Yixian Liu [Mon, 18 Nov 2019 02:34:52 +0000 (10:34 +0800)]
RDMA/hns: Rename the functions used inside creating cq
Current names of functions are not proper, such as hns_roce_free_cq,
actually it means free cqc, thus we rename them. Furthermore, functions
used inside one file can be named without the prefix hns_roce_ which will
make the functions for verbs symbols more eye-catching.
Yixian Liu [Mon, 18 Nov 2019 02:34:51 +0000 (10:34 +0800)]
RDMA/hns: Redefine the member of hns_roce_cq struct
There is no need to package buf and mtt into hns_roce_cq_buf, which will
make code more complex, just delete this struct and move buf and mtt into
hns_roce_cq. Furthermore, we add size member for hns_roce_buf to avoid
repeatly calculating where needed it.
Yixian Liu [Mon, 18 Nov 2019 02:34:50 +0000 (10:34 +0800)]
RDMA/hns: Redefine interfaces used in creating cq
Some interfaces defined with unnecessary input parameters, such as "nent"
and "vector". This patch redefined these interfaces to make the code more
readable and simple.
Daniel Kranzdorf [Thu, 21 Nov 2019 14:15:09 +0000 (16:15 +0200)]
RDMA/efa: Expose RDMA read related attributes
Query the device attributes for RDMA operations, including maximum
transfer size and maximum number of SGEs per RDMA WR, and report them
back to the userspace library.
Link: https://lore.kernel.org/r/20191121141509.59297-4-galpress@amazon.com Signed-off-by: Daniel Kranzdorf <dkkranzd@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>
Gal Pressman [Thu, 21 Nov 2019 14:15:07 +0000 (16:15 +0200)]
RDMA/efa: Store network attributes in device attributes
There's no reason to separate the network attributes from all other
device attributes. Embed the fields inside the device attributes and
query them all in one function.
Link: https://lore.kernel.org/r/20191121141509.59297-2-galpress@amazon.com Reviewed-by: Daniel Kranzdorf <dkkranzd@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>
Colin Ian King [Fri, 22 Nov 2019 15:48:14 +0000 (15:48 +0000)]
IB/hfi1: 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.
Devesh Sharma [Thu, 21 Nov 2019 06:22:22 +0000 (01:22 -0500)]
RDMA/bnxt_re: Fix stat push into dma buffer on gen p5 devices
Due to recent advances in the firmware for Broadcom's gen p5 series of
adaptors the driver code to report hardware counters has been broken
w.r.t. roce devices.
The new firmware command expects dma length to be specified during stat
dma buffer allocation.
Jason Gunthorpe [Fri, 22 Nov 2019 20:08:34 +0000 (16:08 -0400)]
Merge branch 'ib-guids' into rdma.git for-next
Danit Goldberg says:
====================
This series extends RTNETLINK to provide IB port and node GUIDs, which
were configured for Infiniband VFs.
The functionality to set VF GUIDs already existed for a long time, and
here we are adding the missing "get" so that netlink will be symmetric and
various cloud orchestration tools will be able to manage such VFs more
naturally.
The iproute2 was extended too to present those GUIDs.
- ip link show <device>
For example:
- ip link set ib4 vf 0 node_guid 22:44:33:00:33:11:00:33
- ip link set ib4 vf 0 port_guid 10:21:33:12:00:11:22:10
- ip link show ib4
ib4: <BROADCAST,MULTICAST> mtu 4092 qdisc noop state DOWN mode DEFAULT group default qlen 256
link/infiniband 00:00:0a:2d:fe:80:00:00:00:00:00:00:ec:0d:9a:03:00:44:36:8d brd 00:ff:ff:ff:ff:12:40:1b:ff:ff:00:00:00:00:00:00:ff:ff:ff:ff
vf 0 link/infiniband 00:00:0a:2d:fe:80:00:00:00:00:00:00:ec:0d:9a:03:00:44:36:8d brd 00:ff:ff:ff:ff:12:40:1b:ff:ff:00:00:00:00:00:00:ff:ff:ff:ff,
spoof checking off, NODE_GUID 22:44:33:00:33:11:00:33, PORT_GUID 10:21:33:12:00:11:22:10, link-state disable, trust off, query_rss off
====================
Based on the mlx5-next branch from
git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux for
dependencies
* branch 'ib-guids': (35 commits)
IB/mlx5: Implement callbacks for getting VFs GUID attributes
IB/ipoib: Add ndo operation for getting VFs GUID attributes
IB/core: Add interfaces to get VF node and port GUIDs
net/core: Add support for getting VF GUIDs
net/mlx5: Add new chain for netfilter flow table offload
net/mlx5: Refactor creating fast path prio chains
net/mlx5: Accumulate levels for chains prio namespaces
net/mlx5: Define fdb tc levels per prio
net/mlx5: Rename FDB_* tc related defines to FDB_TC_* defines
net/mlx5: Simplify fdb chain and prio eswitch defines
IB/mlx5: Load profile according to RoCE enablement state
IB/mlx5: Rename profile and init methods
net/mlx5: Handle "enable_roce" devlink param
net/mlx5: Document flow_steering_mode devlink param
devlink: Add new "enable_roce" generic device param
net/mlx5: fix spelling mistake "metdata" -> "metadata"
net/mlx5: fix kvfree of uninitialized pointer spec
IB/mlx5: Introduce and use mlx5_core_is_vf()
net/mlx5: E-switch, Enable metadata on own vport
net/mlx5: Refactor ingress acl configuration
...
Michal Kalderon [Mon, 18 Nov 2019 15:06:45 +0000 (17:06 +0200)]
RDMA/qedr: Fix null-pointer dereference when calling rdma_user_mmap_get_offset
When running against rdma-core that doesn't support doorbell recovery, the
rdma_user_mmap_entry won't be allocated for doorbell recovery related
mappings.
We have a flag indicating whether rdma-core supports doorbell recovery or
not which was used during initialization, however some cases didn't check
that the rdma_user_mmap_entry exists before attempting to acquire it's
offset.
Mark Zhang [Fri, 15 Nov 2019 15:45:55 +0000 (17:45 +0200)]
IB/mlx5: Support extended number of strides for Striding RQ
Extends the minimum single WQE strides from 64 to 8, which is exposed
by the "min_single_wqe_log_num_of_strides" field of striding_rq_caps.
Choose right number of strides based on FW capability.
Danit Goldberg [Fri, 15 Nov 2019 15:44:57 +0000 (17:44 +0200)]
IB/mlx4: Update HW GID table while adding vlan GID
When adding a new GID compare the vlan along with the GID and type. This
allows vlan's to have GIDs that alias each other, such as the default
GID. Otherwise they the GID cache view can become inconsistent with the HW
view.
Link: https://lore.kernel.org/r/20191115154457.247763-1-leon@kernel.org Signed-off-by: Danit Goldberg <danitg@mellanox.com> Reviewed-by: Parav Pandit <parav@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Dag Moxnes [Wed, 30 Oct 2019 12:44:00 +0000 (13:44 +0100)]
RDMA/cma: Use ACK timeout for RoCE packetLifeTime
The cma is currently using a hard-coded value, CMA_IBOE_PACKET_LIFETIME,
for the PacketLifeTime, as it can not be determined from the network.
This value might not be optimal for all networks.
The cma module supports the function rdma_set_ack_timeout to set the ACK
timeout for a QP associated with a connection. As per IBTA 12.7.34 local
ACK timeout = (2 * PacketLifeTime + Local CA’s ACK delay). Assuming a
negligible local ACK delay, we can use PacketLifeTime = local ACK
timeout/2 as a reasonable approximation for RoCE networks.
IB/umem: remove the dmasync argument to ib_umem_get
The argument is always ignored, so remove it.
Link: https://lore.kernel.org/r/20191113073214.9514-3-hch@lst.de Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Jason Gunthorpe <jgg@mellanox.com> Acked-by: Michal Kalderon <michal.kalderon@marvell.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Gal Pressman [Tue, 12 Nov 2019 09:26:08 +0000 (11:26 +0200)]
RDMA/efa: Clear the admin command buffer prior to its submission
We cannot rely on the entry memcpy as we only copy the actual size of the
command, the rest of the bytes must be memset to zero.
Currently providing non-zero memory will not have any user visible impact.
However, since admin commands are extendable (in a backwards compatible
way) everything beyond the size of the command must be cleared to prevent
issues in the future.
Fixes: 0420e542569b ("RDMA/efa: Implement functions that submit and complete admin commands") Link: https://lore.kernel.org/r/20191112092608.46964-1-galpress@amazon.com Reviewed-by: Daniel Kranzdorf <dkkranzd@amazon.com> Reviewed-by: Firas JahJah <firasj@amazon.com> Signed-off-by: Gal Pressman <galpress@amazon.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Bernard Metzler [Wed, 13 Nov 2019 15:34:04 +0000 (16:34 +0100)]
RDMA/siw: Cleanup unused mmap structures.
Removes obsolete driver specific mmap information after
generalization of RDMA driver mmap service. Also removes
useless forward declaration of struct siw_mr.
Kamal Heib [Sun, 10 Nov 2019 11:36:45 +0000 (13:36 +0200)]
RDMA/qedr: Make qedr_iw_load_qp() static
The function qedr_iw_load_qp() is only used in qedr_iw_cm.c
Fixes: 82af6d19d8d9 ("RDMA/qedr: Fix synchronization methods and memory leaks in qedr") Link: https://lore.kernel.org/r/20191110113645.20058-1-kamalheib1@gmail.com Signed-off-by: Kamal Heib <kamalheib1@gmail.com> Acked-by: Michal Kalderon <michal.kalderon@marvell.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Viresh Kumar [Thu, 7 Nov 2019 03:20:25 +0000 (08:50 +0530)]
RDMA/qib: Validate ->show()/store() callbacks before calling them
The permissions of the read-only or write-only sysfs files can be
changed (as root) and the user can then try to read a write-only file or
write to a read-only file which will lead to kernel crash here.
Protect against that by always validating the show/store callbacks.
Paul Blakey [Mon, 11 Nov 2019 23:34:29 +0000 (00:34 +0100)]
net/mlx5: Add new chain for netfilter flow table offload
Netfilter tables (nftables) implements a software datapath that
comes after tc ingress datapath. The datapath supports offloading
such rules via the flow table offload API.
This API is currently only used by NFT and it doesn't provide the
global priority in regards to tc offload, so we assume offloading such
rules must come after tc. It does provide a flow table priority
parameter, so we need to provide some supported priority range.
For that, split fastpath prio to two, flow table offload and tc offload,
with one dedicated priority chain for flow table offload.
Next patch will re-use the multi chain API to access this chain by
allowing access to this chain by the fdb_sub_namespace.
Signed-off-by: Paul Blakey <paulb@mellanox.com> Reviewed-by: Mark Bloch <markb@mellanox.com> Acked-by: Pablo Neira Ayuso <pablo@netfilter.org> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Paul Blakey [Mon, 11 Nov 2019 23:34:27 +0000 (00:34 +0100)]
net/mlx5: Accumulate levels for chains prio namespaces
Tc chains are implemented by creating a chained prio steering type, and
inside it there is a namespace for each chain (FDB_TC_MAX_CHAINS). Each
of those has a list of priorities.
Currently, all namespaces in a prio start at the parent prio level.
But since we can jump from chain (namespace) to another chain in the
same prio, we need the levels for higher chains to be higher as well.
So we created unused prios to account for levels in previous namespaces.
Fix that by accumulating the namespaces levels if we are inside a chained
type prio, and removing the unused prios.
Fixes: 328edb499f99 ('net/mlx5: Split FDB fast path prio to multiple namespaces') Signed-off-by: Paul Blakey <paulb@mellanox.com> Reviewed-by: Mark Bloch <markb@mellanox.com> Acked-by: Pablo Neira Ayuso <pablo@netfilter.org> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Bart Van Assche [Tue, 5 Nov 2019 21:46:32 +0000 (13:46 -0800)]
RDMA/srpt: Report the SCSI residual to the initiator
The code added by this patch is similar to the code that already exists in
ibmvscsis_determine_resid(). This patch has been tested by running the
following command:
IB/mlx5: Support flow counters offset for bulk counters
Add support for flow steering counters action with a non-base counter
ID (offset) for bulk counters.
When creating a flow counter object, save the bulk value. This value is
used when a flow action with a non-base counter ID is requested - to
validate that the required offset is in the range of the allocated bulk.
Link: https://lore.kernel.org/r/20191103140723.77411-1-leon@kernel.org Signed-off-by: Yevgeny Kliteynik <kliteyn@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Reviewed-by: Mark Bloch <markb@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Register "enable_roce" param, default value is RoCE enabled.
Current configuration is stored on mlx5_core_dev and exposed to user
through the cmode runtime devlink param.
Changing configuration requires changing the cmode driverinit devlink
param and calling devlink reload.
Lang Cheng [Tue, 5 Nov 2019 11:08:00 +0000 (19:08 +0800)]
RDMA/hns: Modify hns_roce_hw_v2_get_cfg to simplify the code
Merge base configuration of hr_dev into hns_roce_hw_v2_get_cfg(). In
addition, there is no need to return 0 at last, so we change return type
of it to void.
Special QP have no differences with normal qp in data structure, so
definition of struct hns_roce_sqp should be removed and replaced by struct
hns_roce_qp.
Bart Van Assche [Fri, 1 Nov 2019 20:47:56 +0000 (13:47 -0700)]
Revert "RDMA/srpt: Postpone HCA removal until after configfs directory removal"
Although the mentioned patch fixes a use-after-free bug, it introduces a
hang during shutdown. Since the latter is worse, revert this patch.
Link: https://lore.kernel.org/r/20191101204756.182162-1-bvanassche@acm.org Reported-by: Honggang Li <honli@redhat.com> Fixes: 9b64f7d0bb0a ("RDMA/srpt: Postpone HCA removal until after configfs directory removal") Signed-off-by: Bart Van Assche <bvanassche@acm.org> Acked-by: Honggang Li <honli@redhat.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
There is no need to return always zero for function which is not
supported.
Fixes: ac1b36e55a51 ("qedr: Add support for user context verbs") Link: https://lore.kernel.org/r/20191028155931.1114-5-kamalheib1@gmail.com Signed-off-by: Kamal Heib <kamalheib1@gmail.com> Reviewed-by: Jason Gunthorpe <jgg@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Kamal Heib [Mon, 28 Oct 2019 15:59:29 +0000 (17:59 +0200)]
RDMA/hns: Remove unsupported modify_port callback
There is no need to return always zero for function which is not
supported.
Fixes: 9a4435375cd1 ("IB/hns: Add driver files for hns RoCE driver") Link: https://lore.kernel.org/r/20191028155931.1114-3-kamalheib1@gmail.com Signed-off-by: Kamal Heib <kamalheib1@gmail.com> Reviewed-by: Jason Gunthorpe <jgg@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Kamal Heib [Mon, 28 Oct 2019 15:59:28 +0000 (17:59 +0200)]
RDMA/core: Fix return code when modify_port isn't supported
Improve return code from ib_modify_port() by doing the following:
- Use "-EOPNOTSUPP" instead "-ENOSYS" which is the proper return code
- Allow only fake IB_PORT_CM_SUP manipulation for RoCE providers that
didn't implement the modify_port callback, otherwise return
"-EOPNOTSUPP"
Fixes: 61e0962d5221 ("IB: Avoid ib_modify_port() failure for RoCE devices") Link: https://lore.kernel.org/r/20191028155931.1114-2-kamalheib1@gmail.com Signed-off-by: Kamal Heib <kamalheib1@gmail.com> Reviewed-by: Jason Gunthorpe <jgg@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Michal Kalderon [Wed, 30 Oct 2019 09:44:12 +0000 (11:44 +0200)]
RDMA: Connect between the mmap entry and the umap_priv structure
The rdma_user_mmap_io interface created a common interface for drivers to
correctly map hw resources and zap them once the ucontext is destroyed
enabling the drivers to safely free the hw resources.
However, this meant the drivers need to delay freeing the resource to the
ucontext destroy phase to ensure they were no longer mapped. The new
mechanism for a common way of handling user/driver address mapping enabled
notifying the driver if all umap_priv mappings were removed, and enabled
freeing the hw resources when they are done with and not delay it until
ucontext destroy.
Since not all drivers use the mechanism, NULL can be sent to the
rdma_user_mmap_io interface to continue working as before. Drivers that
use the mmap_xa interface can pass the entry being mapped to the
rdma_user_mmap_io function to be linked together.
Michal Kalderon [Wed, 30 Oct 2019 09:44:11 +0000 (11:44 +0200)]
RDMA/core: Create mmap database and cookie helper functions
Create some common API's for adding entries to a xa_mmap. Searching for
an entry and freeing one.
The general approach is copied from the EFA driver and improved to be more
general and do more to help the drivers. Integration with the core allows
a reference counted scheme with a free function so that the driver can
know when its mmaps are all gone.
This significant new functionality will be helpful for drivers to have the
correct lifetime model for mmap objects.
There is a spelling mistake in a esw_warn warning message. Fix it.
Signed-off-by: Colin Ian King <colin.king@canonical.com> Reviewed-by: Parav Pandit <parav@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Colin Ian King [Tue, 5 Nov 2019 18:27:40 +0000 (18:27 +0000)]
net/mlx5: fix kvfree of uninitialized pointer spec
Currently when a call to esw_vport_create_legacy_ingress_acl_group
fails the error exit path to label 'out' will cause a kvfree on the
uninitialized pointer spec. Fix this by ensuring pointer spec is
initialized to NULL to avoid this issue.
Addresses-Coverity: ("Uninitialized pointer read") Fixes: 10652f39943e ("net/mlx5: Refactor ingress acl configuration") Signed-off-by: Colin Ian King <colin.king@canonical.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Michal Kalderon [Wed, 30 Oct 2019 09:44:10 +0000 (11:44 +0200)]
RDMA/core: Move core content from ib_uverbs to ib_core
Move functionality that is called by the driver, which is
related to umap, to a new file that will be linked in ib_core.
This is a first step in later enabling ib_uverbs to be optional.
vm_ops is now initialized in ib_uverbs_mmap instead of
priv_init to avoid having to move all the rdma_umap functions
as well.
Link: https://lore.kernel.org/r/20191030094417.16866-2-michal.kalderon@marvell.com Suggested-by: Jason Gunthorpe <jgg@mellanox.com> Signed-off-by: Ariel Elior <ariel.elior@marvell.com> Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com> Reviewed-by: Jason Gunthorpe <jgg@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Parav Pandit [Mon, 28 Oct 2019 23:35:30 +0000 (23:35 +0000)]
IB/mlx5: Introduce and use mlx5_core_is_vf()
Instead of deciding a given device is virtual function or
not based on a device is PF or not, use already defined
MLX5_COREDEV_VF by introducing an helper API mlx5_core_is_vf().
This enables to clearly identify PF, VF and non virtual functions.
Parav Pandit [Mon, 28 Oct 2019 23:35:28 +0000 (23:35 +0000)]
net/mlx5: E-switch, Enable metadata on own vport
Currently on ECPF, metadata is enabled on the ECPF vport = 0xfffe
(manager vport).
Metadata when supported, must be enabled on own vport which is
used to pass metadata to vport of NIC Rx Flow Table.
Due to this error, traffic tagged by ingress ACL is not processed
correctly at NIC rx flow table level which is supposed to work
on metadata tag.
Hence, instead of working on eswitch manager vport, always working on
eswitch own vport regardless of PF or ECPF.
Given that mlx5_eswitch_query/modify_esw_vport_context() is used to
access other vport in legacy mode and own vport settings in switchdev mode,
extend low level API to explicitly specify other_vport.
Fixes: c1286050cf47 ("net/mlx5: E-Switch, Pass metadata from FDB to eswitch manager") Signed-off-by: Parav Pandit <parav@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Parav Pandit [Mon, 28 Oct 2019 23:35:26 +0000 (23:35 +0000)]
net/mlx5: Refactor ingress acl configuration
Drop, untagged, spoof check and untagged spoof check flow groups are
limited to legacy mode only.
Therefore, following refactoring is done to
(a) improve code readability
(b) have better code split between legacy and offloads mode
1. Move legacy flow groups under legacy structure
2. Add validity check for group deletion
3. Restrict scope of esw_vport_disable_ingress_acl to legacy mode
4. Rename esw_vport_enable_ingress_acl() to
esw_vport_create_ingress_acl_table() and limit its scope to
table creation
5. Introduce legacy flow groups creation helper
esw_legacy_create_ingress_acl_groups() and keep its scope to legacy mode
6. Reduce offloads ingress groups from 4 to just 1 metadata group
per vport
7. Removed redundant IS_ERR_OR_NULL as entries are marked NULL on free.
8. Shortern error message to remove redundant 'E-switch'
Parav Pandit [Mon, 28 Oct 2019 23:35:19 +0000 (23:35 +0000)]
net/mlx5: Move ACL drop counters life cycle close to ACL lifecycle
It is better to create/destroy ACL related drop counters where the actual
drop rule ACLs are created/destroyed, so that ACL configuration is self
contained for ingress and egress.
Parav Pandit [Mon, 28 Oct 2019 23:35:17 +0000 (23:35 +0000)]
net/mlx5: E-switch, Legacy introduce and use per vport acl tables APIs
Introduce and use per vport ACL tables creation and destroy APIs, so that
subsequently patch can use them during enabling/disabling a vport in
unified way for legacy vs offloads mode.
Parav Pandit [Mon, 28 Oct 2019 23:35:13 +0000 (23:35 +0000)]
net/mlx5: Tide up state_lock and vport enabled flag usage
When eswitch is disabled, vport event handler is unregistered.
This unregistration already synchronizes with running EQ event handler
in below code flow.
Additionally vport->enabled flag is set under state_lock during
esw_enable_vport() but is not read under state_lock in
(a) esw_disable_vport() and (b) under atomic context
eswitch_vport_event().
It is also necessary to synchronize with already scheduled vport event.
This is already achieved using below sequence.
Hence,
(a) Remove vport->enabled check in eswitch_vport_event() which
doesn't make any sense.
(b) Remove redundant flush_workqueue() on every vport disable.
(c) Keep esw_disable_vport() symmetric with esw_enable_vport() for
state_lock.
Parav Pandit [Mon, 28 Oct 2019 23:35:07 +0000 (23:35 +0000)]
net/mlx5: Correct comment for legacy fields
fdb_table is used for both legacy and offloads mode.
It was incorrect to comment that fdb_table is legacy specific.
Hence, fix the comment to reflect that fdb_table is used in legacy and
offloads mode.
Parav Pandit [Mon, 28 Oct 2019 23:35:05 +0000 (23:35 +0000)]
net/mlx5: Introduce and use mlx5_esw_is_manager_vport()
Currently esw_enable_vport() does vport check for zero to enable drop
counters regardless of execution on ECPF/PF.
While esw_disable_vport() considers such scenario.
To keep consistency across code for checking for manager_vport,
introduce and use mlx5_esw_is_manager_vport() to check if a specified
vport is eswitch manager vport or not.
Parav Pandit [Mon, 28 Oct 2019 23:35:03 +0000 (23:35 +0000)]
net/mlx5: E-switch, Introduce and use vlan rule config helper
Between legacy mode and switchdev mode, only two fields are changed,
vlan_tag and flow action.
Hence to avoid duplicte code between two modes, introduce and and use
helper function to configure allowed VLAN rule.
Vu Pham [Mon, 28 Oct 2019 23:35:00 +0000 (23:35 +0000)]
net/mlx5: E-Switch, Rename ingress acl config in offloads mode
Changing the function name esw_ingress_acl_common_config() to
esw_ingress_acl_config() to be consistent with egress config
function naming in offloads mode.
Vu Pham [Mon, 28 Oct 2019 23:34:58 +0000 (23:34 +0000)]
net/mlx5: E-Switch, Rename egress config to generic name
Refactor vport egress config in offloads mode
Refactoring vport egress configuration in offloads mode that
includes egress prio tag configuration.
This makes code symmetric to ingress configuration.
Michael Guralnik [Mon, 10 Jun 2019 12:21:24 +0000 (15:21 +0300)]
IB/mlx5: Test write combining support
Linux can run in all sorts of physical machines and VMs where write
combining may or may not be supported. Currently there is no way to
reliably tell if the system supports WC, or not. The driver uses WC to
optimize posting work to the HCA, and getting this wrong in either
direction can cause a significant performance loss.
Add a test in mlx5_ib initialization process to test whether
write-combining is supported on the machine. The test will run as part of
the enable_driver callback to ensure that the test runs after the device
is setup and can create and modify the QP needed, but runs before the
device is exposed to the users.
The test opens UD QP and posts NOP WQEs, the WQE written to the BlueFlame
is different from the WQE in memory, requesting CQE only on the BlueFlame
WQE. By checking whether we received a completion on one of these WQEs we
can know if BlueFlame succeeded and this write-combining must be
supported.
Change reporting of BlueFlame support to be dependent on write-combining
support instead of the FW's guess as to what the machine can do.
Arnd Bergmann [Mon, 7 Oct 2019 21:18:08 +0000 (23:18 +0200)]
RDMA/hns: Fix build error again
This is not the first attempt to fix building random configurations,
unfortunately the attempt in commit a07fc0bb483e ("RDMA/hns: Fix build
error") caused a new problem when CONFIG_INFINIBAND_HNS_HIP06=m and
CONFIG_INFINIBAND_HNS_HIP08=y:
drivers/infiniband/hw/hns/hns_roce_main.o:(.rodata+0xe60): undefined reference to `__this_module'
Revert commits a07fc0bb483e ("RDMA/hns: Fix build error") and a3e2d4c7e766 ("RDMA/hns: remove obsolete Kconfig comment") to get back to
the previous state, then fix the issues described there differently, by
adding more specific dependencies: INFINIBAND_HNS can now only be built-in
if at least one of HNS or HNS3 are built-in, and the individual back-ends
are only available if that code is reachable from the main driver.
Fixes: a07fc0bb483e ("RDMA/hns: Fix build error") Fixes: a3e2d4c7e766 ("RDMA/hns: remove obsolete Kconfig comment") Fixes: dd74282df573 ("RDMA/hns: Initialize the PCI device for hip08 RoCE") Fixes: 08805fdbeb2d ("RDMA/hns: Split hw v1 driver from hns roce driver") Link: https://lore.kernel.org/r/20191007211826.3361202-1-arnd@arndb.de Signed-off-by: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Jason Gunthorpe [Mon, 28 Oct 2019 19:44:35 +0000 (16:44 -0300)]
Merge branch 'odp_rework' into rdma.git for-next
Jason Gunthorpe says:
====================
In order to hoist the interval tree code out of the drivers and into the
mmu_notifiers it is necessary for the drivers to not use the interval tree
for other things.
This series replaces the interval tree with an xarray and along the way
re-aligns all the locking to use a sensible SRCU model where the 'update'
step is done by modifying an xarray.
The result is overall much simpler and with less locking in the critical
path. Many functions were reworked for clarity and small details like
using 'imr' to refer to the implicit MR make the entire code flow here
more readable.
This also squashes at least two race bugs on its own, and quite possibily
more that haven't been identified.
====================
Merge conflicts with the odp statistics patch resolved.
* branch 'odp_rework':
RDMA/odp: Remove broken debugging call to invalidate_range
RDMA/mlx5: Do not race with mlx5_ib_invalidate_range during create and destroy
RDMA/mlx5: Do not store implicit children in the odp_mkeys xarray
RDMA/mlx5: Rework implicit ODP destroy
RDMA/mlx5: Avoid double lookups on the pagefault path
RDMA/mlx5: Reduce locking in implicit_mr_get_data()
RDMA/mlx5: Use an xarray for the children of an implicit ODP
RDMA/mlx5: Split implicit handling from pagefault_mr
RDMA/mlx5: Set the HW IOVA of the child MRs to their place in the tree
RDMA/mlx5: Lift implicit_mr_alloc() into the two routines that call it
RDMA/mlx5: Rework implicit_mr_get_data
RDMA/mlx5: Delete struct mlx5_priv->mkey_table
RDMA/mlx5: Use a dedicated mkey xarray for ODP
RDMA/mlx5: Split sig_err MR data into its own xarray
RDMA/mlx5: Use SRCU properly in ODP prefetch
projects / linux.git / log