Commit Graph

19 Commits

Author SHA1 Message Date
Yuval Shaia b196d4f1d6 hw/rdma: Skip data-path mr_id translation
With the change made in commit 68b89aee71 ("Utilize ibv_reg_mr_iova for
memory registration") the MR emulation is no longer needed in order to
translate the guest addresses into host addresses.
With that, the next obvious step is to skip entirely the processing in
data-path.
To accomplish this, return the backend's lkey to driver so we will not
need to do the emulated mr_id to backend mr_id translation in data-path.

The function build_host_sge_array is still called in data-path but only
for backward computability with statistics collection.

While there, as a cosmetic change to make the code cleaner - make one
copy of the function rdma_backend_create_mr and leave the redundant
guest_start argument in the legacy code.

Signed-off-by: Yuval Shaia <yuval.shaia.ml@gmail.com>
Reviewed-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Message-Id: <20200320143429.9490-3-yuval.shaia.ml@gmail.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2020-03-21 19:16:38 +02:00
Yuval Shaia 68b89aee71 hw/rdma: Utilize ibv_reg_mr_iova for memory registration
The virtual address that is provided by the guest in post_send and
post_recv operations is related to the guest address space. This address
space is unknown to the HCA resides on host so extra step in these
operations is needed to adjust the address to host virtual address.

This step, which is done in data-path affects performances.

An enhanced verion of MR registration introduced here
https://patchwork.kernel.org/patch/11044467/ can be used so that the
guest virtual address space for this MR is known to the HCA in host.

This will save the data-path adjustment.

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Message-Id: <20190818132107.18181-3-yuval.shaia@oracle.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2019-11-06 12:49:04 +02:00
Kamal Heib 8b42cfab82 hw/rdma: Modify create/destroy QP to support SRQ
Modify create/destroy QP to support shared receive queue and rearrange
the destroy_qp() code to avoid touching the QP after calling
rdma_rm_dealloc_qp().

Signed-off-by: Kamal Heib <kamalheib1@gmail.com>
Message-Id: <20190403113343.26384-4-kamalheib1@gmail.com>
Reviewed-by: Yuval Shaia <yuval.shaia@oracle.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2019-05-04 15:55:56 +03:00
Kamal Heib e926c9f1bc hw/rdma: Add SRQ support to backend layer
Add the required functions and definitions to support shared receive
queues (SRQs) in the backend layer.

Signed-off-by: Kamal Heib <kamalheib1@gmail.com>
Message-Id: <20190403113343.26384-2-kamalheib1@gmail.com>
Reviewed-by: Yuval Shaia <yuval.shaia@oracle.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2019-05-04 15:55:56 +03:00
Yuval Shaia 3c890bcf30 hw/pvrdma: Delete unneeded function argument
The function's argument rdma_dev_res is not needed as it is stored in
the backend_dev object at init.

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Message-Id: <1552300155-25216-9-git-send-email-yuval.shaia@oracle.com>
Reviewed-by: Kamal Heib <kamalheib1@gmail.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2019-03-16 15:52:44 +02:00
Yuval Shaia bf4414515b hw/rdma: Free all receive buffers when QP is destroyed
When QP is destroyed the backend QP is destroyed as well. This ensures
we clean all received buffer we posted to it.
However, a contexts of these buffers are still remain in the device.
Fix it by maintaining a list of buffer's context and free them when QP
is destroyed.

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Message-Id: <1552300155-25216-8-git-send-email-yuval.shaia@oracle.com>
Reviewed-by: Kamal Heib <kamalheib1@gmail.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2019-03-16 15:52:44 +02:00
Yuval Shaia 4d71b38ae8 hw/rdma: Switch to generic error reporting way
Utilize error_report for all pr_err calls and some pr_dbg that are
considered as errors.
For the remaining pr_dbg calls, the important ones were replaced by
trace points while other deleted.
Some of the functions got renamed to include prefix "rdma/pvrdma"
in the function name.

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Message-Id: <1552300155-25216-2-git-send-email-yuval.shaia@oracle.com>
Reviewed-by: Kamal Heib <kamalheib1@gmail.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2019-03-16 15:52:44 +02:00
Yuval Shaia 26fd869556 hw/pvrdma: Post CQE when receive invalid gid index
This error should propagate back to guest.

Spotted by Coverity: CID 1398595

Fixes: 2b05705dc8

Reported-by: Li Qiang <liq3ea@163.com>
Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2019-01-19 10:49:40 +02:00
Yuval Shaia ffef47754a hw/pvrdma: Remove max-sge command-line param
This parameter has no effect, fix it.

The function init_dev_caps sets the front-end's max-sge to MAX_SGE. Then
it checks backend's max-sge and adjust it accordingly (we can't send
more than what the device supports).

On send and recv we need to make sure the num_sge in the WQE does not
exceeds the backend device capability.
This check is done in pvrdma level so check on rdma level is deleted.

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Message-Id: <20190109194123.3468-1-yuval.shaia@oracle.com>
Reviewed-by: Marcel Apfelbaum<marcel.apfelbaum@gmail.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2019-01-19 10:31:24 +02:00
Yuval Shaia eaac01005d hw/pvrdma: Fill all CQE fields
Add ability to pass specific WC attributes to CQE such as GRH_BIT flag.

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2018-12-22 11:09:56 +02:00
Yuval Shaia 2b05705dc8 hw/pvrdma: Add support to allow guest to configure GID table
The control over the RDMA device's GID table is done by updating the
device's Ethernet function addresses.
Usually the first GID entry is determined by the MAC address, the second
by the first IPv6 address and the third by the IPv4 address. Other
entries can be added by adding more IP addresses. The opposite is the
same, i.e. whenever an address is removed, the corresponding GID entry
is removed.

The process is done by the network and RDMA stacks. Whenever an address
is added the ib_core driver is notified and calls the device driver
add_gid function which in turn update the device.

To support this in pvrdma device we need to hook into the create_bind
and destroy_bind HW commands triggered by pvrdma driver in guest.
Whenever a change is made to the pvrdma port's GID table a special QMP
message is sent to be processed by libvirt to update the address of the
backend Ethernet device.

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Marcel Apfelbaum<marcel.apfelbaum@gmail.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2018-12-22 11:09:56 +02:00
Yuval Shaia 605ec1663b hw/rdma: Add support for MAD packets
MAD (Management Datagram) packets are widely used by various modules
both in kernel and in user space for example the rdma_* API which is
used to create and maintain "connection" layer on top of RDMA uses
several types of MAD packets.

For more information please refer to chapter 13.4 in Volume 1
Architecture Specification, Release 1.1 available here:
https://www.infinibandta.org/ibta-specifications-download/

To support MAD packets the device uses an external utility
(contrib/rdmacm-mux) to relay packets from and to the guest driver.

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Marcel Apfelbaum<marcel.apfelbaum@gmail.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2018-12-22 11:09:56 +02:00
Yuval Shaia 46462cb161 hw/rdma: Return qpn 1 if ibqp is NULL
Device is not supporting QP0, only QP1.

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2018-12-22 11:09:56 +02:00
Yuval Shaia 430e440c59 hw/rdma: Add reference to pci_dev in backend_dev
The field backend_dev->dev is not initialized, fix it.

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Message-Id: <20180805153518.2983-14-yuval.shaia@oracle.com>
Reviewed-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2018-08-18 18:01:20 +03:00
Yuval Shaia 751522275a hw/rdma: Make distinction between device init and start modes
There are certain operations that are well considered as part of device
configuration while others are needed only when "start" command is
triggered by the guest driver. An example of device initialization step
is msix_init and example of "device start" stage is the creation of a CQ
completion handler thread.

Driver expects such distinction - implement it.

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Message-Id: <20180805153518.2983-2-yuval.shaia@oracle.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2018-08-18 17:59:23 +03:00
Yuval Shaia 9bbb8d3577 hw/rdma: Change host_virt to void *
To avoid compilation warnings on 32-bit machines:
rdma_backend.c: In function 'rdma_backend_create_mr':
rdma_backend.c:409:37: error: cast to pointer from integer of different
size [-Werror=int-to-pointer-cast]
	mr->ibmr = ibv_reg_mr(pd->ibpd, (void *)addr, length, access);

Reported-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Tested-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Message-Id: <20180322095220.9976-2-yuval.shaia@oracle.com>
Signed-off-by: Marcel Apfelbaum <marcel@redhat.com>
2018-03-23 18:38:55 +03:00
Michael S. Tsirkin 0efc9511aa rdma: fix up include directives
Our rule right now is to use <> for external headers only.
RDMA code violates that, fix it up.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Marcel Apfelbaum <marcel@redhat.com>
Signed-off-by: Marcel Apfelbaum <marcel@redhat.com>
2018-03-23 18:38:55 +03:00
Yuval Shaia c99f217431 hw/rdma: Add Query QP operation
This operation is needed by rdma devices - implement it.

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Marcel Apfelbaum <marcel@redhat.com>
Signed-off-by: Marcel Apfelbaum <marcel@redhat.com>
2018-03-23 18:38:55 +03:00
Yuval Shaia ef6d4ccdc9 hw/rdma: Implementation of generic rdma device layers
This layer is composed of two sub-modules, backend and resource manager.
Backend sub-module is responsible for all the interaction with IB layers
such as ibverbs and umad (external libraries).
Resource manager is a collection of functions and structures to manage
RDMA resources such as QPs, CQs and MRs.

Reviewed-by: Dotan Barak <dotanb@mellanox.com>
Reviewed-by: Zhu Yanjun <yanjun.zhu@oracle.com>
Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Signed-off-by: Marcel Apfelbaum <marcel@redhat.com>
2018-02-19 13:03:24 +02:00