Commit Graph

637 Commits

Author SHA1 Message Date
Chen Wang
ea55b03940 nvme/nvme_rdma: free the ctrlr when creating the qpair fails
Release nvme rdma ctrlr before exit the nvme_rdma_ctrlr_construct function
when creating the admin qpair fails.

Fixes GitHub issue #363.

Change-Id: Ib988e0da2f627db06b68bd3fb72c117c52572cf8
Signed-off-by: Chen Wang <chenx.wang@intel.com>
Reviewed-on: https://review.gerrithub.io/420719
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2018-08-01 17:23:49 +00:00
Xiaodong Liu
9928e9d98a ocssd: apply ocssd strings into status arrays
Change-Id: If25463ea76e8382c61f10636e1119376a00104dc
Signed-off-by: Xiaodong Liu <xiaodong.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/411594
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
2018-07-30 03:09:31 +00:00
Ziye Yang
b1da5cecaa nvme: change the type of paramter for timeout_callback set
Change the type of nvme_timeout parameter in
spdk_nvme_ctrlr_register_timeout_callback from uin32_t to uint64_t.

Reason: This will make the timeout trigger test more flexible and
will not affect the original meanings.

Also for the configuration file, still maintain the compatability
support

Change-Id: I94c90f67b2e9c57220ab82ecea11a1590d62aed4
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/419326
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@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>
2018-07-19 07:18:17 +00:00
Pawel Wodkowski
7c57c0f2ad nvme: show command manual completion
If command is completed manually (e.g.: driver decide to fail this
command from some reason) not all NOTICELOG informations about this
command are valid. To not get confused who completed the command (driver
or a device) show addtional information when command is completed
manually (using NOTICELOG like nvme_qpair_print_command and
nvme_qpair_print_completion do).

Change-Id: I7211bd165aec142ad11e806fa3031371375edd2f
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-on: https://review.gerrithub.io/411293
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: Ben Walker <benjamin.walker@intel.com>
2018-07-16 08:23:19 +00:00
Lance Hartmann
b4ceb613e1 nvme: add chk_rdy quirk for some Samsung drives
Add some known Samsung controllers to those requiring the quirk,
NVME_QUIRK_DELAY_BEFORE_CHK_RDY.  Addresses an issue for those
who may not have later firmware that corrects the problem.
Correspondingly, extend the delay from 2 secs to 2.5 secs.

Change-Id: Iee773905a2a49711775042c061f6c347e0da85e9
Signed-off-by: Lance Hartmann <lance.hartmann@oracle.com>
Reviewed-on: https://review.gerrithub.io/419273
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>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
2018-07-14 01:47:47 +00:00
Dariusz Stojaczyk
564db67415 nvme/pcie: make sure sq and cq are physically contiguous
The spdk_dma_zmalloc guarantee about physical memory contiguity
is about to be removed soon. For hardware rings that require
physical memory or IOVA contiguity we will now enforce hugepage
alignment and size restrictions to make sure they occupy only
a single hugepage.

Change-Id: Iebaf1e7b701d676be1f04a9189201c5d89dad395
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/418547
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
2018-07-12 20:13:43 +00:00
Young Tack Jin
6d05186697 ocssd: add chunk info list as mptr of vector reset
This is verified on QEMU NVMe which merged the related patch.

Change-Id: I7c62d7a91350e0a877d1c3651796c38b55122f98
Signed-off-by: Young Tack Jin <youngtack.jin@circuitblvd.com>
Reviewed-on: https://review.gerrithub.io/417077
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Xiaodong Liu <xiaodong.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Matias Bjørling <m@bjorling.me>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2018-07-09 18:54:22 +00:00
Daniel Verkamp
4a9dce9a48 Use SPDK_CONTAINEROF in a few more places
A few open-coded sequences equivalent to SPDK_CONTAINEROF() were
scattered around; replace them with the macro from spdk/util.h.

Change-Id: I95c6e6838902f411420573399ced7c58c2e4ef84
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/418126
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2018-07-06 22:47:04 +00:00
Dariusz Stojaczyk
d36ce206ec nvme/pcie: do not assume tracker array memory is physically contiguous
The spdk_dma_zmalloc guarantee about physical memory contiguity
is about to be removed soon. A single tracker is page size
aligned and is exactly one page big, so it is physically
contiguous, but we can't assume an array of those is physically
contiguous as well.

Change-Id: I3aa4d14dd677601c30aa2d8f15197886d6c46e58
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/416840
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2018-07-06 18:37:09 +00:00
Daniel Verkamp
4af4e4f509 nvme: adjust physically contiguous memory comments
The NVMe PCIe transport only requires physically contiguous allocations
for struct nvme_tracker and the I/O SQ and CQ entries, which are already
handled separately.  Change the comments to indicate that struct
nvme_payload's contiguous type only requires the memory to be virtually
contiguous, since nvme_pcie_prp_list_append() already steps through the
buffer and translates each (4K) page independently.

Change-Id: I45ac8dfb2c033a0fcbf2effbe33af4efc1eb23cb
Reported-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/417045
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2018-07-05 19:08:26 +00:00
Dariusz Stojaczyk
5f14637246 nvme/pcie: merge physically contiguous SGEs
There's no need to split a bufffer if it's physically
contiguous. We can now merge buffers that would be
previously split by the nvme_pcie driver and also
separate SGEs provided by the user that happen to be
physically contiguous.

Change-Id: I9c9de31d52a9dc9e384806555cb94609aff0ccf3
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/417061
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2018-07-02 19:13:23 +00:00
Dariusz Stojaczyk
3320c06b4c nvme/pcie: split HW SGL entries on 2MB address boundary
This allows NVMe PCIe devices to be used with
physically discontiguous I/O payload buffers.

So far this is just a dumb splitting which
doesn't check for physical contiguity. This is
improved in a subsequent patch.

Change-Id: I0ecc443149225eaa0e4156ddda78613bcf034406
Suggested-by: Daniel Verkamp <daniel.verkamp@intel.com>
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/417060
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2018-07-02 19:13:23 +00:00
Dariusz Stojaczyk
2044690e6a env: introduce SPDK_MEMZONE_NO_IOVA_CONTIG
Future DPDK versions may drop physical memory contiguity
guarantee for common memzones. DPDK 18.05 introduces
an RTE_MEMZONE_IOVA_CONTIG (0x00100000) flag, which is
documented as follows:

> RTE_MEMZONE_IOVA_CONTIG - Ensure reserved memzone is IOVA-contiguous.
>                           This option should be used when allocating
>                           memory intended for hardware rings etc.

To preserve backward compatibility, SPDK introduces an opposite
flag, SPDK_MEMZONE_NO_IOVA_CONTIG.

Change-Id: I9ea79b096fdb094051f13c9a802740b0e4ccc98e
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/416977
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2018-07-02 19:13:23 +00:00
Daniel Verkamp
1d260441b4 nvme/rdma: factor out Connect command
This is a generic NVMe-oF command that may be used for other transports.

Change-Id: Id5fbf1f176ef5f75a221b40eff538e693817bcaf
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/416578
Tested-by: SPDK Automated Test System <sys_sgsw@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>
2018-06-27 22:59:18 +00:00
Daniel Verkamp
9f5fb75d1f nvme: move cntlid to struct spdk_nvme_ctrlr
All controllers have a controller ID (cntlid), and this will be needed
in other NVMe-oF transports, so move it to the generic controller
structure.

Change-Id: Iaba5b93e1267e7bef3a6eb7c677c549a3d83985c
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/416577
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2018-06-27 22:59:18 +00:00
Daniel Verkamp
ee9ca4b324 nvme/rdma: factor out NVMe-oF discovery
This can be used for other NVMe-oF transports.

Change-Id: Ic8d2dc483220eb3690cb756bcd750d19c93d98e6
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/416576
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2018-06-27 22:59:18 +00:00
Daniel Verkamp
d81d3fa935 nvme/rdma: factor out NVMe-oF Property Get/Set
These functions are generic and may be used for other NVMe-oF
transports.

Change-Id: Idb3aa30d9b0b1be7b60b85ab4911b28db35977a4
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/416575
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2018-06-27 22:59:18 +00:00
Liang Yan
8c71c208a2 nvme: check ctrlr process while get ctrlr data in hotplug function.
Fix issue #313.
For multi-process test scenarios, the secondary process may access
controller’s CSTS register in the shared ctrlr list. For this situation,
all the controllers are already in the primary shared ctrlr list, but
then each controller is added one by one in the secondary process, so the
secondary process may access CSTS before it is remapped for the BAR space.

In the rpc_config.sh test case, the spdk_nvme_ctrlr_get_regs_csts function
will be called in _nvme_pcie_hotplug_monitor function before calling
spdk_pci_nvme_device_attach. This step caused the secondary process iSCSI
Target access CSTS before it is remapped for the BAR space.

Change-Id: Ifd62c38adf8624f9877a9a2f965ca4db28839d99
Signed-off-by: Liang Yan <liang.z.yan@intel.com>
Reviewed-on: https://review.gerrithub.io/412594
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: GangCao <gang.cao@intel.com>
Reviewed-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2018-06-25 22:05:52 +00:00
Ziye Yang
ff4f94dc5f nvme: Add a break to make error injection more efficient
Change-Id: I3bddbb1caf11e17b2ecfa446adcc221b3aed595b
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-on: https://review.gerrithub.io/416662
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2018-06-25 16:00:34 +00:00
Jakub Radtke
c182da27b5 ocssd: vector commands
This patch adds support for following Open-Channel vector commands:
* Vector Chunk Reset
* Vector Chunk Write
* Vector Chunk Read
* Vector Chunk Copy

Implementation is consistent with Open-Channel specification (rev. 2.0)

This patch provides unit tests for new public NVMe
Open-Channel namespace commands.

Change-Id: Ic71be9357c61c5de82ca672e82a71aa933bd1875
Signed-off-by: Jakub Radtke <jakub.radtke@intel.com>
Reviewed-on: https://review.gerrithub.io/414969
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Xiaodong Liu <xiaodong.liu@intel.com>
Reviewed-by: Young Tack Jin <youngtack.jin@circuitblvd.com>
2018-06-22 21:34:49 +00:00
John Barnard
79cffd37ca nvmf: Add Fibre Channel defs and usage to nvme lib
Add FC definitions to nvme header and library functions.

Change-Id: I8980f55d834c1e1d4f415756cb7a46a3ff1c7db3
Signed-off-by: John Barnard <john.barnard@broadcom.com>
Reviewed-on: https://review.gerrithub.io/416434
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2018-06-22 21:09:09 +00:00
Changpeng Liu
c391fed3e1 nvme: add nvme error injection support
Users can set specified Admin commands or IO commands with
error status, when submitting new commands which are already
set with error status, the commands will return to the caller
with specified error code. So that users can emulate some error
status for their error condition code path.

Change-Id: I4b93c7e4f2b15a659da73b39e26bfa162eb5214e
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/410870
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2018-06-22 17:26:34 +00:00
Daniel Verkamp
841f0beae5 nvme/rdma: set timeout fields for RDMA requests
Change-Id: I7c3969c479c4fa1017423515b27d8db187142420
Fixes: 6b504fda5d ("nvme/rdma: add timeout support to RDMA transport")
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/416245
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2018-06-21 16:46:51 +00:00
Ben Walker
cd82151eba nvme: Allow calling spdk_nvme_ctrlr_set_default_opts prior to connect
Change-Id: Id0408e571362527e7c2d4759223946a0b4d7c675
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/415896
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-06-20 17:50:09 +00:00
Daniel Verkamp
5df15facd2 nvme: add path status codes (TP 4028)
Change-Id: Ifac14f74f6b7681fccbf463f744d145ae8299240
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/415892
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
2018-06-19 23:34:06 +00:00
Xiaodong Liu
5fc12ae9e2 ocssd: check whether ctrlr support ocssd
There isn't a standardized way to identify Open-Channel
SSD, different verdors may have different conditions.
Here just take the Qemu simulated OCSSD device as a
start.

Change-Id: I1aceaac09db438c203875bcf37badd542618bdd7
Signed-off-by: Xiaodong Liu <xiaodong.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/411590
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jakub Radtke <jakub.radtke@intel.com>
2018-06-14 23:09:42 +00:00
Daniel Verkamp
6b504fda5d nvme/rdma: add timeout support to RDMA transport
Change-Id: I3e53773570e66c1f52a6c29c6709684fc393717e
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/414883
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-06-14 03:56:07 +00:00
Daniel Verkamp
d65c23b9bb nvme/rdma: track list of outstanding requests
This will be used to check timeouts.

Change-Id: Ib3cabd3c65a87ffac451e21ac5c786403298c346
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/414882
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2018-06-14 03:56:07 +00:00
Daniel Verkamp
bc165a2664 nvme/rdma: convert rqpair free_reqs to a TAILQ
Future patches will need to remove elements from the middle of the list,
so a singly-linked list won't be efficient.

Change-Id: Idad5df3aea08d58fef2e19770509363441f757c7
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/414881
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2018-06-14 03:56:07 +00:00
Jakub Radtke
b3497d5da7 nvme: add Get/Set Feature wrappers with NSID
Some features are per namespace and require a namespace ID; the existing
get/set feature functions do not allow passing NSID, so add new API
functions that do:
* spdk_nvme_ctrlr_cmd_get_feature_ns
* spdk_nvme_ctrlr_cmd_set_feature_ns

Change-Id: Ia7dc96e57badf1a56489785fb288493592b58b80
Signed-off-by: Jakub Radtke <jakub.radtke@intel.com>
Reviewed-on: https://review.gerrithub.io/414706
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2018-06-12 17:59:33 +00:00
Jakub Radtke
caac0ed9e8 ocssd: nvme driver public API extension for Open-Channel
This patch adds to nvme driver new public API dedicated for
Open-Channel:
* spdk_nvme_ocssd_ctrlr_cmd_geometry

Change-Id: I69592618d9bcc280346258e771195683d5b33893
Signed-off-by: Jakub Radtke <jakub.radtke@intel.com>
Reviewed-on: https://review.gerrithub.io/412816
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Xiaodong Liu <xiaodong.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-06-12 17:59:33 +00:00
Xiaodong Liu
5f1c1189fa nvme: add PI to spdk_nvme_ns_cmd_read/writev()
apptag and its mask are required to set proper PI
elements in nvme read/write cmds.

Change-Id: Ibabc4738f637d13ea16246d5e77e7d045f032af8
Signed-off-by: Xiaodong Liu <xiaodong.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/414786
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Young Tack Jin <youngtack.jin@circuitblvd.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-06-12 17:40:32 +00:00
Changpeng Liu
967339f3e5 nvme: factor out qpair destruction function
Factor qpair destruction function so that we can put common
resource release together in future.

Change-Id: I44139947820c2a384b745ae2673799f1b736369c
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/412604
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-06-08 00:26:05 +00:00
Daniel Verkamp
8b158aaacd nvme: factor out request timeout checking
This will be used in other transports as well.

Change-Id: I05026b0dfea2647d61a173379aca368ca48a2f52
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/413864
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-06-07 15:46:50 +00:00
Daniel Verkamp
cdb3a594a8 nvme: ignore requests submitted before timeout set
If requests are in flight at the time a timeout callback is configured,
we can't retroactively get the submission time of those requests; treat
them as not having a timeout.

Change-Id: Ic589e874a0f2c8c7f4ce352afa7c3aea33b01fae
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/413863
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
2018-06-07 15:46:50 +00:00
Daniel Verkamp
e7b29a14c0 nvme: move timeout information to nvme_request
This is the first step toward timeout handling for other transports.

Change-Id: I386dd990f667d449e94ba4bcedaa3435743755fd
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/413862
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
2018-06-07 15:46:50 +00:00
Daniel Verkamp
1681a055f9 nvme/pcie: restore timeout checking on admin queue
This was partially fixed in commit ddeaeeec19 ("nvme: Only check
timeouts on requests from the same process"), but the function that
calls nvme_pcie_qpair_check_timeout() was also erroneously filtering out
the admin queue.  Restore the original behavior of checking all queue
types.

Change-Id: I26a44ff5eb772735d314ce7b8322ba9222675911
Fixes: 31bf5d795e ("nvme: make timeout function per process")
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/411628
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
2018-06-07 15:46:50 +00:00
Young Tack Jin
f52d800864 nvme: add metadata to spdk_nvme_ns_cmd_read/writev()
verified on QEMU NVMe for OCSSD 2.0 and RFC will be shared soon

Change-Id: I01c513e30768ac1961a5c5af20de3a2490da7729
Signed-off-by: Young Tack Jin <youngtack.jin@circuitblvd.com>
Reviewed-on: https://review.gerrithub.io/413854
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
2018-06-06 23:20:43 +00:00
Changpeng Liu
4c4c8ca269 nvme: don't reset controller when processing NS mangement commands
For attach/detach command, the identify namespace data should be
updated during the namespace attribute notice event callback, while
here, in case of the driver may not set aer callback, so update the
namespace identify same with attach command.

Change-Id: Ie594b2ff646a67488d03af2771c00f9947395aba
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/412884
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2018-06-06 20:02:16 +00:00
Daniel Verkamp
008c111b48 nvme/pcie: only set mmio_ctrlr around actual MMIO
When the shadow doorbell feature is enabled, no actual MMIO takes place
when a shadow update is sufficient; tighten the bounds of the updates to
g_thread_mmio_ctrlr in the two doorbell update locations so that we only
need to touch the thread-local variable when actual MMIO access is
required.

Change-Id: Ida974bec33f56cbb9f7d3611f483c6975ec773ab
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/413856
Tested-by: SPDK Automated Test System <sys_sgsw@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>
2018-06-06 17:10:09 +00:00
Daniel Verkamp
e83a62bf09 nvme: rename quirk from LIGHTNVM to OCSSD
This is consistent with the Open Channel naming we are using elsewhere.

Change-Id: Ib088359bed29a958f8b50e41cf34143a23429f54
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/413840
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
2018-06-06 01:45:36 +00:00
zkhatami88
0cdb08b0e0 env: add size parameter to spdk_mem_map_translate
Change-Id: I808101edaf4d75613baf19a950915f1d8e75b1af
Signed-off-by: zkhatami88 <z.khatami88@gmail.com>
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/413154
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Zahra Khatami <zahra.k.khatami@oracle.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2018-06-05 18:36:00 +00:00
Xiaodong Liu
c6ae008db5 lnvm: add a quirk for identify LightNVM device
Change-Id: I841d7b47bc85498abb608944587e7b7585138263
Signed-off-by: Xiaodong Liu <xiaodong.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/411588
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-06-04 03:31:46 +00:00
Jim Harris
13ed998697 nvme: make basic request functions static inline
This reduces submission+completion time by 10-15
core clocks per IO on an Intel Xeon Platinum
processor.  Similar improvements should be seen
on other processors as well.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I3241ba53ef5f21a8eef930b523a951525922e6b8

Reviewed-on: https://review.gerrithub.io/413284
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
2018-06-04 03:28:19 +00:00
Jim Harris
9c4679bc77 nvme: rename g_pid to g_spdk_nvme_pid
This variable will no longer be static in a future patch.
So make the name a bit more verbose since it will now
be visible outside of the module that defines it.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I5e720ef44aa5c5f38e0fe91de091a89b9970fcb7

Reviewed-on: https://review.gerrithub.io/413283
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
2018-06-04 03:28:19 +00:00
Jim Harris
d76cd984aa nvme: optimize nvme_allocate_request memsets
The memset was zeroing a lot of bytes that get
initialized either later in this function or elsewhere
in the submission code path.  Eliminating these
extra memsets saves a few nanoseconds of CPU overhead
in the NVMe submission path.

Note: one use of the cpl data member depended on
the nvme_allocate_request memset.  Since this use
case is not in the primary I/O path, just memset it
in that specific location before using it.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ife483a4d9c24c033cc7d26d94ec1700905a936f4
Reviewed-on: https://review.gerrithub.io/413153
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2018-06-01 21:01:42 +00:00
Daniel Verkamp
7dff719f7e nvme: optimize layout of struct nvme_payload
Rather than storing nvme_payload::type explicitly, use the SGL reset
function pointer as an indicator: if reset_sgl_fn is non-NULL, then the
payload is an SGL type; otherwise it is a contiguous buffer type.

This eliminates the one-byte type member from struct nvme_payload,
making it an even 32 bytes instead of 33, allowing the removal of the
awkward packing inside struct nvme_request.

Change-Id: If2a32437a23fe14eb5287e096ac060067296f1dd
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/413175
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2018-06-01 21:01:42 +00:00
Daniel Verkamp
caf85d8f23 nvme: add macros to populate nvme_payload
The definitions of these macros will change in an upcoming patch that
modifies the way nvme_payload is laid out.

Change-Id: Ic6edc18928542b07be7519a72bdbf6babbeb0131
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/413174
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2018-06-01 21:01:42 +00:00
Daniel Verkamp
5c2ccd0628 nvme: add helper function to get payload type
This will simplify upcoming patches that change the way nvme_payload
stores its type.

Change-Id: Idf0a5b8dfd7d66a10f89254d2c5c54fee2968a43
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/413173
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2018-06-01 21:01:42 +00:00
Changpeng Liu
be1c82b7a8 nvme: update the NS identify data according to AER
Number of Namespaces of controller identify structure
defines the maximum number of namespaces supported by
this controller, for physical NVMe controllers, the NN
is a fixed number, while here, we set the same rule for
NVMeoF controllers.

After NVMe driver got namespace notice event, it should
update the namespace identify data structure for NS
attach/detach commands.

Change-Id: Id72a2600a2ce9492fa2d6e09924667acbb77ae43
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/412883
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-05-30 17:28:03 +00:00
Piotr Pelplinski
fbf06aca1a nvme: fail when request is too long
Fail when number of child requests is >= NVME_MAX_CHILD_REQUESTS.

Signed-off-by: Piotr Pelplinski <piotr.pelplinski@intel.com>
Change-Id: I8c370053847c9f623b861137da8d2387a66fc030

Reviewed-on: https://review.gerrithub.io/408850
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Maciej Szwed <maciej.szwed@intel.com>
Reviewed-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-05-30 17:22:11 +00:00
Changpeng Liu
266f37a5a0 nvme: make response callback after moving completion queue head
For some cases, especially for Admin commands, there maybe has
recursive commands, e.g.: in AER callback we may send a new AER
request, in such case, the current code can't process such
case.  While here, move the completion queue head to next before
any response callback will fix such issue.

Change-Id: Ide56701d94615881790cf025ede2f07420b9b16e
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/412766
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2018-05-29 18:09:30 +00:00
Daniel Verkamp
c4bb0ea600 nvme: add helper to wait for internal commands
Factor out the common pattern of waiting for an internally-submitted
command to complete.  This will give us a convenient central place to
add error checking.

Change-Id: I65334d654d294cfb208fc86d16fa387ac5432254
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/412545
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
2018-05-28 01:43:55 +00:00
Ben Walker
99c8c6d8e1 nvme: Allow users to request which I/O command set they'd like to use
As of NVMe 1.3b, there is only one command set. But pipe
this through the driver per-spec anyway.

Change-Id: I4faf8596f5ce638e5e2a500b424e00ceb6e89edc
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/412102
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
2018-05-24 22:42:38 +00:00
Changpeng Liu
65e56caa17 nvme: wrapper request completion callback into a function
When IO is finished SPDK will trigger callback at controller layer,
while here, wrapper the completion callback into a function so
that we can add error injection at this function in following patch.

Change-Id: I7b7a6d278d87fd09a05f51f688398fdf2e9c4e05
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/411630
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-05-24 18:03:25 +00:00
Daniel Verkamp
955b295a58 nvme: make AER callback per-process
For the same reason as commit 31bf5d795e ("nvme: make timeout function
per process"), the AER callback also needs to be stored in the
per-process controller data structure.

Change-Id: I41425d81a2ab16c06ef9b900bef6a6128117fcb0
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/410953
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2018-05-22 18:17:43 +00:00
Daniel Verkamp
3148c48079 nvme/rdma: create per-process controller struct
The RDMA transport was not correctly registering new controllers on
creation.  RDMA doesn't support multi-process, but it still needs a
single per-process structure for the owning process.

Change-Id: I337ab9d00b468671e7c7a21175682beed4cfdd2e
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/410958
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-05-21 23:19:54 +00:00
Daniel Verkamp
943c7c69c3 nvme: hold ctrlr_lock when setting timeout callback
The per-process controller data may only be touched while holding the
ctrlr_lock.

Change-Id: I18c8c4e43db4d58e6b86f0c0fd222f6d30830b85
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/410952
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2018-05-21 18:22:50 +00:00
Daniel Verkamp
cbd9c241dc nvme: factor out process lookup into a function
Change-Id: I7598222db5d76c1a1578fbb5935d4348f7c62f54
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/410951
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2018-05-21 18:22:50 +00:00
Daniel Verkamp
f750c4ebb5 nvme: apply Identify CNS quirk to NS ID Descriptor
Avoid sending CNS values other than 0 and 1 to controllers with the
Identify CNS quirk added in commit 6442451b10 ("nvme: add a quirk for
identify 0x2").

This probably doesn't affect either of the controllers with the quirk in
practice, since this command is already only sent to controllers that
report NVMe version 1.3 or newer, but let's add the check anyway for
consistency.

Change-Id: I858c28ab7d43714c501dd22d6797259054f0f0a8
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/410941
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-05-17 23:11:35 +00:00
Young Tack Jin
6442451b10 nvme: add a quirk for identify 0x2
Change-Id: I9cfc237a8514a1d323313851e14576ba2ba69077
Signed-off-by: Young Tack Jin <youngtack.jin@circuitblvd.com>
Reviewed-on: https://review.gerrithub.io/410529
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-05-10 19:38:54 +00:00
Daniel Verkamp
ace321df22 nvme: add API to get maximum data transfer size
Change-Id: I8573732b3049e2a5b471e5a0313e39019fdaad5f
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/410518
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
2018-05-09 17:20:11 +00:00
Daniel Verkamp
f7b58aea2b nvme: capture VS register at init time
This will be used later instead of retrieving VS (potentially via a Get
property command for Fabrics) multiple times.

The Active NS List code was previously depending on the VER field of the
Identify Controller data, but this was only added with NVMe 1.2, so we
can't rely on it to detect NVMe 1.1 controllers; it is changed to use
the new cache VS value instead.

Change-Id: Iba9ed5ecbc82b4654973438d119daba0c4cf0724
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/408895
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2018-04-30 17:19:07 +00:00
Daniel Verkamp
b8edc465e2 nvme: check Optional Asynchronous Events Supported
In addition to checking for the required version, also use the OAES bits
to determine which features to request.

Change-Id: Idb07e4175cca5609904876bd17d912b50bc6b62a
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/409352
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
2018-04-27 23:11:20 +00:00
Changpeng Liu
f0f3a48f40 nvme: set AER configuration bits based on NVMe version
Change-Id: Ia2fd4d31560c9117b167cbf12d2749c303e4cb8c
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/408772
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-04-25 22:24:29 +00:00
Pawel Wodkowski
f9fae3f3a9 nvme: change num_children to be wider type
uint8_t is too small to handle huge payloads. 32M payload already
overflow this.

Change-Id: I083ba7d3ded25b99571d422b7a3a4e7653a8d231
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-on: https://review.gerrithub.io/408677
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-04-23 18:20:17 +00:00
Ben Walker
ddeaeeec19 nvme: Only check timeouts on requests from the same process
Change-Id: I80521c4c01daf033319f88cf273255387a7b5248
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/408403
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-04-20 16:23:36 -04:00
Daniel Verkamp
8e098e4190 nvme: verify remove_cb is non-NULL before calling
This fixes the VFIO hot-remove path, which called remove_cb without
checking to see if it had been specified by the user.  The normal uevent
removal path already checked for remove_cb.

Change-Id: I0ad8d2c90a77b16800a8b505cb69ea05b0706d70
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/408392
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2018-04-19 18:47:51 -04:00
Daniel Verkamp
3fa7c33ac1 nvme: require trid to be valid in nvme_ctrlr_probe
This is an internal NVMe driver function, so we don't need to allow for
the case where trid is NULL.  All callers already passed an address of a
local variable except the unit tests, which can be trivially fixed.

Fixes a static analyzer warning about trid being dereferenced in
nvme_transport_ctrlr_construct() before being checked for NULL in the
caller.

Change-Id: I2bfeb5c92a302093b7c7f2949adcd18baa11855a
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/408395
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-04-19 17:51:14 -04:00
Ben Walker
37ef0cca91 nvme: Don't expose admin qpair in timeout callbacks
This was broken by commit 31bf5d795

Change-Id: I8c81c7b76cd47db347ce9c3f8a0e8296b690cb49
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/408240
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-04-19 15:48:36 -04:00
Ben Walker
63fb2f772c nvme: Close file descriptor if controller fails to initialize
Change-Id: I9fee91ece79b204962a70fc49d9032abe2c55090
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/408218
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-04-18 15:35:12 -04:00
Jonathan Richardson
ce70f29662 nvme: Remove calls to getpid() when submitting nvme requests
As of glibc version 2.3.4 onwards getpid() is no longer cached. SPDK
makes calls to it in nvme_allocate_request() which is called for each
nvme request received. This results in a system calls up to millions of
times per second which slows down nvme submissions. Since the pid never
changes, it only needs to be called once in initialization per process.
This improves the performance of nvme_allocate_request() signficantly.

Change-Id: Idee0f06484d459906b9ce1d9b7360a33119c7e56
Signed-off-by: Jonathan Richardson <jonathan.richardson@broadcom.com>
Signed-off-by: Scott Branden <scott.branden@broadcom.com>
Reviewed-by: Ray Jui <ray.jui@broadcom.com>
Reviewed-on: https://review.gerrithub.io/407599
Reviewed-by: Scott Branden <sbranden@gmail.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-04-16 16:19:44 -04:00
Daniel Verkamp
fa6f7a166d nvme: improve error messages in set_num_qpairs
The functions they were referring to have been renamed; rather than
fixing up the function names, use the spec-defined NVMe command names so
it's more understandable. (The second message was also incorrectly
referring to "set" instead of "get", which is fixed as well.)

Change-Id: Id140a91c837d8c913760d2f55318472689c00f45
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/407593
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
2018-04-16 12:31:26 -04:00
Daniel Verkamp
453c804d1b nvme: continue initialization even if NN=0
Similar to the previous patch, some controllers may report 0 namespaces;
we should still be able to send admin commands in this situation.

Change-Id: Ia14e3ce773c63e645199e1c40ba5b37095da2473
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/407497
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-04-13 15:59:00 -04:00
Daniel Verkamp
c9ef7642c9 nvme: make set_num_qpairs failure non-fatal
A controller that fails the Set Features/Get Features - Number of Queues
won't be able to create I/O queues, but it may still accept admin
commands.

Change-Id: Iec79d641f7d460448a8d8e1295764f1f03f98594
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/407378
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-04-13 15:59:00 -04:00
Ziye Yang
31bf5d795e nvme: make timeout function per process
Change-Id: I6e58baaeb09580b5f70e1acf5323376ca0b26bbf
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/407382
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2018-04-13 12:30:51 -04:00
Ben Walker
aedbb3b81a nvme: Rmove all uses of strncpy
strncpy is going to be added to the list of banned functions because
it does not guarantee strings are null terminated.

Change-Id: Ic18623c281cca7c3d87732bc7677b284d57685c8
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/407023
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-04-12 13:45:04 -04:00
Changpeng Liu
2d192cf8fb nvme: use AER configuation structure when starting controller
Change-Id: I79dad84d1dc58e61eb36b461b41fbd7ee73631fc
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/406899
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-04-10 15:43:38 -04:00
Daniel Verkamp
be4ac912a1 nvme/rdma: improve nvme_rdma_get_event() message
Add the event status code to assist in debugging, and reorder the
message so it is easier to read.

Change-Id: I2a1fb900471a482707fbfb6db84bc81cb3b0cdad
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/406636
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-04-06 18:30:58 -04:00
Ed Rodriguez
06fbf4b34b nvme: Use active namespace list for enumerating namespaces
- Add support for multi page CNS 0x2
 - Use CNS value 0x02 (SPDK_NVME_IDENTIFY_ACTIVE_NS_LIST)
   to query active namespaces
 - Add an API to iterate the active list

Change-Id: Iea524881fa6e3610a7d85ab02a2005a92fd633df
Signed-off-by: John Meneghini <johnm@netapp.com>
Reviewed-on: https://review.gerrithub.io/401957
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-04-02 17:17:40 -04:00
Daniel Verkamp
cdaf4fd922 nvme/rdma: re-use memory registrations if possible
We don't need to re-register memory with the same ibv protection domain
more than once; maintain a global list of already-registered PDs and
reuse the existing registration for other queues.

Change-Id: I7ec9c35ed93083faa00cca4cb5c61104200a4c66
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/405702
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-03-30 17:37:15 -04:00
Daniel Verkamp
a78ddd8231 nvme: add function to get PCI device from ctrlr
This allows us to remove most uses of spdk_pci_get_device(), which looks
up a PCI device structure from an arbitrary PCI address.  This function
is problematic, since it uses internal DPDK data structures that aren't
meant to be part of the public API.  There is still one use in the
codebase, which will be cleaned up in another patch.

Change-Id: Ia1fe1f799c240195f6871c1d92821074f884c4e6
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/405707
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-03-29 01:46:43 -04:00
Daniel Verkamp
15bd6999db nvme: add spdk_nvme_ns_get_uuid() function
This function retrieves the UUID from a namespace, if available.

Change-Id: I98c55375948b92eaf429b41fb36dfea4e2b780a2
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/404734
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-03-27 02:43:46 -04:00
Daniel Verkamp
3d57e4a8f4 nvme: unify Identify command helpers
Convert nvme_ctrlr_cmd_identify_controller() and
nvme_ctrlr_cmd_identify_namespace() into a single function,
nvme_ctrlr_cmd_identify(), with generic parameters that should be
suitable for all current callers as well as future users.

These functions were internal-only, so there is no public API change.

Change-Id: I3dbb3e6b00308b67ba1f161f8a6b11b6333fca57
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/404733
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-03-27 02:43:46 -04:00
Daniel Verkamp
c937fab3cb nvme: use uint32_t consistently for NSID values
A few places were accidentally storing namespace IDs in uint16_t.

Change-Id: Iae9d709fb20bc1ac0a584ccd9683b721ce5de961
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/403886
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-03-16 14:15:08 -04:00
Daniel Verkamp
4c06ce9b9d util: add uuid.h to wrap libuuid
This lets us have a common place to put definitions like the length of
the UUID string, as well as abstract away some of the API warts in
libuuid (non-const values, no size checking for uuid_unparse, etc.).

Change-Id: I80607fcd21ce57fdbb8729442fbb721bc71ccb98
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/402176
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
2018-03-08 10:49:51 -05:00
Daniel Verkamp
8a6ba58cb4 scripts/check_format: check for spaces before tabs
Automatically detect more whitespace errors.

All existing cases are fixed; only whitespace change (verify with
diff -w) except for one comment style fixup in include/spdk/nvme.h.

Change-Id: If750e54b9c8e3421ea6feda5f20184a31431631e
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/402360
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
2018-03-05 11:09:13 -05:00
Stephen Bates
627bee96a4 nvme_pci: Correct bug in CMB allocation
There was a bug reported by Cunyin Chang with regards to how the
cmb_current_offset was calculated when the CMB offset into the CMB BAR
is non-zero. This patch fixes this issue and also fixes the problem
that the last valid offset into the BAR *may* differ if registration
is utilized or not (due to the 2MiB alignment and length requirements
for registered memory).

Change-Id: Id08d6a5a40b828338f6a66599171cc8dd59768a3
Signed-off-by: Stephen Bates <sbates@raithlin.com>
Reviewed-on: https://review.gerrithub.io/401832
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-03-02 13:31:48 -05:00
Pawel Wodkowski
1186c5e707 nvme: free children recursively
Fixes #242

Change-Id: I5ad89e64bcb505522db907ad39c2afb055f511cf
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-on: https://review.gerrithub.io/400943
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-02-23 15:35:32 -05:00
Pan Liu
e51a07dfa1 nvme: add transport id to some log messages
Change-Id: I02ca8aed1bba1922a69a9b22bca22bce06e9c55f
Signed-off-by: Pan Liu <liupan1111@gmail.com>
Reviewed-on: https://review.gerrithub.io/399536
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-02-23 15:28:11 -05:00
Daniel Verkamp
a601c0b2e0 nvme: add debug logs for matched quirks
This can be enabled with -t nvme in debug builds.

Change-Id: I4392d0a7decd65cc567fdf6fd56cac6db0424cd8
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/401052
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-02-23 10:07:39 -05:00
Daniel Verkamp
184ecc4e65 nvme: fix return value of nvme_get_quirks()
This function returns uint64_t, but the existing code was returning
the bool 'false' (which is also 0, so there is no functional change).

Change-Id: I546b15974c2d9e4107efe262950e3eb5613e0e9f
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/401051
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-02-23 10:07:39 -05:00
Daniel Verkamp
d81f3dfd3e util: add spdk_mem_all_zero() function
Unify several similar functions checking for a buffer of all zero bytes
into the util library.

Change-Id: Idfbeffa22add34ac9ed1bd75ee27d6bd8b188940
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/400892
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-02-23 10:05:32 -05:00
Ehud Naim
c83cd9375b nvme: fixing ctrlr mutex free
adding nvme_ctrlr_destruct_finish because nvme_transport_ctrlr_destruct may
use a destroyed mutex.

nvme_ctrlr_destruct() free "ctrlr_lock" and after that call
nvme_transport_ctrlr_destruct()->nvme_pcie_ctrlr_destruct()(with pci)->
nvme_ctrlr_proc_get_devhandle()->nvme_robust_mutex_lock(&ctrlr->ctrlr_lock);

Change-Id: I55714ea9097d2c9d844a00b5a88fa2d51a3f4469
Signed-off-by: Ehud Naim <ehudn@marvell.com>
Reviewed-on: https://review.gerrithub.io/399605
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-02-20 12:31:34 -05:00
Daniel Verkamp
3839639759 nvme: add API to allocate CMB I/O buffers
Change-Id: I2a3c7a272dc08be5a5ecb4339622816482c4cbb0
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Signed-off-by: Stephen Bates <sbates@raithlin.com>
Reviewed-on: https://review.gerrithub.io/397036
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
2018-02-12 19:11:44 -05:00
Daniel Verkamp
f185e4ecf8 nvme/pcie: register CMB with spdk_mem_register()
Enable address translation for I/O buffers within the controller memory
buffer region by registering the CMB using spdk_mem_register().

Change-Id: I44829757ad15fbc3ea96fa494b9fb32dd67a7138
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Signed-off-by: Stephen Bates <sbates@raithlin.com>
Reviewed-on: https://review.gerrithub.io/397035
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
2018-02-12 19:11:44 -05:00
Daniel Verkamp
5e86c80951 nvme/pcie: limit max completions based on queue size
For a given hardware queue size, only allow a quarter of the queue size
to be returned as completions in a single call to
spdk_nvme_qpair_process_completions(), and adjust num_trackers to match
so that num_trackers + max_completions_cap doesn't exceed the hardware
completion queue size.  This ensures that there is room in the
completion queue if new I/O is issued in response to completions before
we ring the completion queue doorbell.

The choice of 1/4 queue size is arbitrary; this seems to be a good
compromise between completion batch size and number of trackers.

Change-Id: I2c5aad7b98bfc8b33e53242240b2c9254fa05b4e
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/393529
Tested-by: SPDK Automated Test System <sys_sgsw@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>
2018-01-05 12:45:28 -05:00
Pawel Wodkowski
891c12a63c util: add spdk_strerror() wrapper with TLS support
This patch remove need for additional buffer when translating error code
to string.

Change-Id: Iaa60088b5c450581d3cdddbb425119b17d55a44b
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/386114
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-01-04 15:00:09 -05:00
Daniel Verkamp
543cb17248 build: remove $(ENV_CFLAGS) where not necessary
Only Makefiles for libraries that directly depend on DPDK (rather than
the SPDK env abstraction) should add $(ENV_CFLAGS).

Change-Id: Ifdf44d3ef8c42bbf7f20edd524b330d00658235b
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/392818
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-01-03 12:05:59 -05:00
Changpeng Liu
381af5775f nvme: re-enable the separate metadata support in nvme driver
Commit ID "269910c0" removed the support of separate metadata,
for those controllers which can support this feature, SPDK driver
can't be used. SPDK provides APIs such as:
spdk_nvme_ctrlr_cmd_io_raw_with_md/spdk_nvme_ns_cmd_write_with_md/
spdk_nvme_ns_cmd_read_with_md, which can support separate metadata.
While here, re-enable this feature with this commit.

Change-Id: If77c21e9ac700c4b334548ebfa7e8e6286285a64
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/392440
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2017-12-21 13:21:55 -05:00