This simplifies the code a little.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Idf53616bda21c82b82f9e9438f4dcb87ffaa59a6
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/472518
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
We can pass bdev, lun->bdev_desc, and lun->io_channel to
bdev_scsi_readwrite() as same as bdev_scsi_sync/unmap().
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ib8b368da4da54b057ae09a91ab60a50388a5c684
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/472517
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
By the recent refactoring, SCSI task is configured when getting
DIF context from SCSI layer. Passing not CDB and offset separately
but SCSI task to SCSI layer is more concise and do in this patch.
In iscsi_send_datain(), we have to update task->scsi.offset for the
case that data is split into a sequence, but the update is no harm
because task has completed what it must to do.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I153352dfa7aa7325db4452f03d863df11b3e0cfa
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/472510
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
One previous patch refined LUN hotplug process and updated the
comment but we still had checked not only outstanding tasks but
also pending tasks to be completed or aborted. But, as written
in the comment, we can wait for only outstanding tasks now.
Management task is the highest priority and is pending only when
there is any outstanding management task, and the completion
callback of management task executes the first pending management
task.
The last patch changed us to abort all pending management tasks
after stopping new submission.
Hence we can do this change not only for IO task but also for
management task.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I66056f2a02af05d5bccaf6462c6f48c608cd0ca3
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/474032
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
SCSI management task is for SCSI tasks which is submitted after it,
and all such SCSI tasks are aborted by the last patch when we
remove LUN dynamically. Hence we can abort all SCSI management tasks
being queued when removing LUN.
Add simple unit tests too.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I9be3f910ab4bbb99cd399f71dc716a7c40f34fe5
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/474022
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Previously iSCSI LUN hotplug had critical bugs and we had no choice but
accept submitting new tasks as late as possible. We fixed the bug now and
we can stop submitting new task immediately after starting LUN removal
process.
By this change, no task is submitted to the LUN and previously queued
tasks have no chance to be kicked. Hence we execute them instead after
stopping new task submission.
This change simplifies LUN hotplug process and reproduce LUN hotplug
issues solidly if we don't have the fix.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I9a33e6a217978b0863d15aaff3d35880dbdccfd4
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/473596
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
This is a preparation to the next patch. If connections detect that
LUN is removed, we have no way to spdk_scsi_lun_execute_tasks()
to the pending tasks. Hence the next patch will call the new
function scsi_lun_execute_tasks() in that case.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ifdf630bd349c7d2099a6a14accc52f77c129f641
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/473610
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Ziye Yang <ziye.yang@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
We didn't have any check if ref count of SCSI task doesn't go negative.
This addition will verify the idea to LUN hotplug issue by subsequent
patches.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: I1d6ca9b9439bc7c4b701b65cc004cdf5cae16e91
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/473585
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
All connections to a single LUN run on a single thread but
this thread may not be the same as the one which opened the backed
bdev. So hold pointer to the thread which opened the backed bdev
to struct spdk_scsi_lun and use it when calling spdk_bdev_close().
All resource of LUN are accessed on a single thread after getting
I/O channel, and so lock is not still necessary.
Fixes issue #1024.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ifc1e238d333afcde0cdf9e9b4af3b56ef65a4f7d
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/473002
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: yidong0635 <dongx.yi@intel.com>
This is for management I/O and from the same idea as the last patch.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Iae11de7848b38b9db1a699d80f595000a6ab2a47
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/471696
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Previously, for iSCSI target, freeing bdev_io of SCSI task was deferred
until the reference count of the SCSI task becomes zero.
But this will cause the use-after-free issue when doing LUN hotplug during
large write I/O workload.
The scenario is the following:
- Large iSCSI write I/O is split into multiple I/Os, the first I/O is from immediate,
and subsetquent I/Os are from R2T.
1. The first I/O allocates iSCSI task as primary, and is submitted to the bdev layer.
The first I/O is pending in the bdev layer.
2. The second I/O allocates iSCSI task as secondary (secondary is associated with
primary by incrementing reference count).
3. Before submitting the second I/O to the bdev layer, LUN hotplug is started.
LUN hotplug waits for getting completion of the first write I/O from the bdev layer.
4. The bdev layer completes the first I/O. The primary iSCSI task is tried to free,
but reference count is still one, and is not done yet.
5. LUN hotplug detects completion of the first write I/O, and returns
LUN I/O channel to the bdev layer.
6. The second I/O is tried to submit to the bdev layer, but LUN is already removed,
and so free the secondary iSCSI task.
7. Then the reference count of the primary iSCSI task becomes zero,
and its bdev_io is freed. However, LUN I/O channel is already freed and freeing
bdev_io fails.
This issue is caused by separating iSCSI task allocation and submission.
For write I/O, we don't have to keep bdev_io after getting completion
of it from the bdev layer.
This applies to other non-read I/O types.
So for non-read I/O, free bdev_io after getting SCSI status in
bdev_scsi_task_complete_cmd(), and for read I/O, set bdev_io to
task as same as before.
The next patch will do the same for management task.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I530fb491514880ce41858e1bea55d422d606dfc4
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/471695
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Refine the public helper function spdk_scsi_dev_has_pending_tasks to
be able to check tasks only from the specific initiator.
Then use the function in iSCSI target to fix the issue.
Besides add UT code to test the updated spdk_scsi_dev_has_pending_tasks().
Automated multi hosts test is much better but some UT code will be of any
help to mitigate the risk of degradation.
Fixes#985
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I50afb940de7174360c8a30479450850002a3e525
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/471337
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Refine helper functions spdk_scsi_lun_has_pending_mgmt_tasks() and
spdk_scsi_lun_has_pending_tasks() to be able to check tasks only from the
specific initiator.
SCSI port is used by passing the pointer and so simple pointer
comparison is appropriate in the functions.
Add UT code to test the updated functions.
The next patch will change spdk_scsi_dev_has_pending_tasks() to
get not only SCSI device but also initiator port and make iSCSI
target use the function to fix the issue.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I89c33e05bc6ab21baa6cbebf60950039a3dcecd0
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/471336
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
When closing iSCSI connection, if we check pending tasks, we must
check tasks only from the corresponding initiator.
We have to add new API to do that.
On the other hand, during IO submission or LUN hotplug, we must check
all tasks.
The latter case is done only in SCSI LUN, and the function is not
necessary to be public.
As a preparation, change scsi_lun_has_pending_tasks/_mgmt_tasks
from public to private.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I2d7d77109ed317435b6768fffb0bf4e21dd60f9f
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/471335
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
The reported github issue #938 has been reported intermettently.
The issue is that the bdev descriptor passed to spdk_bdev_reset()
is not valid and causes seg. fault.
Current implementation of LUN hot plug is that putting IO channel
and removing LUN are done by different poller. Hence if any task
management command is issued between the gap, the reported issue
is likely to occur.
The flag removing is set at the start of LUN hot plug and so
spdk_scsi_dev_get_lun() can return NULL even before completing
removal by referring the flag removing.
Fixes#938.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I1a51d90cc700134e8c0ec399a3ce62620c84ef73
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/467212
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
For MODE_SELECT request we didn't verify the parameter
list length field from CDB and could complete an invalid
I/O without reporting any error. Fix it by adding an
additional check. Just to clarify: the I/O did not do
any harm, we just completed it with success while we
should have completed it with some error status.
Change-Id: I473e321da37259ee6318ca7dadab2726851d2b68
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463065
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
The function didn't do anything.
Change-Id: Id44a7d0c129ab60751eda382911935d677730ec9
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463066
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
As spdk_jsonrpc_begin_result() is not allowed to return NULL we can
remove these checks. We didn't have any tests cases that goes this path
anyway.
Change-Id: I0894e76c0162591e550e70b172566b9060a6dd5f
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Signed-off-by: Pawel Kaminski <pawelx.kaminski@intel.com>
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/459199
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
We should return for the registrant case when the reservation holder
exists.
Change-Id: Ie3cf31554eafdad03294aef2eeb6eaef1536b8c3
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/460305
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Liang Yan <liang.z.yan@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
This patch uses the change by the last patch to initialize DIF
context in SCSI layer. Besides this patch changes the name of a
parameter from offset to data_offset to clarify the meaning.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I54bf1168ec5959432aa15dae0360c0640138b033
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/457541
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Data offset are intended to correspond to DATAO in NVMe/TCP and
Buffer Offset in iSCSI.
Previously for iSCSI, buffer offset had been merged to start block
address, but passing buffer offset separately from start block address
clarifies the logic more.
On the other hand, for NVMe/TCP, passing DATAO separately from start
block address will be critically important because DATAO will bave any
alignment and will be necessary to use for not only reference tag
but also guard computation.
This patch adds data_offset to struct spdk_dif_ctx and adds it to the
parameters of spdk_dif_ctx_init(). ref_tag_offset is also added to struct
spdk_dif_ctx and it is computed by dividing data_offset by data_block_size
and is used to compute reference tag.
The next patch will use this change when getting DIF context in SCSI.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Id0e12ca9b1dc75d0589787520feb0c2ee0f844a5
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/457540
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Vhost-scsi target will not set task's initiator port parameter,
so reservation commands sent from Guest will cause segment fault.
Change-Id: Ifc175effded5371eca08d5bfe7e4aa977dd4b1c6
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/457550
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
All the SCSI commands have two states: allowed and conflict,
based on different reservation types and I_T nexus, the SCSI
module will check each commands before sending to the backend
device.
Change-Id: Ib05cece1c237873360f85c68d139362200d2d47e
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/436097
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Hotremoving a bdev exposed as a vhost-scsi LUN which
has an allocated io_channel is broken now. By detaching
LUNs from their SCSI devices at the start of LUN
hotremoval, we can end up with the LUN's descriptor
completely leaked.
Upon hotremove, each LUN fires a hotremove_cb to the
upper layer (iscsi/vhost) and starts a poller to
periodically check if lun->io_channel has been closed
already. While iSCSI allocates and frees io_channels
for particular LUNs separately using
spdk_scsi_lun_allocate_io_channel(), vhost allocates
and frees io_channels for the entire SCSI device using
spdk_scsi_dev_free_io_channels(), as it knows there's
only one LUN per SCSI device.
Since LUNs are removed from SCSI devices at the start
of LUN hotremoval, the spdk_scsi_dev_free_io_channels()
is not able to close the io_channel of the child LUN.
That LUN is no longer referenced there, and the function
returns immediately without any error.
By reverting this patch, we practically defer removing
LUN from SCSI device until the bdev descriptor is closed,
that is, until that spdk_scsi_dev_free_io_channels()
and the subsequent spdk_scsi_dev_destruct() in vhost
is called.
Historically, spdk_scsi_lun_free_io_channel() was
introduced after vhost-scsi already supported hotremove,
so before we can introduce a change like this one we
have to refactor vhost to use the new APIs first.
This reverts commit 497997bc60.
Change-Id: I58a9988a22694f5b5b927173098ac8218270462e
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/455371
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Pawel Kaminski <pawelx.kaminski@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
A PERSISTENT RESERVE OUT command with PREEMPT service action action is used to:
a) preempt (i.e., replace) the persistent reservation and remove registrations; or
b) remove registrations.
Change-Id: I906b09057e5ddef0ea2fe180bb5fff6e9e0a04f6
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/436092
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Any application client can release the persistent reservation and remove all
registrations from a device server by issuing a PERSISTENT RESERVE OUT command
with CLEAR service action through a registered I_T nexus.
Change-Id: Ie21885f7f9632b9da77e877fbce7c51b2e0b47a7
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/436091
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
An application client releases the persistent reservation by issuing a
PERSISTENT RESERVE OUT command with RELEASE service action through an
I_T nexus that is a persistent reservation holder. The RELEASE service
action will release the persistent reservation and do noting to
existing registrants. Unit Attention isn't supported by SPDK so here
we will not establish any unit attention condition.
Change-Id: If0df3b3fc4e89ffa78d827e2b31cf5c61aa149db
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/436090
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
An application client creates a persistent reservation by issuing a
PERSISTENT RESERVE OUT command with RESERVE service action through
a registered I_T nexus with RESERVATION KEY and TYPE, and persistent
reservation has a scope of LUN, only one persistent reservation is
allowed at a time per LUN.
Change-Id: I052d0ddd439dd9994c0793218dd5c5d6ed176d2c
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/436089
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
To establish a persistent reservation the application client shall first
register an I_T nexus with the device server. An application client registers
with a logical unit by issuing a PERSISTENT RESERVE OUT command with REGISTER
service action or REGISTER AND IGNORE EXISTING KEY service action.
Specify Initiator Ports (SPEC_I_PT) bit and All Target Ports (ALL_TG_PT) bit
are not supported for now, the registrants belong to the I_T nexus who sends
the command.
Also Activate Persist Through Power Loss (APTPL) bit will be supported in
following patches.
Change-Id: If057a764a4bfa73017f98048c94b697dbfa4b4a1
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/436088
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
The new, simplified scsi lun hotremove path doesn't call
lun->hotremove_cb if there's no io_channel allocated for
that lun. Vhost still depends on that callback and currently,
when the underlying bdev is removed, vhost is left completely
unnotified. It keeps a dangling pointer to a scsi lun and
will eventually crash. The vhost scsi controller also can't
be removed in this case.
This reverts commit 19182431c8.
Change-Id: I330330fdd7d6941db070d972192481f535f62977
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/454836
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Both for vhost SCSI and iSCSI target, IO channel is allocated to
LUN before using it. Hence LUN is not used by anyone if IO channel
is not allocated to it. So we can call scsi_lun_remove in this
case.
Change-Id: I6881a5e075ed6ef11802e1b166dfb3f35531d100
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/453968
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
We have observed unexpcted timeout when we remove LUNs from the
active iSCSI target dynamically during FIO workload.
By making destroy_raid_bdev RPC wait for its completion, we could know
the destroy_raid_bdev RPC caused timeout because LUN hot removal didn't
complete.
By investigating the log, incoming I/Os from the host had not stopped
even after hot removal process was started.
The reason was that iSCSI target had continued to accept incoming I/Os
from the host.
By removing LUN from the SCSI device at the start of the LUN hot removal
process, iSCSI target will be able to stop incoming I/Os and LUN hot removal
will complete in finite time.
LUN itself can be accessible even after it is removed from the SCSI device.
LUN hot removal is for not I_T nexus but I_T_L nexus and so we cannot
start connection exiting in this case because connection can have multiple
LUNs. So this fix requires few changes and will be practical.
Fixes#715
Change-Id: I17d7a1f6c6557297289c3bd148a62db46da48ec5
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/453959
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
This was not used by any of the trace register descriptions.
Let's remove it rather keeping it around if we don't need it.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Idda809e2911db5be555ff6aa13695484a14bf665
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/452734
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
spdk_dma_malloc() is not required here, as the buffer
is neither DMA-able nor shared between processes.
The buffer is used to store the scsi response as it's
prepared. At the end it's always memcopied to possibly
multiple DMA-able buffers in the scatter-gatter list
provided by the upper layer.
Change-Id: I92fcede67dc24c532b13399f6364b071b2aeeb56
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/451555
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
This is the end of the patch series. After this patch,
delete_target_node RPC will wait for the completion of
removal of the SCSI device and then free the iSCSI target.
SCSI device holds passed callback and calls it in free_dev().
free_dev() is ensured to be called after all iSCSI sessions
are closed. So iSCSI target resource can be freed safely
after that.
Change-Id: I25921b4014207092b7b3845dfeae58bcdffa2edc
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/450607
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
The next patch will add the function ponter typedef
spdk_scsi_dev_destruct_cb for SCSI device destruction.
Hence add lun to the names of descriptors and callback for SCSI
LUN for clarification.
This patch doesn't change any behavior.
Change-Id: I73f2bce9129f7a6f16770ab6ed18428b16589108
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/450883
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
This case was zeroing the entire structure - overwriting
the peripheral and page_code data already set. Don't
bother zeroing the alloc_len either - we'll set that
later in this case statement.
Fixes issue #750.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I8b7c6f954b5e3c85ddfaf801d64dd4a501f50cd2
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/450922
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
SPDK iSCSI target didn't convert LUN ID from integer to structure
when it sends R2T PDUs. The next patch will fix the issue. Introducing
helper functions into SCSI library and using them will be clean. Hence
this patch adds two helper functions to convert LUN ID between structure
and integer.
The logic of helper functions is derived simply from the current
implementation in SPDK.
Change-Id: I114b546cfcb44109d6cd131a1fa972f4d6bfea38
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/449962
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
This patch adds an API spdk_scsi_bdev_get_dif_ctx().
spdk_scsi_bdev_get_dif_ctx() decodes opcode in CDB, and if opcode
is read or write block commands, it gets LBA and use the lower
32bits of LBA as Reference Tag. It gets DIF information from
specified bdev next. Then it sets all to DIF context and return.
spdk_scsi_bdev_get_dif_ctx() is exported to iSCSI through
spdk_scsi_lun_get_dif_ctx().
Change-Id: Id8aac164c48e9e9d4ff7cfc9fa81bb5090f3e187
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/446224
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
SPDK iSCSI and SCSI target don't expose any metadata and DIF settings
to the corresponding iSCSI and SCSI initiator.
Even when SPDK iSCSI and SCSI target allocate any bdev formatted
with DIF, SCSI commands sent from iSCSI and SCSI initiator don't
have any metadata and DIF information.
For that case, iSCSI target inserts and strips DIF on behalf of
iSCSI and SCSI initiator.
Hence SPDK SCSI target has to use data block size not including
metadata to process SCSI commands correctly.
This patch replaces spdk_bdev_get_block_size by
spdk_bdev_get_data_block_size in necessary places.
Change-Id: I264c8e532d1d1b016f6d8774c8ec03389528044f
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/445083
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
