Commit Graph

16544 Commits

Author SHA1 Message Date
Tomasz Zawadzki
9ce2a8208e doc: fix typo in nvme ref link
spdk/include/spdk/nvme.h:556: error: unable to resolve reference to 'spdk_nvme_ctrlr_get_memory_domain' for \ref command

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I0a01af8e68d9e93bb785bf9a79d9392917557d60
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10386
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
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>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2021-12-02 15:41:33 +00:00
Tomasz Zawadzki
0034340344 doc: fix accel_idxd_kernel link
Resolves issue below
spdk/doc/accel_fw.md:111: error: explicit link request to 'accel_idxd_kernel' could not be resolved

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I5bf205706a43887e0cac0bcc5b8c5de1dc67e7f3
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10385
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2021-12-02 15:41:33 +00:00
Tomasz Zawadzki
9ad1b56ba8 doc: match spdk_scsi_dev_get_next_lun argument name
Documentation for spdk_scsi_dev_get_next_lun now matches
the function.

include/spdk/scsi.h:239: error: argument 'lun' of command @param is not found in the argument list of spdk_scsi_dev_get_next_lun(struct spdk_scsi_lun *prev_lun)

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I40512656cc215933fcd945429fac23318a083e09
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10384
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
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>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2021-12-02 15:41:33 +00:00
Michal Berger
2a1e635f49 test/nvme: Check active namespaces instead of the number of reported namespaces
Upstream QEMU initializes the Number Of Namespaces (NN) on each of
the emulated nvme subsystems to NVME_MAX_NAMESPACES (256) - this is
the case even for a device which doesn't have any active namespaces.

In case nvme_fio_test() finds such a device (no active namespaces)
it still attempts to run fio against it due to a false positive which
comes from looking up the Number Of Namespaces.

Adjust the check to look for strings related to active namespaces
and pick devices which report any.

Signed-off-by: Michal Berger <michalx.berger@intel.com>
Change-Id: I5b222f1152f2a799b0d600ca19ad13eda009878a
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10503
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2021-12-02 08:49:38 +00:00
Krzysztof Karas
9b631aa6c1 spdk_top: move drawing thread, poller and core rows to helper functions
Move row drawing for threads, pollers and cores to separate functions.
This is going to be used in the next patch to avoid enclosing very large
code blocks inside if/else statements.

Changed variable representing columns in core tab from "offset" to "col"
to be consistent with threads' and polllers' functions.

Change-Id: Ie818458e926df71786196fcb857113416297ece9
Signed-off-by: Krzysztof Karas <krzysztof.karas@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10346
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2021-12-02 08:49:26 +00:00
Michal Berger
a3ac80c105 test/config_converter: Drop config_converter tests
It's been some time since SPDK switched from ini to json,
there's no much benefit from keeping these tests around.

Signed-off-by: Michal Berger <michalx.berger@intel.com>
Change-Id: I0cf7fcd6587abe872553211e41bee12e14bf234f
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10065
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Jacek Kalwas <jacek.kalwas@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2021-12-02 08:09:45 +00:00
Maciej Wawryk
dda5efbc8a scripts/nvmf: fix type error in ethtool_after_fio_ramp
TypeError: ethtool_after_fio_ramp() argument after * must be an iterable, not int

Signed-off-by: Maciej Wawryk <maciejx.wawryk@intel.com>
Change-Id: I12403967b5b8ce7282c65296a54e00bd047cf903
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10367
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
2021-12-02 08:09:30 +00:00
Li Feng
73f61bcdc1 vhost: fix the memory free in submit_inflight_desc
SPDK shouldn't use `free` to free the memory allocated by rte_zmalloc_socket.
Otherwises, the vhost-blk/scsi will continuously crash.

In this patch, SPDK don't free the dpdk allocated memory,
DPDK will free it finally. Add a flag to indice the resubmit handle.

Change-Id: I85fd84b7d27a091830006a0f84d541c48290cbb3
Signed-off-by: Li Feng <fengli@smartx.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10383
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
2021-12-02 08:09:18 +00:00
Jacek Kalwas
869929a1ca thread: improve api description
behaviour for spdk_for_each_channel_continue was not clear when user
pass non 0 status, now it is clarified

Signed-off-by: Jacek Kalwas <jacek.kalwas@intel.com>
Change-Id: I1aa5b5226e1aaf150ef069743f363f46d6c19e6d
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10497
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: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2021-12-02 08:08:46 +00:00
Michal Berger
6dcfa49f61 qat_setup: Don't use absolute path to igb_uio driver
This driver is now built by vm_setup.sh and installed under
/lib/modules.

Signed-off-by: Michal Berger <michalx.berger@intel.com>
Change-Id: Icea6b96e60390932c14ff49405614c186e61a99b
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6099
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
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: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2021-12-02 08:08:10 +00:00
Michal Berger
5673325a6f autobuild: Move DPDK patches into the repo
Fetching these patches from external forks of DPDK repo is a bit
cumbersome and hard to maintain so instead have them in one place
for easy apply.

All of the patches were fetched "as-is" from the used forks, with
a commit section trimmed to provide just the relevant info.

Signed-off-by: Michal Berger <michalx.berger@intel.com>
Change-Id: I6bf538ea15ef87fe04d5a77944de36c797cdf284
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10360
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
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: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2021-12-02 07:59:42 +00:00
Jim Harris
7339c2cf45 nvmf: update discovery log when listener is removed
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Iaef6e7b1c133a49390acd985a77b5f4349f78653
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10358
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Dong Yi <dongx.yi@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
2021-12-02 04:02:29 +00:00
Jim Harris
7e68d0baca nvme: configure AER for discovery controllers
Move the CONFIGURE_AER state before SET_KEEP_ALIVE to
make sure that we run the CONFIGURE_AER state for
discovery controllers.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ia4e24f6507c43e3fece06b9161ff8e0b8fa0e97d
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10332
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: Aleksey Marchuk <alexeymar@mellanox.com>
2021-12-02 04:02:29 +00:00
Jim Harris
b962b6bee5 nvme: set AER bit for discovery controllers
We will actually run the CONFIGURE_AER state for
discovery controllers in a future patch.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ib114beb886ab4b9214e4525479eb5ec7e038e5d9
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10331
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: Aleksey Marchuk <alexeymar@mellanox.com>
2021-12-02 04:02:29 +00:00
Josh Soref
b067cba8a3 spelling: rpmbuild
Part of #2256

* configured

Change-Id: Id63410c990522e74263f6612e43996237a9ce0ee
Signed-off-by: Josh Soref <jsoref@gmail.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10407
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2021-12-01 19:41:08 +00:00
Shuhei Matsumoto
1d524bc384 bdev/nvme: Remove unnecessary error check from bdev_nvme_reset_ctrlr()
spdk_for_each_channel() always passes status=0 to its completion callback
if each channel completes the requested function successfully.

bdev_nvme_reset_destroy_qpair() always succeeds.

Hence bdev_nvme_reset_ctrlr() does not have to check if the passed
status is not zero.

The following patches will aggregate multiple flags into a single
state for nvme_ctrlr. This change will simplify these.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I1c30c9b20c96886516029e69e90dc23d777a69b4
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10077
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
2021-12-01 09:20:09 +00:00
Shuhei Matsumoto
f9fba507fe bdev/nvme: Redirect the reset ctrlr operation into nvme_ctrlr->thread
In the following patches, we want to retry reconnect if reconnect failed
in a reset ctrlr sequence but we want to delay the retry. While
we wait the delayed retry, we want to quiesce ctrlr completely.

As part of quiesce ctrlr operations, we want to pause adminq poller but
we need to do it on the nvme_ctrlr->thread.

If a reset ctrlr sequence runs on the nvme_ctrlr->thread, we can avoid
redirecting the pending destruct request at completion too.

So we redirect the reset ctrlr sequence into the nvme_ctrlr->thread.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I538b962e2a7b5cf00ebbac2a1e888482ddeeee61
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10075
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
2021-12-01 09:20:09 +00:00
Mao Jiang
74dcf4aa58 example/nvme/arbitration: add vfio-user transport support
Change-Id: I4aff5ec209de46e4e5e279cd84ce4968df568a60
Signed-off-by: Mao Jiang <maox.jiang@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10464
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: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2021-12-01 09:19:28 +00:00
Jacek Kalwas
5c0e1c2663 nvmf: fix negative path for add transport to tgt
in case of failure groups shall be destroyed

Signed-off-by: Jacek Kalwas <jacek.kalwas@intel.com>
Change-Id: I8933f4128a7a3361bbb55d6a9c08a540521e5bda
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10435
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: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2021-12-01 09:19:13 +00:00
Changpeng Liu
8e38b9882f nvmf/vfio-user: only set S_IRUSR and S_IWUSR for mmapped BAR
Change-Id: Ic02089cd9ec49341b86d92377da734dc013d5cc7
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10335
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2021-12-01 09:18:59 +00:00
Changpeng Liu
8c6ab6ce3c nvmf/vfio-user: define NVME PCI configuration macro
Change-Id: I8a43abe597fe7139ec578322e565c5aa52c2f312
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10365
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2021-12-01 09:18:59 +00:00
Changpeng Liu
9636219e60 nvmf/vfio-user: rename NVMF_VFIO_USER_DOORBELLS_OFFSET macro
Doorbell offset starts from 0x1000 is defined by the NVMe
specification, so rename it to remove `VFIO_USER` prefix.

Change-Id: Ie34b12b3d2618f9b0ad0cf7ccbb103ad2c900f47
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10364
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2021-12-01 09:18:59 +00:00
Changpeng Liu
a9ff168107 nvmf/vfio-user: use macro for BAR size
Calculate supported maximum number of queue pairs based on
BAR0 size, this value isn't allowed to change at runtime, also
define BAR4/5 based on number of MSIX vectors.

Since the maximum number of queues is a large value(512), so we
still define a default value when starting, users still can
overwrite this value with a number no greater than 512.

Change-Id: I1b4b6bdf2ff9d129c8bdd493ffdf0a51f8772d51
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10334
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2021-12-01 09:18:59 +00:00
Changpeng Liu
084db9898a nvmf/vfio-user: use stack variable for sparse mmap
libvfio-user will save a copy inside the library.

Change-Id: If7bb052b03fb92e46abe50fa945b812d149ef01d
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10363
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2021-12-01 09:18:59 +00:00
Ben Walker
d1522dd5bc Revert "env/dpdk: Exclude the orig cpuset in spdk_unaffinitize_thread"
This reverts commit d9561c444f.

This patch is incorrectly iterating the CPU mask assuming it is
contiguous. However, rather than fix it, let's just let the kernel
scheduler place the thread where it thinks is best. It's going to prefer
idle cores anyway. So reverting is the simplest way forward.

Change-Id: I7b66cce7bfb6ddb108aa7576f508aa3b02b79138
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10475
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2021-12-01 09:16:47 +00:00
Krzysztof Karas
ac1abb5be8 hotplug: add check for uio_pci_generic driver
Add a check for this driver and enable iova=pa mode when it is
detected.
Add an option for the hotplug application to force iova mode.

This is to avoid:

EAL:   Expecting 'PA' IOVA mode but current mode is 'VA', not initializing
EAL: Requested device 0000:86:00.0 cannot be used

while using hw_hotplug test.

Change-Id: I7ff819c04b1e567b5ef88fc8f551ecec901806c8
Signed-off-by: Krzysztof Karas <krzysztof.karas@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/9774
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Maciej Szwed <maciej.szwed@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2021-12-01 09:16:29 +00:00
Krzysztof Karas
1e6449d80a test/nvme/hw_hotplug.sh: respect return code of subprocess
Currently we only check return code of the pipe process and
not its subprocesses. This leads to unexpected passes during testing.

Change-Id: Ia14507a282796ad28f067c086b9112ae6463b654
Signed-off-by: Krzysztof Karas <krzysztof.karas@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/9711
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Maciej Szwed <maciej.szwed@intel.com>
Reviewed-by: Michal Berger <michalx.berger@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2021-12-01 09:16:29 +00:00
Tomasz Zawadzki
126bec5f7b env: rename deprecated DPDK MEMPOOL_F_* flags
Starting with DPDK 21.11 MEMPOOL_F_* flags were renamed
to RTE_MEMPOOL_F_*. See DPDK patch below:
(c47d7b90)mempool: add namespace to flags

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I7c1c8818b47c5fc6e547c9b798fdc161e39f1cc5
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10454
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2021-12-01 09:16:12 +00:00
Tomasz Zawadzki
53008067a7 dpdkbuild: fix name of crypto pmd for DPDK 21.11
crypto/aesni_mb is renamed to crypto/ipsec_mb,
starting with DPDK 21.11.

Patch below remedied most of the changes required:
(089cbda8)autobuild: Adjusting crypto build for latest DPDK (21.11)

Yet it missed changing the driver name when using submodule.

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: Iec23d35e2a64ddab975b394a23e72af1a11c7b6e
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10453
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
2021-12-01 09:16:12 +00:00
Josh Soref
0c1fcc7705 spelling: include
Part of #2256

* accelerator
* access
* acknowledge
* address
* adrfam
* aggregation
* allocated
* appearance
* associated
* asynchronously
* authority
* available
* callback
* compare
* construct
* controller
* course
* definitions
* deinitialize
* descriptor
* destroy
* device
* efficiently
* elasticity
* failure
* frequency
* function
* hdgst
* implementation
* indefinitely
* initialization
* initialize
* initiator
* interrupt
* malicious
* management
* milliseconds
* namespace
* negative
* notification
* obtained
* otherwise
* passed
* positive
* request
* responded
* semantics
* sequence
* should
* specified
* structure
* subsystem
* successful
* synchronously
* transport

Change-Id: I808876a3b4b2dc56f95cfc42bc88336cfeec4288
Signed-off-by: Josh Soref <jsoref@gmail.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10404
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2021-12-01 09:15:13 +00:00
Josh Soref
b7876f9a63 spelling: examples
Part of #2256

* asymmetric
* bookkeeping
* current
* errors
* execution
* initialize
* initing
* management
* occurred
* operations
* prepping
* purposes
* similar
* syncing
* terminate

Change-Id: I7336d98c1327020ab83c9e01e6bf1e4f5f7b5d7d
Signed-off-by: Josh Soref <jsoref@gmail.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10403
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: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2021-12-01 09:15:03 +00:00
Josh Soref
ba1e1368cc spelling: dpdkbuild
Part of #2256

* parallel
* several

Change-Id: I192e204cdc34d541e5afdc59624b565abf1d668e
Signed-off-by: Josh Soref <jsoref@gmail.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10402
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2021-12-01 09:14:44 +00:00
Sergei Trofimovich
f269648039 spdk_top: fix format warning around thread_info->core_num
On `ncurses-6.3` format attributes now detect argument mismatch:

    spdk_top.c:2218:60: warning: format '%lu' expects argument of type 'long unsigned int', but argument 5 has type 'int' [-Wformat=]
     2218 |         mvwprintw(thread_win, 3, THREAD_WIN_FIRST_COL + 6, "%" PRIu64,
          |                                                            ^~~
     2219 |                   thread_info->core_num);
          |                   ~~~~~~~~~~~~~~~~~~~~~
          |                              int

Use '%d" for `thread_info->core_num` (declared as `int`).

Signed-off-by: Sergei Trofimovich <slyich@gmail.com>
Change-Id: I99cd4ff41a26917b67199ea8cc1fbf281ce4dd20
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10375
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: John Kariuki <John.K.Kariuki@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2021-11-30 20:07:56 +00:00
Sergei Trofimovich
a3b62f8bc1 spdk_top: always use "%s"-style format for printf()-style functions
`ncuses-6.3` added printf-style function attributes and now makes
it easier to catch cases when user input is used in palce of format
string when built with CFLAGS=-Werror=format-security:

    spdk_top.c:1135:34: error: format not a string literal and no format arguments [-Werror=format-security]
     1135 |         mvwprintw(win, row, col, tmp_str);
          |                                  ^~~~~~~

Let's wrap all the missing places with "%s" format.

Signed-off-by: Sergei Trofimovich <slyich@gmail.com>
Change-Id: I84227668ff698ae2f327a7fb5d87ce0a407ab50d
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10300
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2021-11-30 20:07:56 +00:00
Shuhei Matsumoto
cf8a9bf286 rpc: Fix example of initiator_list of the iscsi_create_initiator_group RPC
We provided list of IP addresses as the example of the list of the
initiator names of the iscsi_create_initiator_group and
iscsi_initiator_group_add_initiators RPCs.

However, they were very confusing and gave little hint about how
to use initiator name.

Fix them by providing IQNs instead.

Fixes issue #2209

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I8ce19c4ed0af54fd8a6f1ab2a74b2e6f865d3d1c
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10236
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
2021-11-30 11:59:31 +00:00
Konrad Sztyber
2f9c97a4f6 nvme: silence debug logs when waiting for CSTS.RDY transitions
These can produce a lot of output, which doesn't really give any
additional information.

Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I572cd203d61c717ce6400f67ef27ec1d7bb54c0c
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10414
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: Jacek Kalwas <jacek.kalwas@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2021-11-30 09:09:11 +00:00
Shuhei Matsumoto
2c32ca4ceb sock: Fix SPDK_ZEROCOPY do not work for IPV6
For IPV6, cm->cmsg_level is SOL_IPV6 and cm->cmsg_type is
IPV6_RECVERR. However these combination was not included.

To clarify the fix check if positive conditions are satisfied and
then reverse the result.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I675f4337f383d3526fed1b86794697f41113ed4c
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10428
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2021-11-30 09:09:03 +00:00
Alexey Marchuk
01887ccc30 rdma: Set REMOTE_WRITE permission for iWARP on target side
iWARP requires REMOTE_WRITE permission ofr RDMA_READ
operation.

Fixes #2253

Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Change-Id: Iddfda091903e000d1c4839c1fce67bf25d4a13c2
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10392
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: Dong Yi <dongx.yi@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2021-11-30 09:08:21 +00:00
Tan Long
83996cc3b9 bdev/rbd: Fix the decode error in bdev_rbd_register_cluster
Incorrect decode function used for the param "config_file" in
rpc_bdev_rbd_register_cluster

Signed-off-by: Tan Long <tanl12@chinatelecom.cn>
Change-Id: I6286c5d0d8396a1b548095975924087ba4ee92d2
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10444
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2021-11-30 09:08:07 +00:00
Michal Berger
c1831303e0 autobuild: Stop patching DPDK versions not tested under CI
Currently CI tests 21.08, 20.11 and the main branch. Maintaining
patches for other versions feels extraneous and adds only extra
work under autobuild.

Signed-off-by: Michal Berger <michalx.berger@intel.com>
Change-Id: I2dfac60fe3745b09fbe7159b170739680c94a8c5
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10359
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2021-11-30 09:07:21 +00:00
Tom Nabarro
921c92e2a5 test/config: verify extra key in config doesnt break parsing
Add autotest case to verify that additional top-level key in JSON config
file doesn't break parsing when loading and initializing subsystems from
said file. This is a regression test to help applications use the same
config file to communicate private and SPDK data.

Signed-off-by: Tom Nabarro <tom.nabarro@intel.com>
Change-Id: I3ef6fe20d21398d30fa8011e20de1524e60ee841
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10204
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Niu Yawei <yawei.niu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2021-11-30 09:07:02 +00:00
Jacek Kalwas
a15b6af0a6 nvmf: fix transport adding to tgt
adding transport to tgt should be the last step

also there is an issue before change i.e. if calloc failed then
transport remains on the list

Signed-off-by: Jacek Kalwas <jacek.kalwas@intel.com>
Change-Id: Iaf29cfc7b0f535d40160c6fdf9ef6a7e6bfb127c
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10429
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
2021-11-30 09:05:52 +00:00
Josh Soref
1960ef167a spelling: module
Part of #2256

* calculated
* changing
* deferred
* deinitialize
* initialization
* particular
* receive
* request
* retrieve
* satisfied
* succeed
* thread
* unplugged
* unregister

Change-Id: I13e38f9160cb1a15a87cb5974785a34604124fa3
Signed-off-by: Josh Soref <jsoref@gmail.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10406
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2021-11-30 09:05:32 +00:00
Josh Soref
a82b365b90 spelling: doc
Part of #2256

* accessible
* bstatic
* example
* initiator
* obvious
* privileged
* scenario
* transparent

Change-Id: I15f30f56e3bb18443c829830454360945878012a
Signed-off-by: Josh Soref <jsoref@gmail.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10401
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
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>
2021-11-30 09:05:19 +00:00
Josh Soref
70b16d445f spelling: deprecation.md
Part of #2256

* versioning

Change-Id: Ibba158baad1d26a264a7329d6645217fad7622c9
Signed-off-by: Josh Soref <jsoref@gmail.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10400
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2021-11-30 09:05:02 +00:00
Josh Soref
ff238359fe spelling: configure
Part of #2256

* compatibility
* sourceable

Change-Id: I7d5edd8e81e01f45f76f775aa5320ca92023b132
Signed-off-by: Josh Soref <jsoref@gmail.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10399
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2021-11-30 09:04:49 +00:00
Josh Soref
6bbb11b16b spelling: app
Part of #2256

* gracefully
* occurred
* output
* right

Change-Id: I1419b5001ab04109f5f16927f050f5d16242232f
Signed-off-by: Josh Soref <jsoref@gmail.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10398
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: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2021-11-30 09:04:05 +00:00
Josh Soref
0e47b2e4f3 spelling: docker
Part of #2256

* absolute

Change-Id: I8628c449088154c9bd2edf04b3e31d72344f897e
Signed-off-by: Josh Soref <jsoref@gmail.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10396
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
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>
2021-11-30 09:03:49 +00:00
Allen Zhu
b42699966c rpc: Fix failure to set config_param of bdev_rbd_register_cluster
A python error caused failure to set librados configuration.

Change-Id: I72c35e9ff819350ffe231b51450e0dc7b4467ec1
Signed-off-by: Allen Zhu <allenzhu@nvidia.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10343
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2021-11-26 08:10:09 +00:00
Karol Latecki
6580419f04 doc: add SPDK NVMe-oF RDMA 21.10 performance report
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Change-Id: Ia10eabd729249396e3cc434424d62b40a71c42d8
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10339
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
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: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Maciej Wawryk <maciejx.wawryk@intel.com>
2021-11-26 08:05:45 +00:00