Commit Graph

128 Commits

Author SHA1 Message Date
Yuval Shaia
a2f1dc6091 hw/pvrdma: Delete pvrdma_exit function
This hook is not called and was implemented by mistake.

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Message-Id: <1552300155-25216-10-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
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
ff30a446b1 hw/rdma: Free all MAD receive buffers when device is closed
When device is going down free all saved MAD buffers.

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Message-Id: <1552300155-25216-7-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
f4b2c02a29 {hmp, hw/pvrdma}: Expose device internals via monitor interface
Allow interrogating device internals through HMP interface.
The exposed indicators can be used for troubleshooting by developers or
sysadmin.
There is no need to expose these attributes to a management system (e.x.
libvirt) because (1) most of them are not "device-management' related
info and (2) there is no guarantee the interface is stable.

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Acked-by: Markus Armbruster <armbru@redhat.com>
Message-Id: <1552300155-25216-6-git-send-email-yuval.shaia@oracle.com>
Reviewed-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2019-03-16 15:52:44 +02:00
Yuval Shaia
c2dd117b38 hw/pvrdma: Collect debugging statistics
Add counters to enable enhance debugging

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Message-Id: <1552300155-25216-5-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
2cfa953009 hw/rdma: Protect against concurrent execution of poll_cq
The function rdma_poll_cq is called from two contexts - completion
handler thread which sense new completion on backend channel and
explicitly as result of guest issuing poll_cq command.

Add lock to protect against concurrent executions.

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Message-Id: <1552300155-25216-4-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
b20fc79510 hw/rdma: Introduce protected qlist
To make code more readable move handling of protected list to a
rdma_utils

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Message-Id: <1552300155-25216-3-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
Marcel Apfelbaum
555b3d67bc hw/rdma: modify struct initialization
Do not initialize structs with {0} since some
CLANG versions do not support it.

Use {} construct instead.

Reviewed-by: Yuval Shaia <yuval.shaia@oracle.com>
Tested-by: Cornelia Huck <cohuck@redhat.com>
Message-Id: <20190118124614.24548-3-marcel.apfelbaum@gmail.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2019-01-19 11:01:33 +02:00
Li Qiang
a5fe209d71 hw: rdma: fix an off-by-one issue
In rdma_rm_get_backend_gid_index(), the 'sgid_idx' is used
to index the array 'dev_res->port.gid_tbl' which size is
MAX_PORT_GIDS. Current the 'sgid_idx' may be MAX_PORT_GIDS
thus cause an off-by-one issue.

Spotted by Coverity: CID 1398594

Signed-off-by: Li Qiang <liq3ea@163.com>
Message-Id: <20190103131251.49271-1-liq3ea@163.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2019-01-19 10:57:48 +02:00
Yuval Shaia
a1aa88b7dc hw/rdma: Verify that ptr is not NULL before freeing
To cover the case where fini() was called even when init() fails make
sure objects are not NULL before calling to non-null-safe destructors.

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Message-Id: <20190116151538.14088-1-yuval.shaia@oracle.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2019-01-19 10:54:37 +02:00
Yuval Shaia
5bb8b73987 hw/pvrdma: Make function pvrdma_qp_send/recv return void.
The functions handles errors internaly, callers have nothing to do with
the return value.

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Message-Id: <20190109202140.4051-1-yuval.shaia@oracle.com>
Reviewed-by: Marcel Apfelbaum<marcel.apfelbaum@gmail.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2019-01-19 10:53:16 +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
732d948ca5 hw/rdma: Delete unused struct member
This member is used only in init_device_caps function, make it local.

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Marcel Apfelbaum<marcel.apfelbaum@gmail.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
2019-01-19 10:45:23 +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
Prasad J Pandit
f1e2e38ee0 pvrdma: check return value from pvrdma_idx_ring_has_ routines
pvrdma_idx_ring_has_[data/space] routines also return invalid
index PVRDMA_INVALID_IDX[=-1], if ring has no data/space. Check
return value from these routines to avoid plausible infinite loops.

Reported-by: Li Qiang <liq3ea@163.com>
Signed-off-by: Prasad J Pandit <pjp@fedoraproject.org>
Reviewed-by: Yuval Shaia <yuval.shaia@oracle.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2018-12-22 11:09:57 +02:00
Prasad J Pandit
7be3a21325 rdma: remove unused VENDOR_ERR_NO_SGE macro
With commit 4481985c (rdma: check num_sge does not exceed MAX_SGE)
macro VENDOR_ERR_NO_SGE is no longer in use - delete it.

Signed-off-by: Prasad J Pandit <pjp@fedoraproject.org>
Reviewed-by: Yuval Shaia <yuval.shaia@oracle.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2018-12-22 11:09:57 +02:00
Prasad J Pandit
509f57c98e pvrdma: release ring object in case of an error
create_cq and create_qp routines allocate ring object, but it's
not released in case of an error, leading to memory leakage.

Reported-by: Li Qiang <liq3ea@163.com>
Signed-off-by: Prasad J Pandit <pjp@fedoraproject.org>
Reviewed-by: Yuval Shaia <yuval.shaia@oracle.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2018-12-22 11:09:57 +02:00
Prasad J Pandit
2c858ce5da pvrdma: check number of pages when creating rings
When creating CQ/QP rings, an object can have up to
PVRDMA_MAX_FAST_REG_PAGES 8 pages. Check 'npages' parameter
to avoid excessive memory allocation or a null dereference.

Reported-by: Li Qiang <liq3ea@163.com>
Signed-off-by: Prasad J Pandit <pjp@fedoraproject.org>
Reviewed-by: Yuval Shaia <yuval.shaia@oracle.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2018-12-22 11:09:57 +02:00
Prasad J Pandit
2aa86456fb pvrdma: add uar_read routine
Define skeleton 'uar_read' routine. Avoid NULL dereference.

Reported-by: Li Qiang <liq3ea@163.com>
Signed-off-by: Prasad J Pandit <pjp@fedoraproject.org>
Reviewed-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2018-12-22 11:09:57 +02:00
Prasad J Pandit
0e68373cc2 rdma: check num_sge does not exceed MAX_SGE
rdma back-end has scatter/gather array ibv_sge[MAX_SGE=4] set
to have 4 elements. A guest could send a 'PvrdmaSqWqe' ring element
with 'num_sge' set to > MAX_SGE, which may lead to OOB access issue.
Add check to avoid it.

Reported-by: Saar Amar <saaramar5@gmail.com>
Signed-off-by: Prasad J Pandit <pjp@fedoraproject.org>
Reviewed-by: Yuval Shaia <yuval.shaia@oracle.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2018-12-22 11:09:57 +02:00
Prasad J Pandit
cce648613b pvrdma: release device resources in case of an error
If during pvrdma device initialisation an error occurs,
pvrdma_realize() does not release memory resources, leading
to memory leakage.

Reported-by: Li Qiang <liq3ea@163.com>
Signed-off-by: Prasad J Pandit <pjp@fedoraproject.org>
Message-Id: <20181212175817.815-1-ppandit@redhat.com>
Reviewed-by: Yuval Shaia <yuval.shaia@oracle.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2018-12-22 11:09:57 +02:00
Yuval Shaia
305fd2ba06 hw/rdma: Do not call rdma_backend_del_gid on an empty gid
When device goes down the function fini_ports loops over all entries in
gid table regardless of the fact whether entry is valid or not. In case
that entry is not valid we'd like to skip from any further processing in
backend 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 11:09:57 +02:00
Yuval Shaia
9a3053d2e8 hw/rdma: Do not use bitmap_zero_extend to free bitmap
bitmap_zero_extend is designed to work for extending, not for
shrinking.
Using g_free instead.

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 11:09:57 +02:00
Yuval Shaia
ffa65d97fc hw/pvrdma: Clean device's resource when system is shutdown
In order to clean some external resources such as GIDs, QPs etc,
register to receive notification when VM is shutdown.

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 11:09:57 +02:00
Yuval Shaia
14c74f7207 hw/rdma: Remove unneeded code that handles more that one port
Device supports only one port, let's remove a dead code that handles
more than one port.

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
091782171f hw/pvrdma: Fill error code in command's response
Driver checks error code let's set it.
In addition, for code simplification purposes, set response's fields
ack, response and err outside of the scope of command handlers.

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
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
e976ebc87c hw/pvrdma: Make device state depend on Ethernet function state
User should be able to control the device by changing Ethernet function
state so if user runs 'ifconfig ens3 down' the PVRDMA function should be
down as well.

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
028c3f93d6 hw/rdma: Initialize node_guid from vmxnet3 mac address
node_guid should be set once device is load.
Make node_guid be GID format (32 bit) of PCI function 0 vmxnet3 device's
MAC.

A new function was added to do the conversion.
So for example the MAC 56:b6:44:e9:62:dc will be converted to GID
54b6:44ff:fee9:62dc.

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
d961ead16e hw/pvrdma: Make sure PCI function 0 is vmxnet3
Guest driver enforces it, we should also.

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
1625bb13da hw/pvrdma: Set the correct opcode for send completion
opcode for WC should be set by the device and not taken from work
element.

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
2bff59e699 hw/pvrdma: Set the correct opcode for recv completion
The function pvrdma_post_cqe populates CQE entry with opcode from the
given completion element. For receive operation value was not set. Fix
it by setting it to IBV_WC_RECV.

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
536692ca1d hw/pvrdma: Make default pkey 0xFFFF
Commit 6e7dba23af ("hw/pvrdma: Make default pkey 0xFFFF") exports
default pkey as external definition but omit the change from 0x7FFF to
0xFFFF.

Fixes: 6e7dba23af ("hw/pvrdma: Make default pkey 0xFFFF")

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
f00c48caab hw/pvrdma: Make function reset_device return void
This function cannot fail - fix it to return void

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
305bdd7a57 hw/rdma: Abort send-op if fail to create addr handler
Function create_ah might return NULL, let's exit with an error.

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
4082e533f6 hw/rdma: Add ability to force notification without re-arm
Upon completion of incoming packet the device pushes CQE to driver's RX
ring and notify the driver (msix).
While for data-path incoming packets the driver needs the ability to
control whether it wished to receive interrupts or not, for control-path
packets such as incoming MAD the driver needs to be notified anyway, it
even do not need to re-arm the notification bit.

Enhance the notification field to support this.

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
dee2e53c86 hw/pvrdma: Check the correct return value
Return value of 0 means ok, we want to free the memory only in case of
error.

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Message-Id: <20181025061700.17050-1-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
Markus Armbruster
b7d89466dd Clean up includes
Clean up includes so that osdep.h is included first and headers
which it implies are not included manually.

This commit was created with scripts/clean-includes, with the changes
to the following files manually reverted:

    contrib/libvhost-user/libvhost-user-glib.h
    contrib/libvhost-user/libvhost-user.c
    contrib/libvhost-user/libvhost-user.h
    linux-user/mips64/cpu_loop.c
    linux-user/mips64/signal.c
    linux-user/sparc64/cpu_loop.c
    linux-user/sparc64/signal.c
    linux-user/x86_64/cpu_loop.c
    linux-user/x86_64/signal.c
    target/s390x/gen-features.c
    tests/migration/s390x/a-b-bios.c
    tests/test-rcu-simpleq.c
    tests/test-rcu-tailq.c

Signed-off-by: Markus Armbruster <armbru@redhat.com>
Message-Id: <20181204172535.2799-1-armbru@redhat.com>
Acked-by: Eduardo Habkost <ehabkost@redhat.com>
Acked-by: Halil Pasic <pasic@linux.ibm.com>
Acked-by: Yuval Shaia <yuval.shaia@oracle.com>
Acked-by: Viktor Prutyanov <viktor.prutyanov@phystech.edu>
2018-12-20 10:29:08 +01:00
Marcel Apfelbaum
21ab34c954 config: split PVRDMA from RDMA
In some BSD systems RDMA migration is possible while
the pvrdma device can't be used because the mremap system call
is missing.

Reported-by: Rebecca Cran <rebecca@bluestop.org>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Message-Id: <20180816151637.24553-1-marcel.apfelbaum@gmail.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
2018-08-18 18:01:34 +03:00
Marcel Apfelbaum
72221d03b8 hw/pvrdma: remove not needed include
No need to include linux/types.h, is empty anyway.

Suggested-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Message-Id: <20180811171534.11917-1-marcel.apfelbaum@gmail.com>
Reviewed-by: Yuval Shaia <yuval.shaia@oracle.com>
2018-08-18 18:01:27 +03:00
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
7d2ce4b016 hw/rdma: Bugfix - Support non-aligned buffers
RDMA application can provide non-aligned buffers to be registered. In
such case the DMA address passed by driver is pointing to the beginning
of the physical address of the mapped page so we can't distinguish
between two addresses from the same page.

Fix it by keeping the offset of the virtual address in mr->virt.

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Message-Id: <20180805153518.2983-13-yuval.shaia@oracle.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2018-08-18 18:00:55 +03:00
Yuval Shaia
abc665aae3 hw/rdma: Print backend QP number in hex format
To be consistent with other prints throughout the code fix places that
print it as decimal number.

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Message-Id: <20180805153518.2983-12-yuval.shaia@oracle.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2018-08-18 18:00:48 +03:00
Yuval Shaia
292dce627b hw/rdma: Cosmetic change - move to generic function
To ease maintenance of struct comp_thread move all related code to
dedicated function.

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Message-Id: <20180805153518.2983-11-yuval.shaia@oracle.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2018-08-18 18:00:39 +03:00
Yuval Shaia
67b32fe250 hw/pvrdma: Cosmetic change - indent right
Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Message-Id: <20180805153518.2983-10-yuval.shaia@oracle.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2018-08-18 18:00:30 +03:00
Yuval Shaia
7131c4b028 hw/rdma: Reorder resource cleanup
To be consistence with allocation do the reverse order in deallocation

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Message-Id: <20180805153518.2983-9-yuval.shaia@oracle.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2018-08-18 18:00:22 +03:00
Yuval Shaia
4c408c9d5b hw/rdma: Do not allocate memory for non-dma MR
There is no use in the memory allocated for non-dma MR.
Delete the code that allocates it.

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Message-Id: <20180805153518.2983-8-yuval.shaia@oracle.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2018-08-18 18:00:15 +03:00
Yuval Shaia
7f99daadbd hw/rdma: Delete useless structure RdmaRmUserMR
The structure RdmaRmUserMR has no benefits, remove it an move all its
fields to struct RdmaRmMR.

Reviewed-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Message-Id: <20180805153518.2983-7-yuval.shaia@oracle.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2018-08-18 18:00:06 +03:00
Yuval Shaia
6e7dba23af hw/pvrdma: Make default pkey 0xFFFF
0x7FFF is not the default pkey - fix it.

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Message-Id: <20180805153518.2983-6-yuval.shaia@oracle.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2018-08-18 17:59:58 +03:00
Yuval Shaia
eca0f2a6be hw/pvrdma: Clean CQE before use
Next CQE is fetched from CQ ring, clean it before usage as it still
carries old CQE values.

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Message-Id: <20180805153518.2983-5-yuval.shaia@oracle.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2018-08-18 17:59:50 +03:00
Yuval Shaia
ef846e026c hw/rdma: Modify debug macros
- Add line counter to ease navigation in log
- Print rdma instead of pvrdma

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Message-Id: <20180805153518.2983-4-yuval.shaia@oracle.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2018-08-18 17:59:42 +03:00
Yuval Shaia
b462a13480 hw/pvrdma: Bugfix - provide the correct attr_mask to query_qp
Calling rdma_rm_query_qp with attr_mask equals to -1 leads to error
where backend query_qp fails to retrieve the needed QP attributes.
Fix it by providing the attr_mask we got from driver.

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Message-Id: <20180805153518.2983-3-yuval.shaia@oracle.com>
Reviewed-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
2018-08-18 17:59:33 +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
Philippe Mathieu-Daudé
78109066e6 hw/rdma: Use the IEC binary prefix definitions
It eases code review, unit is explicit.

Patch generated using:

  $ git grep -E '(1024|2048|4096|8192|(<<|>>).?(10|20|30))' hw/ include/hw/

and modified manually.

Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Reviewed-by: Marcel Apfelbaum <marcel@redhat.com>
Reviewed-by: Yuval Shaia <yuval.shaia@oracle.com>
Message-Id: <20180625124238.25339-40-f4bug@amsat.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2018-07-02 15:41:17 +02:00
Marcel Apfelbaum
d18a530d85 hw/rdma: Fix possible out of bounds access to port GID index
Make sure the backend GID index is less then port's
gid table length.

Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Reviewed-by: Yuval Shaia <yuval.shaia@oracle.com>
Message-Id: <20180430200223.4119-8-marcel.apfelbaum@gmail.com>
2018-05-03 20:52:29 +03:00
Yuval Shaia
6c080b9ea6 hw/rdma: Delete duplicate definition of MAX_RM_TBL_NAME
By a mistake this constant was defined twice - remove the duplication.

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Message-Id: <20180430200223.4119-7-marcel.apfelbaum@gmail.com>
2018-05-03 20:52:29 +03:00
Yuval Shaia
350929172b hw/rdma: Fix possible out of bounds access to regs array
Coverity (CID1390589, CID1390608).
Array size is RDMA_BAR1_REGS_SIZE, let's make sure the given address is
in range.

While there also:
1. Adjust the size of this bar to reasonable size
2. Report the size of the array with sizeof(array)

Reported-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Message-Id: <20180430200223.4119-6-marcel.apfelbaum@gmail.com>
2018-05-03 20:52:29 +03:00
Yuval Shaia
c387e8a4ec hw/rdma: Fix possible out of bounds access to GID table
Array size is MAX_PORT_GIDS, let's make sure the given index is in
range.

While there limit device table size to 1.

Reported-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Message-Id: <20180430200223.4119-5-marcel.apfelbaum@gmail.com>
2018-05-03 20:52:29 +03:00
Yuval Shaia
b9e34872b9 hw/rdma: Delete port's pkey table
Support for PKEY is not yet implemented. Removing the unneeded table
until a support will be added.

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Message-Id: <20180430200223.4119-4-marcel.apfelbaum@gmail.com>
2018-05-03 20:52:29 +03:00
Marcel Apfelbaum
b0197cf80a hw/rdma: Fix possible usage of a NULL pointer
Coverity CID 1390586; The cq handle is provided by the guest
and cannot be trusted to be previuosly allocated.
Fix it by exiting the completion flow.

Reported-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Reviewed-by: Yuval Shaia <yuval.shaia@oracle.com>
Message-Id: <20180430200223.4119-3-marcel.apfelbaum@gmail.com>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
2018-05-03 20:52:29 +03:00
Marcel Apfelbaum
1bad4957c8 hw/rdma: Fix possible munmap call on a NULL pointer
Coverity CID 1390620: we call munmap() on a NULL pointer.

Reported-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Reviewed-by: Yuval Shaia <yuval.shaia@oracle.com>
Message-Id: <20180430200223.4119-2-marcel.apfelbaum@gmail.com>
2018-05-03 20:52:29 +03:00
Yuval Shaia
6f559013c8 hw/rdma: Fix 32-bit compilation
Use the correct printf formats, so that a 32-bit compile doesn't spit
out lots of warnings about %lx being incompatible with uint64_t.

Suggested-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: <20180322095220.9976-4-yuval.shaia@oracle.com>
Signed-off-by: Marcel Apfelbaum <marcel@redhat.com>
2018-03-23 18:38:55 +03:00
Yuval Shaia
94f480b8db hw/rdma: Use correct print format in CHK_ATTR macro
Macro should not cast the given variable to u64 instead it should use
the supplied format argument (fmt).

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: <20180322095220.9976-3-yuval.shaia@oracle.com>
Signed-off-by: Marcel Apfelbaum <marcel@redhat.com>
2018-03-23 18:38:55 +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
Marcel Apfelbaum
197053e212 hw/rdma: fix clang compilation errors
Fix some enum castings and extra parentheses.

Reported-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Marcel Apfelbaum <marcel@redhat.com>
Message-Id: <20180321140316.96045-1-marcel@redhat.com>
Reviewed-by: Yuval Shaia <yuval.shaia@oracle.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
79cfdca7aa hw/rdma: Add support for Query QP verb to pvrdma device
This IB verb is needed by some applications - 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
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
919ae3dd11 hw/rdma: Implementation of PVRDMA device
PVRDMA is the QEMU implementation of VMware's paravirtualized RDMA device.
It works with its Linux Kernel driver AS IS, no need for any special
guest modifications.

While it complies with the VMware device, it can also communicate with
bare metal RDMA-enabled machines and does not require an RDMA HCA in the
host, it can work with Soft-RoCE (rxe).

It does not require the whole guest RAM to be pinned allowing memory
over-commit and, even if not implemented yet, migration support will be
possible with some HW assistance.

Implementation is divided into 2 components, rdma general and pvRDMA
specific functions and structures.

The second PVRDMA sub-module - interaction with PCI layer.
- Device configuration and setup (MSIX, BARs etc).
- Setup of DSR (Device Shared Resources)
- Setup of device ring.
- Device management.

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
Yuval Shaia
98d176f8e5 hw/rdma: PVRDMA commands and data-path ops
First PVRDMA sub-module - implementation of the PVRDMA device.
- PVRDMA commands such as create CQ and create MR.
- Data path QP operations - post_send and post_recv.
- Completion handler.

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
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
Yuval Shaia
b3a9227769 hw/rdma: Definitions for rdma device and rdma resource manager
Definition of various structures and constants used in backend and
resource manager modules.

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
Yuval Shaia
dcbf469aef hw/rdma: Add wrappers and macros
As all mapping for this device are from driver to device,
declare wrappers on top of pci_dma_*map functions.

In addition, declare macros to be used for debug messages.

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