It's handy to store the SPDK structs within the device
structure. The subsequent patch will make us use
spdk_pci_addr much more frequently, so it makes sense
to keep it around rather than build it up from rte_pci_addr
everytime.
The upcoming VMD driver will also benefit from this patch
by being able to fill the spdk_pci_device struct with any
custom PCI details.
Change-Id: I236a19e28beba9a593b29f23b79b1b0b92ef1fa7
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/434418 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/448374
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>
In DPDK 18.11, a device can be potentially detached not only
upon an SPDK request, but also directly from within the DPDK
itself. In a multi-process scenario, when one process detaches
the PCI device, an IPC message - detach request - will be sent
to every other process in the same shared memory group. As we
don't propagate the removal notification to upper layers, the
still-referenced rte_pci_device object will just disappear at
one moment.
SPDK is still not ready for supporting the above case and will
try to avoid it, but just in case some detach request slips
through, then this patch provides the sanity checks preventing
SPDK from crashing.
Change-Id: I3e35d8efb33085163b9acd8a565e86a4221df844
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/434412 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/448373
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>
Very minor cleanup before we start refactoring the code.
Change-Id: I00d768ec0c84f2a37c54b7575de695281c5ebb22
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/434411 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/448372
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>
DPDK already prints at least one error message, so
there's no need to print a yet another one.
Change-Id: I1c7bdfe5ca2095b93ec282bf193a717627d5fa27
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/434410 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/448371
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>
Prepare for storing additional per-device data.
The struct doesn't store any interesting data yet,
but already has a TAILQ_ENTRY that allows us to
put it into a global pci device list. Right now
we use the list only to find the SPDK device once
the corresponding DPDK device gets removed, but
more usages will be implemented soon.
Change-Id: If3abc1da60446e0a647d8d4c642f111ebfbcdb9e
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/434409 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/448370
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>
Now that even DPDK 16.11 (LTS) reaches its end of life in
November 2018, we can surely drop support for DPDK
versions older than that.
The PCI code will go through a major refactor soon, so this
patch cleans it up first.
Since this is the very first SPDK patch that drops support
for older DPDK versions, it also introduces an #error
directive that'll directly fail the build if the used DPDK
lib is too old.
Change-Id: I9bae30c98826c75cc91cda498e47e46979a08ed1
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/433865 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/448369
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>
Despite the scary commit title, this patch just unifies
per-driver mutexes into a single pci mutex.
On each hotplug we modify some DPDK global resources,
which per-driver locks aren't sufficient for. If
multiple threads try to attach devices at the same time,
then we'll likely have a data race. DPDK hotplug APIs
don't provide any kind of thread safety on their own.
Change-Id: I89cca9fea04ecf576ec5854c662bae1d3712b3fb
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/433864 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/448368
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>
We need to do it only for DPDK 16.11, which leaks the
mappings otherwise. DPDK was fixed in version 17.02 with
the following commit:
e84ad157 (pci: unmap resources if probe fails)
Unmapping the resources twice doesn't actually cause
us any trouble, but prints an ambiguous error message.
Change-Id: I8b62e86d5fff8fe924dbf9ae2e37cff29298d412
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/433863 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/448367
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>
This case isn't particularly supported, but still
caused a memory leak and rendered the pci device
inaccessible for the rest of the primary process
lifetime.
This happens when a controller is removed from the
primary process while a secondary process still
uses it. The controller will likely misbehave without
its primary process managing it, but at least there
won't be a leak.
Change-Id: I67581cffa33ce14ff516b5743d13c9ef7b351625
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/434408 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/448366
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>
With various possibilities to leak the rte_pci_device in the
primary process, we could technically construct the controller
in secondary. The nvme stack is not prepared for this and
will fail to initialize the device, but will still leak the
device object memory.
This patch adds an extra check to prevent any controller from
being constructed in secondary process.
Change-Id: I772f42b541c5db53310362b6595cebf9a30e8491
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/434407 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/448365
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>
We only detached the PCI device on the controller destruction,
which happens just once - in the primary process, but secondary
process needs the PCI detach as well.
Requesting to hotremove the NVMe PCIe controller in secondary
process is broken, because DPDK will still keep the device
reference and won't allow SPDK to hotplug it again.
Fix this by detaching the local PCI device whenever removing
a secondary process from spdk_nvme_ctrlr. This does require
an additional transport check in the generic NVMe layer, but
I found it an overkill to create a multi-process transport
abstraction just for this case.
Change-Id: I812dc1c878ade5b149556806228a2afcb49f0b17
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/431487 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/448364
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>
DPDK 18.11 sets the default base-virtaddr to an address
that falls into an area reserved by ASAN. DPDK will try
to remap its memory over and over with the closest
base-virtaddr hint and for ASAN case this would take
a huge amount of time.
This was already raised on DPDK mailing list [1] and
might be eventually fixed or worked around in upstream,
but for now let's just override the default base-virtaddr
to a value that ASAN is known not to occupy.
[1] http://patches.dpdk.org/patch/46130/#88395
Change-Id: Ieada30e82355e8ead458e53795ab98cd12692c1c
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/431257 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/448380
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>
The previous functions were deprecated and now removed.
Change-Id: I076125aaf80b97c627ca45b860700fdf6d87e925
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/430557 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447850
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>
Since we use aligned buffer, I think that the error handling
path here is not correct, the address is wrong.
Change-Id: I5bcb7f050199496423f861fd6aea65e0fe48c804
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-on: https://review.gerrithub.io/435992 (master)
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com> (master)
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com> (master)
Reviewed-by: Seth Howell <seth.howell5141@gmail.com> (master)
Reviewed-on: https://review.gerrithub.io/c/438100
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
The ctrlr may be NULL, so we need to add a check here
to present segment fault.
Change-Id: I6c5361cc829af065082a95df0b8cc2f8d49a6002
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-on: https://review.gerrithub.io/436950 (master)
Reviewed-on: https://review.gerrithub.io/437916
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Maciej Szwed <maciej.szwed@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Check for QP reference counter in RDMA QP destroy function was wrong
and QP resources were never released.
Change-Id: I6ab0ce39452e8263f89589d138c90f749516ebb1
Signed-off-by: Evgeniy Kochetov <evgeniik@mellanox.com>
Signed-off-by: Sasha Kotchubievsky <sashakot@mellanox.com>
Reviewed-on: https://review.gerrithub.io/436974 (master)
Reviewed-on: https://review.gerrithub.io/437348
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Seth Howell <seth.howell5141@gmail.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
At least in case of RDMA transport, poll_group_create (spdk_nvmf_rdma_poll_group_create)
can return error (NULL).
Change-Id: If1576b3515e7f9ede76af08bfa6b1c8399dcda09
Signed-off-by: Sasha Kotchubievsky <sashakot@mellanox.com>
Signed-off-by: Evgeniy Kochetov <evgeniik@mellanox.com>
Reviewed-on: https://review.gerrithub.io/436887 (master)
Reviewed-on: https://review.gerrithub.io/437349
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
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: Ben Walker <benjamin.walker@intel.com>
When last clone of a snapshot is being deleted
we remove that snapshot from snapshots list.
We should not do that as it still works as a
snapshot and it is read-only, but it does not list
as a snpashot from get_bdevs. Instead remove snapshot
entry from the list when blob that represents that
snapshot is being removed.
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: I8d76229567fb0d9f15d29bad3fd94b9813249604
Reviewed-on: https://review.gerrithub.io/436971 (master)
Reviewed-on: https://review.gerrithub.io/437194
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>
This should have always been the case with spdk_mem_map_translate. For
some memory maps (like RDMA) this doesn't matter, but for others like
our virtual to physical map, this is critical for retrieving valid
translations.
This behavior change will only affect maps that have a registered
contiguous memory callback.
Change-Id: I67517667f01d974702d7daa7c81238281aae0cf6
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/436562 (master)
Reviewed-on: https://review.gerrithub.io/437202
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>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
This is a failsafe for finding and reporting data buffers that span
multiple Memory Regions. These errors should never be triggered, but
finding and reporting them will help any debugging.
Change-Id: I3c61e3cc510f5a36039fc1815ff0de45fce794d5
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/436054 (master)
Reviewed-on: https://review.gerrithub.io/437016
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>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
This patch implements the following QP shutdown flow:
1. Move the QP to ERR state
2. Post dummy work requests to send and receive queues
3. Poll CQ until it returns dummy work requests (with WR Flush Error status)
4. Call ibv_destroy_qp and release resources
In order to differentiate dummy and normal WRs new spdk_nvmf_rdma_wr
structure was introduced which contains type of WR. Since now it is
expected that wr_id field in ibv_recv/send_wr and ibv_wc always points
to this structure. Based on WR type wr_id can be safely casted to
correct container structure. In case of unsuccessful work completions
'opcode' can not be used for this purpose because it may be
invalid (see "IB Architecture Specification Volume 1", ch. 11.4.2.1
"Poll for completion").
Change-Id: Ifb791e36114c619c71ad4d831f2c7972fe7cf13d
Signed-off-by: Evgeniy Kochetov <evgeniik@mellanox.com>
Signed-off-by: Sasha Kotchubievsky <sashakot@mellanox.com>
Reviewed-on: https://review.gerrithub.io/430754 (master)
Reviewed-on: https://review.gerrithub.io/436859
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
1.nvmf: change the return type of calloc failed to -ENOMEM and
keep consistency in this file.
2.thread: revise rc condition to ( rc!= 0),to deal with
all abnormal return.
Change-Id: I7cccb548f30448eaa1bac1a5904c3edcad9c1208
Signed-off-by: yidong0635 <dongx.yi@intel.com>
Reviewed-on: https://review.gerrithub.io/431459 (master)
Reviewed-on: https://review.gerrithub.io/436858
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>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
We were previously doing lots of checks in debug mode
to verify the validity of this field. Now we understand
how it works, so these checks are never going to hit
and are just making the code harder to read.
Change-Id: Ic82d479ae34a8c7db06db62aee1cdf6e8bec126e
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/430866 (master)
Reviewed-on: https://review.gerrithub.io/436857
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>
When we thought we could do error recovery we differentiated between
inactive and erro states. However, that's not possible so collapse
them back into one.
Change-Id: I57622c400378f2d4c518efbc12fb52e665a9ba4c
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/430627 (master)
Reviewed-on: https://review.gerrithub.io/436856
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>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
The specification states that opcode is not valid when the status
is not success. Instead, keep track of the operation type ourselves.
Change-Id: I60af4b35e761c46f5f296a61cedfca198836197f
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Co-authored-by: Evgeniy Kochetov <evgeniik@mellanox.com>
Reviewed-on: https://review.gerrithub.io/430865 (master)
Reviewed-on: https://review.gerrithub.io/436855
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>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
After some lengthy discussions with the RDMA experts, the only
way forward on an RDMA qp error is to disconnect it. The initiator
can create a new qp if it wants to later on.
Remove all of the error recovery code and disconnect the qp
any time an error is encountered.
Change-Id: I11e1df5aaeb8592a47ca01529cfd6a069828bd7f
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/430389 (master)
Reviewed-on: https://review.gerrithub.io/436854
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
BSD implementation for config access in DPDK seems to
return 0 on success while Linux implementation returns 0
only on failure. The env wrapper was always treating 0 as
an error and caused some of our PCI initialization code
to fail prematurely.
At one point DPDK harmonized this BSD behavior with Linux,
but only for config reads.
Fixes#484
Change-Id: I4ea850ea50f5e667fad28e8125209b21c377a2a3
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/432401 (master)
Reviewed-on: https://review.gerrithub.io/435682
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>
This keeps us from having to deal with ALLOC and FREE events
for mismatching regions - which necessitated splitting new
regions into individual pages. This caused all kinds of
problems with NVMe-oF - for example, buffers that spanned
memory regions, or bumping up against MR limits on RDMA
NICs.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I18dcdae148436b55d4481bb9fb8799f4832c7de1
Reviewed-on: https://review.gerrithub.io/434895 (master)
Reviewed-on: https://review.gerrithub.io/435692
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
This is necessary to confirm that a buffer that spans a 2_MB boundary is
still in a single MR.
Change-Id: If0d14e514ab2197a0d2e3af4f565f56d50591210
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/435179 (master)
Reviewed-on: https://review.gerrithub.io/435689
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>
We assumed spdk_mem_map_translate() translates only 2MB-aligned
addresses, but that's not true. Both vtophys and NVMf can use it
with any user-provided address and that breaks our contiguous memory
length calculations. Right now each buffer appeared to have the
first n * 2MB of memory always contiguous.
This is a bugfix for NVMf which does check the mapping length
internally. It will also become handy when adding the similar
functionality to spdk_vtophys().
Change-Id: I3bc8e0b2b8d203cb90320a79264effb7ea7037a7
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/433076 (master)
Reviewed-on: https://review.gerrithub.io/435691
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>
There are some use cases such as multipath and RAID expansion where a
vbdev could have been registered before one of its base bdevs.
Currently we unregister bdevs at shutdown in reverse order of their
registration. Continue to do that in general, but skip any bdev that
is still claimed. Any bdevs skipped in this way will eventually be
unregistered once any bdevs that have claimed it have completed
unregistration.
Change-Id: Iafde9558430bc5ce56e8608ef50bcb2b5fbfbf71
Signed-off-by: Andrey Kuzmin <akuzmin@jetstreamsoft.com>
Reviewed-on: https://review.gerrithub.io/432136 (master)
Reviewed-on: https://review.gerrithub.io/435688
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>
In vbdev_crypto_examine() we were failing to unregsiter the io_device
in the event that spdk_vbdev_register() call failed. Found via
inspection.
Change-Id: I73c6c0c5693777b93c1ea02dcf2e2e65d46fe27d
Signed-off-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/432933 (master)
Reviewed-on: https://review.gerrithub.io/435677
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>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
In create_crypto_disk() we were failing to unregsiter the io_device
in the event that spdk_vbdev_register() call failed. Found via
inspection looking into a CI failure however this potentially could
have caused that failure as well (I don't think so though, there
were no prints in the log that it followed this path).
Change-Id: I7085c4e25665a5a15def38d6726d519731b7e44e
Signed-off-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/432932 (master)
Reviewed-on: https://review.gerrithub.io/435676
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>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Found via inspection while invetigating a CI failure. In
vbdev_crypto_examine() we were not looking at the rc from
vbdev_crypto_claim()
Change-Id: I8be09b5844e18e35b95f19e378fe280323d183fa
Signed-off-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/432930 (master)
Reviewed-on: https://review.gerrithub.io/435675
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: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
The io device was previously not being unregistered, this looks
like the root cause to several recent CI failures in the bdev
JSON tests that use RPC to create/save/clear/load configs.
Change-Id: Ia77ed9fe230c79188d8d862e98b17581ae81b31f
Signed-off-by: paul luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/433194 (master)
Reviewed-on: https://review.gerrithub.io/435674
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: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Picked up from recent update to the passthru module.
Change-Id: Ie7404e5aadda6691b15020adbbc1e1f4c23d0a12
Signed-off-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/433384 (master)
Reviewed-on: https://review.gerrithub.io/435673
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Since a PDU can be sentout in many times, so this
function is called multiple times, so move the
caculation function in spdk_iscsi_conn_write_pdu
Change-Id: Ib4da4a74c17709d98e4b01c2e76428021afea947
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-on: https://review.gerrithub.io/429931 (master)
Reviewed-on: https://review.gerrithub.io/435681
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.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>
Code movement only. No other changes.
Change-Id: I04cf179ecd57154172a9369926cbeaaa37e11a52
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/430505
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Sasha Kotchubievsky <sashakot@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-on: https://review.gerrithub.io/435671
This event only occurs when using shared receive queues, which
the target does not currently support.
Change-Id: If155843610cf0e961b9783d4afd64b969b4316f4
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/430388
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Sasha Kotchubievsky <sashakot@mellanox.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-on: https://review.gerrithub.io/435670
There is no guarantee that the first io_channel created for
a LUN will be the last one destroyed. So we need to attach
the poller to the LUN, not the io_channel.
While here, and related to this patch, remove the assert()
that the last channel destroyed must be on the LUN's
master thread. This assertion simply isn't true.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I3e0dfddde2de70caec479bf1b6703f01c9d7b3a2
Reviewed-on: https://review.gerrithub.io/431375
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: Liang Yan <liang.z.yan@intel.com>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Previously there was no consideration for IO that were outstanding
to the crypto device when handling a reset. This patch makes sure
that those IO are completed with FAIL status prior to completing
the reset that we pass down the stack.
It does so by sending down the reset first and in the completion
using spdk_for_each_channel and the poller to quiesce each channel
allowing the crypto side to complete all IOs before we finally
complete the reset IO after the last channel is quiesced.
Resets are tracked on a per bdev basis.
Addresses github issue #449.
Change-Id: Iadb07bada1fcaad33d9f224a60d983a7eb835236
Signed-off-by: paul luse <paul.e.luse@intel.com>
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/428552
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Seth Howell <seth.howell5141@gmail.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Small language fix. But more importantly, the missing return caused
crashes because the released handle was used for the following
rados_ioctx_create.
Change-Id: Ica5efc157b89fe957a55bdee476ee70e6ccc2568
Signed-off-by: Patrick Ohly <patrick.ohly@intel.com>
Reviewed-on: https://review.gerrithub.io/430547
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>
"get_nvme_controllers" can be used to list NVMe controllers.
Names and transport IDs of the NVMe controllers will be
reported by this method.
Change-Id: Ie59b567afc09e70475f97939e86a872af39c5d8a
Signed-off-by: Liu Xiaodong <xiaodong.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/419094
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: GangCao <gang.cao@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
The error message says "Failed to create rados context for
rbd_pool=..." but then included the image name.
Change-Id: Iab78df6f67753705ac422dd63b414a5ba24727b7
Signed-off-by: Patrick Ohly <patrick.ohly@intel.com>
Reviewed-on: https://review.gerrithub.io/430458
Reviewed-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
With all SPDK patches in place, we can now enable dynamic
memory management for all DPDK versions >= 18.05.1
Hugepages can be still reserved with [-s|--mem-size <size>]
option at application startup, but once we use them all up,
instead of failing user allocations with -ENOMEM, we'll try
to dynamically reserve even more. This allows starting DPDK
with `--mem-size 0` and using only as many hugepages as it
was actually necessary.
Change-Id: I9e6f58ea50af2234f96a53e7a32d9e14d2df65ff
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/426828
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
This helps us avoid situations where other bdev modules will break the
rte_pci_bus mappings for qat devices before we have an opportunity to
initialize the qat pmd.
Also, update the blobstore match file to handle the possibility of using
a crypto driver and improve the json_config and spdkcli scripts to
handle allocating qat_crypto drivers.
Change-Id: I7359c67d1992df1d5bb85585eca6d5c342787649
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/430393
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
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 need to resend SET_MEM_TABLE whenever memory
is hotplugged or hotremoved.
Change-Id: I9bdc975f11b07866122bc49b9cf372071c5370f2
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/422582
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
By running random, 64KB, 70% write, and 30% read workload and periodical
TCP disconnection from the initiator, segmentation fault have occurred.
By investigation, when the last write task completed and dequeued
the primary write task in spdk_iscsi_task_cpl(), the primary write task
was already dequeued in spdk_clear_all_transfer_task().
This patch dequeues all primary write tasks after all outstanding
tasks complete.
After starting to exit the connection, the connection will not receive
any command. Hence waiting for completion of all pending tasks first will
avoid double dequeue safely.
Change-Id: I8e2b6b756be3a6e096675acc81cdb93fb6a7e350
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/430397
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
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>
The next patch will change spdk_iscsi_conn_destruct() to fix the
Github issue #457. This patch is a preparation to that.
Change-Id: Iaf1c8a3fe8514d6bbd9f61f19f87b0bb2c27e76e
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/430402
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Piotr Pelpliński <piotr.pelplinski@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
