Commit Graph

1094 Commits

Author SHA1 Message Date
Seth Howell
2248e52150 nvme/rdma: make sure we free resources in error path.
Not sure how we missed this.

Signed-off-by: Seth Howell <seth.howell@intel.com>
Change-Id: If920cb3a7708c33032e1da28c564d4c28ddafdf4
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1122
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>
2020-03-17 08:23:50 +00:00
Seth Howell
3b99ee9929 lib/nvme: move connect directly into alloc_io_qpair.
Signed-off-by: Seth Howell <seth.howell@intel.com>
Change-Id: Iadbada599764c7a2f4cdd4848a81a2fa39a89b46
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1120
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>
2020-03-17 08:23:50 +00:00
Seth Howell
7f82fb653d nvme/rdma: Move stale connection retries to connect call.
This gives us a more standard path in the create_io_qpair path. Eventually
this will allow us to bring the connection commands out to the generic layer
in alloc_io_qpair. Then we can split the calls to create and connect at the
generic level making it possible to add rdma qpairs to a poll group in a meaningful
way.

Signed-off-by: Seth Howell <seth.howell@intel.com>
Change-Id: Ib1b125f834c3c39a2b5050ff4a9bc4a053b95c99
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1119
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>
2020-03-17 08:23:50 +00:00
Seth Howell
1850842461 nvme_rdma: rearrange spdk_nvme_rdma_req.
This allows it to fit on three cachelines instead of four.

Change-Id: I2510b50ffcefb77fa570e738b2c6588749f30a00
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1143
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>
2020-03-17 08:23:50 +00:00
Ben Walker
ea65bf612d Revert "nvme/tcp: Change hdr in nvme_tcp_pdu to pointer"
This reverts commit ea5ad0b286.

This code is moving from the nvmf target to the posix sock
layer in this series.

Change-Id: I333bdf325848e726ab82a9e6916e1bbdcd34009c
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/446
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>
2020-03-17 08:23:07 +00:00
Jacek Kalwas
62e0342eac nvme: minor alignment in ctrlr construct for pcie and rdma
Signed-off-by: Jacek Kalwas <jacek.kalwas@intel.com>
Change-Id: I35db32e867f91269608c72dbb9290a7ed2e3f31d
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1234
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>
2020-03-12 09:04:26 +00:00
Jacek Kalwas
daa8f941e4 nvme: extend ctrlr opts with admin queue size
Align rdma and tcp to respect opts. Reduce default number of entries
for admin queue so it becomes memory optimization.

Linux driver by default creates admin queue with 32 depth, there is no
good reason to enlarge that queue by default within SPDK NVMe driver.

Signed-off-by: Jacek Kalwas <jacek.kalwas@intel.com>
Change-Id: I97ceea8f350c52313021a63190fb0980f604c48e
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1110
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>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
2020-03-12 09:04:18 +00:00
Changpeng Liu
555e186a93 nvme/opal: using opal_start_generic_session() directly
It's more straight forward to call opal_start_generic_session() directly in
different scenarios.  It will help us to use stack variable "prev_data" to
store temporary key during the session, which is more safe.

Change-Id: I70b9190ed3606cd5e26c23319aca82d4a38596cc
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1191
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>
2020-03-11 11:36:08 +00:00
Changpeng Liu
f55717c34e nvme/opal: remove the flush operation before each OPAL method
It's not an error to send a security receive command before each
real OPAL related commands, but we don't need to do it.

Change-Id: I7628988df6ac097264db2137440f63db9e6e3660
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1127
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>
2020-03-11 11:36:08 +00:00
Changpeng Liu
e5bb2b6232 nvme/opal: remove unnecessary Method Status Error codes
Althrough the spec defines the Method Status Error Code, but here the return
value is just from function uses the normal errno, such as ERANGE, so just
remove them.

Change-Id: I43be95f62a4e465090462743b91246b1d63e2acd
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1125
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>
2020-03-11 11:36:08 +00:00
Changpeng Liu
fbfb3aca28 nvme/opal: don't use ComPacket header to check level 0 discovery response
According to the TCG Storage Core Architecture V2.0, the level 0 discovery
response should use level 0 discovery header and feature descriptors to
retrieve the response data buffer.  ComPacket header should be used in upper
layer.

Change-Id: I61e3e206801994b276608f9afbda800eccb2cffa
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1124
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>
2020-03-11 11:36:08 +00:00
Changpeng Liu
c61b70c3d5 nvme/opal: rename spdk_opal_init_dev() and spdk_opal_close() with construct/destruct suffix
Since the OPAL here is just for NVMe device, so we don't need to use dev_handler as common
handler, just rename it to spdk_nvme_ctrlr.  And we don't exit the initialization if
OPAL construnction had a failure.  Also move the timeout initialization to construct().

Change-Id: I11f0aea961eaa3da0c6253eb03d0227f7e7e5f11
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1101
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>
2020-03-11 11:36:08 +00:00
Changpeng Liu
01ddd1120a nvme/opal: refactor level 0 discovery data structures
No actual logic change except re-define some data structures.

Change-Id: Id0a483071591beee675cbc3ef368ac1fb723cfe0
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1099
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>
2020-03-11 11:36:08 +00:00
Changpeng Liu
80ec5489ae opal_spec: optimize level 0 discovery data structure definition
Also uses ComPacket header to check the received data, no actual
function changes.

Change-Id: I905fc6b8bb4656d48d43ff4ff8d1f705b9b595b9
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1074
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>
2020-03-11 11:36:08 +00:00
Ziye Yang
9ba4bb22fe lib/nvme_tcp: get the max_sges from the nvme ctrlr.
Add the error print if there is still remaining_size in
order to provide more meaningful debug info.

Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: I7b15c9c9a630ea7ecb2d3191b73c9c99f7febf31
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1189
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2020-03-11 02:25:12 +00:00
Ben Walker
49e70693c6 nvme: Move prp map code from vhost to nvme driver
This will be re-used in the muser transport of nvmf.

Change-Id: If00e6ea79ffdc0c3bda0402f39c5f9f4f411788b
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/425
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>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
2020-03-10 09:12:29 +00:00
Seth Howell
f146bbe42d lib/nvme: move common connect code into transport shim
This gets rid of some duplicate lines of code.

Change-Id: I24d4864921f6030672f3640b33f88f37a9e8175a
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1136
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: Aleksey Marchuk <alexeymar@mellanox.com>
2020-03-06 10:29:21 +00:00
Alexey Marchuk
94966468ae nvme/rdma: Introduce transport_ack_timeout
Add transport_ack_timeout parameter to nvme controller opts.
This parameter allows to configure RDMA ACK timeout according
to the formula 4.096 * 2^(transport_ack_timeout) usec.
The parameter should be in range 0..31 where 0 means use
driver-specific default value.

Change-Id: I0c8a5a636aa9d816bda5c1ba58f56a00a585b060
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/502
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>
2020-02-27 10:16:00 +00:00
Changpeng Liu
8d6f48fbf8 nvme: set transport string before the probe based on transport type
Users may only set the transport type, but for the actual probe
process, the trstring field is mandatory, so set the trstring
based on transport type at first.  Also remove unnecessary
spdk_nvme_trid_populate_transport() call from each transport
module.

Fix #1228.

Change-Id: I2378065945cf725df4b1997293a737c101969e69
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1001
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2020-02-26 09:26:09 +00:00
Changpeng Liu
bad2c8e86c nvme: detach the controller in STUB and flush the admin active requests at last
In the autotest, when calling kill_stub() function, there is error log
like this: "Device 0000:83:00.0 is still attached at shutdown!", so it's
better to detach the controller when exit the stub process.

But after call spdk_nvme_detach() in the stub process, there is another issue:
1. NVMe stub running as the primary process, and it will send 4 AERs.
2. Using NVMe reset tool as the secondary process.

When doing NVMe reset from the secondary process, it will abort all the
outstanding requests, so for the 4 AERs from the primary process, the 4
requests will be added to the active_proc->active_reqs list.

When calling spdk_nvme_detach() to detach a controller, there is a
assertion in the nvme_ctrlr_free_processes() at last to check the
active requests list of this active process data structure.

We can add a check before destructing the controller to poll the
completion queue, so that the active requests list can be flushed.

Change-Id: I0c473e935333a28d16f4c9fb443341fc47c5c24f
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/977
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>
2020-02-26 09:26:09 +00:00
Changpeng Liu
4f7fa18d69 nvme: export internal security send/receive APIs as public APIs
There are synchronous security send/receive APIs defined in nvme.h,
however, we still need the asynchronous APIs so that we can make the
OPAL library can be used in asynchronous way. As the asynchronous APIs
are already defined in nvme_ctrlr_cmd.c, so just export them to public
APIs.

Change-Id: I5646f342a4bf70faad37daa956476f05a1327bcc
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/675
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>
2020-02-26 09:22:15 +00:00
Allen Zhu
52a0feb404 bdev/nvme: handle namespace resize event
while the size of namespace is changed,
the resize event will be notified.

Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Signed-off-by: Evgeniy Kochetov <evgeniik@mellanox.com>
Signed-off-by: Allen Zhu <allenz@mellanox.com>

Change-Id: I5d85f17df898dc21c0ae1eb9f529dcb624a457ac
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/849
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2020-02-21 09:38:42 +00:00
Jacek Kalwas
a7a0d02d8b nvme: fix command specific status code
Given enum was not aligned with spec. This status can be reported when
size equals 0.

Signed-off-by: Jacek Kalwas <jacek.kalwas@intel.com>
Change-Id: If51f6b051c13880c1fd4e6bb0a02f134b28b5a88
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/928
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>
2020-02-20 09:49:24 +00:00
Seth Howell
b1daf62be5 nvme: add internal function to iterate over transports.
This will come in handy in the new poll group API.

Change-Id: I9cf14082270b28b35f4a440c5cb2471c81e374ba
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/578
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2020-02-18 08:05:08 +00:00
Seth Howell
19260848f6 nvme: publicly declare spdk_nvme_transport
This will be useful in the upcoming spdk_nvme_poll_group api.

Change-Id: Id83340a2ce9887817312f5aac38db4de8c588974
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/577
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: Aleksey Marchuk <alexeymar@mellanox.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2020-02-18 08:05:08 +00:00
Alexey Marchuk
33204a4354 nvme/tcp: Align local variables types
Some of variables have types which don't match their
usage in code

Change-Id: Ic2bd5fd6561c70143dde436ce9cddc0be4d3b0d0
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/521
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2020-02-17 10:06:30 +00:00
Alexey Marchuk
8c1859067f nvme: Move trid to "cold" spdk_nvme_ctrlr section
This field is not used in data path, so move it to "cold" data

Change-Id: I25f2fdb3aff613f9e16a2e13b2b06f8180a60fb2
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/520
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2020-02-17 10:06:30 +00:00
Alexey Marchuk
c3ba9127d0 nvme: Store NVMEoF ioccsz and icdoff in ctrlr structure
This allows to avoid calculation of ioccsz bytes on each request
and removes access to "cold" ctrlr structures in data path.
Add UT to check validness of calculation

Change-Id: I55ceff99eb924156155e69a20f587a4f92b83f0b
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/519
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2020-02-17 10:06:30 +00:00
Ben Walker
450d19d117 nvme/cuse: Don't allocate data buffers from CMB for cuse commands
These data buffers can't later be freed and need to be carefully
managed by the host. Also, this is very likely slower.

Change-Id: I0d205c0c7136e0aa972e927361bd88e765d218c6
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/784
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: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2020-02-17 10:06:20 +00:00
Ben Walker
5ac51a3214 nvme:Make ctrlr_alloc_cmb_io_buffer optional for transports
If the transport doesn't define one, don't call it.

Change-Id: I8b83132f9fc0accbd4faa8fa0fc17a6bd11e543e
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/783
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: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2020-02-17 10:06:20 +00:00
Ben Walker
c29cca539d nvme/pcie: Don't allow both sq and data in CMB at same time
This is allowed by the specification, but preventing using both
of these features simultaneously will make some upcoming patches
much simpler.

Change-Id: I1abb7d9c02c105a50b1603bfab8eec2025289123
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/782
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: Changpeng Liu <changpeng.liu@intel.com>
2020-02-17 10:06:20 +00:00
Ben Walker
c96579410e nvme/pcie: Put all CMB-related registers into a struct
Keep them grouped together for clarity.

Change-Id: I51be01802b69aa722dec458fda56e4e396edbfeb
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/781
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2020-02-17 10:06:20 +00:00
Ben Walker
7dbe0e7c61 nvme: Remove nvme_transport_get_ctrlr_registers
Wasn't used.

Change-Id: I9812e24540f6d86f47d39091ea5fd9b7880b4413
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/735
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: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2020-02-12 12:07:16 +00:00
Ben Walker
486471b1fb nvme: Remove DECLARE_TRANSPORT
We only have the generic transport wrapper now.

Change-Id: Ib1487e9c7b7ba3b573f5ea47597ad6eac1c5407e
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/734
Reviewed-by: Seth Howell <seth.howell5141@gmail.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.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>
2020-02-12 12:07:16 +00:00
Ben Walker
54a022dda2 nvme: Don't DECLARE_TRANSPORT(rdma)
With the transport plugin system, this is no longer necessary.

Change-Id: Ia73878599658db84150603223ac811cb5a34ffba
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/713
Reviewed-by: Seth Howell <seth.howell5141@gmail.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.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>
2020-02-12 12:07:16 +00:00
Ben Walker
f5bc2cbe86 nvme: No longer DECLARE_TRANSPORT(tcp)
With the transport plugin system, this isn't used anymore.

Change-Id: Ib81c73f262d44edb6c937ca0056ac027b1e1ca75
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/712
Reviewed-by: Seth Howell <seth.howell5141@gmail.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.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>
2020-02-12 12:07:16 +00:00
Ben Walker
0b262fdfd2 nvme: Don't DECLARE_TRANSPORT(pcie)
All of the code now goes through the transport plugin system,
so this isn't necessary.

While doing this, caught a bug that the get_registers function
wasn't being set for the PCIe transport.

Change-Id: If19a933e0c6f656bc55232b15d59052e22af3ee9
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/711
Reviewed-by: Seth Howell <seth.howell5141@gmail.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.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>
2020-02-12 12:07:16 +00:00
Alexey Marchuk
f1539c2820 nvme/rdma: Use transport_retry_count from controller opts
This allows to configure desired retry_count instead of using
hard coded value

Change-Id: I25c9601997ace916dfb735469a4b443c0cd2a96b
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/482499
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Community-CI: SPDK CI Jenkins <sys_sgci@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2020-02-04 18:19:20 +00:00
Alexey Marchuk
9727aa281f tcp: refactor of header/data digest support check
Some functions performed incorrect header/data digest
support check, align it with NVMEoF spec. Use a table
to check if PDU supports digest depending on its type.

Change-Id: I6170dd19ace017f37fda0a923f604732799460b9
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/483375
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Community-CI: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2020-02-04 18:18:49 +00:00
Alexey Marchuk
3424def90a nvme: Fix potential use of non-initialized variable
trstring variable in spdk_nvme_trid_populate_transport is not
initialized, that can lead to snprintf() writes some garbage to
trid->trstring if the user passes SPDK_NVME_TRANSPORT_CUSTOM trtype
Add return statement and assert to CUSTOM/default switch

Change-Id: I6c6c37f9aa74d61b346f7be27fb890c7a34e9229
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/483469
Community-CI: SPDK CI Jenkins <sys_sgci@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2020-02-04 09:49:25 +00:00
Tomasz Kulasek
e69baea132 lib/nvme: fix wrong status argument in spdk_nvme_ctrlr_format
For nvme_ctrlr_cmd_format command status should be used as
nvme_completion_poll_cb callback argument instead of pointer to
local variable.

Change-Id: Id65cb395d137c4e907c1ef019b131e8822ddfe34
Signed-off-by: Tomasz Kulasek <tomaszx.kulasek@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/483513
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
2020-02-03 11:39:05 +00:00
Ben Walker
d0f4a51fdc sock/posix: Block recursive calls to spdk_sock_flush
Don't allow calling spdk_sock_flush while the socket is
closed.

Change-Id: I9020a49ab8906b0f343e3f48f8b96bd38308ab17
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/483148
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: SPDK CI Jenkins <sys_sgci@intel.com>
2020-01-30 10:22:20 +00:00
Alexey Marchuk
8818ace2f4 nvme: Don't use stack variable to track request completion
A pointer to a stack variable is passed as an argument to
nvme_completion_poll_cb function, later this variable is used
to track completion in the spdk_nvme_wait_for_completion() function.
If normal scenario a request submitted to the admin queue will be completed
within the function which submitted the request.
spdk_nvme_wait_for_completion() calls nvme_transport_qpair_process_completions
which may return an error to the caller, the caller may exit from the
function which submitted the request and the pointer to the stack variable
will no longer be valid. Thereby the request may not be completed at that time
and completed later (e.g. when the controller/qpair are destroyed)
and that will lead to call to nvme_completion_poll_cb with the pointer
to invalid stack variable.
Fix - Dynamically allocate status structure to track the completion;
Add a new field to nvme_completion_poll_status structure to track status
objects that need to be freed in a completion callback

Fixes #1125

Change-Id: Ie0cd8316e1284d42a67439b056c48ab89f23e0d0
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/481530
Community-CI: Broadcom SPDK FC-NVMe 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: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2020-01-27 22:48:18 +00:00
Seth Howell
ca693eaba8 lib/nvme: fix cm event handling during rdma qpair shutdown.
In the event that we have more than one event outstanding for a qpair
at the time of destruction, we need to ack all of the events, Luckily
the synchronization is already there in the form of the ctrlr lock.

Signed-off-by: Seth Howell <seth.howell@intel.com>
Change-Id: Ib297598f2e28d9b9bd83e904f950795a61fa883a
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/479171
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2020-01-23 15:14:55 +00:00
Or Gerlitz
8e8a5f7c28 nvme/tcp: Use writev_async for sending data on sockets
Amortize the writev syscall cost by using the writev_async socket API.

This allows the socket layer to batch writes into one system call
and also apply further optimizations such as posix's MSG_ZEROCOPY
when they are available. As part of doing so we remove the error
return in the socket layer writev_async implementation for sockets
that don't have a poll group.

Doing so eliminates the send queue processing.

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Change-Id: I5432ae322afaff7b96c22269fc06b75f9ae60b81
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/475420
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>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2020-01-22 13:53:09 +00:00
Seth Howell
9436ab59ba nvme/rdma: inline buffers for all host to ctrlr ops
Not inlining all host to controller operations breaks the target within
the context of fused commands. This issue was discovered when enabling
the compare-and-write fused command. Only the write command buffer was
being inlined which caused the write to jump the compare in the
transport specific state machine on the target side before our fused
command checks in the generic code.

Change-Id: I9e52ae6160e01ffd36d20429ffc8459491c729ef
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/482001
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2020-01-22 13:41:47 +00:00
Jacek Kalwas
7a35a678b8 lib/nvme: extend trtype to str with CUSTOM
Signed-off-by: Jacek Kalwas <jacek.kalwas@intel.com>
Change-Id: I519bb6bf0e930e0cd977ef4b5133bbdd7ca8af86
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/481952
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2020-01-21 23:16:57 +00:00
Alexey Marchuk
52f1e4b029 nvme: Update spdk_nvme_wait_for_completion_robust_lock error handling
Update error handling of spdk_nvme_wait_for_completion_robust_lock to
differentiate cases when request is completed (possibly with error)
or polling was aborted by transport/device error
The function returns 0 on success, -ECANCELED if transport/device
error occurred and -EIO if the request is completed with error

Change-Id: Ibf7f3c330317af0d8f27ba9cd10d8b773f6a796b
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/481529
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Community-CI: SPDK CI Jenkins <sys_sgci@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>
2020-01-17 08:59:46 +00:00
Alexey Marchuk
9ad2046ae1 nvme: Update spdk_nvme_wait_for_completion_timeout error handling
Update error handling of spdk_nvme_wait_for_completion_timeout to
differentiate cases when request is completed (possibly with error)
or polling was aborted by timeout or transport/device error
The function returns 0 on success, -ECANCELED if transport/device
error occurred or operation timed out and -EIO if the
request is completed with error

Change-Id: I314f40d1acaa6cfa9b88e5417b1ee2c9801bbbd6
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/481528
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Community-CI: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2020-01-17 08:59:46 +00:00
Tomasz Kulasek
66585bd4be lib/nvme: fix cuse return status code
For admin as well as for IO operations the ioctl should return
NVMe status code.

Change-Id: Icf8efde674b847fb03e5532f47c00b1c2cdcf328
Signed-off-by: Tomasz Kulasek <tomaszx.kulasek@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/477492
Community-CI: Broadcom SPDK FC-NVMe 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: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
2020-01-16 09:20:20 +00:00
Ziye Yang
0bfaaace8f sock: Add impl_name parameter in spdk_sock_listen/connect.
Purpose: With this patch,

(1)We can support using different sock implementations in
one application together.

(2)For one IP address managed by kernel, we can use different method
to listen/connect, e.g., posix, or uring. With this patch, we can
designate the specified sock implementation if impl_name is not NULL
and valid. Otherwise, spdk_sock_listen/connect will try to use the sock
implementations in the list by order if impl_name is NULL.

Without this patch, the app will always use the same type of sock implementation
if the order is fixed. For example, if we have posix and uring together,
the first one will always be uring.

Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: Ic49563f5025085471d356798e522ff7ab748f586
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/478140
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Community-CI: SPDK CI Jenkins <sys_sgci@intel.com>
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: Jim Harris <james.r.harris@intel.com>
2020-01-16 09:11:32 +00:00
Seth Howell
738b9569f0 lib/nvme: remove extra function calls in tcp transport.
Signed-off-by: Seth Howell <seth.howell@intel.com>
Change-Id: I031cb5263598d09fb4956873c35d74ec3173fe63
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/478875
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>
2020-01-16 09:10:38 +00:00
Seth Howell
b2225ff593 lib/nvme: remove extra transport functions.
Now that we have a more flexible function table strategy for
transports, we can get rid of some of the wrapping we were doing
to match the macro definitions exactly.

Signed-off-by: Seth Howell <seth.howell@intel.com>
Change-Id: I12c868babfa7bd27dc8ed5e86d35e179f8ec984f
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/478874
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>
2020-01-16 09:10:38 +00:00
Seth Howell
f6cf92a31f lib/nvme: make transport.c use fn tables.
Signed-off-by: Seth Howell <seth.howell@intel.com>
Change-Id: Ida58785784b4ed50393e1d43a9cd902de74a2eaa
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/478873
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>
2020-01-16 09:10:38 +00:00
Seth Howell
bf6b1122dc lib/nvme: split out function to get ops.
Signed-off-by: Seth Howell <seth.howell@intel.com>
Change-Id: I7664e6ca16f323fd7032b2c8afd6b9467897a014
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/478872
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>
2020-01-16 09:10:38 +00:00
Seth Howell
e4eef6975c lib/nvme: add function tables for all transports.
Signed-off-by: Seth Howell <seth.howell@intel.com>
Change-Id: I4e7af1c42a19346f4abcb17910a41f8104a2de1b
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/478871
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>
2020-01-16 09:10:38 +00:00
Seth Howell
b2e55c2454 lib/nvme: add functions for registering new transports
Signed-off-by: Seth Howell <seth.howell@intel.com>
Change-Id: I7f04968957fbc80ca8ed3ddd96e13bb9cb855813
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/478866
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>
2020-01-16 09:10:38 +00:00
Seth Howell
017a8f885f lib/nvme: add objects for transport registration.
Signed-off-by: Seth Howell <seth.howell@intel.com>
Change-Id: I33d0a23b646a06acbf219ff283f094197af6b1fc
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/478865
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>
2020-01-16 09:10:38 +00:00
Seth Howell
771d759312 lib/nvme: add spdk_nvme_transport_available_by_name
This new api function will enable us to work with custom transports.

This is needed to enable properly parsing and comparing custom transport
IDs that may all resolve to the same enum value.

Signed-off-by: Seth Howell <seth.howell@intel.com>
Change-Id: I26aa3cb8f76f8273f564799d9b2af8041ea0d219
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/478752
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>
2020-01-16 09:10:38 +00:00
Seth Howell
d4ea320bb5 lib/nvme: add trstring comparison to trid comparison.
Multiple custom transport types could share the same trtype variable. Add this additional check to compare them.

Signed-off-by: Seth Howell <seth.howell@intel.com>
Change-Id: Ief93d0d82aee754c9235cbab3c55827e57869fe9
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/478748
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: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2020-01-16 09:10:38 +00:00
Seth Howell
a050dcf21d lib/nvmf: add a default value to trtype enum.
For custom transports, we should use a range outside the spec value
to identify them.

Signed-off-by: Seth Howell <seth.howell@intel.com>
Change-Id: I82b29c349e143b8906f79ce2de818def116a3fe4
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/478747
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: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2020-01-16 09:10:38 +00:00
Seth Howell
7ed0904b9b lib/nvme: update trid struct with trstring.
The trtype should be stored as both an enum and string. This is intended to
help pave the way for pluggable NVMe-oF transports.

Signed-off-by: Seth Howell <seth.howell@intel.com>
Change-Id: I6af658d7a17c405e191ff401b80ab704c65497e7
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/478744
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: Alexey Marchuk <alexeymar@mellanox.com>
2020-01-16 09:10:38 +00:00
Jim Harris
a828415390 nvme: add spdk_nvme_ctrlr_cmd_get_log_page_ext()
This new function allows specifying some of the extra
cdw10, cdw11 and cdw14 bits added in the more recent
versions of the NVMe specification.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I08a7840ad066b08fe557a2e7b974df491646978f

Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/479737
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
2020-01-10 08:46:33 +00:00
Maciej Szwed
f76713837e nvme: Add spdk_nvme_ns_supports_compare function
This function returns information if compare
operation is supported by device.

Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: I321e9bf6d146ac8d14ea4549cb4380735b30be6f

Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/477925
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: 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: Jim Harris <james.r.harris@intel.com>
2020-01-07 12:31:32 +00:00
Maciej Szwed
b95de9a3ca nvme: Add SPDK_NVME_NS_COMPARE_SUPPORTED flag
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: I24d09cbe21cd2694b4c3433a365dffe75cda2fa8

Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/477924
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: 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: Jim Harris <james.r.harris@intel.com>
2020-01-07 12:31:32 +00:00
Maciej Szwed
c7092e2b3a nvme: Add spdk_nvme_ns_cmd_comparev_with_md function
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: I7eb89412673e01d9c84cb258f5152a31253d7a7f

Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/477025
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2020-01-07 12:31:32 +00:00
Maciej Szwed
334aeff9e1 nvme: Don't ring a doorbell for first of fused commands
This patch adds first_fused_submitted field in spdk_nvme_qpair
structure which is used for postponing ringing a doorbell for
fused commands.

Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: Ibfc43931891ebaadbafa4895c05af9f228440210

Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/477024
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: 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: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
2020-01-07 12:31:32 +00:00
Tomasz Kulasek
1c5d980300 lib/nvme: add hw support for fused operations
Change-Id: I2a184a2d60f18439947afa2d4855d51b92ed282e
Signed-off-by: Tomasz Kulasek <tomaszx.kulasek@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/476137
Community-CI: SPDK CI Jenkins <sys_sgci@intel.com>
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: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
2020-01-07 12:31:32 +00:00
Chunyang Hui
2938dc14b0 Opal: Add clean response buffer process
For nvme Opal, most of the commands are a combination
of security send and receive. There are cases that
application send the security send command and is
shutdown before sending security receive command.
In these cases, when the application restarts, an opal
command will send security send command again and will
cause command sequence error.

Thus, we do a receive first and memset the response
buffer before security send and receive.

Change-Id: Iba02c8074457919816ca576cd00ef9eee6d6dadf
Signed-off-by: Chunyang Hui <chunyang.hui@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/472591
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: yidong0635 <dongx.yi@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-12-24 08:13:57 +00:00
Evgeniy Kochetov
e749c115c6 nvme/rdma: Fix error return code in nvme_rdma_register_rsps
nvme_rdma_register_rsps returned ENOMEM for all failure cases. All of
them are not directly related to shortage of memory. Every point of
failure now sets relevant return code.

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: Ia340f6c6fd3a68d8c34acfefc2c9224ffcdcad3f
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/477302
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Community-CI: SPDK CI Jenkins <sys_sgci@intel.com>
2019-12-23 08:41:48 +00:00
Evgeniy Kochetov
731dca3d77 nvme/rdma: Add work requests batching to NVMe RDMA initiator
RDMA work requests generated between two calls to NVMe RDMA QP
processing function are chained into a list and then posted together
to a queue in next call to processing function.

Batching improves performance in scenarios with deep queues and heavy
load on CPU. But it may cause latency increase on smaller
loads. Batching is configurable with RPC methods and configuration file.

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: I600bce78427eb7e8ed819bbbe523ad318e2da32b
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462585
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-12-23 08:41:48 +00:00
Ben Walker
3d06a83fa4 nvme/rdma: Increase timeout when waiting for CM_EVENTS
In some real data center deployments, 100ms is not enough. Increase
the timeout to 1 second.

Change-Id: I8195a1c1e987b7eff2d8541509f79381be32ed4b
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/478638
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: yidong0635 <dongx.yi@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-12-23 08:41:29 +00:00
Changpeng Liu
912ad8e3aa nvme: use macro defintion instead of magic number for queue priority setting
Change-Id: I7f37478a459db1652a12262a29ca95d88ede1045
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/478261
Community-CI: Broadcom SPDK FC-NVMe 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: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-12-20 10:06:22 +00:00
Changpeng Liu
ff9516bdcc nvme: call the callback for the queued requests when there is submission failure
For the requests which don't have children requests, SPDK may queue them to
the queued_req list due to limited resources, in the completion path, we
may resubmit them to the controller.  When the controller was removed
the submission path will return -ENXIO and we will free the requests directly,
so the callback will not be trigerred for these requests.  Here we added a
flag to indicate the request is from queued_req list or not, so for the failure
submission, we can triger user's callback.

Fix issue #1097

Change-Id: I901ac81733c2319e540d24baf5b8faa1c649eb35
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/477754
Community-CI: SPDK CI Jenkins <sys_sgci@intel.com>
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: Alexey Marchuk <alexeymar@mellanox.com>
2019-12-20 10:04:57 +00:00
Alexey Marchuk
d23f3a85f7 nvme/pcie: Refactor nvme_pcie_qpair_submit_request
Use a lookup table with function pointers to build
the request depending on the payload type and SGL support.
This change helps to remove several if/else branches

Change-Id: I506e4290efc218be68fc8cfda4835b242a99aa77
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/478191
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
2019-12-20 08:56:23 +00:00
Alexey Marchuk
71159819b0 nvme/pcie: Don't use contig SGL commands for admin qpair
Command with cns SPDK_NVME_IDENTIFY_ACTIVE_NS_LIST is issued during
controller initialization and if the controller supports SGL,
this command will be built as a contig SGL. This leads
to a failed completion with the following status:
INVALID FIELD (00/02) sqid:0 cid:95 cdw0:0 sqhd:0004 p:1 m:0 dnr:0
The first identify command SPDK_NVME_IDENTIFY_CTRLR passed since
it was built as a PRP command - we didn't know that the controller
supported SGL at that time. Fix - do not build SGL requests
for admin qpair

Change-Id: I72ab7fe33c03e60ea9f20a9c8afd7c79c40843aa
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/478320
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: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-12-20 08:56:23 +00:00
Ziye Yang
0e3dbd9a60 nvme/tcp: Add a timeout for construct connection.
Purpose: To avoid the hang if there is no response
from the target.

Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: Ib68a9e4c1a28436af2b2ae65891de04067e3dc7d
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/477121
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-12-19 11:06:23 +00:00
Ziye Yang
3455bfad55 nvme/rdma: fix the reaped number caculation issue.
To address the error message:

SPDK_ERRLOG("Unable to resubmit as many requests as we completed.\n");

Reason: The "reaped" variable is used to caculate the free slots
of rdma_reqs after calling the nvme_transport_qpair_process_completions.
And we should correctly caculate the free slots when the rdma_req is
really put.

If we caculate the slots more than we will have, we will trigger
the error print described above.

Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: I269bdb63646eee6444d340b904882736c4cbca36
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/477913
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: qun wan <qun.wan@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Community-CI: SPDK CI Jenkins <sys_sgci@intel.com>
2019-12-17 09:30:24 +00:00
Alexey Marchuk
a092fac4a2 nvme/pci: fix mapping length initialization for contig SGL request
mapping length is initialized with 0 and spdk_vtophys() returns
min(*mapping_length, cur_size) or 0. So length -= mapping_length has no
effect and req will be failed when nseg reaches NVME_MAX_SGL_DESCRIPTORS
Initialize mapping_length = request length

Change-Id: I9082866b7f8055d99fa6930a78335b3b0fdf9b2b
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Signed-off-by: Sasha Kotchubievsky <sashakot@mellanox.com>
Signed-off-by: Evgeniy Kochetov <evgeniik@mellanox.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/477575
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
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>
Community-CI: SPDK CI Jenkins <sys_sgci@intel.com>
2019-12-16 12:31:13 +00:00
Jim Harris
7843321065 nvme: add quirk for a minimum io queue size
Some version of firmware on Intel SSDs exhibit poor performance
with an IO queue size of 256 (the SPDK default).  Add a quirk to
account for this - and use the same size as the Linux driver (1024)
instead.

If the user specified a controller option to explicitly set the
io_queue_size different than the default, the quirk will not take
effect.  Note that users can still override the io_queue_size when
creating the qpair - this only changes the ctrlr's default
io_queue_size.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Iff0f7ab9856fc18f226f7171e5109bb8fe430969

Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/432227
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>
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Community-CI: SPDK CI Jenkins <sys_sgci@intel.com>
2019-12-13 11:02:04 +00:00
Tomasz Kulasek
a7b6702d6f lib/nvme: fix return -EINVAL for invalid io_flags
Previously, invalid io_flags would results in -ENOMEM being
returned to the user which was incorrect.


Change-Id: I53dd0fa8684cb36f3d124baa92244e2ed30e2527
Signed-off-by: Tomasz Kulasek <tomaszx.kulasek@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/476938
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: SPDK CI Jenkins <sys_sgci@intel.com>
2019-12-12 15:30:22 +00:00
Tomasz Kulasek
535dd2ec9b lib/nvme: check if nvme device supports fused operations
Change-Id: I91986f693bd322620a9e7abf598bcc38613bdbd0
Signed-off-by: Tomasz Kulasek <tomaszx.kulasek@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/475859
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-12-12 15:30:22 +00:00
Ben Walker
bed4cdf6c7 nvme: Use sgls, if available, even for contiguous memory
The hardware sgl format can describe large contiguous
buffers using just a single element, so it's more
efficient that a prp list even for a single memory
segment. Always use the sgl format.

Change-Id: I9c62582829f0d64dcd1babdbc48930ddb4d9e626
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/475542
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: 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>
2019-12-11 11:06:57 +00:00
Evgeniy Kochetov
54f81b37ef nvme/rdma: Add 'delay_cmd_submit' option to RDMA transport qpair
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: I12e12d37baf1f74717a60a4f9d8309a994509e42
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/475308
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>
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
2019-12-10 17:32:10 +00:00
Evgeniy Kochetov
ffc7c4a9a9 nvme: Rename 'delay_pcie_doorbell' to 'delay_cmd_submit'
'delay_pcie_doorbel' parameter in 'spdk_nvme_io_qpair_opts' structure
was renamed to 'delay_cmd_submit' to make it suitable for every
transport. Old name is also kept for backward compatibility.

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: I09ef8028133c4a3d4a5bbc5329ced1f065bcaa46
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/475305
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>
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
2019-12-10 17:32:10 +00:00
Tomasz Kulasek
46316bb5db lib/nvme: prevent creating existing cuse device
This patch attempts to solve naming conflict between
CUSE devices created by different SPDK instances.

Each NVMe device is enumerated by SPDK process from 0
up to 127. When process attempts to start cuse device
tries to set exclusive lock on temporary file
"/tmp/spdk_nvme_cuse_lock_<index>" and keep it until
device will be stopped.
If setting lock fails, index is incremented.

It prevents to use the same controller index from
few SPDK instances.

Change-Id: If744ac23f813bd992efb80ae2b61a1acefb5054c
Signed-off-by: Tomasz Kulasek <tomaszx.kulasek@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/474829
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-12-09 17:40:35 +00:00
Tomasz Kulasek
b7b45bc7bc lib/nvme: remove device name parameter from nvme cuse
This patch removes posibility to set cuse device path. Instead
"/dev/spdk/nvme*" path is used.


Change-Id: I7c3087772a3661eebe03fce21356c35cc8204b49
Signed-off-by: Tomasz Kulasek <tomaszx.kulasek@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/474598
Community-CI: Broadcom SPDK FC-NVMe 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: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2019-12-09 17:40:35 +00:00
Changpeng Liu
f4e3f59e0e nvme: fix potential memory leak when there is controller scan failure
The nvme_transport_ctrlr_scan() may return failure while there are
multiple controllers, so the probe context's init_ctrlrs list may
not null for this case, so when free the probe context, let's ensure
there is no controller in the init_ctrlrs list.  Also added a UT to
cover this case.

Fix issue #1095.

Change-Id: I4d9a10ad73cf00bbe159edd1f5b919797333feb6
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/476969
Community-CI: Broadcom SPDK FC-NVMe 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: Jim Harris <james.r.harris@intel.com>
2019-12-09 13:58:01 +00:00
Seth Howell
61537a190e nvme: replace nvme_qpair_state_equals.
nvme_qpair_get_state fits more closely with the semantics in other
modules.

Change-Id: I6ea8e02abe27253d9b4d779a43ac1963be56356a
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/476920
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: Alexey Marchuk <alexeymar@mellanox.com>
2019-12-09 13:55:41 +00:00
Seth Howell
24bca2eadd nvme: add an enum for why a qpair disconnected
Change-Id: I1a9517d9673051615942c873416505704740691a
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/475805
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>
2019-12-09 13:55:41 +00:00
Seth Howell
3911922005 nvme: remove redundant transport_qp_is_failed checks
The qpair state transport_qpair_is_failed is actually equivalent to
NVME_QPAIR_IS_CONNECTED in the qpair state machine.

There are a couple of places where we check against
transport_qp_is_failed and then immediately check to see if we are in
the connected state. If we are failed, or we are not in the connected
state we return the same value to the calling function.

Since the checks for transport_qpair_is_failed are not necessary, they
can be removed. As a result, there is no need to keep track of it and it
can be removed from the qpair structure.

Change-Id: I4aef5d20eb267bfd6118e5d1d088df05574d9ffd
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/475802
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>
2019-12-09 13:55:41 +00:00
Changpeng Liu
0c9057f031 nvme: replace cdw11 with specific union strucutre
Change-Id: I1152b5d6d5f8e3c2f96dcca1353d85a410924fb4
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/475467
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>
2019-12-06 14:43:41 +00:00
Changpeng Liu
1fea1fccf5 nvme: replace cdw10 with specific union command
Change-Id: Ibdbc6d0356749795db26f58aa5c5e68739d5df5e
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/475465
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>
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
2019-12-06 14:43:41 +00:00
Tomasz Kulasek
fd2af7afa9 lib/nvme: stop all NVMe io producers on detach
Now all registered producers should be stopped (unregistered) before
NVMe detach, otherwise NVMe controller cannot be safely detached.

This patch allows to stop all not unregistered io producers before
NVMe detach:

1. Callback to the "struct nvme_io_msg_producer" to stop producer
   started on selected controller.
2. On nvme_io_msg_ctrlr_detach() if there's some unregistered producers,
   stop all before freeing resources.


This approach also fixes issue with not to stop CUSE device when
NVMe controller is detached without unregistering producer (github
issue #1033).

	Fixes #1033

Change-Id: Ia1ffef566bb745edb55c54d6786ea481a35bbefd
Signed-off-by: Tomasz Kulasek <tomaszx.kulasek@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/474273
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>
2019-11-28 12:36:58 +00:00
Tomasz Kulasek
88808c5ab7 lib/nvme: cuse device avoid using signals
This patch uses lowlevel fuse functions to process messages to
eliminate the need to use signals to interrupt blocking read
operation in fuse_session_loop().

  Fixes #1032

Change-Id: Ie9c9ea76cc135c383f5757864aa2d84ac9eb3da3
Signed-off-by: Tomasz Kulasek <tomaszx.kulasek@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/473233
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: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-11-22 13:53:38 +00:00
Seth Howell
e9e3f61525 nvme/rdma: add connect retry in edge case
If the initiator dies without a disconnecting a qpair, the target can
possibly retain the state of the connection. In this case, it will
inform us that the connection is stale, and we need to try again.

Change-Id: I4d349c634aee59ce9ea4af795b07dd8649db56b3
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/473063
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>
2019-11-21 08:03:33 +00:00
Tomasz Kulasek
82a54d29f6 lib/nvme: fix nvme_io_msg_ctrlr_unregister with no io_msg_producer
Change-Id: If2e0d00560311948570a2d7113dc5f730d937c0c
Signed-off-by: Tomasz Kulasek <tomaszx.kulasek@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/474257
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: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2019-11-21 08:01:57 +00:00
Tomasz Kulasek
9eb0ffa90c lib/nvme: change api for io message
API changes in this patch:

 1) nvme_io_msg_ctrlr_start                         => nvme_io_msg_ctrlr_register
 2) nvme_io_msg_ctrlr_stop with (shutdown == false) => nvme_io_msg_ctrlr_unregister
 3) nvme_io_msg_ctrlr_stop with (shutdown == true)  => nvme_io_msg_ctrlr_detach


Change-Id: I60153ebbfb0d0b22575128d106f9333c3887213d
Signed-off-by: Tomasz Kulasek <tomaszx.kulasek@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/474096
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>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-11-21 08:01:57 +00:00
Tomasz Kulasek
53184430a5 lib/nvme: fix do not use external_io_msg_qpair after free
Change-Id: I20ef8303c2fae6abf43d15ebb025ea368c0dfd67
Signed-off-by: Tomasz Kulasek <tomaszx.kulasek@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/473282
Tested-by: SPDK CI Jenkins <sys_sgci@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>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2019-11-21 08:01:57 +00:00
Jim Harris
c3aaaa0181 nvme: don't monitor hotplug events in secondary process
NVMe hotplug must be monitored in the primary process -
DPDK doesn't support trying to handle it in the
secondary process.

This issue was somewhat masked previously in secondary
processes, since usually it would just probe(NULL) which
meant probe all attached NVMe controllers.  So in the
secondary process, we would probe just once, and create
the hotplug fd - it would never actually try to monitor
it.

But when explicitly specifying multiple trids in a
secondary process, probe would get called multiple
times.  First time would be fine since it only creates
the hotplug fd.  But second time would segfault since
monitoring for hotplug requires checking the DPDK-allocated
context which doesn't exist in the secondary process.

Fixes issue #1063.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I2a9a91e222c206034293d90e30e3f598c8d7baa8

Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/475015
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: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-11-20 09:34:18 +00:00
Jim Harris
27e88b8d91 nvme: add g_ prefix to hotplug_fd
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I8cc03e1a8b5d2eb28bf945115f3c9b3980b30f1c

Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/475014
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: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-11-20 09:34:18 +00:00
Seth Howell
6b87dd8023 nvme_rdma: Detect stale connection failures.
This is the first step in properly reconnecting after a hard power off
event.

Change-Id: I9739bffacd66ec6d9f8f1d376bf42291c84f90f2
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/473061
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: Jim Harris <james.r.harris@intel.com>
2019-11-15 20:26:46 +00:00
Seth Howell
208fbb675c nvme_rdma: more cm_event validation to a helper function.
This step is going to become more involved, so it's best to keep it in a
separate function entirely.

Change-Id: Iefa9860420edf28e858c4ed8aa932985c686cfd9
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/473060
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: Jim Harris <james.r.harris@intel.com>
2019-11-15 20:26:46 +00:00
Seth Howell
f6646fd9fa nvme/tcp: detect cq errors.
We should alert the upper layer when the qpair becomes unusable due to
qpair errors.

Change-Id: Icdee3b55a14441a60111f3bd7a44dceef93bbb09
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/474095
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-11-15 18:27:27 +00:00
Ziye Yang
542185b7e0 nvme/qpair: merge two if case into one.
Purpose: To remove the duplicated code.

Change-Id: Iab9989f9928698967533e45e7cffad4f09bde16a
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/473376
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-11-08 22:18:18 +00:00
Jim Harris
e93449910a nvme: use -EFAULT for vtophys-related failures
Currently we have a mix of -1 and -EINVAL which
is confusing, especially since these types of failures
also result in the caller's callback routine getting
invoked.

While here, document this new -EFAULT return code for
all of the functions that could return it.

Fixes issue #797.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I8dfbba0ec0b83db0f2ec055b15830981af1965df

Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/473054
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: yidong0635 <dongx.yi@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2019-11-06 15:19:48 +00:00
Jim Harris
3ca9d4fc5e nvme: simplify nvme_pcie_qpair_build_contig_request
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ib43c411516b0b9e5804e307a5ab45117cf20a720

Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/472439
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>
2019-11-06 15:19:48 +00:00
Jim Harris
e0a0f90b0f nvme: don't enable adminq until we know discovery_ctrlr exists
Fixes issue #1029.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I489dfc853804b005d385b1c51815f0e7f342b39b

Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/473237
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: yidong0635 <dongx.yi@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-11-06 14:47:05 +00:00
Ben Walker
83ffb2075e nvme/tcp: Rename pdu->ctx to pdu->req
This is always the request pointer, so rename it for clarity.

Change-Id: Ifbda7db7787c65f0deb190a1e94f0676b2c0d99a
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/470530
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
2019-11-01 17:56:16 +00:00
Ben Walker
11739f3cb1 nvme/cuse: Poll the io_msg queue when the admin queue is polled
Users already have to poll the admin queue, so embed the io_msg
queue polling there to simplify the API.

Change-Id: I4d4d3be100be0798bee4096e0bbda96e20d2405e
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/472833
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-10-31 14:05:23 +00:00
Seth Howell
13f30a254e nvme: don't disconnect qpairs from admin thread.
Disconnecting qpairs from the admin thread during a reset led to an
inevitable race with the data thread. QP related memory is freed during
the disconnect and cannot be touched from the other threads.

The only way to fix this is to force the qpair disconnect onto the
data thread.

This requires a small change in the way that resets are handled for
pcie. Please see the code in reset.c for that change.

fixes: bb01a089

Change-Id: I8a39e444c7cbbe85fafca42ffd040e929721ce95
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/472749
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-10-31 04:50:59 +00:00
Seth Howell
a4925ba744 nvme: take the lock when disconnecting qpairs.
If we disconnect qpairs without taking the lock, we run the risk of
trying to double free qpair resources before they have been marked as
NULL.
For example, polling on one thread and calling
nvme_rdma_qpair_disconnect from one thread while doing an
nvme_ctrlr_reset on another thread. nvme_ctrlr_reset will call down to
nvme_rdma_qpair_disconnect on the same qpair and without any locking it
can result in trying to destroy the qpair resources multiple times.

Change-Id: I9eef6f2f92961ef8e3f8ece0e4a3d54f3434cff8
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/472413
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>
2019-10-28 17:19:46 +00:00
Seth Howell
eb2dee2444 test/nvmf: add a test case for trid failover.
Modifying the target_disconnect.sh test to include an example of
transport_id failover for an NVMe-oF controller.

Change-Id: I746ed737ab56c7dec6ee99e840c631ba46ee359e
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/472230
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>
2019-10-24 23:46:39 +00:00
Tomasz Kulasek
74906b01b6 lib/nvme: add RPC for interacting with CUSE devices
Added RPC commands to register/unregister CUSE devices
to NVMe controllers:

 - bdev_nvme_cuse_register
 - bdev_nvme_cuse_unregister

Additionally two RPC now return CUSE device names:

 - bdev_get_bdevs for namespaces
 - bdev_nvme_get_controllers for controllers


Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: I69c4bf41ec8f78a7522894268a67dd733881712f
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Signed-off-by: Tomasz Kulasek <tomaszx.kulasek@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/472211
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-10-24 23:43:59 +00:00
Maciej Szwed
63364ccc4f lib/nvme: CUSE add IO requests processing
IO request handling implementation for CUSE namespaces:
  - NVME_IOCTL_SUBMIT_IO,
    a. SPDK_NVME_OPC_READ,
    b. SPDK_NVME_OPC_WRITE,

Other ioctls related to the namespace:
  - NVME_IOCTL_ID,
  - BLKPBSZGET,
  - BLKGETSIZE,
  - BLKGETSIZE64,

Additionally NVME_IOCTL_ADMIN_CMD has been implemented
for namespace to send admin cmd to its controller.


Change-Id: Iaa2a5ee409b35c682ae8b2bd2309e8b67eb51981
Signed-off-by: Tomasz Kulasek <tomaszx.kulasek@intel.com>
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469691
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-10-24 23:43:59 +00:00
Maciej Szwed
39283f0074 lib/nvme: CUSE add admin requests
Admin requests handling for CUSE io producer:
  - NVME_IOCTL_ADMIN_CMD,
  - NVME_IOCTL_RESET

Change-Id: I24169f7d08b90fd0a695b5bf3341fd56e0382b9f
Signed-off-by: Tomasz Kulasek <tomaszx.kulasek@intel.com>
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469690
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-10-24 23:43:59 +00:00
Tomasz Kulasek
805d994281 lib/nvme: add NVMe character device
NVMe character device implementation. This patch adds implementation
of IO producer using CUSE library. It allows to create nvme device
nodes in linux kernel for controller as well as for namespace and
process ioctl requests as usual from linux environment.

Both devices (controller and namespaces) are exposed as character
devices.

To compile NVMe CUSE module use "./configure --with-nvme-cuse".

Names for created CUSE devices can be retrieved using
spdk_nvme_cuse_get_ctrlr_name() and spdk_nvme_cuse_get_ns_name().


Signed-off-by: Jim Harris <james.r.harris@intel.com>
Signed-off-by: Tomasz Kulasek <tomaszx.kulasek@intel.com>
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: I0fc9a9a1ef3c9c2b3112d07c2b4b1f8d49665ee1
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/466917
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-10-24 23:43:59 +00:00
Maciej Szwed
72e079a880 lib/nvme: implement external IO processing
This patch allows to send IO requests from external module to the nvme
device.

External module should call nvme_io_msg_ctrlr_start() to start IO message
producer on the controller and enable sending messages.

nvme_io_msg_send() is used to send IO to NVMe driver thread context,
where passed function will be called. Allowing the external module to
issue IO as needed.

NVMe driver users should poll spdk_nvme_io_msg_process() to move forward,
sending IO from external module and process their completions.

Change-Id: Ie59abac69870c4e4daa50120c747f3b620395921
Signed-off-by: Tomasz Kulasek <tomaszx.kulasek@intel.com>
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/471386
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-10-24 23:43:59 +00:00
Seth Howell
5215fad6ef nvme: Add an API for updating a controller trid.
This can be useful when trying to perform multipath failover at the
application level. However, the controller must be in the failed state
before calling this function.

Change-Id: I5403c0036fed5dd3600ee20592925297494ba8aa
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/470699
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>
2019-10-24 17:36:31 +00:00
Seth Howell
7d3771f93c nvme_ctrlr: add get/set for ctrlr->is_failed.
These will be useful helper functions for the trid modification code
that gets introduced later.

Change-Id: Ief73e3045710bf35c511794c19b4dfefb93018f1
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/471780
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>
2019-10-24 17:36:31 +00:00
Seth Howell
e45b619c3d nvme: add function to reconnect qpairs.
While it is unlikely that a single qpair will be failed, it is important
to make it possible to reconnect a single qpair.

This function is also handy at the application layer when going through
a reconnect workflow. If we get -ENXIO from a qpair when we poll, we
will turn around and call this function. If we get -ENXIO from this
function, then we know the whole controller is failed and we need to do
a reset.

Change-Id: I6a8ea0ce27fce2f5fc0a5b3db05834acd68e6a39
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/471417
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-10-24 17:36:31 +00:00
Chunyang Hui
5f42a71745 opal: Fix get locking range info memory leak
Previously, get locking range info will allocate
memory everytime. Thus calling this function multiple
times will cause memory leak.

Now, we allocate only if it is NULL. If it is not,
then we just memset to zero.

Change-Id: If048416a2056176f86206a33e2b5db210288fe4f
Signed-off-by: Chunyang Hui <chunyang.hui@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/472112
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
2019-10-24 17:09:57 +00:00
Chunyang Hui
ac4949807b Opal: Add async function for revert TPer
Some nvme drives might take 6-7mins for
this operation. Thus, introduce async function
to avoid waiting.

Change-Id: Id48478aec653d3fb75a3c5ce75d4997284ed016c
Signed-off-by: Chunyang Hui <chunyang.hui@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/468916
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
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>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
2019-10-24 17:09:57 +00:00
Seth Howell
ae3a9b8f08 nvme_qpair: return -ENXIO when the qpair is failed.
This will be the canonical way of informing the user that we have lost
the qpair connection somehow.

Also update all of the functions that will return -ENXIO to the user.

Change-Id: Ic6c7c2d0e07e9d3e857a3476bb6b91fb4b6454fa
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/471416
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>
2019-10-22 21:14:22 +00:00
Seth Howell
81b20a4d96 nvme_ctrlr: Allow resets from failed state
Failed is not a final state for either fabric or pcie controllers. We
have historically not allowed resets in the failed state, but we should.

Instead of checking for the failed state, we should check for the
removed state. If the controller is removed, then we cannot even attempt
a reset.

Change-Id: I2c1a3d85db84f84cd1895cbfaf16575c8b496155
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/471415
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-10-22 21:14:22 +00:00
Seth Howell
3e1569e875 nvme_ctrlr: combine spdk_nvme_ctrlr_reset functions
We no longer need the private function with a public wrapper.

Change-Id: I0d24dfb282461174729d3eb649c78ac27e42fc8d
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/471552
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>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
2019-10-22 21:14:22 +00:00
Seth Howell
0a42e658b5 nvme_rdma: let UL know when we fail qpairs.
Also, adds a field to the generic qpair for future use in other
transports.

Change-Id: Ie5a66e7f5ebfec1131155fc07e3c671be814fb9b
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/471414
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>
2019-10-22 21:14:22 +00:00
Seth Howell
552898ec17 nvme_qpair: fail the ctrlr only for errors on admin qpair.
We shouldn't always fail the whole controller if we get a failure on an
individual qpair.

Change-Id: Id0c90af83e5231593a895be66e7a7de48939e240
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/471660
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-10-22 21:14:22 +00:00
Seth Howell
6b314fb5dc nvme_rdma: properly separate alloc_reqs and register_reqs.
The way these two functions were separated previously represented a
pretty sserious bug when doing a controller reset.

If there were any outstanding requests in the rqpair, they would get
overwritten during the call to nvme_rdma_qpair_register_reqs and the
application would never get a completion for the higher level requests.
The only thing that we need to do in this function is assign the proper
lkeys.

Change-Id: I304c70646daf9b563cd00badba7141e5e8653aad
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/471659
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-10-22 21:14:22 +00:00
Seth Howell
4c1a18c41d nvme_qpair: fix check_enabled.
check_enabled had a couple bugs in it that made it unfriendly for enabling
I/O qpairs after a reset.
1. It was calling nvme_qpair_abort_queued_requests before setting the
enabled flag to true. For applications that submit new I/O in the
completion callback for old I/O, this means you enter an infinite loop
of submitting requests, and then immediately completing them. SO
instead, wait for the qpair to reset, then just submit those requests to
the lower layer.
2. It didn't check whether we were already in the middle of calling it,
so we could reenter function calls like
nvme_qpair_abort_queued_requests.

Also, now that we have a coherent state machine for qpairs, we can limit
the enabling to a specific state in that state machine.

Change-Id: Ie0b74819a6b16839965bced47c33dec967f725a8
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/470256
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-10-22 21:14:22 +00:00
Seth Howell
a1ce725c0a nvme_fabric: enable the discovery_ctrlr admin queue
As the todo states later on in the function, the discovery controller
should really be initialized through traditional methods, but it was
hacked in. For now, enable the admin qpair to get past the non-standard
nature of this controller.

Change-Id: I2cbf1cd47d7249ae3d12bcfc2e8d21e8fb98df7e
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/471779
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-10-22 21:14:22 +00:00
Seth Howell
6035f73d7b nvme_fabrics: move ctrlr_scan to common code.
This function is identical between the two transports.

Change-Id: If50b781259f224eb2c21de7da14564e6ce487650
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/471778
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-10-22 21:14:22 +00:00
Seth Howell
08d4d977e8 nvme: combine qpair->is_connecting and is_enabled
These will form the base of a little state machine for managing the nvme
qpair structure.

Change-Id: If6f6df38cc17221ac8fcb7d8c0d7e2e808897a99
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/470534
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-10-22 21:14:22 +00:00
Seth Howell
5cd7634939 nvme_ctrlr: enable the admin qpair before init.
The driver has historically waited until we have to do a listen
before enabling the admin qpair. That is a very PCIe-centric mindset.
For fabric controllers, a lot of the early initialization operations such
as get_cc and set_cc are handled through the admin qpair so it should be
enabled before we begin the initialization process.

As a side effect of this cahnge, the internal API
nvme_ctrlr_enable_admin_qpair has been removed. It would have turned
into a one-liner.

Change-Id: Icd162657d01a85c227a3f20c295d0208e07ce44d
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/471743
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: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
2019-10-22 21:14:22 +00:00
Seth Howell
fa9f668a8b nvme: call the generic qpair_connect fn from all transports.
This wasn't being done in the previous case which meant that I/O qpairs
were not being moved to the connecting state when connecting for the
first time. However, to prepare the way for a coherent state machine for
nvme qpairs, we need to ensure that all qpairs go through the same
states.

Change-Id: I3cfe799a003acd926b24c107ab1461a96239c1bb
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/471753
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-10-22 21:14:22 +00:00
Seth Howell
c2df8f6d84 nvme: unify ctrlr_scan function between rdma & tcp
These functions are functionally equivalent. Just unify the way they
wait for completions so that they are completely identical and we can
merge them into a common function.

Change-Id: Id5d734b6ae613b3ac828d89853d986cdadfb211a
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/471936
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-10-22 21:14:22 +00:00
Seth Howell
1399a42bbc nvme_rdma: put requests when ibv_post_send fails.
Leaving these on the stack outstanding list can cause unnecessary
buildup. If we fail to post the request to ibv, then the upper layer
request will be freed immediately for reuse, but we will keep that
request in the outstanding queue at the RDMA layer.

Change-Id: Ib422dc9fcb50344ce7c01749f3e20ea9310fd5cb
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/470255
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-10-15 16:53:59 +00:00
Seth Howell
85d9f0a9ab Revert "nvme: call the remove_cb in nvme_ctrlr_fail."
This reverts commit bc4e31d6b2.
This change was accidentally merged after it was decided to go with a
different architecture.

Change-Id: Ifc9d8b08bd1fcbc4ace8dd6fb4bd0014330916ed
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/471144
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>
2019-10-15 16:33:12 +00:00
Seth Howell
4473732398 nvme: allow fabrics commands during reconnect.
When doing a reset on an NVMe-oF target with active I/O qpairs, we need
to be able to submit fabrics commands on them in order to perform a reset.
Currently, resetting a fabric controller with any I/O qpairs active will
cause the reset to hang indefinitely.

Change-Id: Ic972a301390a4dd64adabedfe01aa4e5253e40b0
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469935
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: Jim Harris <james.r.harris@intel.com>
2019-10-11 20:13:26 +00:00
Seth Howell
bc4e31d6b2 nvme: call the remove_cb in nvme_ctrlr_fail.
The remove callback is a built in way of alerting the user application
that we have removed a controller. Once we fail a controller, we never
move it back out of that state so it is in essence removed.

Change-Id: Iaad6bef0994e9ddd5a424f6b83502f9191b2de49
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469637
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@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>
2019-10-11 20:13:26 +00:00
Seth Howell
2575aaec5a nvme: make sure we queue requests in order.
My recent changes that introduced batching to queued request
resubmission also introduced a regression that can lead to reordering
requests before submitting them to the drive. This change prevents that.

We wait until inside the internal _nvme_qpair_submit_request function to
check for queued entries to avoid queueing a request that has children.

If a request that has children gets queued, when we process completions
and resubmit the parent, it will result in the children being submitted.
Since we only account for the number of requests we completed in the
last iteration, some of the child requests may be requeued out of order,
or worse, none of the child requests will end up being submitted to the
transport and they will all be queued behind previously queued requests.

Change-Id: I58e1c458c25fbf3f9f75364f05b1076b166a6212
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/470890
Reviewed-by: Ziye Yang <ziye.yang@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: Changpeng Liu <changpeng.liu@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-10-11 18:45:13 +00:00
Seth Howell
d7d03bd36a nvme: store the probe destroy_cb in the ctrlr.
Making this structure available from the ctrlr allows us to call the
remove callback when the controller is failed/removed on transports
other than pcie.

Change-Id: I2c66dfef12b039c0d6daf7df83da745757818006
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469636
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>
2019-10-09 14:32:36 +00:00
Seth Howell
2476a74550 nvme: don't fail the ctrlr in nvme_ctrlr_reset
This paves the way for doing multiple reconnect attempts before failing
the controller.

Change-Id: I1ff4ee6d41a5ffb47dd186d76793d670287c4783
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469934
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: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: John Kariuki <John.K.Kariuki@intel.com>
2019-10-09 14:32:36 +00:00
Seth Howell
4dd94a25a3 nvme: move spdk_nvme_ctrlr_reset.
By moving the contents of spdk_nvme_ctrlr_reset to a new internal
function, I am paving the way for providing two reset paths. One, which
can be used by the user as an external API function and which provides
the same legacy behavior. Specifically, that it will always fail the
ctrlr after an attempted reset, and a second, internal path, which will
be used by the qpair reconnect code which will defer failing the qpair
to the qpair code.

Change-Id: I9ec9df55c1fecc2f00476c175bcf988207c31257
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469933
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@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>
2019-10-09 14:32:36 +00:00
Seth Howell
584a630287 nvme: don't fail the ctrlr from ctrlr_process_init
If we are to have multiple reconnect attempts, we have to control
whetehr the controller is placed in the failed state from outside the
reset function itself. This will allow us to fail the controller only
after all of our retries are exhausted.

Change-Id: Ia82e10325272f25b2b8527336dc3bc507c93b401
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469932
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: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
2019-10-07 15:05:00 +00:00
Seth Howell
f5d88e46e2 nvme: always set ctrlr->is_failed through API
Use the standard API function to fail the controller in all cases.

This patch, and the several following patches are aimed at creating a
mechanism for reporting up to the application layer that a controller is
failed and or removed. To do this, I use the reset_cb to inform the
upper layer that the controller is failed.
This also requires changes to how we handle a controller reset to
pave the way for doing optional reset retries in the libraries.

Change-Id: I06dfce08326c23472a1caa8f6efbac2fd1a720f2
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469635
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>
2019-10-07 15:05:00 +00:00
Seth Howell
2c68fef058 nvme: move queued request resubmit to generic layer
We were already passing up from each transport the number of completions
done during the transport specific call. So just use that return code
and batch all of the submissions together at one time in the generic
code.

This change and subsequent moves of code from the transport layer to the
genric layer are aimed at making reset handling at the generic NVMe
layer simpler.

Change-Id: I028aea86d76352363ffffe661deec2215bc9c450
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469757
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.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>
2019-10-07 15:05:00 +00:00
Seth Howell
afc9800b06 nvme: _nvme_qpair_submit_request does not requeue
This will be handled by nvme_qpair_submit_request when it receives
-EAGAIN from _nvme_qpair_submit_request.

Change-Id: I5e76aae170c981df0cadaadcd5da1163c715006f
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/470407
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>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
2019-10-07 15:05:00 +00:00
Seth Howell
18dc53c531 nvme: move submit_request impl to a private function
This patch series is aimed at preserving the order of qpair entries
when resubmitting queued requests. The hope is that we will make the API
fool proof and future proof against ever reordering any queued requests.

Change-Id: Ib20d61d3abaed637c9c305b75081947630190fd4
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/470062
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>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
2019-10-07 15:05:00 +00:00
Chunyang Hui
f74b33ad0b Opal: Small fixes
1. Log level change to info when checking support
2. Delete new lines
3. Enlarge the timeout seconds to 10min for revert
   TPer as it sometimes need 6-7min for this operation.

Change-Id: I1b7e32917bd99c859f1515b07f2530669418f0db
Signed-off-by: Chunyang Hui <chunyang.hui@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/468915
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>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
2019-10-01 14:12:57 +00:00