When removing a listener, there's a small window when the listener is
already freed, while the controllers that were created on that listener
are still active. It happens, because the listener is removed before
disconnecting its qpairs and in turn destroying the controllers.
The ctrlr->listener pointer is now cleared when a listener is freed and
its value is checked for NULL before each use.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: Iace65a46eebc5972cc4ef0f1c1822ffc5d3e559e
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/9237
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ziye Yang <ziye.yang@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
When a subsystem is being deleted, we disconnect all qpairs
and when the last qpair for some controller is disconnected,
we start controller desctruction process. This process requires
to send a message to subsystem's thread to remove the controller
from the list in the subsystem and after that send a message to
controller's thread to release resources.
The problem is that the subsystem also destroys all attached
controllers. This order is unpredictable and we may get
heap-use-after-free or double free.
To fix this problem we can rely on the fact that the subsystem
can only be destroyed in incative state, that means that all
qpairs linked to the subsystem are already disconnected and
all controllers are already destroyed or in the process of
destruction.
spdk_nvmf_subsystem_destroy API is now can be asyncrhonous,
it accepts a callback with cb argument.
Change-Id: Ic72d69200bc8302dae2f8cd8ca44bc640c6a8116
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6660
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: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Refine ANA state from per subsystem listener to per subsystem listener
per ANA group.
Add an array of ANA state per ANA group to subsystem listener. The array is
indexed by ANA group ID - 1.
Then in I/O paths, we get ANA state by
ctrlr->listener->ana_state[ns->anagrpid - 1].
The NVMe specification indicates the existence of NVM subsystem specific
ANA state when FFFFFFFFh is specified as NSID for the Get Features
and the Set Features commands. For these, we return the optimized state.
Update the nvmf_subsystem_get_listeners RPC to return all ANA states
of the underlying ANA groups. The nvmf_subsystem_get_listeners RPC is
not matured and not used in the test code yet. Hence compatibility is
not high priority.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ia2d4d5361ac01236f595c22765fd35e4c5fdee0e
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/9064
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: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
This is the first patch in the patch series to control ANA states not only
as a unit of subsystem listener but also as a unit of ANA group and create
user preferred mapping between namespaces and ANA groups within a single
subsystem.
This patch adds anagrpid to both spdk_nvmf_ns and spdk_nvmf_ns_opts, and adds
ana_group array to spdk_nvmf_subsystem to count number of namespaces per ANA
group within a single subsystem. The size of the ana_group array is equal
with the size of the namespaces.
For each subsystem, allocate ana_group array regardless of the value of
ana_reporting of the subsystem.
For each namespace, at its creation, initialize anagrpid explicitly to be equal
with nsid by default and increments the corresponding entry of the ana_group
array of the subsystem regardless of teh value of the ana_reporting of thee
subsystem.
Hence the contents of the created ANA log page is not changed even if the
algorithm to crete ANA log page is changed.
Additionally this patch adds a unit test case that one ANA group
has multiple namespaces.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I78539db4e7248c2953c6927ff8128cb5a7e34b96
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/9102
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>
Only one active socket connection is supported in libvfio-user,
RESERVATION should not be supported in this case.
Change-Id: I36a746f479da767d857425e84dfed5f2bef30b17
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/9124
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Windows will always sends a Set Feature Interrupt Coalescing even
SPDK reports we can't support it in Get Feature command. Here
we return Feature Not Changeable instead of Invalid Field which
is more meaningful.
Change-Id: Ie08086c3eba1e2d790a7ae4976653b6f9085028c
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/8923
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: Jim Harris <james.r.harris@intel.com>
The data buffer isn't available at the beginning.
Change-Id: Ieeb1a297ff52dfdc6cd999d04862a0cd96483650
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/8932
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Implemented nvmf code to allow transports to use ZCOPY. Note ZCOPY
has to be enabled within the individual transport layer
Signed-off-by: matthewb <matthew.burbridge@hpe.com>
Change-Id: I273b3d4ab44d882c916ac39e821505e1f4211ded
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6817
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Xiaodong Liu <xiaodong.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Since we are using NVMf fabric library to emulate a PCIe based SSD via
vfio-user target, so there maybe some commands that are related with
PCIe SSD only, such as set/get features with interrupt coalescing
and Interrupt Mask Set/Interrupt Mask Clear registers. Even the
NVMf library doesn't support that, it is not a fatal error to Host
NVMe driver, so here we use the info log instead of error log for
this case so that to avoid noise logs.
Fix#2036.
Change-Id: I8283bcde5779080835d6ab827dbd852b3816176f
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/8766
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: <dongx.yi@intel.com>
Reviewed-by: Ziye Yang <ziye.yang@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>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
The NVMf library will not implement interrupt coalescing and ignore them, but we can
report this via get_features.
Some OS may check the result from get_features so that it will not send set_features
for interrupt coalescing.
Change-Id: I7466bcbc0ea5b3b067751cdf1979b2e0681c0043
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/8765
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: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Bit 1 in the CMIC of the Identify Controller Data Structure specifies
if the NVM subsystem may have multiple controllers or not.
However, multi_host indicated a particular use case such that the NVM
subsystem is used by multiple hosts.
multi_ctrlr will be more appropriate.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I0246096a5cc44721aeff3ff6f96473a2abe11964
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/8719
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: Aleksey Marchuk <alexeymar@mellanox.com>
The vfio-user target emulated NVMe device is treated as
PCIe NVMe SSD in the Guest VM, so when doing controller
reset or shutdown, we should abort the AERs which in the
NVMf library.
Users may switch kernel NVMe driver to SPDK NVMe driver
in the VM, without this fix, we will got "AERL exceeded"
response very frequently, because the AERs submitted by
previous driver will never be aborted in runtime.
Change-Id: I0222ed509629ccb0e98217414dd9043857105686
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/8558
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>
When users remove kernel NVMe driver in the VM, after 120 seconds,
SPDK NVMf target will disconnect ADMIN queue pair due to association
timer timeout, and for vfio-user transport, the ADMIN queue pair
connection is associated with the socket connection, so when probing
the NVMe controller again, because there is no active ADMIN connection
for fabric register R/W commands, it will cause segment fault.
Here we set the association timeout value to 0 for vfio-user transport,
so that the ADMIN connection will not be disconnected when shutdown the
controller, the ADMIN queue pair will be disconnected when the socket
connection breaks.
Change-Id: I3613169229bae384405889653e50f581d30d7c07
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/8557
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>
It is better to not fail connect commands when a subsystem
is not ready. The host will not be expecting that and will
typically treat it as a catastrophic failure (i.e. it won't
retry the connect).
So instead when this situation occurs, start a poller for
the connect request. We will continue to retry processing
it until the subsystem is ready to handle it.
Fixes issue #1985.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Id8835df8f0edf1e889fdd7e754e261c2a880cbb6
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/8571
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: Ziye Yang <ziye.yang@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
When the property is 8 bytes but the host only requested
4, we need to mask and only return the bytes requested
by the host. Wait to do the DEBUGLOG until after
that has happened.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I8f476a47e9fd07bf652fd64f3b1c17d650374167
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/8506
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: <dongx.yi@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Commit b7cc4dd added support multiple AERs, but didn't
remove the code that hardcodes aerl=0 for non-discovery
controllers. So even though the target now supports
multiple AERs, we never indicate that for non-discovery
controllers.
The spec also recommends that implementations support
a minimum of 4 AERs - so the current behavior is not
recommended.
It seems that at least on Windows (when testing with
vfio-user transport) we see the limit get exceeded
which results in ERRLOGs. Let's keep the ERRLOG there
for now, assuming that once we report we support 4
AERs that Windows won't try to send more than that.
Fixes issue #2000.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I6a07a6f37aaa6e531ae2cf1e1c46da036b00785b
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/8488
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: <dongx.yi@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
We cannot control what the host may send to the target.
For example, we have empirical evidence that Windows
will send vendor-specific IDs for features and log pages
(when testing with the vfio-user target transport).
So let's change the ERRLOGs in these cases to DEBUGLOGs.
Fixes issues #2004, #2007, #2008.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I8d5b92fc5e33d698af246f2f1c34f7cf51e6488a
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/8487
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: <dongx.yi@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
nvmf_ctrlr_get_log_page used req->data to store the log page result.
While the req->data only contains the first iov, if req->iovcnt is
larger than 1, the req->data may not hold the complete log page; and
even worse, the log page result may be written to invalid address and
cause memory corruption.
Change-Id: Ie6415a6bd2327419fe4b32f21ac814fd827c9e95
Signed-off-by: Jiewei Ke <jiewei@smartx.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/7970
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
POSIX defines %z for printing size_t values in a portable way.
Replace a reference to %ld to remove the assumption about
the type of size_t.
Signed-off-by: Nick Connolly <nick.connolly@mayadata.io>
Change-Id: I2186aa5e7072f565ea75de935e22c2c23acf1a1a
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/8341
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
The traces are tracking the lifecycle of a poll group: creating it,
adding and disconnecting qpairs, and finally destroying the group.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I075b7f24d14b8fbb42bb18ddd70a668a8bace118
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/7158
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
vfio-user transport `req_complete` callback will zero the internal
NVMe command and response fields, the common NVMf library should
not use them after the callback, so here we use stack variables
to save them before the `req_complete` callback.
Fix issue #1965.
Change-Id: Iff2342b6095d9496cdf112d657a0a99ce1fb5d12
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/8129
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-by: <dongx.yi@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
In struct spdk_nvmf_poll_group_stat, there are statistics of cumulative IO and
admin queue pair counts. But current qpair counts are not reflected. Use
this patch to add current admin and io qpair counts for a poll group.
Signed-off-by: Rui Chang <rui.chang@arm.com>
Change-Id: I7d40aed8b3fb09f9d34e5b5232380d162b97882b
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/7969
Reviewed-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-by: Eugene Kochetov <evgeniik@nvidia.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: GangCao <gang.cao@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
nvmf_get_ana_log_page used req->data to store the log page result.
While the req->data only contains the first iov, if req->iovcnt is
larger than 1, the req->data may not hold the complete log page; and
even worse, the log page result may be written to invalid address and
cause memory corruption.
The following patch will fix the same issue for other commands in
nvmf_ctrlr_get_log_page.
Fix#1946
Signed-off-by: Jiewei Ke <jiewei@smartx.com>
Change-Id: I495f3be05c82be5cd53609772c655c8924b9179f
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/7923
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Community-CI: Mellanox Build Bot
Support ACRE (Advanced Command Retry Enable) feature. Currently set
all crdt to 0 and only select crdt[0] (crd=1) when the IO has any
error.
Signed-off-by: Peng Yu <yupeng0921@gmail.com>
Change-Id: If7bc30f91f5b2d0839002dead17188a4b3a52d5d
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/7885
Community-CI: Broadcom CI
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>
This patch fixes missing free of qpair_mask when a listener error
occurs in ctrlr_create.
Signed-off-by: Jonas Pfefferle <pepperjo@japf.ch>
Change-Id: I09162b86d8ac73bf9fc2006a08dcc0a955f222b3
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/7818
Community-CI: Broadcom CI
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Similar issue was fixed in
813869d823
nvmf: Fix possible race condition when adding IO qpair
This patch fixes the same issue which occurs a bit later,
when a message is delivered to another thread. This issue
occurred on CI, callstack is the following:
00:11:46.296 #6 0x00007f2705199f05 in __ubsan_handle_type_mismatch_v1 () from /lib64/libubsan.so.1
00:11:46.296 No symbol table info available.
00:11:46.296 #7 0x00007f27067ace6f in ctrlr_add_qpair_and_update_rsp (qpair=0x221edc0, ctrlr=0x1dc4ea0, rsp=0x2242918) at ctrlr.c:230
00:11:46.296 __PRETTY_FUNCTION__ = "ctrlr_add_qpair_and_update_rsp"
00:11:46.296 __func__ = "ctrlr_add_qpair_and_update_rsp"
00:11:46.296 #8 0x00007f27067b1d0b in nvmf_ctrlr_add_io_qpair (ctx=0x2242540) at ctrlr.c:534
00:11:46.296 req = 0x2242540
00:11:46.296 rsp = 0x2242918
00:11:46.296 qpair = 0x221edc0
00:11:46.296 ctrlr = 0x1dc4ea0
00:11:46.296 __func__ = "nvmf_ctrlr_add_io_qpair"
00:11:46.296 #9 0x00007f27062553ce in msg_queue_run_batch (thread=0x1cff540, max_msgs=8) at thread.c:553
where line 230 in ctrlr.c was
assert(ctrlr->admin_qpair->group->thread == spdk_get_thread());
That means that admin qpair was disconnected from the poll
group and controller is in the process of destruction
Change-Id: I818ba56adda5ed3488a8df78483c0b6839758192
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6364
Community-CI: Broadcom CI
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>
Aspects of bit fields are 'implementation defined'. On some platforms
alignment will occur if two adjacent fields are of different types. This
occurs in spdk_nvme_feat_async_event_configutation after the crit_warn
member which is effectively an int8_t, followed by an int16_t. There
isn't a generic way of changing the compiler's behaviour, so the best
options are:
- Change crit_warn to a uint32_t bit field and copy the value to/from
a spdk_nvme_critical_warning_state variable to use it. This requires
changes to code using the field.
- Adjust the structure definition to use smaller types to avoid the
problem. This preserves existing semantics, but the field order will
need to be reviewed if big-endian support is ever added (other places
in nvme_spec.h will need similar attention). A second reserved field
is required.
Use smaller types which seems the most straightforward option. Adjust
the use of the spdk_nvme_feat_async_event_configuration reserved fields
in lib/nvmf/ctrlr.c.
The new structure is binary compatible and the fields behave in the same
way, with the exception of an additional reserved field, so updating
CHANGELOG.md probably isn't necessary.
Signed-off-by: Nick Connolly <nick.connolly@mayadata.io>
Change-Id: I7d8163c84b4f410fc95a5b7064506ad7b4b62c6c
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6340
Community-CI: Broadcom CI
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Additionally, the user can specify a namespace to also pause during the
operation.
This allows for the management of hosts, listeners, and the addition of
namespaces all while I/O to other namespaces is occurring. Pausing a
specific namespace also allows for the removal of that namespace without
impacting I/O to other namespaces in the subsystem.
Change-Id: I364336df16df92fe2069114674cb7a68076de6fb
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4997
Community-CI: Broadcom CI
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
There is a chance that admin qpair is being destroyed at
the moment when IO qpair is added to a controller due to e.g.
expired keep alive timer. Part of the qpair destruction process
is change of qpair's state to DEACTIVATING and removing it
from poll group. We can check admin qpair's state and poll
group pointer before sending a message to poll group's thread
and fail connect command.
Logs and backtrace from one CI build that hit this problem:
00:10:53.192 [2021-01-22 15:29:46.671869] ctrlr.c: 185:nvmf_ctrlr_keep_alive_poll: *NOTICE*: Disconnecting host from subsystem nqn.2016-06.io.spdk:cnode1 due to keep alive timeout.
00:10:53.374 [2021-01-22 15:29:46.854223] ctrlr.c: 185:nvmf_ctrlr_keep_alive_poll: *NOTICE*: Disconnecting host from subsystem nqn.2016-06.io.spdk:cnode2 due to keep alive timeout.
00:10:53.374 ctrlr.c:587:41: runtime error: member access within null pointer of type 'struct spdk_nvmf_poll_group'
00:10:53.486 #0 0x7f9307d3d3d8 in _nvmf_ctrlr_add_io_qpair /home/vagrant/spdk_repo/spdk/lib/nvmf/ctrlr.c:587
00:10:53.486 #1 0x7f93077ea3cd in msg_queue_run_batch /home/vagrant/spdk_repo/spdk/lib/thread/thread.c:553
00:10:53.486 #2 0x7f93077eb66f in thread_poll /home/vagrant/spdk_repo/spdk/lib/thread/thread.c:631
00:10:53.486 #3 0x7f93077ede54 in spdk_thread_poll /home/vagrant/spdk_repo/spdk/lib/thread/thread.c:740
00:10:53.486 #4 0x7f93078366c3 in _reactor_run /home/vagrant/spdk_repo/spdk/lib/event/reactor.c:677
00:10:53.486 #5 0x7f9307836ec8 in reactor_run /home/vagrant/spdk_repo/spdk/lib/event/reactor.c:721
00:10:53.486 #6 0x7f9307837dfb in spdk_reactors_start /home/vagrant/spdk_repo/spdk/lib/event/reactor.c:838
00:10:53.486 #7 0x7f930782f1c4 in spdk_app_start /home/vagrant/spdk_repo/spdk/lib/event/app.c:580
00:10:53.486 #8 0x4024fa in main /home/vagrant/spdk_repo/spdk/app/nvmf_tgt/nvmf_main.c:75
00:10:53.486 #9 0x7f930716d1a2 in __libc_start_main (/lib64/libc.so.6+0x271a2)
00:10:53.486 #10 0x40228d in _start (/home/vagrant/spdk_repo/spdk/build/bin/nvmf_tgt+0x40228d)
Change-Id: I0968eabd1bcd532b8d69434ad5503204c0a2d92b
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6071
Community-CI: Broadcom CI
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: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: <dongx.yi@intel.com>
A ctrlr disconnect (due to EN=0 or SHN) results in
async operations that we need to make sure don't
complete after the associated controller has been
destructed. So make sure we do not start the ctrlr
destruct if a disconnect is in progress. We can
basically just continue to send the destruct message
to itself over and over again until the disconnect
has finished.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Id722ad206c0dde26ee013dfd98815af3901a9cac
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6057
Community-CI: Broadcom CI
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: <dongx.yi@intel.com>
Currently we fetch the value from the transport
via the admin_qpair. But there are corner cases where
the admin_qpair may be disconnected after an EN=0 or
shutdown process has started.
We could do something like detect if the controller
is being destructed before starting the association
timer, but I think just saving the timeout value in
the ctrlr is a bit cleaner.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Iaf4ceb2f9d38cee3c9a258e1fdf367972030fbe9
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6056
Community-CI: Broadcom CI
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: <dongx.yi@intel.com>
spdk_nvmf_request_exec_fabrics() is still required because for coming
vfio-user transport, Fabric commands are executed synchronously, and
at that monment, the ADMIN queue was not in active state.
Change-Id: I6c53950680d0ad0ab199f66e88ab34a0af46dc14
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4234
Community-CI: Broadcom CI
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: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Use a DEBUGLOG instead of ERRLOG when nvmf target
receives a command for an invalid nsid. This condition
can happen when namespaces are removed while I/O is
in progress, so we don't want to create lots of error
messages when that happens.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I629119c37f8744541708ca8fe2afd5d9dcef0e54
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/5766
Community-CI: Broadcom CI
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Michael Haeuptle <michaelhaeuptle@gmail.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Per section 5.2 of the NVMe 1.3 spec:
"When the controller posts a completion queue entry for an outstanding
Asynchronous Event Request command and thus reports an asynchronous
event, subsequent events of that event type are automatically masked by
the controller until the host clears that event. An event is cleared by
reading the log page associated with that event using the Get Log Page
command (see section 5.14)."
Signed-off-by: Jiewei Ke <jiewei@smartx.com>
Change-Id: I0773ce1b704c2124db354fd19e0a8a19da48da54
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/5462
Community-CI: Broadcom CI
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Add support to queue pending async events to avoid event lost if
multiple async events happen when there is no outstanding AER requests.
Pending async events will be consumes in FIFO order once any AER
requests are received.
Signed-off-by: Jiewei Ke <jiewei@smartx.com>
Change-Id: I545f0baa4ec2996e9e02ec12c176d639e3c0d55a
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/5117
Community-CI: Broadcom CI
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
nvmf_subsystem_state_change() protects against going
starting the pause/change/resume chain again if we
haven't completed the previous chain. But add
some asserts to make sure the cb_fn and cb_args
never get set twice. This also requires setting
them back to NULL after they've been used.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I56c6c89bfb108223f731d5ac28100abbb746ab2f
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/5531
Community-CI: Broadcom CI
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
There is a public API spdk_nvmf_qpair_get_listen_trid() and it can
get trid of the specified qpair safely for any transport including
pluggable transports.
The API was overlooked when implementing the multipath feature for
NVMe-oF target. trid pointer was added to struct spdk_nvmf_qpair and
was used to find a subsystem listener.
However, pluggable transports got seg. fault because trid of the
qpair was not set.
To avoid such segmentation fault for any transport, change
nvmf_ctrlr_create() to use spdk_nvmf_qpair_get_listen_trid().
The struct spdk_nvmf_qpair is located in the public header file,
and so leave the added trid for now. It will be deprecated eventually.
Reported-by: Jacek Kalwas <jacek.kalwas@intel.com>
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I5e0bd24bd58b6ffdf1352332a179a82682f1589f
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/5323
Community-CI: Broadcom CI
Community-CI: Mellanox Build Bot
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jacek Kalwas <jacek.kalwas@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
checks
Check if the subsystem is paused before checking whether the qpair is
active. The order of these checks doesn't really matter, but in the next
patch it will be more convenient to check the subsystem first.
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Change-Id: Ibc95e2578e9a95296f5fbc6023af3b542e954781
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/5015
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
This function is only called from one spot, so it's simpler to combine
it with that function.
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Change-Id: I0a35e11edaf6c4446de530a3b0f538aa4a3238f7
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/5014
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Added asynchronous event notices for discovery log change
as per nvme fabrics spec 1.1. This allows a host with persistent
connection to discovery controller to automatically connect to any
new subsystem available to the host automatically.
According to nvme fabrics spec 1.1, if the connect command specifies a
non-zero keep alive timer value and the discovery controller does not
support asynchronous events then we need to return Connect Invalid.
Since SPDK does not implement this check instead added support
for asynchronous events in discovery controller.
Change-Id: I4cade5f7d24826ce97a2fa2b4ca688a1d728c1db
Signed-off-by: Madhu Adav MJ <madhu.adav@flipkart.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4870
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Michael Haeuptle <michaelhaeuptle@gmail.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Anil Veerabhadrappa <anil.veerabhadrappa@broadcom.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Community-CI: Broadcom CI
Fixes issue #1635.
Under rare circumstances, the CC.en and CC.shn are both set
which then results in setting the association timer twice.
This scenario was observed during hot plug testing when the
initiator tries to reset the subsystem that contains the
removed device.
The end result is that when the ctrlr is destructed, then
one of the timers can still fire and access freed memory.
Change-Id: Ie5880ab325a28f19361f73712bdeb5b58894ee68
Signed-off-by: Michael Haeuptle <michael.haeuptle@hpe.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4935
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: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Issue:
ctrlr.c:1851:13: warning: Although the value stored
to 'copy_len' is used in the enclosing expression,
the value is never actually read from 'copy_len'
next_pos = copy_len = 0;
^ ~
Signed-off-by: yidong0635 <dongx.yi@intel.com>
Change-Id: Ie6d402cd4ad206ae5713deb15e2d03929bac94f4
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4823
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Community-CI: Mellanox Build Bot
If the initiator sends a property set command to a valid register, but
the value contains bits that are reserved by the NVMe specification,
don't fail the whole command. Just log an error message.
Previously, any valid bits set would take effect but then the command
would also fail. That confuses the initiator and thinks it must retry
the full property set.
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Change-Id: I566bc68c4469b9f41c69902e276f825c86683075
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4814
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: John Kariuki <John.K.Kariuki@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
