The field safely extends the RDMA_NLDEV_ATTR_CAP_FLAGS operand as it was
exported as 64 bit to allow this kind of extension.
Signed-off-by: Michael Guralnik <michaelgur@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Add a helper to zero fill fields before copying data to
UVERBS_ATTR_STRUCT.
As UVERBS_ATTR_STRUCT can be used as an extensible struct, we want to make
sure that if the user supplies us with a struct that has new fields that
we are not aware of, we return them zeroed to the user.
This helper should be used when using UVERBS_ATTR_STRUCT for an extendable
data structure and there is a need to make sure that extended members of
the struct, that the kernel doesn't handle, are returned zeroed to the
user. This is needed due to the fact that UVERBS_ATTR_STRUCT allows
non-zero values for members after 'last' member.
Signed-off-by: Michael Guralnik <michaelgur@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>
Yishai Hadas [Wed, 19 Dec 2018 14:28:15 +0000 (16:28 +0200)]
IB/mlx5: Use the correct commands for UMEM and UCTX allocation
During testing the command format was changed to close a security
hole. Revise the driver to use the command format that will actually be
supported in GA firmware.
Both the UMEM and UCTX are intended only for use by the kernel and cannot
be executed using a general command.
Since the UMEM and CTX are not part of the general object the caps bits
were moved to be some log_xxx location in the general HCA caps.
The firmware code was adapted as well to match the above.
Yishai Hadas [Wed, 19 Dec 2018 14:28:11 +0000 (16:28 +0200)]
IB/mlx5: Use uid as part of alloc/dealloc transport domain
Use uid as part of alloc/dealloc transport domain to let firmware manages
the resources correctly.
Fixes: d2d19121ae2f ("IB/mlx5: Set uid as part of TD commands") Signed-off-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>
Jason Gunthorpe [Thu, 20 Dec 2018 20:24:50 +0000 (13:24 -0700)]
Merge branch 'mlx5-next' into rdma.git
From git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux
mlx5 updates taken for dependencies on following patches.
* branche 'mlx5-next': (23 commits)
IB/mlx5: Introduce uid as part of alloc/dealloc transport domain
net/mlx5: Add shared Q counter bits
net/mlx5: Continue driver initialization despite debugfs failure
net/mlx5: Fold the modify lag code into function
net/mlx5: Add lag affinity info to log
net/mlx5: Split the activate lag function into two routines
net/mlx5: E-Switch, Introduce flow counter affinity
IB/mlx5: Unify e-switch representors load approach between uplink and VFs
net/mlx5: Use lowercase 'X' for hex values
net/mlx5: Remove duplicated include from eswitch.c
net/mlx5: Remove the get protocol device interface entry
net/mlx5: Support extended destination format in flow steering command
net/mlx5: E-Switch, Change vhca id valid bool field to bit flag
net/mlx5: Introduce extended destination fields
net/mlx5: Revise gre and nvgre key formats
net/mlx5: Add monitor commands layout and event data
net/mlx5: Add support for plugged-disabled cable status in PME
net/mlx5: Add support for PCIe power slot exceeded error in PME
net/mlx5: Rework handling of port module events
net/mlx5: Move flow counters data structures from flow steering header
...
Devesh Sharma [Wed, 12 Dec 2018 09:56:24 +0000 (01:56 -0800)]
RDMA/bnxt_re: Increase depth of control path command queue
Increasing the depth of control path command queue to 8K entries to handle
burst of commands. This feature needs support from FW and the driver/fw
compatibility is checked from the interface version number.
This commit moves the usdev_lock acquisition after the rtnl lock has been
released.
This is safe to do because usdev_lock is not protecting anything being
accessed in ib_get_eth_speed(). Hence, the correct order of holding locks
(rtnl -> usdev_lock) is not violated.
Signed-off-by: Parvi Kaustubhi <pkaustub@cisco.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Bart Van Assche [Mon, 17 Dec 2018 21:20:46 +0000 (13:20 -0800)]
RDMA/srpt: Add support for immediate data
Modify allocation of the non-SRQ receive queues such that immediate
data is aligned on a 512 byte boundary. That alignment is necessary
to pass the immediate data without copying to the block layer. When
receiving an SRP_CMD with immediate data, postpone the ib_post_recv()
call until target_execute_cmd() has finished. See also
srpt_release_cmd().
Bart Van Assche [Mon, 17 Dec 2018 21:20:44 +0000 (13:20 -0800)]
RDMA/srpt: Remove driver version and release date
Neither a driver version number nor a release data is useful in
an upstream driver. Remove the word "InfiniBand" from the driver
description because recently RoCE support has been added to this
driver.
Bart Van Assche [Mon, 17 Dec 2018 21:20:41 +0000 (13:20 -0800)]
RDMA/srpt: Improve coding style conformance
Use tabs instead of spaces for indentation. Make sure that multi-line
expressions have the operator at the end of a line instead of the start.
Avoid a complaint about a missing space in a ternary expression by
changing '(boolean) ? 1: 0' into 'boolean'.
Bart Van Assche [Mon, 17 Dec 2018 21:20:39 +0000 (13:20 -0800)]
RDMA/srp: Add support for immediate data
Request permission to send immediate data during login. If the SRP
target grants this request, send the payload of write requests <= 8 KB
as immediate data.
Bart Van Assche [Mon, 17 Dec 2018 21:20:38 +0000 (13:20 -0800)]
RDMA/srp: Rework handling of the maximum information unit length
Move the maximum initiator to target information unit length parameter
from struct srp_target_port into struct srp_rdma_ch. This patch does
not change any functionality but makes the next patch easier to read.
Bart Van Assche [Mon, 17 Dec 2018 21:20:36 +0000 (13:20 -0800)]
RDMA/srp: Propagate ib_post_send() failures to the SCSI mid-layer
This patch avoids that the SCSI mid-layer keeps retrying forever if
ib_post_send() fails. This was discovered while testing immediate
data support and passing a too large num_sge value to ib_post_send().
Bart Van Assche [Mon, 17 Dec 2018 21:20:35 +0000 (13:20 -0800)]
RDMA/srp: Handle large SCSI CDBs correctly
Reserve additional space for CDBs that contain more than sixteen bytes
and set the add_cdb_len field for such CDBs as required. From the SRP
standard: "The ADDITIONAL CDB LENGTH field contains the length in
dwords of the ADDITIONAL CDB field."
Drivers should be using udata to determine if a method is invoked from
user space or kernel space. A pd does not necessarily say a different
objects is kernel or user.
Transforming the tests to use udata eliminates a large number of uobject
references from the drivers.
Signed-off-by: Shamir Rabinovitch <shamir.rabinovitch@oracle.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
RDMA/restrack: Resource-tracker should not use uobject pointers
Having uobject pointer embedded in ib core objects is not aligned with a
future shared ib_x model. The resource tracker only does this to keep
track of user/kernel objects - track this directly instead.
Signed-off-by: Shamir Rabinovitch <shamir.rabinovitch@oracle.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Moni Shoua [Tue, 11 Dec 2018 11:37:53 +0000 (13:37 +0200)]
IB/mlx5: Add advise_mr() support
The verb advise_mr() is used to give advice to the kernel about an address
range that belongs to a MR. Implement the verb and register it on the
device. The current implementation supports the only known advice to date,
prefetch.
Signed-off-by: Moni Shoua <monis@mellanox.com> Reviewed-by: Guy Levi <guyle@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Moni Shoua [Tue, 11 Dec 2018 11:37:52 +0000 (13:37 +0200)]
IB/uverbs: Add support to advise_mr
Add new ioctl method for the MR object - ADVISE_MR.
This command can be used by users to give an advice or directions to the
kernel about an address range that belongs to memory regions.
A new ib_device callback, advise_mr(), is introduced here to suupport the
new command. This command takes the following arguments:
- pd: The protection domain to which all memory regions belong
- advice: The type of the advice
* IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH - Pre-fetch a range of
an on-demand paging MR
* IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH_WRITE - Pre-fetch a range
of an on-demand paging MR with write intention
- flags: The properties of the advice
* IB_UVERBS_ADVISE_MR_FLAG_FLUSH - Operation must end before
return to the caller
- sg_list: The list of memory ranges
- num_sge: The number of memory ranges in the list
- attrs: More attributes to be parsed by the provider
Signed-off-by: Moni Shoua <monis@mellanox.com> Reviewed-by: Guy Levi <guyle@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Moni Shoua [Tue, 11 Dec 2018 11:37:51 +0000 (13:37 +0200)]
IB/uverbs: Add helper to get array size from ptr attribute
When the parser of an ioctl command has the knowledge that a ptr attribute
in a bundle represents an array of structures, it is useful for it to know
the number of elements in the array. This is done by dividing the
attribute length with the element size.
Signed-off-by: Moni Shoua <monis@mellanox.com> Reviewed-by: Guy Levi <guyle@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Parav Pandit [Fri, 30 Nov 2018 11:16:48 +0000 (13:16 +0200)]
RDMA/uverbs: Add an ioctl method to destroy an object
Add an ioctl method to destroy the PD, MR, MW, AH, flow, RWQ indirection
table and XRCD objects by handle which doesn't require any output response
during destruction.
Signed-off-by: Parav Pandit <parav@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Dan Carpenter [Mon, 17 Dec 2018 07:08:15 +0000 (10:08 +0300)]
RDMA/hns: Fix an error code in hns_roce_create_srq()
The function accidentally returns success on this error path.
Fixes: c7bcb13442e1 ("RDMA/hns: Add SRQ support for hip08 kernel mode") Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Acked-by: Lijun Ou <oulijun@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Dan Carpenter [Mon, 17 Dec 2018 07:05:36 +0000 (10:05 +0300)]
IB/qib: Fix an error code in qib_sdma_verbs_send()
We accidentally return success on this error path.
Fixes: f931551bafe1 ("IB/qib: Add new qib driver for QLogic PCIe InfiniBand adapters") Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Parav Pandit [Tue, 18 Dec 2018 12:16:00 +0000 (14:16 +0200)]
RDMA/core: Delete RoCE GID in hw when corresponding IP is deleted
Currently a RoCE GID entry is removed from the hardware when all
references to the GID entry drop to zero. This is a change in behavior
from before the fixed patch. The GID entry should be removed from the
hardware when GID entry deletion is requested. This allows the driver
terminate ongoing traffic through the RoCE GID.
While a GID is deleted from the hardware, GID slot in the software GID
cache is not freed. GID slot is freed once all references of such GID are
dropped. This continue to ensure that such GID slot of hardware is not
allocated to new GID entry allocation request. It is allocated once all
references to GID entry drop.
This approach allows drivers to put a tombestone of some kind on the HW
GID index to block the traffic.
Fixes: b150c3862d21 ("IB/core: Introduce GID entry reference counts") Signed-off-by: Parav Pandit <parav@mellanox.com> Reviewed-by: Mark Bloch <markb@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Jason Gunthorpe [Fri, 30 Nov 2018 11:06:21 +0000 (13:06 +0200)]
RDMA/uverbs: Implement an ioctl that can call write and write_ex handlers
Now that the handlers do not process their own udata we can make a
sensible ioctl that wrappers them. The ioctl follows the same format as
the write_ex() and has the user explicitly specify the core and driver
in/out opaque structures and a command number.
This works for all forms of write commands.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
The failure to create debugfs entry is unpleasant event, but not enough
to abort drier initialization. Align the mlx5_core code to debugfs design
and continue execution whenever debugfs_create_dir() successes or not.
This dictates the device affinity for eswitch flow counters, set by the FW
according to the HW device capabilities.
Under "source eswitch" affinity, the counter should be allocated on the
device related to the source vport in the match. This covers both non
merged e-switch mode as well as old FW that does not advertise this cap.
Under "flow eswitch" affinity, the counter should be allocated on the
device where the eswitch rule is set.
Signed-off-by: Shahar Klein <shahark@mellanox.com> Signed-off-by: Roi Dayan <roid@mellanox.com> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Mark Bloch [Thu, 13 Dec 2018 03:11:37 +0000 (19:11 -0800)]
IB/mlx5: Unify e-switch representors load approach between uplink and VFs
When in switchdev mode and the add function is called by the core
level driver, make sure we only register the callbacks, but don't
create the mlx5 IB device or initialize anything. With this change
all the IB devices in switchdev mode are created only once the load
callback is invoked by the e-switch core sub-module. This follows
the design paradigm under which the all the Eth representors must
be loaded before any of IB reprs is loaded.
Signed-off-by: Mark Bloch <markb@mellanox.com> Acked-by: Or Gerlitz <ogerlitz@mellanox.com> Reviewed-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Kamal Heib [Mon, 10 Dec 2018 19:09:38 +0000 (21:09 +0200)]
RDMA/mlx5: Initialize ib_device_ops struct
Initialize ib_device_ops with the supported operations using
ib_set_device_ops().
Signed-off-by: Kamal Heib <kamalheib1@gmail.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Kamal Heib [Mon, 10 Dec 2018 19:09:30 +0000 (21:09 +0200)]
RDMA/core: Introduce ib_device_ops
This change introduces the ib_device_ops structure that defines all the
InfiniBand device operations in one place, so the code will be more
readable and clean, unlike today when the ops are mixed with ib_device
data members.
The providers will need to define the supported operations and assign them
using ib_set_device_ops(), that will also make the providers code more
readable and clean.
Signed-off-by: Kamal Heib <kamalheib1@gmail.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Leon Romanovsky [Tue, 11 Dec 2018 10:04:42 +0000 (12:04 +0200)]
RDMA/ocrdma: Use PCI-ID as an identification in debugfs
In opposite to current implementation of identification based on device
name, PCI-ID identification provides stable names suitable for device
rename. Change ocrdma debugfs representation to use PCI-ID.
Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Reviewed-by: Yuval Shaia <yuval.shaia@oracle.com> Acked-by: Selvin Xavier <selvin.xavier@broadcom.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Leon Romanovsky [Mon, 10 Dec 2018 09:19:49 +0000 (11:19 +0200)]
RDMA/mlx5: Fail early if user tries to create flows on IB representors
IB representors don't support creation of RAW ethernet QP flows. Disable
them by reusing existing RDMA/core support macros. We do it for both
creation and matcher because latter is not usable if no flow creation is
available.
Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Michael Guralnik <michaelgur@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>
Report HDR speed when HDR is supported in CapabilityMask2 and the actual
speed is HDR.
Signed-off-by: Michael Guralnik <michaelgur@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>
CapabilityMask2 exists when IB_PORT_CAP_MASK2_SUP is set in the original
capability mask. In such cases, query its value and report it in query
port.
Signed-off-by: Michael Guralnik <michaelgur@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>
Add the new rates that were added to Infiniband spec as part of HDR and 2x
support.
Signed-off-by: Michael Guralnik <michaelgur@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>
Add the new 2X port width that is part of IB spec 1.3
Signed-off-by: Michael Guralnik <michaelgur@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>
CapabilityMask2 was added in IB Spec 1.3 under PortInfo attribute. The
new Capapbility mask is needed in order to expose the new 2X width and HDR
speed.
Signed-off-by: Michael Guralnik <michaelgur@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>
Lijun Ou [Sat, 8 Dec 2018 10:40:11 +0000 (18:40 +0800)]
RDMA/hns: Bugfix for RoCE loopback test
This patch implements a cmdq to enable the loopback of ssu module
according to the modified hardware desgin.
The ssu consists of ingress unit, packet buffer and programmable packet
process unit. if the loopback bit of ssu is not enabled, the roce packet
with loopback bit will fail.
Signed-off-by: Lijun Ou <oulijun@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Lijun Ou [Sat, 8 Dec 2018 10:40:10 +0000 (18:40 +0800)]
RDMA/hns: Update posting & querying mailbox
This patch updates the implementation of the mailbox command interface by
using command queue instead of operating registers. With this update, the
software can be well decoupled with the hardware.
Signed-off-by: Lijun Ou <oulijun@huawei.com> Signed-off-by: Yixian Liu <liuyixian@huawei.com> Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Lijun Ou [Sat, 8 Dec 2018 10:40:07 +0000 (18:40 +0800)]
RDMA/hns: Init qp context when modify qp from reset to init
It needs to clear qp context previous when init qp context. Otherwise,
the newly created qp context residue has the contents of the qp context
before the uninstall, and the qp context content is disordered, causing
the task to fail.
Signed-off-by: Lijun Ou <oulijun@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Eli Britstein [Mon, 10 Dec 2018 21:15:16 +0000 (13:15 -0800)]
net/mlx5: Support extended destination format in flow steering command
Update the flow steering command formatting according to the extended
destination API.
Note that the FW dictates that multi destination FTEs that involve at
least one encap must use the extended destination format, while single
destination ones must use the legacy format.
Using extended destination format requires FW support. Check for its
capabilities and return error if not supported.
Signed-off-by: Eli Britstein <elibr@mellanox.com> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Reviewed-by: Oz Shlomo <ozsh@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Eli Britstein [Mon, 10 Dec 2018 21:15:15 +0000 (13:15 -0800)]
net/mlx5: E-Switch, Change vhca id valid bool field to bit flag
Change the driver flow destination struct to use bit flags with the vhca
id valid being the 1st one. The flags field is more extendable and will
be used in downstream patch.
Signed-off-by: Eli Britstein <elibr@mellanox.com> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Reviewed-by: Oz Shlomo <ozsh@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Eli Britstein [Mon, 10 Dec 2018 21:15:14 +0000 (13:15 -0800)]
net/mlx5: Introduce extended destination fields
Extended destinations provide the ability to configure different
encapsulation properties per destination on a single FTE. This is
needed for use-cases such as remote mirroring over tunneled networks.
Signed-off-by: Eli Britstein <elibr@mellanox.com> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Reviewed-by: Oz Shlomo <ozsh@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>