Commit Graph

9873 Commits

Author SHA1 Message Date
Pawel Kaminski
3650a73353 rpc: Rename get_tpoint_group_mask trace_get_tpoint_group_mask
Change-Id: I65f8d75e0968b16dca3e379022da82bc52042411
Signed-off-by: Pawel Kaminski <pawelx.kaminski@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469142
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>
2019-10-01 13:59:37 +00:00
Pawel Kaminski
ecca55c996 rpc: Rename disable_tpoint_group to trace_disable_tpoint_group
Change-Id: I3a41353ca8ff44163efcf1d0ee07a4332ba3ac85
Signed-off-by: Pawel Kaminski <pawelx.kaminski@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469137
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>
2019-10-01 13:59:37 +00:00
Pawel Kaminski
dd29bd7e8d rpc: Rename enable_tpoint_group to trace_enable_tpoint_group
Change-Id: I1f9948ceacc615a9f0156c45de4c45cbe23ae9b0
Signed-off-by: Pawel Kaminski <pawelx.kaminski@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469135
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Maciej Wawryk <maciejx.wawryk@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-10-01 13:59:37 +00:00
Maciej Wawryk
378ad60b88 RPC: rename get_subsystem_config to framework_get_config
Signed-off-by: Maciej Wawryk <maciejx.wawryk@intel.com>
Change-Id: Ia0d20a04cf2dd5b23ad201d2ae9677a703ec92f3
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/468682
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>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
2019-10-01 13:57:36 +00:00
Maciej Wawryk
8710b60062 RPC: rename get_subsystems to framework_get_subsystems
Signed-off-by: Maciej Wawryk <maciejx.wawryk@intel.com>
Change-Id: Iaeaf20e2a16b41796cb89a92fadd99cb1d341720
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/468670
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>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
2019-10-01 13:57:36 +00:00
Seth Howell
7630daa204 nvme: move queueing requests to the generic layer
The tailq and the requests all belong to the generic layer, might as
well put the queueing code there for better encapsulation.

Change-Id: Id5f08f798121b50a21044cfc61856999c50ca227
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469758
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>
2019-09-30 21:17:47 +00:00
Seth Howell
fd892b333d nvme_ctrlr: when reconnecting admin queue, check rc.
This was being ignored, and can cause some problems when trying to reset
a defunt controller over a fabric.

Change-Id: I32c11a0e2df0e140e20f870fe0fb5b9045a567b3
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469638
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>
2019-09-30 21:17:47 +00:00
Seth Howell
13fb1b690e nvme_rdma: add a timeout for spinning on cm events.
Previously we would just sit forever. preventing us from properly
attempting reconnects and timing out.

Change-Id: Id7386ab95cf75fd9ac972b44afa2719aad412f49
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469021
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>
2019-09-30 21:17:47 +00:00
Seth Howell
37152dc56d test/nvmf: isolate bdevio and nvmf_tgt cores.
These shouldn't compete for cores.

Change-Id: I9793cec0561d7991e603c57d65b0359338dfedce
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469763
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>
2019-09-30 21:17:47 +00:00
Seth Howell
5ac814e36c nvme_rdma: share the cm_event channel between qpairs.
This enables us to create a single file descriptor and a single event
channel to poll for completions. With that accomplished, we can easily
poll for events on the admin qpair each time we check it for
completions.

Change-Id: I8b901252510744a956bef12594d1e045715e002e
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/467549
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>
2019-09-30 21:17:47 +00:00
Seth Howell
f12e6bc041 nvme_rdma: in qp_disconnect, set resources to NULL
This prevents us from failing a reset and then trying to double put the
rqpair->cq which ends up causing seg faults.

Change-Id: If3e14a3d039b4b19cc587a7482157f4b23f8ee32
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469609
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>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
2019-09-30 21:17:47 +00:00
Seth Howell
06746448c1 nvme: fix confusion around nvme_ctrlr_set_state
In most places, we are passing NVME_TIMEOUT_INFINITE as the
timeout_in_ms argument to nvme_ctrlr_set_state, presumably in an attempt
to specify an infinite timeout. However, nvme_ctrlr_set_state only
checked against 0 when setting the actual timeout, and we didn't have
any logic to check for overflow so we just ended up setting random
timeout_tsc values which changes the behavior of the
nvme_ctrlr_process_init function in several places.

So, change NVME_TIMEOUT_INFINITE to 0, and add some integer overflow
checking to nvme_ctrlr_set_state.

Change-Id: Ic9d0cc57ed153df30c3b20313c3742072a5f992d
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469485
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>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
2019-09-30 21:17:47 +00:00
Maciej Wawryk
a10d0ce79c RPC: rename context_switch_monitor to framework_monitor_context_switch
Signed-off-by: Maciej Wawryk <maciejx.wawryk@intel.com>
Change-Id: I6de7bf824b5f57e535168afaafca55f4c758fc94
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/468667
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: Ben Walker <benjamin.walker@intel.com>
2019-09-30 21:13:41 +00:00
Maciej Wawryk
fb3918a0ca RPC: rename wait_subsystem_init to framework_wait_init
Signed-off-by: Maciej Wawryk <maciejx.wawryk@intel.com>
Change-Id: Ib9bb2de327a3461081f5f0dfc359b53f61019e28
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/468133
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
2019-09-30 21:13:41 +00:00
Maciej Wawryk
e85d47123c RPC: rename start_subsystem_init to framework_start_init
Signed-off-by: Maciej Wawryk <maciejx.wawryk@intel.com>
Change-Id: I44a96f87f5565b3984f0a6919bf7f276207637a3
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/468130
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>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-09-30 21:13:41 +00:00
Shuhei Matsumoto
68ee93aac7 nvmf/rdma: Pass pointer to iovec directly to nvmf_rdma_fill_wr_sge()
nvmf_rdma_fill_wr_sge() gets pointer to iovec at its head, but
nvmf_rdma_fill_wr_sgl() can pass it to nvmf_rdma_fill_wr_sge()
simply.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I16176d5d36ca9daf57640bfcbc49dfbf997afe54
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469639
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-09-30 21:11:52 +00:00
Shuhei Matsumoto
91f9c6f376 nvmf/rdma: Simplify nvmf_rdma_request_parse_sgl() by cached pointers
Pointers to struct spdk_nvmf_request and struct ibv_send_wr are
used in many lines of spdk_nvmf_rdma_request_parse_sgl().

Caching and using them simplifies and improves readability a little
for spdk_nvmf_rdma_request_parse_sgl().

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ib000c9d4e7fb7bb415f4ac4622b32b12cc787c80
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469537
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-09-30 21:11:52 +00:00
Shuhei Matsumoto
063c79d13c nvmf: Optimize nvmf_request_get_buffers by merging buffer and iovec loops
We can merge two loops of req->buffers and req->iov into a single
loop and merge two variables, req->num_buffers and req->iovcnt into
a single variable. For the latter, use req->iovcnt because it is
also used for in-capsule data.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ia164f2054b98bbcb00308791774e3ffa4fc70baf
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469489
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-09-30 21:11:52 +00:00
Shuhei Matsumoto
e1f72b2cd2 nvmf/rdma: Include nvmf/transport.c into UT code and remove copied functions
This follows the good practice of FC transport.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Change-Id: I84a6bb28a27b529335f100c8cab12d642bc156ff
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469488
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>
2019-09-30 21:11:52 +00:00
Shuhei Matsumoto
fda0e558a1 nvmf/rdma: Return rc simply when spdk_nvmf_request_get_buffers/_multi fails
spdk_nvmf_request_get_buffers()/_multi() may return not only -ENOMEM
but also -EINVAL, but spdk_nvmf_rdma_request_fill_iovs() and
nvmf_rdma_request_fill_iovs_multi_sgl() had returned -ENOMEM
regardless of the actual return value. Fix them in this patch.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ic19593ffa9c0731f63d198d4ae16feb3bb47f57c
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469378
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-09-30 21:11:52 +00:00
Shuhei Matsumoto
0462157650 nvmf/rdma: Add spdk_nvmf_request_get_buffers_multi() for multi SGL case
This patch is the end of the effort to unify buffer allocation
among NVMe-oF transports.

This patch aggregates multiple calls of spdk_nvmf_request_get_buffers()
into a single spdk_nvmf_request_get_buffers_multi().

As a side effect, we can move zeroing req->iovcnt into
spdk_nvmf_request_get_buffers() and spdk_nvmf_request_get_buffers_multi()
and do it in this patch.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I728bd330a1f533019957d58e06831a79fc17e382
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469206
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-09-30 21:11:52 +00:00
Shuhei Matsumoto
c0ee8ef7d5 nvmf: Merge each transport's fill_buffers() into spdk_nvmf_request_get_buffers()
This patch is close to the end of the effort to unify buffer allocation
among NVMe-oF transports.

Merge each transport's fill_buffers() into common
spdk_nvmf_request_get_buffers() of the generic NVMe-oF transport.

One noticeable change is to set req->data_from_pool to true not in
each specific transport but in the generic transport.

The next patch will add spdk_nvmf_request_get_multi_buffers() for
multi SGL case of RDMA transport.

This relatively long patch series is a preparation to support
zcopy APIs in NVMe-oF target.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Icb04e3a1fa4f5a360b1b26d2ab7c67606ca7c9a0
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469205
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-09-30 21:11:52 +00:00
Shuhei Matsumoto
16365fd802 nvmf/rdma: Merge filling wr->sg_list of non DIF case and DIF case
This patch merges nvmf_rdma_fill_wr_sgl_with_md_interleave()
into nvmf_rdma_fill_wr_sge(), and then removes
nvmf_rdma_fill_wr_sgl_with_md_interleave().

In nvmf_rdma_fill_wr_sgl(), pass DIF context, remaining data block
size, and offset to nvmf_rdma_fill_wr_sge() in the while loop.
For non DIF case, initialize all of them by zero.

In nvmf_rdma_fill_wr_sge(), classify non-DIF case and DIF case
by checking if DIF context is NULL.

As a minor change of wording, remaining is sufficiently descriptive
and simpler than remaining_io_buffer_length and so use remaining.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I55ed749c540ef34b9a328dca7fd3b4694e669bfe
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469350
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-09-30 21:11:52 +00:00
Shuhei Matsumoto
b48a97d454 nvmf/rdma: Separate filling wr->sg_list from filling req->iov for DIF case
This patch separates filling wr->sg_list from filling req->iov
in nvmf_rdma_fill_buffers_with_md_interleave() and create an new helper function
nvmf_rdma_fill_wr_sgl_with_md_interleave() to fill wr->sg_list by adding iovcnt to
struct spdk_nvmf_rdma_request.

The subsequent patches will merge nvmf_rdma_fill_buffers() into
spdk_nvmf_request_get_buffers().

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I03206895e37cf385fb8bd7498f2f4a24797c7ce1
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469204
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-09-30 21:11:52 +00:00
Shuhei Matsumoto
5593b61f93 nvmf/rdma: Separate filling wr->sg_list from filling req->iov
This patch separates filling wr->sg_list from filling req->iov
in nvmf_rdma_fill_buffers() and create an new helper function
nvmf_rdma_fill_wr_sgl() to fill wr->sg_list by adding iovcnt to
struct spdk_nvmf_rdma_request.

The next patch will do the same change for
nvmf_rdma_fill_buffers_with_md_interleave().

The subsequent patches will merge nvmf_rdma_fill_buffers() into
spdk_nvmf_request_get_buffers().

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ia4cdf134df39997deb06522cbcb6af6666712ccc
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469203
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-09-30 21:11:52 +00:00
Shuhei Matsumoto
5ea1c95947 nvmf/rdma: Update only iov_base when buffer replacement succeeds
When buffer replacement succeeds, only iov_base has to be updated.
This change is small but will be helpful to disaggregate buffer
allocation and filling WR SGL.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ifc72fd783b515dfaecac04939c183097f939e29b
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469202
Community-CI: Broadcom SPDK FC-NVMe 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: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-09-30 21:11:52 +00:00
paul luse
a5d9d77821 module/raid: move a single function up
In prep for future RAID1E patch so that the completion function
can be shared by multiple RAID levels.

Change-Id: I169e2d64388fab701e9b467f8803aacd5d1250d2
Signed-off-by: paul luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469743
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>
2019-09-30 20:35:03 +00:00
paul luse
75cb691c97 module/raid: replace hardcoded "0" with #define for RAID0
Small cleanup in prep for future RAID levels and to improve
readability.

Change-Id: I66ae64320593ee5b242ccdc50a0041a4ec8207fb
Signed-off-by: paul luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469742
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>
2019-09-30 20:35:03 +00:00
Shuhei Matsumoto
7fc89387da nvmf/rdma: Factor out setup WR operation from nvmf_rdma_fill_buffers_with_md_interleave()
Factor out setup WR operation from nvmf_rdma_fillbuffers_with_md_interleave()
into a function nvmf_rdma_fill_wr_with_md_interleave().

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I92689daa7dcc93aaa68ecf5706d4e1b75d7fabae
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469066
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-09-27 20:03:16 +00:00
Shuhei Matsumoto
8bbde3758a nvmf/rdma: Cleanup nvmf_rdma_fill_buffers_with_md_interleave()
This patch
- applies nvmf_rdma_get_lkey(),
- changes pointer to struct iovec from iovec to iov,
- changes pointer to ibv_sge from sg_list to sg_ele, and
- passes DIF context instead of decoded data block size and metadata size
- use cached pointer to nvmf_request to call
- change the ordering of operations to setup sg_ele slightly
for nvmf_rdma_fill_buffers_with_md_interleave().

Name changes are from the previous patch.

They are for consistency with nvmf_rdma_fill_buffers() and a
preparation for the next patch.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I942fb9d07db52b9ef9f43fdfa8235a9e864964c0
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469201
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-09-27 20:03:16 +00:00
Shuhei Matsumoto
c2f60ea452 nvmf/rdma: Move nvmf_rdma_get_lkey() up in a file
This reduces the diff in the next patch.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I85dccdc1a1a5a51777934121f50a6af97feda5a5
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469480
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-09-27 20:03:16 +00:00
Marcin Dziegielewski
8f80af4c2a test/ocf/management/multicore: change in test to prevent failure
Because now bdev_ocf_delete function can fail if examine of this
bdev is still in progress, so to prevent that situation and in
consequence test fail, this patch adds small sleep to enasue that
examine are done before call bdev_ocf_delete.

Signed-off-by: Marcin Dziegielewski <marcin.dziegielewski@intel.com>
Change-Id: I7f7ac4921b539f20b0d22d68bd401b247cd9a813
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469407
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>
2019-09-27 15:27:55 +00:00
Marcin Dziegielewski
d1c9e2f779 lib/bdev/ocf: fix race between examine and delete in mulicore test
Fixes #962

Issue mentioned above was caused by race between examine on ocf bdev
(which is partially asynhronous) and bdev delete.

This patch adds new ocf bdev state "starting" it means that register
procedure was started, base on this state, we are not allowing to
destruct vbdev during registering path.

Deleting of vbdev will be still possible on started vbdev or when
register procedure are not started yet.

Signed-off-by: Marcin Dziegielewski <marcin.dziegielewski@intel.com>
Change-Id: I12099dfba75a46f95299c118f748d39af27df86a
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469406
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>
2019-09-27 15:27:55 +00:00
Shuhei Matsumoto
1aa8e4e5b2 lib/iscsi: Add iscsi_portal_group_set_auth for per portal group CHAP authentication
Add an new RPC iscsi_portal_group_set_auth. This RPC overwrites
the setting of CHAP authentication for discovery sessions by the
global parameters specific for the portal group.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I01578b2d01e3dbed599db10340d5053fb0a3738d
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469369
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>
2019-09-27 15:24:14 +00:00
Shuhei Matsumoto
b72893a6f2 lib/iscsi: Portal group holds CHAP params and passes them to connections
This is another preparation to support per portal group CHAP authentication
for discovery session.

Add CHAP params into struct spdk_iscsi_portal_grp, and initialize them
by global parameters at spdk_iscsi_portal_grp_create().

Copy CHAP params from portal group to connection at spdk_iscsi_conn_construct().

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I1ecb812266ac3d090f8e6db21d1d6a090f1811d9
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469368
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>
2019-09-27 15:24:14 +00:00
Shuhei Matsumoto
a398d87467 lib/iscsi: Separate CHAP params setup and authentication process
This is a preparation to support per portal group CHAP authentication
for discovery session.

Previously require_chap, disable_chap, and mutual_chap had been set
and used in iscsi_negotiate_param(), and chap_group had been set
and used in iscsi_get_authinfo().

If a connection is in a discovery session, the connection can get
all CHAP params at its creation, spdk_iscsi_conn_construct().

If a connection is in a normal session, the connection can get all
CHAP params in iscsi_op_login_negotiate_chap_param().

Each connection is in either discovery session or normal session.

So the following change is possible and is done in this patch.

spdk_iscsi_conn_construct() sets all CHAP params of the connection
by global parameters. Then iscsi_op_login_negotiate_chap_param()
overwrites them by the corresponding target's parameters.
iscsi_negotiate_chap_param() and iscsi_get_authinfo() just refer
the CHAP params.

Besides, iscsi_get_authinfo() changed to call just
spdk_iscsi_chap_get_authinfo() inside, and so inline
spdk_iscsi_chap_get_authinfo() into iscsi_auth_params() and then
remove iscsi_get_authinfo().

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I8028673cc6923e1b8bc20af55e0c3cc933972fc0
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469218
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>
2019-09-27 15:24:14 +00:00
Ben Walker
a6e3a930bb test/compress: Use gen_nvme.sh to create NVMe device
This script additionally checks that the device is bound to
uio or vfio, so it won't let the test wipe your boot disk.

Change-Id: I0424424d63dec5c626223a04181508198f75bd5b
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469622
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-09-27 14:57:20 +00:00
Ben Walker
ab854135ec test: waitforbdev now accepts alias names
Change-Id: I366657ce00e5f0e17c6e9a7510a7fc2314c2782a
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469621
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-09-27 14:57:20 +00:00
Seth Howell
de1f019edf nvme/perf: remove unused variable.
Change-Id: I3a1d237b7a7a25511d476d7612221537bf283ddd
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469633
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>
2019-09-27 07:42:44 +00:00
yidong0635
46d6711825 test/nvme: Add test sanitize to unittest.
Add test_sanitize in nvme_ctrlr_cmd_ut.c, this will
increase code coverage rate.

Change-Id: I80dec6eed5e2114c91db1406d1aa6c6a5e287293
Signed-off-by: yidong0635 <dongx.yi@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469576
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>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-09-27 04:23:10 +00:00
Benjamin Saunders
6bcd3588d1 nvme: add support for write uncorrectable command
Change-Id: I9fb7a998f7c13ce53cba630a895e8e11cf5f4a1c
Signed-off-by: Benjamin Saunders <bsaunders@google.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/467559
Reviewed-by: Paul Luse <paul.e.luse@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>
2019-09-26 18:42:57 +00:00
Maciej Wawryk
6956b0ec1e test: Shellcheck - correct rule "backslash+linefeed is literal"
Correct shellcheck rule SC1004: This backslash+linefeed is literal.
Break outside single quotes if you just want to break the line.

Signed-off-by: Maciej Wawryk <maciejx.wawryk@intel.com>
Change-Id: I7b872fa3c66685c1e8e7989f7b3b74a9e4f35325
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/468467
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-09-26 16:37:42 +00:00
Maciej Wawryk
bebda9fb40 test: Shellcheck - correct rule "using pgrep"
Correct shellcheck rule SC2009: Consider using
pgrep instead of grepping ps output.

Signed-off-by: Maciej Wawryk <maciejx.wawryk@intel.com>
Change-Id: If00080ffb62a589c21b684e2f8f2945c77b38bdd
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/466911
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-09-26 16:37:42 +00:00
Maciej Wawryk
93ae0344c8 test: Shellcheck - include check "prevent whitespace problems"
Remove from shellcheck excluded SC2048: Use "$@" (with quotes)
to prevent whitespace problems.

Signed-off-by: Maciej Wawryk <maciejx.wawryk@intel.com>
Change-Id: Ib9d4b538c442450c6743f749016be4811981cff4
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/466903
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
2019-09-26 16:37:42 +00:00
Maciej Wawryk
fe9bc4eb47 test: Shellcheck - include check "word is outside of quotes"
Remove from shellcheck excluded SC2026: This word is outside
of quotes. Did you intend to 'nest '"'single quotes'"' instead'

Signed-off-by: Maciej Wawryk <maciejx.wawryk@intel.com>
Change-Id: Ic71c464de9dccebe9ead9c47b5cdb15d8fcc025b
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/466902
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Karol Latecki <karol.latecki@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>
2019-09-26 16:37:42 +00:00
Wojciech Malikowski
a9e6fadf3e lib/bdev: Added spdk_bdev_io_get_append_location()
spdk_bdev_io_get_append_location() will be
used during zone append command to retrieve
location of data write.

Change-Id: I1f46ae9d2f745aa53264c1a01da3f7cef4f38c72
Signed-off-by: Wojciech Malikowski <wojciech.malikowski@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469164
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>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
2019-09-26 16:17:34 +00:00
Seth Howell
8a2527836d log: remove old-style errlog entries.
SPDK_ERRLOG lists the function name, so remove old references that
assume it doesn't and reprint the function name.

Change-Id: I69da6ca0a25bf0eda07d8dad52bcfadf964ac715
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469487
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>
2019-09-26 16:15:11 +00:00
Evgeniy Kochetov
e0e4f4ead6 ut/nvmf/subsystem: Add unit tests for namespace event callback
Signed-off-by: Evgeniy Kochetov <evgeniik@mellanox.com>
Signed-off-by: Sasha Kotchubievsky <sashakot@mellanox.com>
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Change-Id: I5ea7baafb7fcf2bc5b915e01369a390ecbf8410d
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/468542
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-09-26 16:14:14 +00:00
Evgeniy Kochetov
657575210d nvmf/subsystem: Open block device with extended API
Signed-off-by: Evgeniy Kochetov <evgeniik@mellanox.com>
Signed-off-by: Sasha Kotchubievsky <sashakot@mellanox.com>
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Change-Id: I471cceefd58ad4c4c64c140fcc66dc25dde43254
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/468541
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: Ben Walker <benjamin.walker@intel.com>
2019-09-26 16:14:14 +00:00
Pawel Kaminski
5017a67fdc test: Shellcheck - apply rule SC2191
The = here is literal. To assign by index, use ( [index]=value )
with no spaces. To keep as literal, quote it.

Change-Id: I14cada0e8c132286959aa47a1d37ede5e025d85f
Signed-off-by: Pawel Kaminski <pawelx.kaminski@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/467863
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-09-26 16:13:18 +00:00