to make this function easier to read:
- Return void (the return value is always 0 and never used)
- Split out Fabrics/admin queue processing 'if' block
- Remove unnecessary switch on status (it can only be 2 values)
Additionally, simplify the I/O command checking logic: we don't need to
check for CC.EN = 1, because it is only possible for I/O queues to be
created after CC.EN is set to 1.
Change-Id: Ib4c39a6e0d9e28912dbb0f0737fd223be0a80207
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/379218
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
virtio_dev can now be freed via virtio_dev_deinit.
While here, also rename virtio_init_device to
virtio_dev_init for name consistency.
This patch also adds some error-checking.
Change-Id: Ic1222756b8686fbd8a14d8631f25525249529e1d
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/379335
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Added virtio_hw->pci_bar[6] to store information
about mapped memory regions. They have to be
stored to make it possible to unmap them.
The unmapping itself is done in a separate
patch.
Change-Id: I5dcffd0674e855a02086b3d8e4adc5fac451229a
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/380779
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Generic virtio_dev has the same field already.
The field was previously used to store vhost-user
GET_QUEUE_NUM response, that will be later assigned
to virtio_dev->max_queues via virtio_user_read_dev_config.
This patch removes virtio_user_dev->max_queues
with entire virtio_user_read_dev_config functionality
for virtio_user.
Change-Id: I508f728215a95cf977d6b0b20350fcf2ae11fe3a
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/379155
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Replaced direct DPDK calls with SPDK env/pci
equivalents. This patch also makes the PCI scan
happen only conditionally when user has
configured proper field in the bdev_virtio config
file.
Change-Id: Ib6ad81d0b421b20ad0cd9d02cb40b2213af823e6
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/379489
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
The same condition is already checked
in spdk_bdev_free_io().
Change-Id: I31f937036d3835e2d16633c6338ebca1a2237de9
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/379722
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
A device without LUNs can't be used at all,
so remove it automatically
Change-Id: Iefea73916c83dfddf0229bbfac5dacb23590d920
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/371299
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
A random host ID is generated per SPDK application startup if the user
doesn't specify a host ID during controller startup.
This also changes the default host NQN for NVMe-oF connections to a
random UUID NQN based on the host ID.
Change-Id: Ib0f70dd63e53087716842b412a1f134a9991d4da
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/380528
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Also updated docs.
Change-Id: I2e53c31b2c9c575d8adea23ed92f113e69f324ed
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/380490
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Current UNMAP implementation supports only
up to 2^32-1 unmapped blocks per request.
Change-Id: Ib473831fa32aaba465f76694afad71137288a73a
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/377688
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
This is required for upcoming UNMAP implementation.
Change-Id: I81fb744e0813121cebd64aa60a03a80bfbecc94d
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/377421
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
This is required for upcoming UNMAP
implementation in bdev_virtio.
While here, also added documentation for
spdk_bdev_io_get_buf().
Change-Id: Ia769ee9b8b132f31208ae66598b29a1c9ed37312
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/379721
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
A vdev can change between the time the event
is enqueued and executed on proper reactor.
To detect this case, the event callback
was looking up vdev with the same name and
comparing it with old vdev pointer (from
the enqueue). This is now being simplified,
by looking up the current vdev just by
it's ID.
Change-Id: I33de03809b9d56840dd99caa8ccdf190a631ef31
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/380647
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
This makes the async event body non-blocking
and also fixes potential deadlock scenario:
* call_external_event() enqueues vhost_event
* destroy_device() locks g_spdk_vhost_mutex
* destroy_device() enqueues it's vhost_event
* reactor dequeues events
* cb from call_external_event is dequeued first
* g_spdk_vhost_mutex is locked (deadlock)
* destroy_device() times out, abort()
Change-Id: If8f51ada3ee5c47ba126f74187a40a285c001c77
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/380634
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
spdk_bdev_unmap_blocks() accepts a 64-bit number of blocks, which can
exceed the NVMe Dataset Management range's 32-bit number of blocks,
which can represent up to 2 TB with 512-byte blocks.
We can support up to 0.5 PB unmap requests by using the maximum number
of descriptors in a single Dataset Management command, which should be
sufficient for now.
Change-Id: I0a4ee77a9be148355991e1a081007ffa020a3ee5
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/379202
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
This patch adds hotremove support of lvol base bdev
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: I04dc7a0cc73fd6959824873f354d5c7db8c09a9b
Reviewed-on: https://review.gerrithub.io/379348
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
This is in preparation for enabling hot remove of logical volumes when
their underlying blobstore device is hot-removed.
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: I310a3f64f0de5d628609c20a1a3b4d38df0755aa
Reviewed-on: https://review.gerrithub.io/377041
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Previously incorrectly it was assumed that cluster size
was always to be 1MiB. For most evident example of this
please see spdk_lvol_create() sz > free_clusters comparison.
This is now fixed and lvol->sz was changed to lvol->cluster_num.
It was done to increase readability - only dealing with
number of clusters when creating or resizing lvol.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: If8cdbad18978319e57b6952dbf5a55d56785f108
Reviewed-on: https://review.gerrithub.io/380467
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
This patch allows unmap bdev_io to
be used with spdk_bdev_io_get_buf.
bdev_io->iovs/iovcnt has been zeroed-out for other
I/O types to overwrite any previous values/pointers.
Change-Id: I570a4d82d9e4db6630a6831b1aab3259fb46cdd8
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/377687
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Three checks are added to options passed to spdk_bs_init,
with appropriate errors returned:
- whether any of the options is set to 0
- device size has to be bigger than cluster size
- pages reserved for metadata exceed total number of clusters
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: Idee3c194b653e737ec7c7a768f1973ff72452c5b
Reviewed-on: https://review.gerrithub.io/379676
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Now bs_dev is destroyed only in two instances:
- within spdk_bs_init() on failure path
- vbdev_lvs_create() if spdk_lvs_init() errors out,
before even calling spdk_bs_init()
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I7b8af39fbe83907b0c47797f0f55ca3b941729d9
Reviewed-on: https://review.gerrithub.io/379848
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Change-Id: Ic094c34f1dc9063f12df80d77b2c70ebae9a4977
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/380066
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Fixes condition where blobstore was prematurely calling the
application callback on spdk_bs_unload(), if the application
tries to do something too quickly bad things happen.
To avoid application changes with how the g_devlist_mutex is
held, it is no longer held while calling
_spdk_io_device_attempt_free() because the app unload CB is
called from that function and may want to call
spdk_io_device_unregister() from its unload CB. So the lock
is now held and releases strictly around the list its
protecting which allows the CB from _spdk_io_device_attempt_free()
to be called without issue.
Change-Id: Ib451cfe6b33ea0c3f9e66c86785316f9d88837c7
Signed-off-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/377872
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
This reverts commit d3828a23ec.
GitHub issue #202 reports that this causes a crash with two or more
iSCSI connections on the same LUN.
Change-Id: I9ffb85d393eb506aac9d176299a3b3bcf021a38c
Reviewed-on: https://review.gerrithub.io/379866
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I46d564523ea20bc7c79a3896dfb024d3d5172a93
Signed-off-by: GangCao <gang.cao@intel.com>
Reviewed-on: https://review.gerrithub.io/379911
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ia07efcdec742d6ae5339e9f1c860ab58107d9f85
Signed-off-by: Jin Tsai <caijin11331007@gmail.com>
Reviewed-on: https://review.gerrithub.io/379928
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Until now we queued all IO to hardcoded
SCSI target 0.
Change-Id: Iefb229899725f53f26e927c4fb23e8d1d613c187
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/379840
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
replaced "remove_vhost_scsi_controller" and "remove_vhost_blk_controller"
with "remove_vhost_controller".
Change-Id: I6f4b180054c13f25aae992e9be50375d3750a376
Signed-off-by: Pawel Niedzwiecki <pawelx.niedzwiecki@intel.com>
Reviewed-on: https://review.gerrithub.io/377197
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
bdev_module_init_done could be called
multiple times when more than device
is available.
Change-Id: I17ee63a818945359648953c4f8f67678d10e8907
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/379864
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Added new struct virtio_driver together
with it's global instance. The struct should
keep all bdev_virtio related information.
Change-Id: If78967c68c4131c89cd86cb4b46f5f0194bca323
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/379863
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
This patch only adds the pci_virtio.c file,
without changing any functionality. This
is required for future rte_virtio migration
to SPDK.
Change-Id: I7774cdfdaf8934fde588e25b5db5dd86a9cbfb3f
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/379484
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
A mid-step towards porting virtio_pci to
use SPDK env/pci layer. See the next patch
for details.
Change-Id: Ia7cb417415bce686c3a888f949853834ddf6c7a6
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/379488
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
SPDK env/pci layer does not provide equivalent
call to actually map all pci resources. This
patch will smooth future transition of rte_virtio
to SPDK.
Change-Id: I7a67c46a99824be83875385703dd6bbf0ec9645e
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/380001
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
New functions for reading/writing any length of data.
Also simplified specific 8/16/32-bit reads/writes.
Change-Id: I518cdb3ce8d27a25353e80f2e7ca21162b0bd12b
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/379487
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Fixed memleak on vbdev_gpt_read_gpt failure.
gpt_base->ch was never freed.
Change-Id: I97f6e433b26ab95253eac4753b68083f3433547b
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/377913
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Iad98baef576fe3d843967d0c02e9922dfc347830
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/378675
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
This code was still using an old paradigm of returning the
number of bytes associated with a successful submission.
Just return 0 on success instead - if caller needs the
number of bytes for some reason they have the information
to get it.
While here, return an appropriate negated errno where possible -
we especially want ENOMEM returned when an ioat channel runs out
of descriptors.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I5858ccd6cff916b6c80fda7d2c9fce96fb39ef89
Reviewed-on: https://review.gerrithub.io/378858
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Some of the internal functions used to return the
number of bytes associated with a successfully submitted
IO, but that was changed a while ago to just return 0
for success.
So change some of the callers of these functions to
just look for != 0 for failure rather than < 0. This
preps for some upcoming ENOMEM handling changes.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I0a66dd6bfac9053e0fd6103dee1ea36b20d902df
Reviewed-on: https://review.gerrithub.io/378856
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I374910a7d5ecf0125228d0c99ab523804956ca78
Reviewed-on: https://review.gerrithub.io/378852
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
This patch introduces per-channel flags to keep state of information
needed in the primary I/O path. Setting/clearing of these flags
should only done through an spdk_for_each_channel() call. Currently
there is only a RESET_IN_PROGRESS flag defined but more may be added
in the future.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ia81817e2dabc9997c12beebae72fb129cb5dcf9a
Reviewed-on: https://review.gerrithub.io/377828
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
This was removed in NVMe 1.2.1 ECN 002.
Change-Id: Icacd53c1f33043cf1c9f30bff1fb9dce1efa69b3
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/378681
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
The Logout Request reason field is the low 7 bits of byte byte 1; the
last bit of byte 1 is specified to be always 1, and we shouldn't
consider it to be part of the reason field.
The existing debug print code was parsing the reason field correctly (by
masking it against 0x7f), but it's simpler to just make the reason field
into a bitfield of the proper size; this fixes the real bug in the
reqh->reason != 0 check, which did not use the 0x7f mask.
Fixes GitHub issue #198.
Change-Id: I4813da2236c70dc1761e303b34d321750ee36626
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/378658
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
It does not seem nessecary to include it, when this it used just once
in lvol disk creation.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I42ead55329f0ac7e55bb73702d071f118a5c7931
Reviewed-on: https://review.gerrithub.io/379678
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
To increase readability, union in spdk_lvol_store_req is now split
into four separate structures.
As well spdk_bdev from lvs_basic/spdk_lvs_req was removed as it was
not needed.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I65c5155f3d15151a97cf8f8e425b26aa1966b677
Reviewed-on: https://review.gerrithub.io/379169
Reviewed-by: Maciej Szwed <maciej.szwed@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: Ife45dc8e27d767b9f09b67e7fae3b94837a14491
Reviewed-on: https://review.gerrithub.io/379458
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Now that the bdev_io read and write branches of the union have been
unified, the virtio-scsi bdev I/O code can be simplified a little bit.
Change-Id: Iadbe55862770a1b0e7f854b724a70d94c704218e
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/379696
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Previously, we naively assumed that a completed
reset was the reset in progress, and would
unilaterally set reset_in_progres to false.
So change reset_in_progress to a bdev_io pointer
instead. If this is not NULL, a reset is not in
progress. Then when a reset completes, we only
set the reset_in_progress pointer to NULL if we
are completing the reset that is in progress.
We also were not aborting queued resets when
destroying a channel so that is fixed here too.
The added unit test covers both fixes above - it will
submit two resets on a different channels, then destroy
the second channel. This will abort the second reset
and check that the bdev still sees the first reset as in
progress.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I61df677cfa272c589ca03cb81753f71b0807a182
Reviewed-on: https://review.gerrithub.io/378199
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Upper layers are not supposed to put an I/O channel if there
are still I/O outstanding. This should apply to resets as well.
To better detect this case, do not remove the reset from
the channel's queued_reset list until it is ready to be
submitted to the bdev module. This ensures:
1) We can detect if a channel is put with a reset outstanding.
2) We do not access freed memory, when the channel is destroyed
before the reset message can submit the reset I/O.
3) Abort the queued reset if a channel is destroyed.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I0c03eee8b3642155c19c2996e25955baac22d406
Reviewed-on: https://review.gerrithub.io/378198
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
