Jason Gunthorpe [Tue, 9 Jul 2019 12:44:47 +0000 (09:44 -0300)]
RDMA/core: Make rdma_counter.h compile stand alone
5.4-rc1 will have new compile time debugging to test that headers can be
compiled stand alone. Many rdma headers are already broken and excluded
from the mechanism, however to avoid compile failures during the merge
window fix enough so that the newly added header compiles clean.
Fixes: 413d3347503b ("RDMA/counter: Add set/clear per-port auto mode support") Reported-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com> Signed-off-by: Mark Zhang <markz@mellanox.com>
IB/core: Work on the caller socket net namespace in nldev_newlink()
While creating new RDMA devices based on netdevice name, consider the net
namespace of the caller skb's socket similar to rest of the doit()
callbacks and nldev_dellink() which deletes the RDMA device created using
nldev_newlink().
Fixes: 3856ec4b93c94 ("RDMA/core: Add RDMA_NLDEV_CMD_NEWLINK/DELLINK support") Signed-off-by: Parav Pandit <parav@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Reviewed-by: Jason Gunthorpe <jgg@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
RDMA/rxe: Fill in wc byte_len with IB_WC_RECV_RDMA_WITH_IMM
Calculate the correct byte_len on the receiving side when a work
completion is generated with IB_WC_RECV_RDMA_WITH_IMM opcode.
According to the IBA byte_len must indicate the number of written bytes,
whereas it was always equal to zero for the IB_WC_RECV_RDMA_WITH_IMM
opcode, even though data was transferred.
Fixes: 8700e3e7c485 ("Soft RoCE driver") Signed-off-by: Konstantin Taranov <konstantin.taranov@inf.ethz.ch> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Added the interface in the infiniband driver that applies the rdma_dim
adaptive moderation. There is now a special function for allocating an
ib_cq that uses rdma_dim.
Performance improvement (ConnectX-5 100GbE, x86) running FIO benchmark over
NVMf between two equal end-hosts with 56 cores across a Mellanox switch
using null_blk device:
The rdma_dim algorithm was designed to measure the effectiveness of
moderation on the flow in a general way and thus should be appropriate
for all RDMA storage protocols.
rdma_dim is configured to be the default option based on performance
improvement seen after extensive tests.
Signed-off-by: Yamin Friedman <yaminf@mellanox.com> Reviewed-by: Max Gurtovoy <maxg@mellanox.com> Reviewed-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
RDMA DIM implements a different algorithm from net DIM and is based on
completions which is how we can implement interrupt moderation in RDMA.
The algorithm optimizes for number of completions and ratio between
completions and events. In order to avoid long latencies, the
implementation performs fast reduction of moderation level when the
traffic changes.
Signed-off-by: Yamin Friedman <yaminf@mellanox.com> Reviewed-by: Max Gurtovoy <maxg@mellanox.com> Reviewed-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Jason Gunthorpe [Mon, 8 Jul 2019 17:58:59 +0000 (14:58 -0300)]
Merge tag 'blk-dim-v2' into rdma.git for-next
Generic DIM
From: Tal Gilboa and Yamin Fridman
Implement net DIM over a generic DIM library, add RDMA DIM
dim.h lib exposes an implementation of the DIM algorithm for
dynamically-tuned interrupt moderation for networking interfaces.
We want a similar functionality for other protocols, which might need to
optimize interrupts differently. Main motivation here is DIM for NVMf
storage protocol.
Current DIM implementation prioritizes reducing interrupt overhead over
latency. Also, in order to reduce DIM's own overhead, the algorithm might
take some time to identify it needs to change profiles. While this is
acceptable for networking, it might not work well on other scenarios.
Here we propose a new structure to DIM. The idea is to allow a slightly
modified functionality without the risk of breaking Net DIM behavior for
netdev. We verified there are no degradations in current DIM behavior with
the modified solution.
Suggested solution:
- Common logic is implemented in lib/dim/dim.c
- Net DIM (existing) logic is implemented in lib/dim/net_dim.c, which uses
the common logic in dim.c
- Any new DIM logic will be implemented in "lib/dim/new_dim.c".
This new implementation will expose modified versions of profiles,
dim_step() and dim_decision().
- DIM API is declared in include/linux/dim.h for all implementations.
Pros for this solution are:
- Zero impact on existing net_dim implementation and usage
- Relatively more code reuse (compared to two separate solutions)
- Increased extensibility
IB/mlx5: Report correctly tag matching rendezvous capability
Userspace expects the IB_TM_CAP_RC bit to indicate that the device
supports RC transport tag matching with rendezvous offload. However the
firmware splits this into two capabilities for eager and rendezvous tag
matching.
Only if the FW supports both modes should userspace be told the tag
matching capability is available.
Cc: <stable@vger.kernel.org> # 4.13 Fixes: eb761894351d ("IB/mlx5: Fill XRQ capabilities") Signed-off-by: Danit Goldberg <danitg@mellanox.com> Reviewed-by: Yishai Hadas <yishaih@mellanox.com> Reviewed-by: Artemy Kovalyov <artemyko@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
docs: infiniband: add it to the driver-api bookset
While this contains some uAPI stuff, it was intended to be read by a
kernel doc. So, let's not move it to a different dir, but, instead, just
add it to the driver-api bookset.
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Jason Gunthorpe [Mon, 8 Jul 2019 16:48:55 +0000 (13:48 -0300)]
Merge branch 'vhca-tunnel' into rdma.git for-next
Max Gurtovoy says:
====================
Those two patches introduce VHCA tunnel mechanism to DEVX interface
needed for Bluefield SOC. See extensive commit messages for more
information.
====================
Based on the mlx5-next branch from
git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux for
dependencies
Max Gurtovoy [Mon, 1 Jul 2019 18:14:02 +0000 (21:14 +0300)]
IB/mlx5: Implement VHCA tunnel mechanism in DEVX
This mechanism will allow function-A to perform operations "on behalf" of
function-B via tunnel object. Function-A will have privileges for creating
and using this tunnel object.
For example, in the device emulation feature presented in Bluefield-1 SoC,
using device emulation capability, one can present NVMe function to the
host OS.
Since the NVMe function doesn't have a normal command interface to the HCA
HW, here is a need to create a channel that will be able to issue commands
"on behalf" of this function.
This channel is the VHCA_TUNNEL general object. The emulation software
will create this tunnel for every managed function and issue commands via
devx general cmd interface using the appropriate tunnel ID. When devX
context will receive a command with non-zero vhca_tunnel_id, it will pass
the command as-is down to the HCA.
All the validation, security and resource tracking of the commands and the
created tunneled objects is in the responsibility of the HCA FW. When a
VHCA_TUNNEL object destroyed, the device will issue an internal
FLR (function level reset) to the emulated function associated with this
tunnel. This will destroy all the created resources using the tunnel
mechanism.
Signed-off-by: Max Gurtovoy <maxg@mellanox.com> Reviewed-by: Yishai Hadas <yishaih@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Jason Gunthorpe [Mon, 8 Jul 2019 15:17:48 +0000 (12:17 -0300)]
RDMA/rvt: Do not use a kernel header in the ABI
rvt was using ib_sge as part of it's ABI, which is not allowed. Introduce
a new struct with the same layout and use it instead.
Fixes: dabac6e460ce ("IB/hfi1: Move receive work queue struct into uapi directory") Reported-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Xi Wang [Mon, 24 Jun 2019 11:47:51 +0000 (19:47 +0800)]
RDMA/hns: Fixs hw access invalid dma memory error
When smmu is enable, if execute the perftest command and then use 'kill
-9' to exit, follow this operation repeatedly, the kernel will have a high
probability to print the following smmu event:
This is because the hw will periodically refresh the qpc cache until the
next reset.
This patch fixed it by removing the action that release qpc memory in the
'hns_roce_qp_free' function.
Fixes: 9a4435375cd1 ("IB/hns: Add driver files for hns RoCE driver") Signed-off-by: Xi Wang <wangxi11@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Lijun Ou [Mon, 24 Jun 2019 11:47:49 +0000 (19:47 +0800)]
RDMA/hns: Bugfix for calculating qp buffer size
The buffer size of qp which used to allocate qp buffer space for storing
sqwqe and rqwqe will be the length of buffer space. The kernel driver will
use the buffer address and the same size to get the user memory. The same
size named buff_size of qp. According the algorithm of calculating, The
size of the two is not equal when users set the max sge of sq.
Fixes: b28ca7cceff8 ("RDMA/hns: Limit extend sq sge num") Signed-off-by: Lijun Ou <oulijun@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Max Gurtovoy [Mon, 1 Jul 2019 18:14:01 +0000 (21:14 +0300)]
net/mlx5: Introduce VHCA tunnel device capability
When using the device emulation feature (introduced in Bluefield-1 SOC),
a privileged function (the device emulation manager) will be able to
create a channel to execute commands on behalf of the emulated function.
This channel will be a general object of type VHCA_TUNNEL that will have
a unique ID for each emulated function. This ID will be passed in each
cmd that will be issued by the emulation SW in a well known offset in
the command header.
This channel is needed since the emulated function doesn't have a normal
command interface to the HCA HW, but some basic configuration for that
function is needed (e.g. initialize and enable the HCA). For that matter,
a specific command-set was defined and only those commands will be issued
by the HCA.
Signed-off-by: Max Gurtovoy <maxg@mellanox.com> Reviewed-by: Yishai Hadas <yishaih@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Lang Cheng [Mon, 24 Jun 2019 11:47:48 +0000 (19:47 +0800)]
RDMA/hns: Set reset flag when hw resetting
When hw resetting, there is no response from hw when driver sending cmdq.
If driver still send cmdq to hw, the reset process may be blocked. So
reset flag should be set to intercept the cmdq command when driver
receiving "notify down" signal.
Signed-off-by: Lang Cheng <chenglang@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Yangyang Li [Mon, 24 Jun 2019 11:47:47 +0000 (19:47 +0800)]
RDMA/hns: Modify ba page size for cqe
Currently, the depth of cq only supports 64K. According to the UM, the
depth of cq is up to 4M, Therefore the ba page size of cqe was modified to
support the maximum specification of cq depth.
Signed-off-by: Yangyang Li <liyangyang20@huawei.com> Signed-off-by: Lijun Ou <oulijun@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Lijun Ou [Mon, 24 Jun 2019 11:47:45 +0000 (19:47 +0800)]
RDMA/hns: Bugfix for cleaning mtr
It uses hns_roce_mtr_init in hns_roce_create_qp_common function. As a
result, it should use hns_roce_mtr_cleanup function for cleaning mtr when
destroying qp.
Fixes: 8d18ad83f19b ("RDMA/hns: Fix bug when wqe num is larger than 16K") Signed-off-by: Xi Wang <wangxi11@huawei.com> Signed-off-by: Lijun Ou <oulijun@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Mark Zhang [Tue, 2 Jul 2019 10:02:45 +0000 (13:02 +0300)]
RDMA/nldev: Allow get counter mode through RDMA netlink
Provide an option to get current counter mode through RDMA netlink.
Signed-off-by: Mark Zhang <markz@mellanox.com> Reviewed-by: Majd Dibbiny <majd@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Mark Zhang [Tue, 2 Jul 2019 10:02:44 +0000 (13:02 +0300)]
RDMA/nldev: Allow counter manual mode configration through RDMA netlink
Provide an option to allow users to manually bind a qp with a counter
through RDMA netlink. Limit it to users with ADMIN capability only.
Signed-off-by: Mark Zhang <markz@mellanox.com> Reviewed-by: Majd Dibbiny <majd@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Mark Zhang [Tue, 2 Jul 2019 10:02:43 +0000 (13:02 +0300)]
RDMA/counter: Allow manual mode configuration support
In manual mode a QP is bound to a counter manually. If counter is not
specified then a new one will be allocated.
Manual mode is enabled when user binds a QP, and disabled when the last
manually bound QP is unbound.
When auto-mode is turned off and there are counters left, manual mode is
enabled so that the user is able to access these counters.
Signed-off-by: Mark Zhang <markz@mellanox.com> Reviewed-by: Majd Dibbiny <majd@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Mark Zhang [Tue, 2 Jul 2019 10:02:42 +0000 (13:02 +0300)]
RDMA/core: Get sum value of all counters when perform a sysfs stat read
Since a QP can only be bound to one counter, then if it is bound to a
separate counter, for backward compatibility purpose, the statistic value
must be:
* stat of default counter
+ stat of all running allocated counters
+ stat of all deallocated counters (history stats)
Signed-off-by: Mark Zhang <markz@mellanox.com> Reviewed-by: Majd Dibbiny <majd@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Mark Zhang [Tue, 2 Jul 2019 10:02:41 +0000 (13:02 +0300)]
IB/mlx5: Add counter_alloc_stats() and counter_update_stats() support
Add support for ib callback counter_alloc_stats() and
counter_update_stats().
Signed-off-by: Mark Zhang <markz@mellanox.com> Reviewed-by: Majd Dibbiny <majd@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Mark Zhang [Tue, 2 Jul 2019 10:02:40 +0000 (13:02 +0300)]
RDMA/netlink: Implement counter dumpit calback
This patch adds the ability to return all available counters together with
their properties and hwstats.
Signed-off-by: Mark Zhang <markz@mellanox.com> Reviewed-by: Majd Dibbiny <majd@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Mark Zhang [Tue, 2 Jul 2019 10:02:39 +0000 (13:02 +0300)]
RDMA/nldev: Allow counter auto mode configration through RDMA netlink
Provide an option to enable/disable per-port counter auto mode through
RDMA netlink. Limit it to users with ADMIN capability only.
Signed-off-by: Mark Zhang <markz@mellanox.com> Reviewed-by: Majd Dibbiny <majd@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Mark Zhang [Tue, 2 Jul 2019 10:02:38 +0000 (13:02 +0300)]
IB/mlx5: Support statistic q counter configuration
Add support for ib callbacks counter_bind_qp(), counter_unbind_qp() and
counter_dealloc().
Signed-off-by: Mark Zhang <markz@mellanox.com> Reviewed-by: Majd Dibbiny <majd@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Mark Zhang [Tue, 2 Jul 2019 10:02:37 +0000 (13:02 +0300)]
IB/mlx5: Add counter set id as a parameter for mlx5_ib_query_q_counters()
Add counter set id as a parameter so that this API can be used for
querying any q counter.
Signed-off-by: Mark Zhang <markz@mellanox.com> Reviewed-by: Majd Dibbiny <majd@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Mark Zhang [Tue, 2 Jul 2019 10:02:36 +0000 (13:02 +0300)]
IB/mlx5: Support set qp counter
Support bind a qp with counter. If counter is null then bind the qp to the
default counter. Different QP state has different operation:
- RESET: Set the counter field so that it will take effective during
RST2INIT change;
- RTS: Issue an RTS2RTS change to update the QP counter;
- Other: Set the counter field and mark the counter_pending flag, when QP
is moved to RTS state and this flag is set, then issue an RTS2RTS
modification to update the counter.
Signed-off-by: Mark Zhang <markz@mellanox.com> Reviewed-by: Majd Dibbiny <majd@mellanox.com> Acked-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Mark Zhang [Tue, 2 Jul 2019 10:02:35 +0000 (13:02 +0300)]
RDMA/counter: Add "auto" configuration mode support
In auto mode all QPs belong to one category are bind automatically to a
single counter set. Currently only "qp type" is supported.
In this mode the qp counter is set in RST2INIT modification, and when a qp
is destroyed the counter is unbound.
Signed-off-by: Mark Zhang <markz@mellanox.com> Reviewed-by: Majd Dibbiny <majd@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Mark Zhang [Tue, 2 Jul 2019 10:02:34 +0000 (13:02 +0300)]
RDMA/counter: Add set/clear per-port auto mode support
Add an API to support set/clear per-port auto mode.
Signed-off-by: Mark Zhang <markz@mellanox.com> Reviewed-by: Majd Dibbiny <majd@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Mark Zhang [Tue, 2 Jul 2019 10:02:33 +0000 (13:02 +0300)]
RDMA/restrack: Make is_visible_in_pid_ns() as an API
Remove is_visible_in_pid_ns() from nldev.c and make it as a restrack API,
so that it can be taken advantage by other parts like counter.
Signed-off-by: Mark Zhang <markz@mellanox.com> Reviewed-by: Majd Dibbiny <majd@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Mark Zhang [Tue, 2 Jul 2019 10:02:32 +0000 (13:02 +0300)]
RDMA/restrack: Add an API to attach a task to a resource
Add rdma_restrack_attach_task() which is able to attach a task other then
"current" to a resource.
Signed-off-by: Mark Zhang <markz@mellanox.com> Reviewed-by: Majd Dibbiny <majd@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Mark Zhang [Tue, 2 Jul 2019 10:02:31 +0000 (13:02 +0300)]
RDMA/restrack: Introduce statistic counter
Introduce statistic counter as a new resource. It allows a user to monitor
specific objects (e.g., QPs) by binding to a counter.
In some cases a user counter resource is created with task other then
"current", because its creation is done as part of rdmatool call.
Signed-off-by: Mark Zhang <markz@mellanox.com> Reviewed-by: Majd Dibbiny <majd@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Jason Gunthorpe [Fri, 5 Jul 2019 13:16:19 +0000 (10:16 -0300)]
Merge mlx5-next into rdma for-next
From git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux
Required for dependencies in the next patches.
* mlx5-next:
net/mlx5: Add rts2rts_qp_counters_set_id field in hca cap
net/mlx5: Properly name the generic WQE control field
net/mlx5: Introduce TLS TX offload hardware bits and structures
net/mlx5: Refactor mlx5_esw_query_functions for modularity
net/mlx5: E-Switch prepare functions change handler to be modular
net/mlx5: Introduce and use mlx5_eswitch_get_total_vports()
Daniel Kranzdorf [Sun, 30 Jun 2019 14:53:02 +0000 (17:53 +0300)]
RDMA/efa: Entropy in admin commands id
Make admin commands id easier to distinguish by using relevant bits from
the producer counter.
This allows us to differentiate admin commands with the same producer
index (happens after admin queue overlap), which is helpful when
debugging.
Signed-off-by: Daniel Kranzdorf <dkkranzd@amazon.com> Reviewed-by: Firas JahJah <firasj@amazon.com> Reviewed-by: Yossi Leybovich <sleybo@amazon.com> Signed-off-by: Gal Pressman <galpress@amazon.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Valentine Fatiev [Sun, 30 Jun 2019 13:48:41 +0000 (16:48 +0300)]
IB/ipoib: Add child to parent list only if device initialized
Despite failure in ipoib_dev_init() we continue with initialization flow
and creation of child device. It causes to the situation where this child
device is added too early to parent device list.
Change the logic, so in case of failure we properly return error from
ipoib_dev_init() and add child only in success path.
Fixes: eaeb39842508 ("IB/ipoib: Move init code to ndo_init") Signed-off-by: Valentine Fatiev <valentinef@mellanox.com> Reviewed-by: Feras Daoud <ferasda@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Reviewed-by: Jason Gunthorpe <jgg@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Colin Ian King [Thu, 4 Jul 2019 12:50:27 +0000 (13:50 +0100)]
RDMA/uverbs: remove redundant assignment to variable ret
The variable ret is being initialized with a value that is never read and
it is being updated later with a new value. The initialization is
redundant and can be removed.
Addresses-Coverity: ("Unused value") Signed-off-by: Colin Ian King <colin.king@canonical.com> Reviewed-by: Jason Gunthorpe <jgg@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Lijun Ou [Thu, 4 Jul 2019 06:22:58 +0000 (14:22 +0800)]
RDMA/hns: Fix building modular hns
The patch below wasn't fully tested for all combinations of module and
configs, and causes a compile failure:
WARNING: modpost: missing MODULE_LICENSE() in drivers/infiniband/hw/hns/hns_roce_ah.o
see include/linux/module.h for more information
WARNING: modpost: missing MODULE_LICENSE() in drivers/infiniband/hw/hns/hns_roce_alloc.o
see include/linux/module.h for more information
WARNING: modpost: missing MODULE_LICENSE() in drivers/infiniband/hw/hns/hns_roce_cmd.o
see include/linux/module.h for more information
WARNING: modpost: missing MODULE_LICENSE() in drivers/infiniband/hw/hns/hns_roce_cq.o
see include/linux/module.h for more information
WARNING: modpost: missing MODULE_LICENSE() in drivers/infiniband/hw/hns/hns_roce_db.o
see include/linux/module.h for more information
WARNING: modpost: missing MODULE_LICENSE() in drivers/infiniband/hw/hns/hns_roce_hem.o
see include/linux/module.h for more information
WARNING: modpost: missing MODULE_LICENSE() in drivers/infiniband/hw/hns/hns_roce_mr.o
see include/linux/module.h for more information
WARNING: modpost: missing MODULE_LICENSE() in drivers/infiniband/hw/hns/hns_roce_pd.o
see include/linux/module.h for more information
WARNING: modpost: missing MODULE_LICENSE() in drivers/infiniband/hw/hns/hns_roce_qp.o
see include/linux/module.h for more information
WARNING: modpost: missing MODULE_LICENSE() in drivers/infiniband/hw/hns/hns_roce_restrack.o
see include/linux/module.h for more information
WARNING: modpost: missing MODULE_LICENSE() in drivers/infiniband/hw/hns/hns_roce_srq.o
see include/linux/module.h for more information
ERROR: "hns_roce_bitmap_cleanup" [drivers/infiniband/hw/hns/hns_roce_srq.ko] undefined!
ERROR: "hns_roce_bitmap_init" [drivers/infiniband/hw/hns/hns_roce_srq.ko] undefined!
ERROR: "hns_roce_free_cmd_mailbox" [drivers/infiniband/hw/hns/hns_roce_srq.ko] undefined!
ERROR: "hns_roce_alloc_cmd_mailbox" [drivers/infiniband/hw/hns/hns_roce_srq.ko] undefined!
ERROR: "hns_roce_table_get" [drivers/infiniband/hw/hns/hns_roce_srq.ko] undefined!
ERROR: "hns_roce_bitmap_alloc" [drivers/infiniband/hw/hns/hns_roce_srq.ko] undefined!
ERROR: "hns_roce_table_find" [drivers/infiniband/hw/hns/hns_roce_srq.ko] undefined!
The fix is to put the module sub components in the right line.
Fixes: e9816ddf2a33 ("RDMA/hns: Cleanup unnecessary exported symbols") Reported-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Xi Wang <wangxi11@huawei.com> Signed-off-by: Lijun Ou <oulijun@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Yishai Hadas [Sun, 30 Jun 2019 16:23:32 +0000 (19:23 +0300)]
IB/mlx5: Implement DEVX dispatching event
Implement DEVX dispatching event by looking up for the applicable
subscriptions for the reported event and using their target fd to
signal/set the event.
Signed-off-by: Yishai Hadas <yishaih@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Reviewed-by: Jason Gunthorpe <jgg@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Yishai Hadas [Sun, 30 Jun 2019 16:23:31 +0000 (19:23 +0300)]
IB/mlx5: Enable subscription for device events over DEVX
Enable subscription for device events over DEVX.
Each subscription is added to the two level xarray data structure
according to its event number and the DEVX object information in case was
given with the given target fd.
Those events will be reported over the given fd once will occur.
Downstream patches will mange the dispatching to any subscription.
Signed-off-by: Yishai Hadas <yishaih@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Reviewed-by: Jason Gunthorpe <jgg@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Parav Pandit [Fri, 7 Jun 2019 12:16:58 +0000 (07:16 -0500)]
net/mlx5: Refactor mlx5_esw_query_functions for modularity
Functions change event output data size changes when functions other
than VFs will be enabled in HCA CAP.
With current API, multiple callers needs to align, calculate accurate
size of the output data depending on number on non VF functions enabled
in the device.
Instead of duplicating such math at multiple places, refactor
mlx5_esw_query_functions() to return raw output allocated by itself.
Caller must free the allocated memory using kvfree() as described in the
function comment section.
This hides calcuation within mlx5_esw_query_functions() and provides
simpler API.
Parav Pandit [Fri, 7 Jun 2019 11:44:17 +0000 (06:44 -0500)]
net/mlx5: E-Switch prepare functions change handler to be modular
Eswitch function change handler will service multiple type of events for
VFs and non VF functions update.
Hence, introduce and use the helper function
esw_vfs_changed_event_handler() for handling change in num VFs to improve
the code readability.
Parav Pandit [Wed, 15 May 2019 05:04:27 +0000 (00:04 -0500)]
net/mlx5: Introduce and use mlx5_eswitch_get_total_vports()
Instead MLX5_TOTAL_VPORTS, use mlx5_eswitch_get_total_vports().
mlx5_eswitch_get_total_vports() in subsequent patch accounts for SF
vports as well.
Expanding MLX5_TOTAL_VPORTS macro would require exposing SF internals to
more generic vport.h header file. Such exposure is not desired.
Hence a mlx5_eswitch_get_total_vports() is introduced.
Given that mlx5_eswitch_get_total_vports() API wants to work on const
mlx5_core_dev*, change its helper functions also to accept const *dev.
Jason Gunthorpe [Wed, 3 Jul 2019 19:43:45 +0000 (16:43 -0300)]
Merge mlx5-next into rdma for-next
From git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux
Required for dependencies in the next patches.
Resolved the conflicts:
- esw_destroy_offloads_acl_tables() use the newer mlx5_esw_for_all_vports()
version
- esw_offloads_steering_init() drop the cap test
- esw_offloads_init() drop the extra function arguments
* branch 'mlx5-next': (39 commits)
net/mlx5: Expose device definitions for object events
net/mlx5: Report EQE data upon CQ completion
net/mlx5: Report a CQ error event only when a handler was set
net/mlx5: mlx5_core_create_cq() enhancements
net/mlx5: Expose the API to register for ANY event
net/mlx5: Use event mask based on device capabilities
net/mlx5: Fix mlx5_core_destroy_cq() error flow
net/mlx5: E-Switch, Handle UC address change in switchdev mode
net/mlx5: E-Switch, Consider host PF for inline mode and vlan pop
net/mlx5: E-Switch, Use iterator for vlan and min-inline setups
net/mlx5: E-Switch, Reg/unreg function changed event at correct stage
net/mlx5: E-Switch, Consolidate eswitch function number of VFs
net/mlx5: E-Switch, Refactor eswitch SR-IOV interface
net/mlx5: Handle host PF vport mac/guid for ECPF
net/mlx5: E-Switch, Use correct flags when configuring vlan
net/mlx5: Reduce dependency on enabled_vfs counter and num_vfs
net/mlx5: Don't handle VF func change if host PF is disabled
net/mlx5: Limit scope of mlx5_get_next_phys_dev() to PCI PF devices
net/mlx5: Move pci status reg access mutex to mlx5_pci_init
net/mlx5: Rename mlx5_pci_dev_type to mlx5_coredev_type
...
mlx5_ib_process_mad() fails on 2nd port when both the ports are not fully
setup at the device level (because 2nd port is unaffiliated).
As a result, get_perf_mad() registers different PMA counter group for 1st
and 2nd port, namely pma_counter_ext and pma_counter. However both ports
have the same capability and counter offsets.
Due to this when counters are read by the user via sysfs in below code
flow, counters are queried from wrong location from the device mainly from
PPCNT instead of VPORT counters.
To overcome this, process_pma_cmd() is invoked, and when unaffiliated port
is not yet setup during device registration phase, make the query on the
first port. while at it, only process_pma_cmd() needs to work on the
native port number and underlying mdev, so shift the get, put calls to
where its needed inside process_pma_cmd().
Fixes: 212f2a87b74f ("IB/mlx5: Route MADs for dual port RoCE") Signed-off-by: Parav Pandit <parav@mellanox.com> Reviewed-by: Daniel Jurgens <danielj@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Yishai Hadas [Sun, 30 Jun 2019 16:23:26 +0000 (19:23 +0300)]
net/mlx5: Report a CQ error event only when a handler was set
Report a CQ error event only when a handler was set.
This enables mlx5_ib to not set a handler upon CQ creation and use some
other mechanism to get this event as of other events by the
mlx5_eq_notifier_register API.
Yishai Hadas [Sun, 30 Jun 2019 16:23:22 +0000 (19:23 +0300)]
net/mlx5: Fix mlx5_core_destroy_cq() error flow
The firmware command to destroy a CQ might fail when the object is
referenced by other object and the ref count is managed by the firmware.
To enable a second successful destruction post the first failure need to
change mlx5_eq_del_cq() to be a void function.
As an error in mlx5_eq_del_cq() is quite fatal from the option to
recover, a debug message inside it should be good enougth and it was
changed to be void.
RDMA/hns: Remove set but not used variable 'fclr_write_fail_flag'
Fixes gcc '-Wunused-but-set-variable' warning:
drivers/infiniband/hw/hns/hns_roce_hw_v2.c: In function 'hns_roce_function_clear':
drivers/infiniband/hw/hns/hns_roce_hw_v2.c:1135:7: warning:
variable 'fclr_write_fail_flag' set but not used [-Wunused-but-set-variable]
It is never used, so can be removed.
Signed-off-by: YueHaibing <yuehaibing@huawei.com> Reviewed-by: Leon Romanovsky <leonro@mellanox.com> Reviewed-by: Jason Gunthorpe <jgg@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Fuqian Huang [Fri, 28 Jun 2019 02:47:19 +0000 (10:47 +0800)]
IB: Remove unneeded memset
In commit af7ddd8a627c ("Merge tag 'dma-mapping-4.21' of
git://git.infradead.org/users/hch/dma-mapping"),
dma_alloc_coherent/dmam_alloc_coherent always zeroed the returned memory.
So the memset after a coherent allocation function is not needed.
Signed-off-by: Fuqian Huang <huangfq.daxian@gmail.com> Reviewed-by: Jason Gunthorpe <jgg@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Jason Gunthorpe [Tue, 2 Jul 2019 19:57:54 +0000 (16:57 -0300)]
Merge branch 'siw' into rdma.git for-next
Bernard Metzler says:
====================
This patch set contributes the SoftiWarp driver rebased for latest
rdma-next. SoftiWarp (siw) implements the iWarp RDMA protocol over kernel
TCP sockets. The driver integrates with the linux-rdma framework.
A matching userlevel driver is available as PR at
https://github.com/linux-rdma/rdma-core/pull/536
Many thanks for reviewing and testing the driver, especially to Leon,
Jason, Steve, Doug, Olga, Dennis, Gal. You all helped to significantly
improve the driver over the last year.
Please find below a list of changes and comments, compared to older
versions of the siw driver.
Many thanks!
Bernard.
CHANGES:
========
v3 (this version)
-----------------
- Rebased to rdma-next
- Removed unneccessary initialization of enums in siw-abi.h
- Added comment on sizing of all work queues to power of two.
v2
-----------------
- Changed recieve path CRC calculation to compute CRC32c not
on target buffer after placement, but on original skbuf.
This change severely hurts performance, if CRC is switched
on, since skb must now be walked twice. It is planned to
work on an extension to skb_copy_bits() to fold in CRC
computation.
- Moved debugging to using ibdev_dbg().
- Dropped detailed packet debug printing.
- Removed siw_debug.[ch] files.
- Removed resource tracking, code now relies on restrack of
RDMA midlayer. Only object counting to enforce reported
device limits is left in place.
- Removed all nested switch-case statements.
- Cleaned up header file #include's
- Moved CQ create/destroy to new semantics,
where midlayer creates/destroys containing object.
- Set siw's ABI version to 1 (was 0 before)
- Removed all enum initialization where not needed.
- Fixed MAINTANERS entry for siw driver
- This version stays with the current siw specific
management of user memory (siw_umem_get() vs.
ib_umem_get(), etc.). This, since the current ib_umem
implementation is less efficient for user page lookup
on the fast path, where effciency is important for a
SW RDMA driver.
It is planned to contribute enhancements to the ib_umem
framework, wich makes it suitable for SW drivers as well.
v1 (first version after v9 of siw RFC)
--------------------------------------
- Rebased to 5.2-rc1
- All IDR code got removed.
- Both MR and QP deallocation verbs now synchronously
free the resources referenced by the RDMA mid-layer.
- IPv6 support was added.
- For compatibility with Chelsio iWarp hardware, the RX
path was slightly reworked. It now allows packet intersection
between tagged and untagged RDMAP operations. While not
a defined behavior as of IETF RFC 5040/5041, some RDMA hardware
may intersect an ongoing outbound (large) tagged message, such
as an multisegment RDMA Read Response with sending an untagged
message, such as an RDMA Send frame. This behavior was only
detected in an NVMeF setup, where siw was used at target side,
and RDMA hardware at client side (during file write). siw now
implements two input paths for tagged and untagged messages each,
and allows the intersected placement of both messages.
- The siw kernel abi file got renamed from siw_user.h to siw-abi.h.
====================
* branch 'siw':
SIW addition to kernel build environment
SIW completion queue methods
SIW receive path
SIW transmit path
SIW queue pair methods
SIW application buffer management
SIW application interface
SIW connection management
SIW network and RDMA core interface
SIW main include file
iWarp wire packet format
Bodong Wang [Fri, 28 Jun 2019 22:36:23 +0000 (22:36 +0000)]
net/mlx5: E-Switch, Handle UC address change in switchdev mode
When NVME device emulation mode is enabled, more than one PFs use the
same physical port. In this case, MPFS is required to program L2
addresses.
It used to rely on netdev set_rx_mode in switchdev mode, but driver
later changed to not create netdev for eswitch manager once in
switchdev mode. So, UC address event should be handled.
Signed-off-by: Bodong Wang <bodong@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Bodong Wang [Fri, 28 Jun 2019 22:36:20 +0000 (22:36 +0000)]
net/mlx5: E-Switch, Use iterator for vlan and min-inline setups
Use the defined iterators to traversal VF reps/vport. Also, rely on
num of VFs rather than the counter of enabled vports as PF will also
be enabled from ECPF side, and the counter will be different from
num of VFs.
Bodong Wang [Fri, 28 Jun 2019 22:36:18 +0000 (22:36 +0000)]
net/mlx5: E-Switch, Reg/unreg function changed event at correct stage
When driver is doing eswitch mode change, it's critical to keep number
of enabled VFs unchanged. However, it can be changed on the fly once
function changed event is registered.
To remove this uncertainty, function changed event should not be
registered before all setups, and first be unregistered before all
cleanups. Wrap this functionality together with vport event handler.
Fixes: 61fc880839e6 ("net/mlx5: E-Switch, Handle representors creation in handler context") Signed-off-by: Bodong Wang <bodong@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Bodong Wang [Fri, 28 Jun 2019 22:36:16 +0000 (22:36 +0000)]
net/mlx5: E-Switch, Consolidate eswitch function number of VFs
Enabled number of VFs is key for eswich manager to do flow steering
initialization and vport configurations. However, the number of
enabled VFs may come from two sources as below.
PF: num of VFs is provided by enabled SR-IOV of itself.
ECPF: num of VFs is provided by enabled SR-IOV from its peer PF. And
SR-IOV can't be enabled from ECPF itself.
Current driver handles the two cases in different stages and passing
the number of enabled VFs among a large scope of internal functions.
It is usually hard to find out where is the real number of VFs from
due to layers of argument pass-in.
This patch consolidated that number from the entry point of doing
eswitch setup, and maintained a copy so that eswitch functions can
refer to it directly.
Eswitch driver shall always use this number when referring to enabled
number of VFs, don't use other numbers such as from SR-IOV.
Signed-off-by: Bodong Wang <bodong@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Bodong Wang [Fri, 28 Jun 2019 22:36:11 +0000 (22:36 +0000)]
net/mlx5: E-Switch, Use correct flags when configuring vlan
Before the offending commit, vlan will be configured if either vlan
or qos is set. After the change with new set flags, function callers
should provide flags accordingly.
Fixes: e33dfe316cf3 ("net/mlx5: E-Switch, Allow fine tuning of eswitch vport push/pop vlan") Signed-off-by: Bodong Wang <bodong@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Parav Pandit [Fri, 28 Jun 2019 22:36:06 +0000 (22:36 +0000)]
net/mlx5: Reduce dependency on enabled_vfs counter and num_vfs
While enabling SR-IOV, PCI core already checks that if SR-IOV is already
enabled, it returns failure error code.
Hence, remove such duplicate check from mlx5_core driver.
While at it, make mlx5_device_disable_sriov() to perform cleanup of VFs in
reverse order of mlx5_device_enable_sriov().
Bodong Wang [Fri, 28 Jun 2019 22:36:04 +0000 (22:36 +0000)]
net/mlx5: Don't handle VF func change if host PF is disabled
When ECPF eswitch manager is at offloads mode, it monitors functions
changed event from host PF side and acts according to the number of
VFs enabled/disabled.
As ECPF and host PF work in two independent hosts, it's possible that
host PF OS reboots but ECPF system is still kept on and continues
monitoring events from host PF. When kernel from host PF side is
booting, PCI iov driver does sriov_init and compute_max_vf_buses by
iterating over all valid num of VFs. This triggers FLR and generates
functions changed events, even though host PF HCA is not enabled at
this time. However, ECPF is not aware of this information, and still
handles these events as usual. ECPF system will see massive number of
reps are created, but destroyed immediately once creation finished.
To eliminate this noise, a bit is added to host parameter context to
indicate host PF is disabled. ECPF will not handle the VF changed
event if this bit is set.
Signed-off-by: Bodong Wang <bodong@mellanox.com> Reviewed-by: Daniel Jurgens <danielj@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Parav Pandit [Fri, 28 Jun 2019 22:36:00 +0000 (22:36 +0000)]
net/mlx5: Move pci status reg access mutex to mlx5_pci_init
mlx5_pci_init() performs pci specific initialization of the
mlx5_core_dev struct.
Hence move pci_status_mutex to pci initialization routine
mlx5_pci_init().
This allows reusing mlx5_mdev_init() to non PCI devices.
Bodong Wang [Fri, 28 Jun 2019 22:35:55 +0000 (22:35 +0000)]
RDMA/mlx5: Cleanup rep when doing unload
When an IB rep is loaded, netdev for the same vport is saved for later
reference. However, it's not cleaned up when doing unload. For ECPF,
kernel crashes when driver is referring to the already removed netdev.
Following steps lead to a shown call trace:
1. Create n VFs from host PF
2. Distroy the VFs
3. Run "rdma link" from ARM
Bodong Wang [Fri, 28 Jun 2019 22:35:53 +0000 (22:35 +0000)]
{IB, net}/mlx5: E-Switch, Use index of rep for vport to IB port mapping
In the single IB device mode, the mapping between vport number and
rep relies on a counter. However for dynamic vport allocation, it is
desired to keep consistent map of eswitch vport and IB port.
Hence, simplify code to remove the free running counter and instead
use the available vport index during load/unload sequence from the
eswitch.
Signed-off-by: Bodong Wang <bodong@mellanox.com> Suggested-by: Parav Pandit <parav@mellanox.com> Reviewed-by: Parav Pandit <parav@mellanox.com> Reviewed-by: Mark Bloch <markb@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>