With the new added property access API, we can send a internal
property access request to NVMf library, and we can use
it to reset controller.
Change-Id: Iee8b1146d9eb31bc98a9b297e5c635e43e6fdb12
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10952
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Dong Yi <dongx.yi@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
VFIO in QEMU uses region 9 as the PCI passthrough devices' migration channel.
The format of the region 9 migration region is as follows:
------------------------------------------------------------------
|vfio_device_migration_info| data section |
------------------------------------------------------------------
QEMU will access vfio_device_migration_info to controll the migration
process.
For SPDK vfio-user target, we also implement the BAR9 via libvfio-user,
and we also define the NVMe device specific migration data stored in
data section of BAR9. QEMU doesn't care about the format in data section,
it will help us to gather the NVMe specific migration data in source VM and
then restore the migration date to data section of BAR9 in destination VM.
The core idea to implement live migration will following the device state
change which is controlled by QEMU. First QEMU will try to STOP the device
in the source VM, and set the destination VM to RESUME state, SPDK will save
NVMe devic state data structure to BAR9 in the source VM once the subsystem
is paused, then QEMU will read BAR9 in source VM and restore the content of
BAR9 in destination VM, finally in the destination VM, we will restore the
NVMe device state include BARs/PCI CFG/queue pairs in the destination VM.
Change-Id: I42e38f28c3ff59831be63290038b50d199d06658
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/7617
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Thanos Makatos <thanos.makatos@nutanix.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
To avoid re-use of descriptors that may have fields set that are
reserved by the one being used now. For example:
If a batch desc is being built and was previously used by a copy
we need to clear out the dst_addr field or things will explode
as this is a reserved field for a batch.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: I6ba50b76589e38a276683291f5ec2970c80e8aa8
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11308
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
When subsystem is destroyed, it removes its listeners,
however transport level listeners remain active.
This patch removes all transport listerners when
the transport is being destroyed.
Fixes issue 2353/
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Change-Id: Ica7bcb0052b626aa62d0da9049bb8f216027dc49
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11307
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
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: Konrad Sztyber <konrad.sztyber@intel.com>
DPDK could be compiled as shared libraries by specifying
`--default-library=shared`. This is the default in packaged DPDK.
Building SPDK statically did not work with such DPDK builds,
since we always assumed the same type for both.
This patch makes detects the type of builds separately and
allows for any combination.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I40b81446cc1c02f18a0b986fb5f0a7a6e31de467
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6491
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
to a single command
Change-Id: Ic0ca65b7399f3cbc4153327d83de7db69de48709
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11209
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
We saw this unexpected behavior by the current SPDK master.
Add the check to clarify this behavior occurs only when we use
Soft RoCE.
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: I3a5eaa9064a0601c65139e7868898545926d0dbf
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11225
Community-CI: Mellanox Build Bot
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: Dong Yi <dongx.yi@intel.com>
This reverts commit eb09178a59.
Reason for revert:
This caused a degradation for adminq.
For adminq, ctrlr_delete_io_qpair() is not called until ctrlr is destructed.
So necessary delete operations are not done for adminq.
Reverting the patch is practical for now.
Change-Id: Ib55ff81dfe97ee1e2c83876912e851c61f20e354
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10878
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
When doing live migration the migration BAR region is bytes stream
data, so here we use the helper function to save current controller
state into the stream in source VM and load it as internl data
structure from steam in destination VM.
We will remove the `unused` attrubute in next patch.
Change-Id: Ib44adb351c697b50b9220ce6943cc017137a6064
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10336
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
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>
When doing live migration, the destination VM will construct
ADMIN queue pair at the beginning, but the controller isn't
in READY state, we should not poll the ADMIN queue pair right
now. This is fine for normal controllers, normal controllers
will set ADMIN queue pair state in CC callback.
Change-Id: I0db36f75a463fb7476ee62323f9ed0c74c2451dc
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10621
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
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>
When doing live migration, there are some spdk_nvmf_ctrlr internal
data structures need to be saved/restored.
Change-Id: Ie39482e8c49765c36fc3700fbac4ce47ef306f29
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10058
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
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>
When doing live migration we need to restore the AER commands
in the destination VM, so here to provide an API to save
these CIDs and the transport layer can save the value.
After migration in destination VM, we should allocate
new AER requests based on CIDs in vfio-user.
Change-Id: I5881f833bbfacb0f030a2b135b4dd47726240378
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10040
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Dong Yi <dongx.yi@intel.com>
Fix issue: #2320
Only the primary process will do the unmap bar operation as for
the map bar operation.
The DevHandle is process specific and the issue here is the
secondary process's function pointer of DevHandle is not properly
set.
Change-Id: I95dddc76c6ce4be8775b6aaf54699002baffd3b9
Signed-off-by: GangCao <gang.cao@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11216
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Using the latest DSA we aren't supposed to (a) touch WQ space that
we aren't configuring and (b) touch WQ config fields that we are
configuring even if we are configuring that WQ. So, this patch
will read in initial values of only the number of desired WQs
and update them accordingly before updating the HW.
Also updates a few vars to use shorter local variables consistently.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: I7641cdfc5ccc839e37a1d46d760248799a8fce1f
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10981
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
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>
Found via inspection during spec review of latest HW. We were using the
wrong stride for the WQCFG regsiter when configuring but it just so
happened to be the right value for the current DSA version. We were
mixing up the size of the WQCFG register with the stride value used to
configure the next WQCFG regsiter as they are not contiguous in HW, we
need to read another capabilities bit to determine the address of the
next wqcfg to configure..
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: I14d1ff95e0131fd30121aa955bfbc8c8fb3fc512
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10968
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Compliant with both current and next gen DSA.
Note: some fields in gencap were mapped incorrectly
previously, but this did not impact the SPDK driver
because the only times those values (max_xfer_shift
and max_batch_shift) were used were in asserts.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: I9648184670f661166136e7898d0d8c7e07d8c746
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10966
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
There is a race condition between controller destruction and
subsystem state change, e.g. admin qpair may already be freed
when a namespace is added or removed. As result in function
poll_group_update_subsystem we may get heap-use-after-free error
Another problem is that some qpair's live time may exceed controller's
life time. To avoid it, start controller destruction process when the last
qpair finished the disconnect process (previously controller started
the descruction process before the last qpair starts to disconnect
and it could lead to raise conditions)
Fixes#2055
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Change-Id: Ibc99b1d840e4796e1588cc217d65834bb556b909
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/9995
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Using contructor/destructor to handle g_dpdk_sem will
help later in the series when splitting vhost fini
between vhost.c and virtio abstraction.
Otherwise multiple callbacks would be needed during vhost fini.
Ex. spdk_vhost_fini -> vhost_user_fini to stop the sessions ->
-> back to spdk_vhost_fini to remove vhost devices ->
-> vhost_user_fini to destroy the g_dpdk_sem
g_dpdk_sem will only be used from rte_vhost_user.c.
Until all references are moved, it is placed in vhost_internal.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I0505b906621f0eb0cb1226f96a3b6cf49f66778f
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11055
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
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: Konrad Sztyber <konrad.sztyber@intel.com>
There is no need to zero out the g_vhost_core_mask on vhost_fini.
Removing it will help later in the series when splitting vhost fini
between vhost.c and virtio abstraction.
g_vhost_core_mask will only be used in vhost.c and any cpu_mask
shall be passed to virtio abstraction after going through
vhost_parse_core_mask. There is no need to make the
g_vhost_core_mask accessible for virtio transports.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: Ic936c2a8dd1bb6f93b6f6209ea48e3278b19b54e
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11054
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
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: Konrad Sztyber <konrad.sztyber@intel.com>
In later patches rte_vhost functions will be moved
to rte_vhost_user.c. To prepare for this,
iterator is used in place of accessing g_vhost_devices.
While here, followed the same style of iterating in
spdk_vhost_config_json().
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I1b73c00dfe1391f359421d044686e49a8c6c9176
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11022
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
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: Konrad Sztyber <konrad.sztyber@intel.com>
g_vhost_mutex scope is only within vhost.c as
it should. Meanwhile there is an internal vhost API to
use this lock from any of the vhost files.
Later patches in the series move some functions from
vhost.c to rte_vhost_user.c, where using only the
internal vhost API locks will be better suited.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I5916d4dc824ec980fa510fd3cbbd0c8e082d6611
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11021
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
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: Konrad Sztyber <konrad.sztyber@intel.com>
Creation of sockets is specific to rte_vhost, so it
functionality responsible for setting path for them.
dev_dirname is renamed to g_vhost_user_dev_dirname
and its definition is moved to rte_vhost_user.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I9bae67667b0f6624f2daf3244a048d10e94e553c
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10631
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
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: Konrad Sztyber <konrad.sztyber@intel.com>
Changing the vsession coalescing setting is specific
to rte_vhost as such it should be moved the rte_vhost_user
that focues on rte_vhost specific functionality.
Renamed with vhost_user_* prefix to match the file.
Since the rte_vhost functions are still called directly from
vhost.c, temporarily they are added to vhost_internal.h.
Once implementing virtio transport abstraction is complete,
some will be removed and others will be replaced with
a generic callback structure.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I98b3746952cfe09fb724c49e4050efc0c42985a5
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10630
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
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: Konrad Sztyber <konrad.sztyber@intel.com>
For some time already the DPDK rte_vhost interface was
accomodating for other types of devices than virtio-net.
rte_vhost_compat.c file contained the use of DPDK rte_vhost,
rather than workarounds. To make that clear it is now renamed
to rte_vhost_user.c.
This patch is first in series that reworks vhost library
with two goals in mind:
1) Refactor vhost and vhost-blk to no longer depend on rte_vhost.
All references to that API will be moved to rte_vhost_user.c.
2) Add a transport abstraction for virtio-blk devices.
vhost-blk will now be able to expose virtio-blk using multiple
implementations of the interface.
First one will be vhost_user that depends on DPDK rte_vhost library.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: Ib6d4e4a6352069fa76e6b017ec203dab75f887b8
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11052
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
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: Konrad Sztyber <konrad.sztyber@intel.com>
A somewhat hidden functionality was present in spdk_vhost_dev_find().
Caller could match a vhost controller by controller name (socket filename)
or by full path to the socket.
This function is used by vhost RPC too.
The functionality of matching by full path was not documented,
nor matches what is presented in spdk_vhost_dev_get_name()
or vhost_get_controllers RPC.
This patch removes this functionality as part of series
to enable non-vhost-user type controllers, which might
not use the path to sockets.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I0e5ce75ac80ed8d1da962eabba86af69f59a43db
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10436
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
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: Konrad Sztyber <konrad.sztyber@intel.com>
Previously we didn't post the response for CREATE IO SQ command
until the queue pair is connected finally, but for coming live
migration support, we will connect IO queue pairs in the destination
VM, and this function will also be called for this case, so here
we add a flag to indicate the CREATE IO SQ case.
Change-Id: Iab4c64a7ebb72bcffbfff712dc729c40eead7c7d
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/9464
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
The miration region data structure is from `vfio_device_migration_info`
defined in `linux/vfio.h`, `vfio_device_migration_info` is in the 0th
offset of the VFIO_REGION_SUBTYPE_MIGRATION region, and in vfio-user,
we reserve first one page of BAR9 for this MMIO accesses.
libvfio-user already helps us to hide some implementation details
based on vfio migration specification, here we just use the two
fields to help the migration process.
Change-Id: I8917ba892bbfdfdf4f135f5d6b4923ab0e4a6250
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/7628
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
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>
We will report the live migration region to VM via sparse
mmap, offset after 0x1000 is the NVMe device state data
structure, and offset start from 0 is the structure
vfio_device_migration_info defined by the VFIO driver.
All accesses between 0x0-0x1000 will use the MMIO callbacks,
and accesses to NVMe device state will use shared memory map
way.
Change-Id: Ib456fc61f587c1bffa8b38506b4480a6066abe87
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/7627
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
We will use the NVMe device state data structure to save/restore
a NVMe controller in source/destination VM.
NVMe device migration region is defined as below:
----------------------------------------------------------------------
| nvme_migr_device_state | private controller data | queue pairs | BARs |
----------------------------------------------------------------------
Change-Id: Idc73976e1de7f6da2da58e71db86df8cbb0d314d
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/7626
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
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>
For CREATE IO SQ command, we will defer to post completion
until the SQ was connected, we may call post_completion()
in different threads, so here we will send a message
to CQ thread when necessary.
Change-Id: I87a0f8982811c76ce8eb49db6a136f4cbe6e0a93
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11078
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
We should disconnect ADMIN queue pair after shutdown
returned, or we may leak ADMIN socket resources after
free the controller data structure.
Fix issue #2289.
Change-Id: I956191fcd51cdcef5de2c3c7b15ffc70f22b040b
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11133
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Dong Yi <dongx.yi@intel.com>
Reviewed-by: <qun.wan@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
From SAM-4, section 5.13 (Sense Data);
“When a command terminates with a CHECK CONDITION status, sense data shall be returned
in the same I_T_L_Q nexus transaction (see 3.1.50) as the CHECK CONDITION status. After
the sense data is returned, it shall be cleared except when it is associated with a unit
attention condition and the UA_INTLCK_CTRL field in the Control mode page (see SPC-4)
contains 10b or 11b.”
SPDK does not set UA_INTLCK_CTRL to 10b or 11b, so we set the unit attention condition
immediately against a single IO or Admin IO after reporting it via a CHECK CONDITION.
Once the failed IO received at iSCSI initiator side, it will be retried. In the case of
resize operation, if there is no IO from iSCSI initiator side, the unit attention
condition will be delayed to report until the first IO is received at the iSCSI target
side.
Meanwhile, we clear the resizing (newly added) flag on our SCSI LUN structure after
first time we report the resize unit attention condition.
The kernel initiator won’t actually resize the corresponding block device automatically.
It will report a uevent, and then you can set up udev rules to trigger a rescan. SPDK
iSCSI initiator will automatically report the LUN size change.
Change-Id: Ifc85b8d4d3fbea13e76fb5d1faf1ac6c8f662e6c
Signed-off-by: GangCao <gang.cao@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11086
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Xiaodong Liu <xiaodong.liu@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Convert the batch to the single command inside of it.
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Change-Id: Ia117175ef3f4a8290d313e0bdc794f6a3276e042
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11166
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Increase the batch size and with it the effective queue depth per
channel to 512.
Change-Id: Ide665e92d47ee753c141f34dd6a8bc4d040fe8db
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11031
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: John Kariuki <John.K.Kariuki@intel.com>
Transparently group independent operations into idxd batch operations
between polls. This increases the effective queue depth.
Change-Id: Ic09b21ed29aaefe2eccef9a6ae0e1b05990ef631
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10998
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
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 is no longer needed.
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Change-Id: I11b7e9acbcf1239a0ad2f49169d7e3d5844a1b93
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11029
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
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 RDMA target reports msdbd=16, these addtitional
SGL descriptors are located in capsule. The user can
set ICD size lower than required for msdbd=16. This
patch verifies that ICD can hold all additional SGLs.
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Change-Id: I875d40e14e6506c39169d084e56df7ca5d761209
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10686
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
We will assign each SQ with different poll group in round
robin way by default, this may cause race condition to
post completions to one CQ in different threads, so here
we will assign the SQs which share one CQ into same poll
group.
Also enable multiple cores NVMe compliance tests so that
to cover shared IO CQ case.
Change-Id: I9d7cc78aaedceed23986d9f89ed945e0eb337e09
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11115
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
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 we mixed SQ/CQ definition together, one queue pair
data structure may contain CQ,SQ or both CQ and SQ separately,
while here, we split the queue pair definition into SQ and CQ
respectively as code cleanup.
The NVMf library uses queue pair concept, but for vfio-user
case, each SQ created by VM is mapped to NVMf queue pair, so
we also change `connected_qps` to `connected_sqs` to reflect
the fact.
No actual code logic change in this commit.
Change-Id: I293ccbfbf054fe864d348fc56793dd1ccd366f6d
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11036
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
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>
libvfio-user will call quiesce callback when there are
memory region add/remove and device state change requests
from client, and in the quiesce callback, we will pause
the subsystem so that it's safe to do everything after
it, then after quiesce callback, we will resume the
subsystem. The quiesce callback is also used in
live migration, each device state change will quiesce
the device first.
Change-Id: I3a6a0320ad76c6b2d1d65c754b9f79cce5c9c683
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10620
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
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>
We will use the controller state to implement the coming
device quiesce feature, it's safe to do anyting when
a subsystem is in PAUSED state.
Change-Id: I3b466ed01848e668a1ffcea1d4f1466e971afa23
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10619
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
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>
Users may remove the listener while VM is connected, the endpoint is
associated with Unix Domain socket file, we should destroy the endpoint,
however, the controller maybe still active for now, because nvmf
library will help us to disconnect all queue pairs in asynchronous
way. Here we use the same way as the NVMf library to destroy the
controller when there is no connected queue pairs.
Fix#2246.
Change-Id: I0775d5294269d848d859968edafc8eaa1d89a32c
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10379
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
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>
The controller may be freed eailer than endpoint, so we still
need to unregister the memory region from SPDK. The case
can happen when removing the listener while VM is connected.
Change-Id: I95d49cefdbff3e0bdea316fac824ef8b218fcd2c
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10378
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>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
We should hold the transport lock to iterate endpoints.
Fix issue #2313.
Change-Id: I8e0539a51e843a3299908d9da7749fe9becb5e7e
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11037
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
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: Dong Yi <dongx.yi@intel.com>
Reviewed-by: John Levon <levon@movementarian.org>
