- Devel - libvirt List Archives

[PATCH-for-9.1] rdma: Remove RDMA subsystem and pvrdma device
by Philippe Mathieu-Daudé 28 Mar '24

28 Mar '24

The whole RDMA subsystem was deprecated in commit e9a54265f5 ("hw/rdma: Deprecate the pvrdma device and the rdma subsystem") released in v8.2. Time to remove it. Keep the RAM_SAVE_FLAG_HOOK definition since it might appears in old migration streams. Remove the dependencies on libibumad and libibverbs. Remove the generated vmw_pvrdma/ directory from linux-headers. Remove RDMA handling from migration. Remove RDMA handling in GlusterFS block driver. Remove rdmacm-mux tool from contrib/. Remove PVRDMA device. Cc: Peter Xu <peterx(a)redhat.com> Cc: Li Zhijian <lizhijian(a)fujitsu.com> Cc: Yuval Shaia <yuval.shaia.ml(a)gmail.com> Cc: Marcel Apfelbaum <marcel.apfelbaum(a)gmail.com> Signed-off-by: Philippe Mathieu-Daudé <philmd(a)linaro.org> --- MAINTAINERS | 17 - docs/about/deprecated.rst | 9 - docs/about/removed-features.rst | 4 + docs/devel/migration/main.rst | 6 - docs/pvrdma.txt | 345 -- docs/rdma.txt | 420 -- docs/system/device-url-syntax.rst.inc | 4 +- docs/system/loongarch/virt.rst | 2 +- docs/system/qemu-block-drivers.rst.inc | 1 - meson.build | 59 - qapi/machine.json | 17 - qapi/migration.json | 31 +- qapi/qapi-schema.json | 1 - qapi/rdma.json | 38 - contrib/rdmacm-mux/rdmacm-mux.h | 61 - hw/rdma/rdma_backend.h | 129 - hw/rdma/rdma_backend_defs.h | 76 - hw/rdma/rdma_rm.h | 97 - hw/rdma/rdma_rm_defs.h | 146 - hw/rdma/rdma_utils.h | 63 - hw/rdma/trace.h | 1 - hw/rdma/vmw/pvrdma.h | 144 - hw/rdma/vmw/pvrdma_dev_ring.h | 46 - hw/rdma/vmw/pvrdma_qp_ops.h | 28 - hw/rdma/vmw/trace.h | 1 - include/hw/rdma/rdma.h | 37 - include/monitor/hmp.h | 1 - .../infiniband/hw/vmw_pvrdma/pvrdma_dev_api.h | 685 --- .../infiniband/hw/vmw_pvrdma/pvrdma_verbs.h | 348 -- .../standard-headers/rdma/vmw_pvrdma-abi.h | 310 -- migration/migration-stats.h | 6 +- migration/migration.h | 9 - migration/options.h | 2 - migration/rdma.h | 69 - block/gluster.c | 39 - contrib/rdmacm-mux/main.c | 831 ---- hw/core/machine-qmp-cmds.c | 32 - hw/rdma/rdma.c | 30 - hw/rdma/rdma_backend.c | 1401 ------ hw/rdma/rdma_rm.c | 812 ---- hw/rdma/rdma_utils.c | 126 - hw/rdma/vmw/pvrdma_cmd.c | 815 ---- hw/rdma/vmw/pvrdma_dev_ring.c | 141 - hw/rdma/vmw/pvrdma_main.c | 735 --- hw/rdma/vmw/pvrdma_qp_ops.c | 298 -- migration/migration-stats.c | 5 +- migration/migration.c | 31 - migration/options.c | 16 - migration/qemu-file.c | 1 - migration/ram.c | 86 +- migration/rdma.c | 4184 ----------------- migration/savevm.c | 2 +- monitor/qmp-cmds.c | 1 - Kconfig.host | 3 - contrib/rdmacm-mux/meson.build | 7 - hmp-commands-info.hx | 13 - hw/Kconfig | 1 - hw/meson.build | 1 - hw/rdma/Kconfig | 3 - hw/rdma/meson.build | 12 - hw/rdma/trace-events | 31 - hw/rdma/vmw/trace-events | 17 - meson_options.txt | 4 - migration/meson.build | 1 - migration/trace-events | 68 +- qapi/meson.build | 1 - qemu-options.hx | 6 - .../ci/org.centos/stream/8/x86_64/configure | 1 - scripts/ci/setup/build-environment.yml | 2 - scripts/coverity-scan/run-coverity-scan | 2 +- scripts/meson-buildoptions.sh | 6 - scripts/update-linux-headers.sh | 27 - tests/lcitool/projects/qemu.yml | 2 - tests/migration/guestperf/engine.py | 4 +- 74 files changed, 20 insertions(+), 12991 deletions(-) delete mode 100644 docs/pvrdma.txt delete mode 100644 docs/rdma.txt delete mode 100644 qapi/rdma.json delete mode 100644 contrib/rdmacm-mux/rdmacm-mux.h delete mode 100644 hw/rdma/rdma_backend.h delete mode 100644 hw/rdma/rdma_backend_defs.h delete mode 100644 hw/rdma/rdma_rm.h delete mode 100644 hw/rdma/rdma_rm_defs.h delete mode 100644 hw/rdma/rdma_utils.h delete mode 100644 hw/rdma/trace.h delete mode 100644 hw/rdma/vmw/pvrdma.h delete mode 100644 hw/rdma/vmw/pvrdma_dev_ring.h delete mode 100644 hw/rdma/vmw/pvrdma_qp_ops.h delete mode 100644 hw/rdma/vmw/trace.h delete mode 100644 include/hw/rdma/rdma.h delete mode 100644 include/standard-headers/drivers/infiniband/hw/vmw_pvrdma/pvrdma_dev_api.h delete mode 100644 include/standard-headers/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h delete mode 100644 include/standard-headers/rdma/vmw_pvrdma-abi.h delete mode 100644 migration/rdma.h delete mode 100644 contrib/rdmacm-mux/main.c delete mode 100644 hw/rdma/rdma.c delete mode 100644 hw/rdma/rdma_backend.c delete mode 100644 hw/rdma/rdma_rm.c delete mode 100644 hw/rdma/rdma_utils.c delete mode 100644 hw/rdma/vmw/pvrdma_cmd.c delete mode 100644 hw/rdma/vmw/pvrdma_dev_ring.c delete mode 100644 hw/rdma/vmw/pvrdma_main.c delete mode 100644 hw/rdma/vmw/pvrdma_qp_ops.c delete mode 100644 migration/rdma.c delete mode 100644 contrib/rdmacm-mux/meson.build delete mode 100644 hw/rdma/Kconfig delete mode 100644 hw/rdma/meson.build delete mode 100644 hw/rdma/trace-events delete mode 100644 hw/rdma/vmw/trace-events diff --git a/MAINTAINERS b/MAINTAINERS index a07af6b9d4..05226cea0a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3426,13 +3426,6 @@ F: docs/devel/migration.rst F: qapi/migration.json F: tests/migration/ F: util/userfaultfd.c -X: migration/rdma* - -RDMA Migration -R: Li Zhijian <lizhijian(a)fujitsu.com> -R: Peter Xu <peterx(a)redhat.com> -S: Odd Fixes -F: migration/rdma* Migration dirty limit and dirty page rate M: Hyman Huang <yong.huang(a)smartx.com> @@ -4060,16 +4053,6 @@ F: block/replication.c F: tests/unit/test-replication.c F: docs/block-replication.txt -PVRDMA -M: Yuval Shaia <yuval.shaia.ml(a)gmail.com> -M: Marcel Apfelbaum <marcel.apfelbaum(a)gmail.com> -S: Odd Fixes -F: hw/rdma/* -F: hw/rdma/vmw/* -F: docs/pvrdma.txt -F: contrib/rdmacm-mux/* -F: qapi/rdma.json - Semihosting M: Alex Bennée <alex.bennee(a)linaro.org> S: Maintained diff --git a/docs/about/deprecated.rst b/docs/about/deprecated.rst index 7b548519b5..29eae69e50 100644 --- a/docs/about/deprecated.rst +++ b/docs/about/deprecated.rst @@ -376,15 +376,6 @@ recommending to switch to their stable counterparts: - "Zve64f" should be replaced with "zve64f" - "Zve64d" should be replaced with "zve64d" -``-device pvrdma`` and the rdma subsystem (since 8.2) -^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ - -The pvrdma device and the whole rdma subsystem are in a bad shape and -without active maintenance. The QEMU project intends to remove this -device and subsystem from the code base in a future release without -replacement unless somebody steps up and improves the situation. - - Block device options '''''''''''''''''''' diff --git a/docs/about/removed-features.rst b/docs/about/removed-features.rst index f9cf874f7b..4d5bdc43b4 100644 --- a/docs/about/removed-features.rst +++ b/docs/about/removed-features.rst @@ -909,6 +909,10 @@ contains native support for this feature and thus use of the option ROM approach was obsolete. The native SeaBIOS support can be activated by using ``-machine graphics=off``. +``pvrdma`` and the RDMA subsystem (removed in 9.1) +'''''''''''''''''''''''''''''''''''''''''''''''''' + +The 'pvrdma' device and the whole RDMA subsystem have been removed. Related binaries ---------------- diff --git a/docs/devel/migration/main.rst b/docs/devel/migration/main.rst index 54385a23e5..70278ce1e3 100644 --- a/docs/devel/migration/main.rst +++ b/docs/devel/migration/main.rst @@ -47,12 +47,6 @@ over any transport. QEMU interference. Note that QEMU does not flush cached file data/metadata at the end of migration. -In addition, support is included for migration using RDMA, which -transports the page data using ``RDMA``, where the hardware takes care of -transporting the pages, and the load on the CPU is much lower. While the -internals of RDMA migration are a bit different, this isn't really visible -outside the RAM migration code. - All these migration protocols use the same infrastructure to save/restore state devices. This infrastructure is shared with the savevm/loadvm functionality. diff --git a/docs/pvrdma.txt b/docs/pvrdma.txt deleted file mode 100644 index 5c122fe818..0000000000 --- a/docs/pvrdma.txt +++ /dev/null @@ -1,345 +0,0 @@ -Paravirtualized RDMA Device (PVRDMA) -==================================== - - -1. Description -=============== -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 as peers. - -It 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. - -A project presentation accompany this document: -- https://blog.linuxplumbersconf.org/2017/ocw/system/presentations/4730/origi… - - - -2. Setup -======== - - -2.1 Guest setup -=============== -Fedora 27+ kernels work out of the box, older distributions -require updating the kernel to 4.14 to include the pvrdma driver. - -However the libpvrdma library needed by User Level Software is still -not available as part of the distributions, so the rdma-core library -needs to be compiled and optionally installed. - -Please follow the instructions at: - https://github.com/linux-rdma/rdma-core.git - - -2.2 Host Setup -============== -The pvrdma backend is an ibdevice interface that can be exposed -either by a Soft-RoCE(rxe) device on machines with no RDMA device, -or an HCA SRIOV function(VF/PF). -Note that ibdevice interfaces can't be shared between pvrdma devices, -each one requiring a separate instance (rxe or SRIOV VF). - - -2.2.1 Soft-RoCE backend(rxe) -=========================== -A stable version of rxe is required, Fedora 27+ or a Linux -Kernel 4.14+ is preferred. - -The rdma_rxe module is part of the Linux Kernel but not loaded by default. -Install the User Level library (librxe) following the instructions from: -https://github.com/SoftRoCE/rxe-dev/wiki/rxe-dev:-Home - -Associate an ETH interface with rxe by running: - rxe_cfg add eth0 -An rxe0 ibdevice interface will be created and can be used as pvrdma backend. - - -2.2.2 RDMA device Virtual Function backend -========================================== -Nothing special is required, the pvrdma device can work not only with -Ethernet Links, but also Infinibands Links. -All is needed is an ibdevice with an active port, for Mellanox cards -will be something like mlx5_6 which can be the backend. - - -2.2.3 QEMU setup -================ -Configure QEMU with --enable-rdma flag, installing -the required RDMA libraries. - - - -3. Usage -======== - - -3.1 VM Memory settings -====================== -Currently the device is working only with memory backed RAM -and it must be mark as "shared": - -m 1G \ - -object memory-backend-ram,id=mb1,size=1G,share \ - -numa node,memdev=mb1 \ - - -3.2 MAD Multiplexer -=================== -MAD Multiplexer is a service that exposes MAD-like interface for VMs in -order to overcome the limitation where only single entity can register with -MAD layer to send and receive RDMA-CM MAD packets. - -To build rdmacm-mux run -# make rdmacm-mux - -Before running the rdmacm-mux make sure that both ib_cm and rdma_cm kernel -modules aren't loaded, otherwise the rdmacm-mux service will fail to start. - -The application accepts 3 command line arguments and exposes a UNIX socket -to pass control and data to it. --d rdma-device-name Name of RDMA device to register with --s unix-socket-path Path to unix socket to listen (default /var/run/rdmacm-mux) --p rdma-device-port Port number of RDMA device to register with (default 1) -The final UNIX socket file name is a concatenation of the 3 arguments so -for example for device mlx5_0 on port 2 this /var/run/rdmacm-mux-mlx5_0-2 -will be created. - -pvrdma requires this service. - -Please refer to contrib/rdmacm-mux for more details. - - -3.3 Service exposed by libvirt daemon -===================================== -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 the device hooks into the create_bind and -destroy_bind HW commands triggered by pvrdma driver in guest. - -Whenever changed is made to the pvrdma port's GID table a special QMP -messages is sent to be processed by libvirt to update the address of the -backend Ethernet device. - -pvrdma requires that libvirt service will be up. - - -3.4 PCI devices settings -======================== -RoCE device exposes two functions - an Ethernet and RDMA. -To support it, pvrdma device is composed of two PCI functions, an Ethernet -device of type vmxnet3 on PCI slot 0 and a PVRDMA device on PCI slot 1. The -Ethernet function can be used for other Ethernet purposes such as IP. - - -3.5 Device parameters -===================== -- netdev: Specifies the Ethernet device function name on the host for - example enp175s0f0. For Soft-RoCE device (rxe) this would be the Ethernet - device used to create it. -- ibdev: The IB device name on host for example rxe0, mlx5_0 etc. -- mad-chardev: The name of the MAD multiplexer char device. -- ibport: In case of multi-port device (such as Mellanox's HCA) this - specify the port to use. If not set 1 will be used. -- dev-caps-max-mr-size: The maximum size of MR. -- dev-caps-max-qp: Maximum number of QPs. -- dev-caps-max-cq: Maximum number of CQs. -- dev-caps-max-mr: Maximum number of MRs. -- dev-caps-max-pd: Maximum number of PDs. -- dev-caps-max-ah: Maximum number of AHs. - -Notes: -- The first 3 parameters are mandatory settings, the rest have their - defaults. -- The last 8 parameters (the ones that prefixed by dev-caps) defines the top - limits but the final values is adjusted by the backend device limitations. -- netdev can be extracted from ibdev's sysfs - (/sys/class/infiniband/<ibdev>/device/net/) - - -3.6 Example -=========== -Define bridge device with vmxnet3 network backend: -<interface type='bridge'> - <mac address='56:b4:44:e9:62:dc'/> - <source bridge='bridge1'/> - <model type='vmxnet3'/> - <address type='pci' domain='0x0000' bus='0x00' slot='0x10' function='0x0' multifunction='on'/> -</interface> - -Define pvrdma device: -<qemu:commandline> - <qemu:arg value='-object'/> - <qemu:arg value='memory-backend-ram,id=mb1,size=1G,share'/> - <qemu:arg value='-numa'/> - <qemu:arg value='node,memdev=mb1'/> - <qemu:arg value='-chardev'/> - <qemu:arg value='socket,path=/var/run/rdmacm-mux-rxe0-1,id=mads'/> - <qemu:arg value='-device'/> - <qemu:arg value='pvrdma,addr=10.1,ibdev=rxe0,netdev=bridge0,mad-chardev=mads'/> -</qemu:commandline> - - - -4. Implementation details -========================= - - -4.1 Overview -============ -The device acts like a proxy between the Guest Driver and the host -ibdevice interface. -On configuration path: - - For every hardware resource request (PD/QP/CQ/...) the pvrdma will request - a resource from the backend interface, maintaining a 1-1 mapping - between the guest and host. -On data path: - - Every post_send/receive received from the guest will be converted into - a post_send/receive for the backend. The buffers data will not be touched - or copied resulting in near bare-metal performance for large enough buffers. - - Completions from the backend interface will result in completions for - the pvrdma device. - - -4.2 PCI BARs -============ -PCI Bars: - BAR 0 - MSI-X - MSI-X vectors: - (0) Command - used when execution of a command is completed. - (1) Async - not in use. - (2) Completion - used when a completion event is placed in - device's CQ ring. - BAR 1 - Registers - -------------------------------------------------------- - | VERSION | DSR | CTL | REQ | ERR | ICR | IMR | MAC | - -------------------------------------------------------- - DSR - Address of driver/device shared memory used - for the command channel, used for passing: - - General info such as driver version - - Address of 'command' and 'response' - - Address of async ring - - Address of device's CQ ring - - Device capabilities - CTL - Device control operations (activate, reset etc) - IMG - Set interrupt mask - REQ - Command execution register - ERR - Operation status - - BAR 2 - UAR - --------------------------------------------------------- - | QP_NUM | SEND/RECV Flag || CQ_NUM | ARM/POLL Flag | - --------------------------------------------------------- - - Offset 0 used for QP operations (send and recv) - - Offset 4 used for CQ operations (arm and poll) - - -4.3 Major flows -=============== - -4.3.1 Create CQ -=============== - - Guest driver - - Allocates pages for CQ ring - - Creates page directory (pdir) to hold CQ ring's pages - - Initializes CQ ring - - Initializes 'Create CQ' command object (cqe, pdir etc) - - Copies the command to 'command' address - - Writes 0 into REQ register - - Device - - Reads the request object from the 'command' address - - Allocates CQ object and initialize CQ ring based on pdir - - Creates the backend CQ - - Writes operation status to ERR register - - Posts command-interrupt to guest - - Guest driver - - Reads the HW response code from ERR register - -4.3.2 Create QP -=============== - - Guest driver - - Allocates pages for send and receive rings - - Creates page directory(pdir) to hold the ring's pages - - Initializes 'Create QP' command object (max_send_wr, - send_cq_handle, recv_cq_handle, pdir etc) - - Copies the object to 'command' address - - Write 0 into REQ register - - Device - - Reads the request object from 'command' address - - Allocates the QP object and initialize - - Send and recv rings based on pdir - - Send and recv ring state - - Creates the backend QP - - Writes the operation status to ERR register - - Posts command-interrupt to guest - - Guest driver - - Reads the HW response code from ERR register - -4.3.3 Post receive -================== - - Guest driver - - Initializes a wqe and place it on recv ring - - Write to qpn|qp_recv_bit (31) to QP offset in UAR - - Device - - Extracts qpn from UAR - - Walks through the ring and does the following for each wqe - - Prepares the backend CQE context to be used when - receiving completion from backend (wr_id, op_code, emu_cq_num) - - For each sge prepares backend sge - - Calls backend's post_recv - -4.3.4 Process backend events -============================ - - Done by a dedicated thread used to process backend events; - at initialization is attached to the device and creates - the communication channel. - - Thread main loop: - - Polls for completions - - Extracts QEMU _cq_num, wr_id and op_code from context - - Writes CQE to CQ ring - - Writes CQ number to device CQ - - Sends completion-interrupt to guest - - Deallocates context - - Acks the event to backend - - - -5. Limitations -============== -- The device obviously is limited by the Guest Linux Driver features implementation - of the VMware device API. -- Memory registration mechanism requires mremap for every page in the buffer in order - to map it to a contiguous virtual address range. Since this is not the data path - it should not matter much. If the default max mr size is increased, be aware that - memory registration can take up to 0.5 seconds for 1GB of memory. -- The device requires target page size to be the same as the host page size, - otherwise it will fail to init. -- QEMU cannot map guest RAM from a file descriptor if a pvrdma device is attached, - so it can't work with huge pages. The limitation will be addressed in the future, - however QEMU allocates Guest RAM with MADV_HUGEPAGE so if there are enough huge - pages available, QEMU will use them. QEMU will fail to init if the requirements - are not met. - - - -6. Performance -============== -By design the pvrdma device exits on each post-send/receive, so for small buffers -the performance is affected; however for medium buffers it will became close to -bare metal and from 1MB buffers and up it reaches bare metal performance. -(tested with 2 VMs, the pvrdma devices connected to 2 VFs of the same device) - -All the above assumes no memory registration is done on data path. diff --git a/docs/rdma.txt b/docs/rdma.txt deleted file mode 100644 index bd8dd799a9..0000000000 --- a/docs/rdma.txt +++ /dev/null @@ -1,420 +0,0 @@ -(RDMA: Remote Direct Memory Access) -RDMA Live Migration Specification, Version # 1 -============================================== -Wiki: https://wiki.qemu.org/Features/RDMALiveMigration -Github: git@github.com:hinesmr/qemu.git, 'rdma' branch - -Copyright (C) 2013 Michael R. Hines <mrhines(a)us.ibm.com> - -An *exhaustive* paper (2010) shows additional performance details -linked on the QEMU wiki above. - -Contents: -========= -* Introduction -* Before running -* Running -* Performance -* RDMA Migration Protocol Description -* Versioning and Capabilities -* QEMUFileRDMA Interface -* Migration of VM's ram -* Error handling -* TODO - -Introduction: -============= - -RDMA helps make your migration more deterministic under heavy load because -of the significantly lower latency and higher throughput over TCP/IP. This is -because the RDMA I/O architecture reduces the number of interrupts and -data copies by bypassing the host networking stack. In particular, a TCP-based -migration, under certain types of memory-bound workloads, may take a more -unpredictable amount of time to complete the migration if the amount of -memory tracked during each live migration iteration round cannot keep pace -with the rate of dirty memory produced by the workload. - -RDMA currently comes in two flavors: both Ethernet based (RoCE, or RDMA -over Converged Ethernet) as well as Infiniband-based. This implementation of -migration using RDMA is capable of using both technologies because of -the use of the OpenFabrics OFED software stack that abstracts out the -programming model irrespective of the underlying hardware. - -Refer to openfabrics.org or your respective RDMA hardware vendor for -an understanding on how to verify that you have the OFED software stack -installed in your environment. You should be able to successfully link -against the "librdmacm" and "libibverbs" libraries and development headers -for a working build of QEMU to run successfully using RDMA Migration. - -BEFORE RUNNING: -=============== - -Use of RDMA during migration requires pinning and registering memory -with the hardware. This means that memory must be physically resident -before the hardware can transmit that memory to another machine. -If this is not acceptable for your application or product, then the use -of RDMA migration may in fact be harmful to co-located VMs or other -software on the machine if there is not sufficient memory available to -relocate the entire footprint of the virtual machine. If so, then the -use of RDMA is discouraged and it is recommended to use standard TCP migration. - -Experimental: Next, decide if you want dynamic page registration. -For example, if you have an 8GB RAM virtual machine, but only 1GB -is in active use, then enabling this feature will cause all 8GB to -be pinned and resident in memory. This feature mostly affects the -bulk-phase round of the migration and can be enabled for extremely -high-performance RDMA hardware using the following command: - -QEMU Monitor Command: -$ migrate_set_capability rdma-pin-all on # disabled by default - -Performing this action will cause all 8GB to be pinned, so if that's -not what you want, then please ignore this step altogether. - -On the other hand, this will also significantly speed up the bulk round -of the migration, which can greatly reduce the "total" time of your migration. -Example performance of this using an idle VM in the previous example -can be found in the "Performance" section. - -Note: for very large virtual machines (hundreds of GBs), pinning all -*all* of the memory of your virtual machine in the kernel is very expensive -may extend the initial bulk iteration time by many seconds, -and thus extending the total migration time. However, this will not -affect the determinism or predictability of your migration you will -still gain from the benefits of advanced pinning with RDMA. - -RUNNING: -======== - -First, set the migration speed to match your hardware's capabilities: - -QEMU Monitor Command: -$ migrate_set_parameter max-bandwidth 40g # or whatever is the MAX of your RDMA device - -Next, on the destination machine, add the following to the QEMU command line: - -qemu ..... -incoming rdma:host:port - -Finally, perform the actual migration on the source machine: - -QEMU Monitor Command: -$ migrate -d rdma:host:port - -PERFORMANCE -=========== - -Here is a brief summary of total migration time and downtime using RDMA: -Using a 40gbps infiniband link performing a worst-case stress test, -using an 8GB RAM virtual machine: - -Using the following command: -$ apt-get install stress -$ stress --vm-bytes 7500M --vm 1 --vm-keep - -1. Migration throughput: 26 gigabits/second. -2. Downtime (stop time) varies between 15 and 100 milliseconds. - -EFFECTS of memory registration on bulk phase round: - -For example, in the same 8GB RAM example with all 8GB of memory in -active use and the VM itself is completely idle using the same 40 gbps -infiniband link: - -1. rdma-pin-all disabled total time: approximately 7.5 seconds @ 9.5 Gbps -2. rdma-pin-all enabled total time: approximately 4 seconds @ 26 Gbps - -These numbers would of course scale up to whatever size virtual machine -you have to migrate using RDMA. - -Enabling this feature does *not* have any measurable affect on -migration *downtime*. This is because, without this feature, all of the -memory will have already been registered already in advance during -the bulk round and does not need to be re-registered during the successive -iteration rounds. - -RDMA Protocol Description: -========================== - -Migration with RDMA is separated into two parts: - -1. The transmission of the pages using RDMA -2. Everything else (a control channel is introduced) - -"Everything else" is transmitted using a formal -protocol now, consisting of infiniband SEND messages. - -An infiniband SEND message is the standard ibverbs -message used by applications of infiniband hardware. -The only difference between a SEND message and an RDMA -message is that SEND messages cause notifications -to be posted to the completion queue (CQ) on the -infiniband receiver side, whereas RDMA messages (used -for VM's ram) do not (to behave like an actual DMA). - -Messages in infiniband require two things: - -1. registration of the memory that will be transmitted -2. (SEND only) work requests to be posted on both - sides of the network before the actual transmission - can occur. - -RDMA messages are much easier to deal with. Once the memory -on the receiver side is registered and pinned, we're -basically done. All that is required is for the sender -side to start dumping bytes onto the link. - -(Memory is not released from pinning until the migration -completes, given that RDMA migrations are very fast.) - -SEND messages require more coordination because the -receiver must have reserved space (using a receive -work request) on the receive queue (RQ) before QEMUFileRDMA -can start using them to carry all the bytes as -a control transport for migration of device state. - -To begin the migration, the initial connection setup is -as follows (migration-rdma.c): - -1. Receiver and Sender are started (command line or libvirt): -2. Both sides post two RQ work requests -3. Receiver does listen() -4. Sender does connect() -5. Receiver accept() -6. Check versioning and capabilities (described later) - -At this point, we define a control channel on top of SEND messages -which is described by a formal protocol. Each SEND message has a -header portion and a data portion (but together are transmitted -as a single SEND message). - -Header: - * Length (of the data portion, uint32, network byte order) - * Type (what command to perform, uint32, network byte order) - * Repeat (Number of commands in data portion, same type only) - -The 'Repeat' field is here to support future multiple page registrations -in a single message without any need to change the protocol itself -so that the protocol is compatible against multiple versions of QEMU. -Version #1 requires that all server implementations of the protocol must -check this field and register all requests found in the array of commands located -in the data portion and return an equal number of results in the response. -The maximum number of repeats is hard-coded to 4096. This is a conservative -limit based on the maximum size of a SEND message along with empirical -observations on the maximum future benefit of simultaneous page registrations. - -The 'type' field has 12 different command values: - 1. Unused - 2. Error (sent to the source during bad things) - 3. Ready (control-channel is available) - 4. QEMU File (for sending non-live device state) - 5. RAM Blocks request (used right after connection setup) - 6. RAM Blocks result (used right after connection setup) - 7. Compress page (zap zero page and skip registration) - 8. Register request (dynamic chunk registration) - 9. Register result ('rkey' to be used by sender) - 10. Register finished (registration for current iteration finished) - 11. Unregister request (unpin previously registered memory) - 12. Unregister finished (confirmation that unpin completed) - -A single control message, as hinted above, can contain within the data -portion an array of many commands of the same type. If there is more than -one command, then the 'repeat' field will be greater than 1. - -After connection setup, message 5 & 6 are used to exchange ram block -information and optionally pin all the memory if requested by the user. - -After ram block exchange is completed, we have two protocol-level -functions, responsible for communicating control-channel commands -using the above list of values: - -Logically: - -qemu_rdma_exchange_recv(header, expected command type) - -1. We transmit a READY command to let the sender know that - we are *ready* to receive some data bytes on the control channel. -2. Before attempting to receive the expected command, we post another - RQ work request to replace the one we just used up. -3. Block on a CQ event channel and wait for the SEND to arrive. -4. When the send arrives, librdmacm will unblock us. -5. Verify that the command-type and version received matches the one we expected. - -qemu_rdma_exchange_send(header, data, optional response header & data): - -1. Block on the CQ event channel waiting for a READY command - from the receiver to tell us that the receiver - is *ready* for us to transmit some new bytes. -2. Optionally: if we are expecting a response from the command - (that we have not yet transmitted), let's post an RQ - work request to receive that data a few moments later. -3. When the READY arrives, librdmacm will - unblock us and we immediately post a RQ work request - to replace the one we just used up. -4. Now, we can actually post the work request to SEND - the requested command type of the header we were asked for. -5. Optionally, if we are expecting a response (as before), - we block again and wait for that response using the additional - work request we previously posted. (This is used to carry - 'Register result' commands #6 back to the sender which - hold the rkey need to perform RDMA. Note that the virtual address - corresponding to this rkey was already exchanged at the beginning - of the connection (described below). - -All of the remaining command types (not including 'ready') -described above all use the aforementioned two functions to do the hard work: - -1. After connection setup, RAMBlock information is exchanged using - this protocol before the actual migration begins. This information includes - a description of each RAMBlock on the server side as well as the virtual addresses - and lengths of each RAMBlock. This is used by the client to determine the - start and stop locations of chunks and how to register them dynamically - before performing the RDMA operations. -2. During runtime, once a 'chunk' becomes full of pages ready to - be sent with RDMA, the registration commands are used to ask the - other side to register the memory for this chunk and respond - with the result (rkey) of the registration. -3. Also, the QEMUFile interfaces also call these functions (described below) - when transmitting non-live state, such as devices or to send - its own protocol information during the migration process. -4. Finally, zero pages are only checked if a page has not yet been registered - using chunk registration (or not checked at all and unconditionally - written if chunk registration is disabled. This is accomplished using - the "Compress" command listed above. If the page *has* been registered - then we check the entire chunk for zero. Only if the entire chunk is - zero, then we send a compress command to zap the page on the other side. - -Versioning and Capabilities -=========================== -Current version of the protocol is version #1. - -The same version applies to both for protocol traffic and capabilities -negotiation. (i.e. There is only one version number that is referred to -by all communication). - -librdmacm provides the user with a 'private data' area to be exchanged -at connection-setup time before any infiniband traffic is generated. - -Header: - * Version (protocol version validated before send/recv occurs), - uint32, network byte order - * Flags (bitwise OR of each capability), - uint32, network byte order - -There is no data portion of this header right now, so there is -no length field. The maximum size of the 'private data' section -is only 192 bytes per the Infiniband specification, so it's not -very useful for data anyway. This structure needs to remain small. - -This private data area is a convenient place to check for protocol -versioning because the user does not need to register memory to -transmit a few bytes of version information. - -This is also a convenient place to negotiate capabilities -(like dynamic page registration). - -If the version is invalid, we throw an error. - -If the version is new, we only negotiate the capabilities that the -requested version is able to perform and ignore the rest. - -Currently there is only one capability in Version #1: dynamic page registration - -Finally: Negotiation happens with the Flags field: If the primary-VM -sets a flag, but the destination does not support this capability, it -will return a zero-bit for that flag and the primary-VM will understand -that as not being an available capability and will thus disable that -capability on the primary-VM side. - -QEMUFileRDMA Interface: -======================= - -QEMUFileRDMA introduces a couple of new functions: - -1. qemu_rdma_get_buffer() (QEMUFileOps rdma_read_ops) -2. qemu_rdma_put_buffer() (QEMUFileOps rdma_write_ops) - -These two functions are very short and simply use the protocol -describe above to deliver bytes without changing the upper-level -users of QEMUFile that depend on a bytestream abstraction. - -Finally, how do we handoff the actual bytes to get_buffer()? - -Again, because we're trying to "fake" a bytestream abstraction -using an analogy not unlike individual UDP frames, we have -to hold on to the bytes received from control-channel's SEND -messages in memory. - -Each time we receive a complete "QEMU File" control-channel -message, the bytes from SEND are copied into a small local holding area. - -Then, we return the number of bytes requested by get_buffer() -and leave the remaining bytes in the holding area until get_buffer() -comes around for another pass. - -If the buffer is empty, then we follow the same steps -listed above and issue another "QEMU File" protocol command, -asking for a new SEND message to re-fill the buffer. - -Migration of VM's ram: -==================== - -At the beginning of the migration, (migration-rdma.c), -the sender and the receiver populate the list of RAMBlocks -to be registered with each other into a structure. -Then, using the aforementioned protocol, they exchange a -description of these blocks with each other, to be used later -during the iteration of main memory. This description includes -a list of all the RAMBlocks, their offsets and lengths, virtual -addresses and possibly includes pre-registered RDMA keys in case dynamic -page registration was disabled on the server-side, otherwise not. - -Main memory is not migrated with the aforementioned protocol, -but is instead migrated with normal RDMA Write operations. - -Pages are migrated in "chunks" (hard-coded to 1 Megabyte right now). -Chunk size is not dynamic, but it could be in a future implementation. -There's nothing to indicate that this is useful right now. - -When a chunk is full (or a flush() occurs), the memory backed by -the chunk is registered with librdmacm is pinned in memory on -both sides using the aforementioned protocol. -After pinning, an RDMA Write is generated and transmitted -for the entire chunk. - -Chunks are also transmitted in batches: This means that we -do not request that the hardware signal the completion queue -for the completion of *every* chunk. The current batch size -is about 64 chunks (corresponding to 64 MB of memory). -Only the last chunk in a batch must be signaled. -This helps keep everything as asynchronous as possible -and helps keep the hardware busy performing RDMA operations. - -Error-handling: -=============== - -Infiniband has what is called a "Reliable, Connected" -link (one of 4 choices). This is the mode in which -we use for RDMA migration. - -If a *single* message fails, -the decision is to abort the migration entirely and -cleanup all the RDMA descriptors and unregister all -the memory. - -After cleanup, the Virtual Machine is returned to normal -operation the same way that would happen if the TCP -socket is broken during a non-RDMA based migration. - -TODO: -===== -1. Currently, 'ulimit -l' mlock() limits as well as cgroups swap limits - are not compatible with infiniband memory pinning and will result in - an aborted migration (but with the source VM left unaffected). -2. Use of the recent /proc/<pid>/pagemap would likely speed up - the use of KSM and ballooning while using RDMA. -3. Also, some form of balloon-device usage tracking would also - help alleviate some issues. -4. Use LRU to provide more fine-grained direction of UNREGISTER - requests for unpinning memory in an overcommitted environment. -5. Expose UNREGISTER support to the user by way of workload-specific - hints about application behavior. diff --git a/docs/system/device-url-syntax.rst.inc b/docs/system/device-url-syntax.rst.inc index 7dbc525fa8..43b5c2596b 100644 --- a/docs/system/device-url-syntax.rst.inc +++ b/docs/system/device-url-syntax.rst.inc @@ -87,8 +87,8 @@ These are specified using a special URL syntax. ``GlusterFS`` GlusterFS is a user space distributed file system. QEMU supports the - use of GlusterFS volumes for hosting VM disk images using TCP, Unix - Domain Sockets and RDMA transport protocols. + use of GlusterFS volumes for hosting VM disk images using TCP and Unix + Domain Sockets transport protocols. Syntax for specifying a VM disk image on GlusterFS volume is diff --git a/docs/system/loongarch/virt.rst b/docs/system/loongarch/virt.rst index c37268b404..0a8e0766e4 100644 --- a/docs/system/loongarch/virt.rst +++ b/docs/system/loongarch/virt.rst @@ -39,7 +39,7 @@ can be accessed by following steps. .. code-block:: bash - ./configure --disable-rdma --disable-pvrdma --prefix=/usr \ + ./configure --prefix=/usr \ --target-list="loongarch64-softmmu" \ --disable-libiscsi --disable-libnfs --disable-libpmem \ --disable-glusterfs --enable-libusb --enable-usb-redir \ diff --git a/docs/system/qemu-block-drivers.rst.inc b/docs/system/qemu-block-drivers.rst.inc index 105cb9679c..384e95ba76 100644 --- a/docs/system/qemu-block-drivers.rst.inc +++ b/docs/system/qemu-block-drivers.rst.inc @@ -737,7 +737,6 @@ Examples |qemu_system| -drive file=gluster+tcp://[1:2:3:4:5:6:7:8]:24007/testvol/dir/a.img |qemu_system| -drive file=gluster+tcp://server.domain.com:24007/testvol/dir/a.img |qemu_system| -drive file=gluster+unix:///testvol/dir/a.img?socket=/tmp/glusterd.socket - |qemu_system| -drive file=gluster+rdma://1.2.3.4:24007/testvol/a.img |qemu_system| -drive file=gluster://1.2.3.4/testvol/a.img,file.debug=9,file.logfile=/var/log/qemu-gluster.log |qemu_system| 'json:{"driver":"qcow2", "file":{"driver":"gluster", diff --git a/meson.build b/meson.build index c9c3217ba4..bd65abad13 100644 --- a/meson.build +++ b/meson.build @@ -1854,21 +1854,6 @@ if numa.found() and not cc.links(''' endif endif -rdma = not_found -if not get_option('rdma').auto() or have_system - libumad = cc.find_library('ibumad', required: get_option('rdma')) - rdma_libs = [cc.find_library('rdmacm', has_headers: ['rdma/rdma_cma.h'], - required: get_option('rdma')), - cc.find_library('ibverbs', required: get_option('rdma')), - libumad] - rdma = declare_dependency(dependencies: rdma_libs) - foreach lib: rdma_libs - if not lib.found() - rdma = not_found - endif - endforeach -endif - cacard = not_found if not get_option('smartcard').auto() or have_system cacard = dependency('libcacard', required: get_option('smartcard'), @@ -2246,7 +2231,6 @@ endif config_host_data.set('CONFIG_OPENGL', opengl.found()) config_host_data.set('CONFIG_PLUGIN', get_option('plugins')) config_host_data.set('CONFIG_RBD', rbd.found()) -config_host_data.set('CONFIG_RDMA', rdma.found()) config_host_data.set('CONFIG_RELOCATABLE', get_option('relocatable')) config_host_data.set('CONFIG_SAFESTACK', get_option('safe_stack')) config_host_data.set('CONFIG_SDL', sdl.found()) @@ -2399,12 +2383,6 @@ if rbd.found() dependencies: rbd, prefix: '#include <rbd/librbd.h>')) endif -if rdma.found() - config_host_data.set('HAVE_IBV_ADVISE_MR', - cc.has_function('ibv_advise_mr', - dependencies: rdma, - prefix: '#include <infiniband/verbs.h>')) -endif have_asan_fiber = false if get_option('sanitizers') and \ @@ -2829,37 +2807,6 @@ config_host_data.set('CONFIG_ARM_AES_BUILTIN', cc.compiles(''' void foo(uint8x16_t *p) { *p = vaesmcq_u8(*p); } ''')) -have_pvrdma = get_option('pvrdma') \ - .require(rdma.found(), error_message: 'PVRDMA requires OpenFabrics libraries') \ - .require(cc.compiles(gnu_source_prefix + ''' - #include <sys/mman.h> - int main(void) - { - char buf = 0; - void *addr = &buf; - addr = mremap(addr, 0, 1, MREMAP_MAYMOVE | MREMAP_FIXED); - - return 0; - }'''), error_message: 'PVRDMA requires mremap').allowed() - -if have_pvrdma - config_host_data.set('LEGACY_RDMA_REG_MR', not cc.links(''' - #include <infiniband/verbs.h> - int main(void) - { - struct ibv_mr *mr; - struct ibv_pd *pd = NULL; - size_t length = 10; - uint64_t iova = 0; - int access = 0; - void *addr = NULL; - - mr = ibv_reg_mr_iova(pd, addr, length, iova, access); - ibv_dereg_mr(mr); - return 0; - }''')) -endif - if get_option('membarrier').disabled() have_membarrier = false elif host_os == 'windows' @@ -2993,7 +2940,6 @@ host_kconfig = \ (have_vhost_kernel ? ['CONFIG_VHOST_KERNEL=y'] : []) + \ (have_virtfs ? ['CONFIG_VIRTFS=y'] : []) + \ (host_os == 'linux' ? ['CONFIG_LINUX=y'] : []) + \ - (have_pvrdma ? ['CONFIG_PVRDMA=y'] : []) + \ (multiprocess_allowed ? ['CONFIG_MULTIPROCESS_ALLOWED=y'] : []) + \ (vfio_user_server_allowed ? ['CONFIG_VFIO_USER_SERVER_ALLOWED=y'] : []) + \ (hv_balloon ? ['CONFIG_HV_BALLOON_POSSIBLE=y'] : []) @@ -3357,8 +3303,6 @@ if have_system 'hw/pci', 'hw/pci-host', 'hw/ppc', - 'hw/rdma', - 'hw/rdma/vmw', 'hw/rtc', 'hw/s390x', 'hw/scsi', @@ -4028,7 +3972,6 @@ if have_tools }] endforeach - subdir('contrib/rdmacm-mux') subdir('contrib/elf2dmp') executable('qemu-edid', files('qemu-edid.c', 'hw/display/edid-generate.c'), @@ -4433,8 +4376,6 @@ summary_info += {'Multipath support': mpathpersist} summary_info += {'Linux AIO support': libaio} summary_info += {'Linux io_uring support': linux_io_uring} summary_info += {'ATTR/XATTR support': libattr} -summary_info += {'RDMA support': rdma} -summary_info += {'PVRDMA support': have_pvrdma} summary_info += {'fdt support': fdt_opt == 'disabled' ? false : fdt_opt} summary_info += {'libcap-ng support': libcap_ng} summary_info += {'bpf support': libbpf} diff --git a/qapi/machine.json b/qapi/machine.json index e8b60641f2..e9f0f0c49a 100644 --- a/qapi/machine.json +++ b/qapi/machine.json @@ -1737,23 +1737,6 @@ 'returns': 'HumanReadableText', 'features': [ 'unstable' ] } -## -# @x-query-rdma: -# -# Query RDMA state -# -# Features: -# -# @unstable: This command is meant for debugging. -# -# Returns: RDMA state -# -# Since: 6.2 -## -{ 'command': 'x-query-rdma', - 'returns': 'HumanReadableText', - 'features': [ 'unstable' ] } - ## # @x-query-roms: # diff --git a/qapi/migration.json b/qapi/migration.json index 8c65b90328..9a56d403be 100644 --- a/qapi/migration.json +++ b/qapi/migration.json @@ -221,8 +221,8 @@ # # @setup-time: amount of setup time in milliseconds *before* the # iterations begin but *after* the QMP command is issued. This is -# designed to provide an accounting of any activities (such as -# RDMA pinning) which may be expensive, but do not actually occur +# designed to provide an accounting of any activities which may be +# expensive, but do not actually occur # during the iterative migration rounds themselves. (since 1.6) # # @cpu-throttle-percentage: percentage of time guest cpus are being @@ -430,10 +430,6 @@ # for certain work loads, by sending compressed difference of the # pages # -# @rdma-pin-all: Controls whether or not the entire VM memory -# footprint is mlock()'d on demand or all at once. Refer to -# docs/rdma.txt for usage. Disabled by default. (since 2.0) -# # @zero-blocks: During storage migration encode blocks of zeroes # efficiently. This essentially saves 1MB of zeroes per block on # the wire. Enabling requires source and target VM to support @@ -547,7 +543,7 @@ # Since: 1.2 ## { 'enum': 'MigrationCapability', - 'data': ['xbzrle', 'rdma-pin-all', 'auto-converge', 'zero-blocks', + 'data': ['xbzrle', 'auto-converge', 'zero-blocks', { 'name': 'compress', 'features': [ 'deprecated' ] }, 'events', 'postcopy-ram', { 'name': 'x-colo', 'features': [ 'unstable' ] }, @@ -606,7 +602,6 @@ # -> { "execute": "query-migrate-capabilities" } # <- { "return": [ # {"state": false, "capability": "xbzrle"}, -# {"state": false, "capability": "rdma-pin-all"}, # {"state": false, "capability": "auto-converge"}, # {"state": false, "capability": "zero-blocks"}, # {"state": false, "capability": "compress"}, @@ -1654,14 +1649,12 @@ # # @exec: Direct the migration stream to another process. # -# @rdma: Migrate via RDMA. -# # @file: Direct the migration stream to a file. # # Since: 8.2 ## { 'enum': 'MigrationAddressType', - 'data': [ 'socket', 'exec', 'rdma', 'file' ] } + 'data': [ 'socket', 'exec', 'file' ] } ## # @FileMigrationArgs: @@ -1701,7 +1694,6 @@ 'data': { 'socket': 'SocketAddress', 'exec': 'MigrationExecCommand', - 'rdma': 'InetSocketAddress', 'file': 'FileMigrationArgs' } } ## @@ -1804,14 +1796,6 @@ # -> { "execute": "migrate", # "arguments": { # "channels": [ { "channel-type": "main", -# "addr": { "transport": "rdma", -# "host": "10.12.34.9", -# "port": "1050" } } ] } } -# <- { "return": {} } -# -# -> { "execute": "migrate", -# "arguments": { -# "channels": [ { "channel-type": "main", # "addr": { "transport": "file", # "filename": "/tmp/migfile", # "offset": "0x1000" } } ] } } @@ -1879,13 +1863,6 @@ # "/some/sock" ] } } ] } } # <- { "return": {} } # -# -> { "execute": "migrate-incoming", -# "arguments": { -# "channels": [ { "channel-type": "main", -# "addr": { "transport": "rdma", -# "host": "10.12.34.9", -# "port": "1050" } } ] } } -# <- { "return": {} } ## { 'command': 'migrate-incoming', 'data': {'*uri': 'str', diff --git a/qapi/qapi-schema.json b/qapi/qapi-schema.json index 8304d45625..5e33da7228 100644 --- a/qapi/qapi-schema.json +++ b/qapi/qapi-schema.json @@ -54,7 +54,6 @@ { 'include': 'dump.json' } { 'include': 'net.json' } { 'include': 'ebpf.json' } -{ 'include': 'rdma.json' } { 'include': 'rocker.json' } { 'include': 'tpm.json' } { 'include': 'ui.json' } diff --git a/qapi/rdma.json b/qapi/rdma.json deleted file mode 100644 index 195c001850..0000000000 --- a/qapi/rdma.json +++ /dev/null @@ -1,38 +0,0 @@ -# -*- Mode: Python -*- -# vim: filetype=python -# - -## -# = RDMA device -## - -## -# @RDMA_GID_STATUS_CHANGED: -# -# Emitted when guest driver adds/deletes GID to/from device -# -# @netdev: RoCE Network Device name -# -# @gid-status: Add or delete indication -# -# @subnet-prefix: Subnet Prefix -# -# @interface-id: Interface ID -# -# Since: 4.0 -# -# Example: -# -# <- {"timestamp": {"seconds": 1541579657, "microseconds": 986760}, -# "event": "RDMA_GID_STATUS_CHANGED", -# "data": -# {"netdev": "bridge0", -# "interface-id": 15880512517475447892, -# "gid-status": true, -# "subnet-prefix": 33022}} -## -{ 'event': 'RDMA_GID_STATUS_CHANGED', - 'data': { 'netdev' : 'str', - 'gid-status' : 'bool', - 'subnet-prefix' : 'uint64', - 'interface-id' : 'uint64' } } diff --git a/contrib/rdmacm-mux/rdmacm-mux.h b/contrib/rdmacm-mux/rdmacm-mux.h deleted file mode 100644 index 07a4722913..0000000000 --- a/contrib/rdmacm-mux/rdmacm-mux.h +++ /dev/null @@ -1,61 +0,0 @@ -/* - * QEMU paravirtual RDMA - rdmacm-mux declarations - * - * Copyright (C) 2018 Oracle - * Copyright (C) 2018 Red Hat Inc - * - * Authors: - * Yuval Shaia <yuval.shaia(a)oracle.com> - * Marcel Apfelbaum <marcel(a)redhat.com> - * - * This work is licensed under the terms of the GNU GPL, version 2 or later. - * See the COPYING file in the top-level directory. - * - */ - -#ifndef RDMACM_MUX_H -#define RDMACM_MUX_H - -#include "linux/if.h" -#include <infiniband/verbs.h> -#include <infiniband/umad.h> -#include <rdma/rdma_user_cm.h> - -typedef enum RdmaCmMuxMsgType { - RDMACM_MUX_MSG_TYPE_REQ = 0, - RDMACM_MUX_MSG_TYPE_RESP = 1, -} RdmaCmMuxMsgType; - -typedef enum RdmaCmMuxOpCode { - RDMACM_MUX_OP_CODE_REG = 0, - RDMACM_MUX_OP_CODE_UNREG = 1, - RDMACM_MUX_OP_CODE_MAD = 2, -} RdmaCmMuxOpCode; - -typedef enum RdmaCmMuxErrCode { - RDMACM_MUX_ERR_CODE_OK = 0, - RDMACM_MUX_ERR_CODE_EINVAL = 1, - RDMACM_MUX_ERR_CODE_EEXIST = 2, - RDMACM_MUX_ERR_CODE_EACCES = 3, - RDMACM_MUX_ERR_CODE_ENOTFOUND = 4, -} RdmaCmMuxErrCode; - -typedef struct RdmaCmMuxHdr { - RdmaCmMuxMsgType msg_type; - RdmaCmMuxOpCode op_code; - union ibv_gid sgid; - RdmaCmMuxErrCode err_code; -} RdmaCmUHdr; - -typedef struct RdmaCmUMad { - struct ib_user_mad hdr; - char mad[RDMA_MAX_PRIVATE_DATA]; -} RdmaCmUMad; - -typedef struct RdmaCmMuxMsg { - RdmaCmUHdr hdr; - int umad_len; - RdmaCmUMad umad; -} RdmaCmMuxMsg; - -#endif diff --git a/hw/rdma/rdma_backend.h b/hw/rdma/rdma_backend.h deleted file mode 100644 index 225af481e0..0000000000 --- a/hw/rdma/rdma_backend.h +++ /dev/null @@ -1,129 +0,0 @@ -/* - * RDMA device: Definitions of Backend Device functions - * - * Copyright (C) 2018 Oracle - * Copyright (C) 2018 Red Hat Inc - * - * Authors: - * Yuval Shaia <yuval.shaia(a)oracle.com> - * Marcel Apfelbaum <marcel(a)redhat.com> - * - * This work is licensed under the terms of the GNU GPL, version 2 or later. - * See the COPYING file in the top-level directory. - * - */ - -#ifndef RDMA_BACKEND_H -#define RDMA_BACKEND_H - -#include "qapi/error.h" -#include "chardev/char-fe.h" - -#include "rdma_rm_defs.h" -#include "rdma_backend_defs.h" - -/* Vendor Errors */ -#define VENDOR_ERR_FAIL_BACKEND 0x201 -#define VENDOR_ERR_TOO_MANY_SGES 0x202 -#define VENDOR_ERR_NOMEM 0x203 -#define VENDOR_ERR_QP0 0x204 -#define VENDOR_ERR_INV_NUM_SGE 0x205 -#define VENDOR_ERR_MAD_SEND 0x206 -#define VENDOR_ERR_INVLKEY 0x207 -#define VENDOR_ERR_MR_SMALL 0x208 -#define VENDOR_ERR_INV_MAD_BUFF 0x209 -#define VENDOR_ERR_INV_GID_IDX 0x210 - -/* Add definition for QP0 and QP1 as there is no userspace enums for them */ -enum ibv_special_qp_type { - IBV_QPT_SMI = 0, - IBV_QPT_GSI = 1, -}; - -static inline uint32_t rdma_backend_qpn(const RdmaBackendQP *qp) -{ - return qp->ibqp ? qp->ibqp->qp_num : 1; -} - -static inline uint32_t rdma_backend_mr_lkey(const RdmaBackendMR *mr) -{ - return mr->ibmr ? mr->ibmr->lkey : 0; -} - -static inline uint32_t rdma_backend_mr_rkey(const RdmaBackendMR *mr) -{ - return mr->ibmr ? mr->ibmr->rkey : 0; -} - -int rdma_backend_init(RdmaBackendDev *backend_dev, PCIDevice *pdev, - RdmaDeviceResources *rdma_dev_res, - const char *backend_device_name, uint8_t port_num, - struct ibv_device_attr *dev_attr, - CharBackend *mad_chr_be); -void rdma_backend_fini(RdmaBackendDev *backend_dev); -int rdma_backend_add_gid(RdmaBackendDev *backend_dev, const char *ifname, - union ibv_gid *gid); -int rdma_backend_del_gid(RdmaBackendDev *backend_dev, const char *ifname, - union ibv_gid *gid); -int rdma_backend_get_gid_index(RdmaBackendDev *backend_dev, - union ibv_gid *gid); -void rdma_backend_start(RdmaBackendDev *backend_dev); -void rdma_backend_stop(RdmaBackendDev *backend_dev); -void rdma_backend_register_comp_handler(void (*handler)(void *ctx, - struct ibv_wc *wc)); -void rdma_backend_unregister_comp_handler(void); - -int rdma_backend_query_port(RdmaBackendDev *backend_dev, - struct ibv_port_attr *port_attr); -int rdma_backend_create_pd(RdmaBackendDev *backend_dev, RdmaBackendPD *pd); -void rdma_backend_destroy_pd(RdmaBackendPD *pd); - -int rdma_backend_create_mr(RdmaBackendMR *mr, RdmaBackendPD *pd, void *addr, - size_t length, uint64_t guest_start, int access); -void rdma_backend_destroy_mr(RdmaBackendMR *mr); - -int rdma_backend_create_cq(RdmaBackendDev *backend_dev, RdmaBackendCQ *cq, - int cqe); -void rdma_backend_destroy_cq(RdmaBackendCQ *cq); -void rdma_backend_poll_cq(RdmaDeviceResources *rdma_dev_res, RdmaBackendCQ *cq); - -int rdma_backend_create_qp(RdmaBackendQP *qp, uint8_t qp_type, - RdmaBackendPD *pd, RdmaBackendCQ *scq, - RdmaBackendCQ *rcq, RdmaBackendSRQ *srq, - uint32_t max_send_wr, uint32_t max_recv_wr, - uint32_t max_send_sge, uint32_t max_recv_sge); -int rdma_backend_qp_state_init(RdmaBackendDev *backend_dev, RdmaBackendQP *qp, - uint8_t qp_type, uint32_t qkey); -int rdma_backend_qp_state_rtr(RdmaBackendDev *backend_dev, RdmaBackendQP *qp, - uint8_t qp_type, uint8_t sgid_idx, - union ibv_gid *dgid, uint32_t dqpn, - uint32_t rq_psn, uint32_t qkey, bool use_qkey); -int rdma_backend_qp_state_rts(RdmaBackendQP *qp, uint8_t qp_type, - uint32_t sq_psn, uint32_t qkey, bool use_qkey); -int rdma_backend_query_qp(RdmaBackendQP *qp, struct ibv_qp_attr *attr, - int attr_mask, struct ibv_qp_init_attr *init_attr); -void rdma_backend_destroy_qp(RdmaBackendQP *qp, RdmaDeviceResources *dev_res); - -void rdma_backend_post_send(RdmaBackendDev *backend_dev, - RdmaBackendQP *qp, uint8_t qp_type, - struct ibv_sge *sge, uint32_t num_sge, - uint8_t sgid_idx, union ibv_gid *sgid, - union ibv_gid *dgid, uint32_t dqpn, uint32_t dqkey, - void *ctx); -void rdma_backend_post_recv(RdmaBackendDev *backend_dev, - RdmaBackendQP *qp, uint8_t qp_type, - struct ibv_sge *sge, uint32_t num_sge, void *ctx); - -int rdma_backend_create_srq(RdmaBackendSRQ *srq, RdmaBackendPD *pd, - uint32_t max_wr, uint32_t max_sge, - uint32_t srq_limit); -int rdma_backend_query_srq(RdmaBackendSRQ *srq, struct ibv_srq_attr *srq_attr); -int rdma_backend_modify_srq(RdmaBackendSRQ *srq, struct ibv_srq_attr *srq_attr, - int srq_attr_mask); -void rdma_backend_destroy_srq(RdmaBackendSRQ *srq, - RdmaDeviceResources *dev_res); -void rdma_backend_post_srq_recv(RdmaBackendDev *backend_dev, - RdmaBackendSRQ *srq, struct ibv_sge *sge, - uint32_t num_sge, void *ctx); - -#endif diff --git a/hw/rdma/rdma_backend_defs.h b/hw/rdma/rdma_backend_defs.h deleted file mode 100644 index 4e6c0ad695..0000000000 --- a/hw/rdma/rdma_backend_defs.h +++ /dev/null @@ -1,76 +0,0 @@ -/* - * RDMA device: Definitions of Backend Device structures - * - * Copyright (C) 2018 Oracle - * Copyright (C) 2018 Red Hat Inc - * - * Authors: - * Yuval Shaia <yuval.shaia(a)oracle.com> - * Marcel Apfelbaum <marcel(a)redhat.com> - * - * This work is licensed under the terms of the GNU GPL, version 2 or later. - * See the COPYING file in the top-level directory. - * - */ - -#ifndef RDMA_BACKEND_DEFS_H -#define RDMA_BACKEND_DEFS_H - -#include "qemu/thread.h" -#include "chardev/char-fe.h" -#include <infiniband/verbs.h> -#include "contrib/rdmacm-mux/rdmacm-mux.h" -#include "rdma_utils.h" - -typedef struct RdmaDeviceResources RdmaDeviceResources; - -typedef struct RdmaBackendThread { - QemuThread thread; - bool run; /* Set by thread manager to let thread know it should exit */ - bool is_running; /* Set by the thread to report its status */ -} RdmaBackendThread; - -typedef struct RdmaCmMux { - CharBackend *chr_be; - int can_receive; -} RdmaCmMux; - -typedef struct RdmaBackendDev { - RdmaBackendThread comp_thread; - PCIDevice *dev; - RdmaDeviceResources *rdma_dev_res; - struct ibv_device *ib_dev; - struct ibv_context *context; - struct ibv_comp_channel *channel; - uint8_t port_num; - RdmaProtectedGQueue recv_mads_list; - RdmaCmMux rdmacm_mux; -} RdmaBackendDev; - -typedef struct RdmaBackendPD { - struct ibv_pd *ibpd; -} RdmaBackendPD; - -typedef struct RdmaBackendMR { - struct ibv_pd *ibpd; - struct ibv_mr *ibmr; -} RdmaBackendMR; - -typedef struct RdmaBackendCQ { - RdmaBackendDev *backend_dev; - struct ibv_cq *ibcq; -} RdmaBackendCQ; - -typedef struct RdmaBackendQP { - struct ibv_pd *ibpd; - struct ibv_qp *ibqp; - uint8_t sgid_idx; - RdmaProtectedGSList cqe_ctx_list; -} RdmaBackendQP; - -typedef struct RdmaBackendSRQ { - struct ibv_srq *ibsrq; - RdmaProtectedGSList cqe_ctx_list; -} RdmaBackendSRQ; - -#endif diff --git a/hw/rdma/rdma_rm.h b/hw/rdma/rdma_rm.h deleted file mode 100644 index d69a917795..0000000000 --- a/hw/rdma/rdma_rm.h +++ /dev/null @@ -1,97 +0,0 @@ -/* - * RDMA device: Definitions of Resource Manager functions - * - * Copyright (C) 2018 Oracle - * Copyright (C) 2018 Red Hat Inc - * - * Authors: - * Yuval Shaia <yuval.shaia(a)oracle.com> - * Marcel Apfelbaum <marcel(a)redhat.com> - * - * This work is licensed under the terms of the GNU GPL, version 2 or later. - * See the COPYING file in the top-level directory. - * - */ - -#ifndef RDMA_RM_H -#define RDMA_RM_H - -#include "qapi/error.h" -#include "rdma_backend_defs.h" -#include "rdma_rm_defs.h" - -int rdma_rm_init(RdmaDeviceResources *dev_res, - struct ibv_device_attr *dev_attr); -void rdma_rm_fini(RdmaDeviceResources *dev_res, RdmaBackendDev *backend_dev, - const char *ifname); - -int rdma_rm_alloc_pd(RdmaDeviceResources *dev_res, RdmaBackendDev *backend_dev, - uint32_t *pd_handle, uint32_t ctx_handle); -RdmaRmPD *rdma_rm_get_pd(RdmaDeviceResources *dev_res, uint32_t pd_handle); -void rdma_rm_dealloc_pd(RdmaDeviceResources *dev_res, uint32_t pd_handle); - -int rdma_rm_alloc_mr(RdmaDeviceResources *dev_res, uint32_t pd_handle, - uint64_t guest_start, uint64_t guest_length, - void *host_virt, int access_flags, uint32_t *mr_handle, - uint32_t *lkey, uint32_t *rkey); -RdmaRmMR *rdma_rm_get_mr(RdmaDeviceResources *dev_res, uint32_t mr_handle); -void rdma_rm_dealloc_mr(RdmaDeviceResources *dev_res, uint32_t mr_handle); - -int rdma_rm_alloc_uc(RdmaDeviceResources *dev_res, uint32_t pfn, - uint32_t *uc_handle); -RdmaRmUC *rdma_rm_get_uc(RdmaDeviceResources *dev_res, uint32_t uc_handle); -void rdma_rm_dealloc_uc(RdmaDeviceResources *dev_res, uint32_t uc_handle); - -int rdma_rm_alloc_cq(RdmaDeviceResources *dev_res, RdmaBackendDev *backend_dev, - uint32_t cqe, uint32_t *cq_handle, void *opaque); -RdmaRmCQ *rdma_rm_get_cq(RdmaDeviceResources *dev_res, uint32_t cq_handle); -void rdma_rm_req_notify_cq(RdmaDeviceResources *dev_res, uint32_t cq_handle, - bool notify); -void rdma_rm_dealloc_cq(RdmaDeviceResources *dev_res, uint32_t cq_handle); - -int rdma_rm_alloc_qp(RdmaDeviceResources *dev_res, uint32_t pd_handle, - uint8_t qp_type, uint32_t max_send_wr, - uint32_t max_send_sge, uint32_t send_cq_handle, - uint32_t max_recv_wr, uint32_t max_recv_sge, - uint32_t recv_cq_handle, void *opaque, uint32_t *qpn, - uint8_t is_srq, uint32_t srq_handle); -RdmaRmQP *rdma_rm_get_qp(RdmaDeviceResources *dev_res, uint32_t qpn); -int rdma_rm_modify_qp(RdmaDeviceResources *dev_res, RdmaBackendDev *backend_dev, - uint32_t qp_handle, uint32_t attr_mask, uint8_t sgid_idx, - union ibv_gid *dgid, uint32_t dqpn, - enum ibv_qp_state qp_state, uint32_t qkey, - uint32_t rq_psn, uint32_t sq_psn); -int rdma_rm_query_qp(RdmaDeviceResources *dev_res, RdmaBackendDev *backend_dev, - uint32_t qp_handle, struct ibv_qp_attr *attr, - int attr_mask, struct ibv_qp_init_attr *init_attr); -void rdma_rm_dealloc_qp(RdmaDeviceResources *dev_res, uint32_t qp_handle); - -RdmaRmSRQ *rdma_rm_get_srq(RdmaDeviceResources *dev_res, uint32_t srq_handle); -int rdma_rm_alloc_srq(RdmaDeviceResources *dev_res, uint32_t pd_handle, - uint32_t max_wr, uint32_t max_sge, uint32_t srq_limit, - uint32_t *srq_handle, void *opaque); -int rdma_rm_query_srq(RdmaDeviceResources *dev_res, uint32_t srq_handle, - struct ibv_srq_attr *srq_attr); -int rdma_rm_modify_srq(RdmaDeviceResources *dev_res, uint32_t srq_handle, - struct ibv_srq_attr *srq_attr, int srq_attr_mask); -void rdma_rm_dealloc_srq(RdmaDeviceResources *dev_res, uint32_t srq_handle); - -int rdma_rm_alloc_cqe_ctx(RdmaDeviceResources *dev_res, uint32_t *cqe_ctx_id, - void *ctx); -void *rdma_rm_get_cqe_ctx(RdmaDeviceResources *dev_res, uint32_t cqe_ctx_id); -void rdma_rm_dealloc_cqe_ctx(RdmaDeviceResources *dev_res, uint32_t cqe_ctx_id); - -int rdma_rm_add_gid(RdmaDeviceResources *dev_res, RdmaBackendDev *backend_dev, - const char *ifname, union ibv_gid *gid, int gid_idx); -int rdma_rm_del_gid(RdmaDeviceResources *dev_res, RdmaBackendDev *backend_dev, - const char *ifname, int gid_idx); -int rdma_rm_get_backend_gid_index(RdmaDeviceResources *dev_res, - RdmaBackendDev *backend_dev, int sgid_idx); -static inline union ibv_gid *rdma_rm_get_gid(RdmaDeviceResources *dev_res, - int sgid_idx) -{ - return &dev_res->port.gid_tbl[sgid_idx].gid; -} -void rdma_format_device_counters(RdmaDeviceResources *dev_res, GString *buf); - -#endif diff --git a/hw/rdma/rdma_rm_defs.h b/hw/rdma/rdma_rm_defs.h deleted file mode 100644 index 534f2f74d3..0000000000 --- a/hw/rdma/rdma_rm_defs.h +++ /dev/null @@ -1,146 +0,0 @@ -/* - * RDMA device: Definitions of Resource Manager structures - * - * Copyright (C) 2018 Oracle - * Copyright (C) 2018 Red Hat Inc - * - * Authors: - * Yuval Shaia <yuval.shaia(a)oracle.com> - * Marcel Apfelbaum <marcel(a)redhat.com> - * - * This work is licensed under the terms of the GNU GPL, version 2 or later. - * See the COPYING file in the top-level directory. - * - */ - -#ifndef RDMA_RM_DEFS_H -#define RDMA_RM_DEFS_H - -#include "rdma_backend_defs.h" - -#define MAX_PORTS 1 /* Do not change - we support only one port */ -#define MAX_PORT_GIDS 255 -#define MAX_GIDS MAX_PORT_GIDS -#define MAX_PORT_PKEYS 1 -#define MAX_PKEYS MAX_PORT_PKEYS -#define MAX_UCS 512 -#define MAX_MR_SIZE (1UL << 27) -#define MAX_QP 1024 -#define MAX_SGE 4 -#define MAX_CQ 2048 -#define MAX_MR 1024 -#define MAX_PD 1024 -#define MAX_QP_RD_ATOM 16 -#define MAX_QP_INIT_RD_ATOM 16 -#define MAX_AH 64 -#define MAX_SRQ 512 - -#define MAX_RM_TBL_NAME 16 -#define MAX_CONSEQ_EMPTY_POLL_CQ 4096 /* considered as error above this */ - -typedef struct RdmaRmResTbl { - char name[MAX_RM_TBL_NAME]; - QemuMutex lock; - unsigned long *bitmap; - size_t tbl_sz; - size_t res_sz; - void *tbl; - uint32_t used; /* number of used entries in the table */ -} RdmaRmResTbl; - -typedef struct RdmaRmPD { - RdmaBackendPD backend_pd; - uint32_t ctx_handle; -} RdmaRmPD; - -typedef enum CQNotificationType { - CNT_CLEAR, - CNT_ARM, - CNT_SET, -} CQNotificationType; - -typedef struct RdmaRmCQ { - RdmaBackendCQ backend_cq; - void *opaque; - CQNotificationType notify; -} RdmaRmCQ; - -/* MR (DMA region) */ -typedef struct RdmaRmMR { - RdmaBackendMR backend_mr; - void *virt; - uint64_t start; - size_t length; - uint32_t pd_handle; - uint32_t lkey; - uint32_t rkey; -} RdmaRmMR; - -typedef struct RdmaRmUC { - uint64_t uc_handle; -} RdmaRmUC; - -typedef struct RdmaRmQP { - RdmaBackendQP backend_qp; - void *opaque; - uint32_t qp_type; - uint32_t qpn; - uint32_t send_cq_handle; - uint32_t recv_cq_handle; - enum ibv_qp_state qp_state; - uint8_t is_srq; -} RdmaRmQP; - -typedef struct RdmaRmSRQ { - RdmaBackendSRQ backend_srq; - uint32_t recv_cq_handle; - void *opaque; -} RdmaRmSRQ; - -typedef struct RdmaRmGid { - union ibv_gid gid; - int backend_gid_index; -} RdmaRmGid; - -typedef struct RdmaRmPort { - RdmaRmGid gid_tbl[MAX_PORT_GIDS]; - enum ibv_port_state state; -} RdmaRmPort; - -typedef struct RdmaRmStats { - uint64_t tx; - uint64_t tx_len; - uint64_t tx_err; - uint64_t rx_bufs; - uint64_t rx_bufs_len; - uint64_t rx_bufs_err; - uint64_t rx_srq; - uint64_t completions; - uint64_t mad_tx; - uint64_t mad_tx_err; - uint64_t mad_rx; - uint64_t mad_rx_err; - uint64_t mad_rx_bufs; - uint64_t mad_rx_bufs_err; - uint64_t poll_cq_from_bk; - uint64_t poll_cq_from_guest; - uint64_t poll_cq_from_guest_empty; - uint64_t poll_cq_ppoll_to; - uint32_t missing_cqe; -} RdmaRmStats; - -struct RdmaDeviceResources { - RdmaRmPort port; - RdmaRmResTbl pd_tbl; - RdmaRmResTbl mr_tbl; - RdmaRmResTbl uc_tbl; - RdmaRmResTbl qp_tbl; - RdmaRmResTbl cq_tbl; - RdmaRmResTbl cqe_ctx_tbl; - RdmaRmResTbl srq_tbl; - GHashTable *qp_hash; /* Keeps mapping between real and emulated */ - QemuMutex lock; - RdmaRmStats stats; -}; - -#endif diff --git a/hw/rdma/rdma_utils.h b/hw/rdma/rdma_utils.h deleted file mode 100644 index 54e4f56edd..0000000000 --- a/hw/rdma/rdma_utils.h +++ /dev/null @@ -1,63 +0,0 @@ -/* - * RDMA device: Debug utilities - * - * Copyright (C) 2018 Oracle - * Copyright (C) 2018 Red Hat Inc - * - * - * Authors: - * Yuval Shaia <yuval.shaia(a)oracle.com> - * Marcel Apfelbaum <marcel(a)redhat.com> - * - * This work is licensed under the terms of the GNU GPL, version 2 or later. - * See the COPYING file in the top-level directory. - * - */ - -#ifndef RDMA_UTILS_H -#define RDMA_UTILS_H - -#include "qemu/error-report.h" -#include "sysemu/dma.h" - -#define rdma_error_report(fmt, ...) \ - error_report("%s: " fmt, "rdma", ## __VA_ARGS__) -#define rdma_warn_report(fmt, ...) \ - warn_report("%s: " fmt, "rdma", ## __VA_ARGS__) -#define rdma_info_report(fmt, ...) \ - info_report("%s: " fmt, "rdma", ## __VA_ARGS__) - -typedef struct RdmaProtectedGQueue { - QemuMutex lock; - GQueue *list; -} RdmaProtectedGQueue; - -typedef struct RdmaProtectedGSList { - QemuMutex lock; - GSList *list; -} RdmaProtectedGSList; - -void *rdma_pci_dma_map(PCIDevice *dev, dma_addr_t addr, dma_addr_t len); -void rdma_pci_dma_unmap(PCIDevice *dev, void *buffer, dma_addr_t len); -void rdma_protected_gqueue_init(RdmaProtectedGQueue *list); -void rdma_protected_gqueue_destroy(RdmaProtectedGQueue *list); -void rdma_protected_gqueue_append_int64(RdmaProtectedGQueue *list, - int64_t value); -int64_t rdma_protected_gqueue_pop_int64(RdmaProtectedGQueue *list); -void rdma_protected_gslist_init(RdmaProtectedGSList *list); -void rdma_protected_gslist_destroy(RdmaProtectedGSList *list); -void rdma_protected_gslist_append_int32(RdmaProtectedGSList *list, - int32_t value); -void rdma_protected_gslist_remove_int32(RdmaProtectedGSList *list, - int32_t value); - -static inline void addrconf_addr_eui48(uint8_t *eui, const char *addr) -{ - memcpy(eui, addr, 3); - eui[3] = 0xFF; - eui[4] = 0xFE; - memcpy(eui + 5, addr + 3, 3); - eui[0] ^= 2; -} - -#endif diff --git a/hw/rdma/trace.h b/hw/rdma/trace.h deleted file mode 100644 index b3fa8ebc51..0000000000 --- a/hw/rdma/trace.h +++ /dev/null @@ -1 +0,0 @@ -#include "trace/trace-hw_rdma.h" diff --git a/hw/rdma/vmw/pvrdma.h b/hw/rdma/vmw/pvrdma.h deleted file mode 100644 index 4cbc10c980..0000000000 --- a/hw/rdma/vmw/pvrdma.h +++ /dev/null @@ -1,144 +0,0 @@ -/* - * QEMU VMWARE paravirtual RDMA device definitions - * - * Copyright (C) 2018 Oracle - * Copyright (C) 2018 Red Hat Inc - * - * Authors: - * Yuval Shaia <yuval.shaia(a)oracle.com> - * Marcel Apfelbaum <marcel(a)redhat.com> - * - * This work is licensed under the terms of the GNU GPL, version 2 or later. - * See the COPYING file in the top-level directory. - * - */ - -#ifndef PVRDMA_PVRDMA_H -#define PVRDMA_PVRDMA_H - -#include "qemu/units.h" -#include "qemu/notify.h" -#include "hw/pci/msix.h" -#include "hw/pci/pci_device.h" -#include "chardev/char-fe.h" -#include "hw/net/vmxnet3_defs.h" - -#include "../rdma_backend_defs.h" -#include "../rdma_rm_defs.h" - -#include "standard-headers/drivers/infiniband/hw/vmw_pvrdma/pvrdma_dev_api.h" -#include "pvrdma_dev_ring.h" -#include "qom/object.h" - -/* BARs */ -#define RDMA_MSIX_BAR_IDX 0 -#define RDMA_REG_BAR_IDX 1 -#define RDMA_UAR_BAR_IDX 2 -#define RDMA_BAR0_MSIX_SIZE (16 * KiB) -#define RDMA_BAR1_REGS_SIZE 64 -#define RDMA_BAR2_UAR_SIZE (0x1000 * MAX_UCS) /* each uc gets page */ - -/* MSIX */ -#define RDMA_MAX_INTRS 3 -#define RDMA_MSIX_TABLE 0x0000 -#define RDMA_MSIX_PBA 0x2000 - -/* Interrupts Vectors */ -#define INTR_VEC_CMD_RING 0 -#define INTR_VEC_CMD_ASYNC_EVENTS 1 -#define INTR_VEC_CMD_COMPLETION_Q 2 - -/* HW attributes */ -#define PVRDMA_HW_NAME "pvrdma" -#define PVRDMA_HW_VERSION 17 -#define PVRDMA_FW_VERSION 14 - -/* Some defaults */ -#define PVRDMA_PKEY 0xFFFF - -typedef struct DSRInfo { - dma_addr_t dma; - struct pvrdma_device_shared_region *dsr; - - union pvrdma_cmd_req *req; - union pvrdma_cmd_resp *rsp; - - PvrdmaRingState *async_ring_state; - PvrdmaRing async; - - PvrdmaRingState *cq_ring_state; - PvrdmaRing cq; -} DSRInfo; - -typedef struct PVRDMADevStats { - uint64_t commands; - uint64_t regs_reads; - uint64_t regs_writes; - uint64_t uar_writes; - uint64_t interrupts; -} PVRDMADevStats; - -struct PVRDMADev { - PCIDevice parent_obj; - MemoryRegion msix; - MemoryRegion regs; - uint32_t regs_data[RDMA_BAR1_REGS_SIZE]; - MemoryRegion uar; - uint32_t uar_data[RDMA_BAR2_UAR_SIZE]; - DSRInfo dsr_info; - int interrupt_mask; - struct ibv_device_attr dev_attr; - uint64_t node_guid; - char *backend_eth_device_name; - char *backend_device_name; - uint8_t backend_port_num; - RdmaBackendDev backend_dev; - RdmaDeviceResources rdma_dev_res; - CharBackend mad_chr; - VMXNET3State *func0; - Notifier shutdown_notifier; - PVRDMADevStats stats; -}; -typedef struct PVRDMADev PVRDMADev; -DECLARE_INSTANCE_CHECKER(PVRDMADev, PVRDMA_DEV, - PVRDMA_HW_NAME) - -static inline int get_reg_val(PVRDMADev *dev, hwaddr addr, uint32_t *val) -{ - int idx = addr >> 2; - - if (idx >= RDMA_BAR1_REGS_SIZE) { - return -EINVAL; - } - - *val = dev->regs_data[idx]; - - return 0; -} - -static inline int set_reg_val(PVRDMADev *dev, hwaddr addr, uint32_t val) -{ - int idx = addr >> 2; - - if (idx >= RDMA_BAR1_REGS_SIZE) { - return -EINVAL; - } - - dev->regs_data[idx] = val; - - return 0; -} - -static inline void post_interrupt(PVRDMADev *dev, unsigned vector) -{ - PCIDevice *pci_dev = PCI_DEVICE(dev); - - if (likely(!dev->interrupt_mask)) { - dev->stats.interrupts++; - msix_notify(pci_dev, vector); - } -} - -int pvrdma_exec_cmd(PVRDMADev *dev); - -#endif diff --git a/hw/rdma/vmw/pvrdma_dev_ring.h b/hw/rdma/vmw/pvrdma_dev_ring.h deleted file mode 100644 index d231588ce0..0000000000 --- a/hw/rdma/vmw/pvrdma_dev_ring.h +++ /dev/null @@ -1,46 +0,0 @@ -/* - * QEMU VMWARE paravirtual RDMA ring utilities - * - * Copyright (C) 2018 Oracle - * Copyright (C) 2018 Red Hat Inc - * - * Authors: - * Yuval Shaia <yuval.shaia(a)oracle.com> - * Marcel Apfelbaum <marcel(a)redhat.com> - * - * This work is licensed under the terms of the GNU GPL, version 2 or later. - * See the COPYING file in the top-level directory. - * - */ - -#ifndef PVRDMA_DEV_RING_H -#define PVRDMA_DEV_RING_H - - -#define MAX_RING_NAME_SZ 32 - -typedef struct PvrdmaRingState { - int prod_tail; /* producer tail */ - int cons_head; /* consumer head */ -} PvrdmaRingState; - -typedef struct PvrdmaRing { - char name[MAX_RING_NAME_SZ]; - PCIDevice *dev; - uint32_t max_elems; - size_t elem_sz; - PvrdmaRingState *ring_state; /* used only for unmap */ - int npages; - void **pages; -} PvrdmaRing; - -int pvrdma_ring_init(PvrdmaRing *ring, const char *name, PCIDevice *dev, - PvrdmaRingState *ring_state, uint32_t max_elems, - size_t elem_sz, dma_addr_t *tbl, uint32_t npages); -void *pvrdma_ring_next_elem_read(PvrdmaRing *ring); -void pvrdma_ring_read_inc(PvrdmaRing *ring); -void *pvrdma_ring_next_elem_write(PvrdmaRing *ring); -void pvrdma_ring_write_inc(PvrdmaRing *ring); -void pvrdma_ring_free(PvrdmaRing *ring); - -#endif diff --git a/hw/rdma/vmw/pvrdma_qp_ops.h b/hw/rdma/vmw/pvrdma_qp_ops.h deleted file mode 100644 index bf2b15c5ce..0000000000 --- a/hw/rdma/vmw/pvrdma_qp_ops.h +++ /dev/null @@ -1,28 +0,0 @@ -/* - * QEMU VMWARE paravirtual RDMA QP Operations - * - * Copyright (C) 2018 Oracle - * Copyright (C) 2018 Red Hat Inc - * - * Authors: - * Yuval Shaia <yuval.shaia(a)oracle.com> - * Marcel Apfelbaum <marcel(a)redhat.com> - * - * This work is licensed under the terms of the GNU GPL, version 2 or later. - * See the COPYING file in the top-level directory. - * - */ - -#ifndef PVRDMA_QP_OPS_H -#define PVRDMA_QP_OPS_H - -#include "pvrdma.h" - -int pvrdma_qp_ops_init(void); -void pvrdma_qp_ops_fini(void); -void pvrdma_qp_send(PVRDMADev *dev, uint32_t qp_handle); -void pvrdma_qp_recv(PVRDMADev *dev, uint32_t qp_handle); -void pvrdma_srq_recv(PVRDMADev *dev, uint32_t srq_handle); -void pvrdma_cq_poll(RdmaDeviceResources *dev_res, uint32_t cq_handle); - -#endif diff --git a/hw/rdma/vmw/trace.h b/hw/rdma/vmw/trace.h deleted file mode 100644 index 3ebc9fb7ad..0000000000 --- a/hw/rdma/vmw/trace.h +++ /dev/null @@ -1 +0,0 @@ -#include "trace/trace-hw_rdma_vmw.h" diff --git a/include/hw/rdma/rdma.h b/include/hw/rdma/rdma.h deleted file mode 100644 index 80b2e531c4..0000000000 --- a/include/hw/rdma/rdma.h +++ /dev/null @@ -1,37 +0,0 @@ -/* - * RDMA device interface - * - * Copyright (C) 2019 Oracle - * Copyright (C) 2019 Red Hat Inc - * - * Authors: - * Yuval Shaia <yuval.shaia(a)oracle.com> - * - * This work is licensed under the terms of the GNU GPL, version 2 or later. - * See the COPYING file in the top-level directory. - * - */ - -#ifndef RDMA_H -#define RDMA_H - -#include "qom/object.h" - -#define INTERFACE_RDMA_PROVIDER "rdma" - -typedef struct RdmaProviderClass RdmaProviderClass; -DECLARE_CLASS_CHECKERS(RdmaProviderClass, RDMA_PROVIDER, - INTERFACE_RDMA_PROVIDER) -#define RDMA_PROVIDER(obj) \ - INTERFACE_CHECK(RdmaProvider, (obj), \ - INTERFACE_RDMA_PROVIDER) - -typedef struct RdmaProvider RdmaProvider; - -struct RdmaProviderClass { - InterfaceClass parent; - - void (*format_statistics)(RdmaProvider *obj, GString *buf); -}; - -#endif diff --git a/include/monitor/hmp.h b/include/monitor/hmp.h index 13f9a2dedb..f4cf8f6717 100644 --- a/include/monitor/hmp.h +++ b/include/monitor/hmp.h @@ -37,7 +37,6 @@ void hmp_info_spice(Monitor *mon, const QDict *qdict); void hmp_info_balloon(Monitor *mon, const QDict *qdict); void hmp_info_irq(Monitor *mon, const QDict *qdict); void hmp_info_pic(Monitor *mon, const QDict *qdict); -void hmp_info_rdma(Monitor *mon, const QDict *qdict); void hmp_info_pci(Monitor *mon, const QDict *qdict); void hmp_info_tpm(Monitor *mon, const QDict *qdict); void hmp_info_iothreads(Monitor *mon, const QDict *qdict); diff --git a/include/standard-headers/drivers/infiniband/hw/vmw_pvrdma/pvrdma_dev_api.h b/include/standard-headers/drivers/infiniband/hw/vmw_pvrdma/pvrdma_dev_api.h deleted file mode 100644 index a5a1c8234e..0000000000 --- a/include/standard-headers/drivers/infiniband/hw/vmw_pvrdma/pvrdma_dev_api.h +++ /dev/null @@ -1,685 +0,0 @@ -/* - * Copyright (c) 2012-2016 VMware, Inc. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of EITHER the GNU General Public License - * version 2 as published by the Free Software Foundation or the BSD - * 2-Clause License. This program is distributed in the hope that it - * will be useful, but WITHOUT ANY WARRANTY; WITHOUT EVEN THE IMPLIED - * WARRANTY OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE. - * See the GNU General Public License version 2 for more details at - * http://www.gnu.org/licenses/old-licenses/gpl-2.0.en.html. - * - * You should have received a copy of the GNU General Public License - * along with this program available in the file COPYING in the main - * directory of this source tree. - * - * The BSD 2-Clause License - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and/or other materials - * provided with the distribution. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS - * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE - * COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, - * INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES - * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR - * SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) - * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, - * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) - * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED - * OF THE POSSIBILITY OF SUCH DAMAGE. - */ - -#ifndef __PVRDMA_DEV_API_H__ -#define __PVRDMA_DEV_API_H__ - -#include "standard-headers/linux/types.h" - -#include "pvrdma_verbs.h" - -/* - * PVRDMA version macros. Some new features require updates to PVRDMA_VERSION. - * These macros allow us to check for different features if necessary. - */ - -#define PVRDMA_ROCEV1_VERSION 17 -#define PVRDMA_ROCEV2_VERSION 18 -#define PVRDMA_PPN64_VERSION 19 -#define PVRDMA_QPHANDLE_VERSION 20 -#define PVRDMA_VERSION PVRDMA_QPHANDLE_VERSION - -#define PVRDMA_BOARD_ID 1 -#define PVRDMA_REV_ID 1 - -/* - * Masks and accessors for page directory, which is a two-level lookup: - * page directory -> page table -> page. Only one directory for now, but we - * could expand that easily. 9 bits for tables, 9 bits for pages, gives one - * gigabyte for memory regions and so forth. - */ - -#define PVRDMA_PDIR_SHIFT 18 -#define PVRDMA_PTABLE_SHIFT 9 -#define PVRDMA_PAGE_DIR_DIR(x) (((x) >> PVRDMA_PDIR_SHIFT) & 0x1) -#define PVRDMA_PAGE_DIR_TABLE(x) (((x) >> PVRDMA_PTABLE_SHIFT) & 0x1ff) -#define PVRDMA_PAGE_DIR_PAGE(x) ((x) & 0x1ff) -#define PVRDMA_PAGE_DIR_MAX_PAGES (1 * 512 * 512) -#define PVRDMA_MAX_FAST_REG_PAGES 128 - -/* - * Max MSI-X vectors. - */ - -#define PVRDMA_MAX_INTERRUPTS 3 - -/* Register offsets within PCI resource on BAR1. */ -#define PVRDMA_REG_VERSION 0x00 /* R: Version of device. */ -#define PVRDMA_REG_DSRLOW 0x04 /* W: Device shared region low PA. */ -#define PVRDMA_REG_DSRHIGH 0x08 /* W: Device shared region high PA. */ -#define PVRDMA_REG_CTL 0x0c /* W: PVRDMA_DEVICE_CTL */ -#define PVRDMA_REG_REQUEST 0x10 /* W: Indicate device request. */ -#define PVRDMA_REG_ERR 0x14 /* R: Device error. */ -#define PVRDMA_REG_ICR 0x18 /* R: Interrupt cause. */ -#define PVRDMA_REG_IMR 0x1c /* R/W: Interrupt mask. */ -#define PVRDMA_REG_MACL 0x20 /* R/W: MAC address low. */ -#define PVRDMA_REG_MACH 0x24 /* R/W: MAC address high. */ - -/* Object flags. */ -#define PVRDMA_CQ_FLAG_ARMED_SOL BIT(0) /* Armed for solicited-only. */ -#define PVRDMA_CQ_FLAG_ARMED BIT(1) /* Armed. */ -#define PVRDMA_MR_FLAG_DMA BIT(0) /* DMA region. */ -#define PVRDMA_MR_FLAG_FRMR BIT(1) /* Fast reg memory region. */ - -/* - * Atomic operation capability (masked versions are extended atomic - * operations. - */ - -#define PVRDMA_ATOMIC_OP_COMP_SWAP BIT(0) /* Compare and swap. */ -#define PVRDMA_ATOMIC_OP_FETCH_ADD BIT(1) /* Fetch and add. */ -#define PVRDMA_ATOMIC_OP_MASK_COMP_SWAP BIT(2) /* Masked compare and swap. */ -#define PVRDMA_ATOMIC_OP_MASK_FETCH_ADD BIT(3) /* Masked fetch and add. */ - -/* - * Base Memory Management Extension flags to support Fast Reg Memory Regions - * and Fast Reg Work Requests. Each flag represents a verb operation and we - * must support all of them to qualify for the BMME device cap. - */ - -#define PVRDMA_BMME_FLAG_LOCAL_INV BIT(0) /* Local Invalidate. */ -#define PVRDMA_BMME_FLAG_REMOTE_INV BIT(1) /* Remote Invalidate. */ -#define PVRDMA_BMME_FLAG_FAST_REG_WR BIT(2) /* Fast Reg Work Request. */ - -/* - * GID types. The interpretation of the gid_types bit field in the device - * capabilities will depend on the device mode. For now, the device only - * supports RoCE as mode, so only the different GID types for RoCE are - * defined. - */ - -#define PVRDMA_GID_TYPE_FLAG_ROCE_V1 BIT(0) -#define PVRDMA_GID_TYPE_FLAG_ROCE_V2 BIT(1) - -/* - * Version checks. This checks whether each version supports specific - * capabilities from the device. - */ - -#define PVRDMA_IS_VERSION17(_dev) \ - (_dev->dsr_version == PVRDMA_ROCEV1_VERSION && \ - _dev->dsr->caps.gid_types == PVRDMA_GID_TYPE_FLAG_ROCE_V1) - -#define PVRDMA_IS_VERSION18(_dev) \ - (_dev->dsr_version >= PVRDMA_ROCEV2_VERSION && \ - (_dev->dsr->caps.gid_types == PVRDMA_GID_TYPE_FLAG_ROCE_V1 || \ - _dev->dsr->caps.gid_types == PVRDMA_GID_TYPE_FLAG_ROCE_V2)) \ - -#define PVRDMA_SUPPORTED(_dev) \ - ((_dev->dsr->caps.mode == PVRDMA_DEVICE_MODE_ROCE) && \ - (PVRDMA_IS_VERSION17(_dev) || PVRDMA_IS_VERSION18(_dev))) - -/* - * Get capability values based on device version. - */ - -#define PVRDMA_GET_CAP(_dev, _old_val, _val) \ - ((PVRDMA_IS_VERSION18(_dev)) ? _val : _old_val) - -enum pvrdma_pci_resource { - PVRDMA_PCI_RESOURCE_MSIX, /* BAR0: MSI-X, MMIO. */ - PVRDMA_PCI_RESOURCE_REG, /* BAR1: Registers, MMIO. */ - PVRDMA_PCI_RESOURCE_UAR, /* BAR2: UAR pages, MMIO, 64-bit. */ - PVRDMA_PCI_RESOURCE_LAST, /* Last. */ -}; - -enum pvrdma_device_ctl { - PVRDMA_DEVICE_CTL_ACTIVATE, /* Activate device. */ - PVRDMA_DEVICE_CTL_UNQUIESCE, /* Unquiesce device. */ - PVRDMA_DEVICE_CTL_RESET, /* Reset device. */ -}; - -enum pvrdma_intr_vector { - PVRDMA_INTR_VECTOR_RESPONSE, /* Command response. */ - PVRDMA_INTR_VECTOR_ASYNC, /* Async events. */ - PVRDMA_INTR_VECTOR_CQ, /* CQ notification. */ - /* Additional CQ notification vectors. */ -}; - -enum pvrdma_intr_cause { - PVRDMA_INTR_CAUSE_RESPONSE = (1 << PVRDMA_INTR_VECTOR_RESPONSE), - PVRDMA_INTR_CAUSE_ASYNC = (1 << PVRDMA_INTR_VECTOR_ASYNC), - PVRDMA_INTR_CAUSE_CQ = (1 << PVRDMA_INTR_VECTOR_CQ), -}; - -enum pvrdma_gos_bits { - PVRDMA_GOS_BITS_UNK, /* Unknown. */ - PVRDMA_GOS_BITS_32, /* 32-bit. */ - PVRDMA_GOS_BITS_64, /* 64-bit. */ -}; - -enum pvrdma_gos_type { - PVRDMA_GOS_TYPE_UNK, /* Unknown. */ - PVRDMA_GOS_TYPE_LINUX, /* Linux. */ -}; - -enum pvrdma_device_mode { - PVRDMA_DEVICE_MODE_ROCE, /* RoCE. */ - PVRDMA_DEVICE_MODE_IWARP, /* iWarp. */ - PVRDMA_DEVICE_MODE_IB, /* InfiniBand. */ -}; - -struct pvrdma_gos_info { - uint32_t gos_bits:2; /* W: PVRDMA_GOS_BITS_ */ - uint32_t gos_type:4; /* W: PVRDMA_GOS_TYPE_ */ - uint32_t gos_ver:16; /* W: Guest OS version. */ - uint32_t gos_misc:10; /* W: Other. */ - uint32_t pad; /* Pad to 8-byte alignment. */ -}; - -struct pvrdma_device_caps { - uint64_t fw_ver; /* R: Query device. */ - uint64_t node_guid; - uint64_t sys_image_guid; - uint64_t max_mr_size; - uint64_t page_size_cap; - uint64_t atomic_arg_sizes; /* EX verbs. */ - uint32_t ex_comp_mask; /* EX verbs. */ - uint32_t device_cap_flags2; /* EX verbs. */ - uint32_t max_fa_bit_boundary; /* EX verbs. */ - uint32_t log_max_atomic_inline_arg; /* EX verbs. */ - uint32_t vendor_id; - uint32_t vendor_part_id; - uint32_t hw_ver; - uint32_t max_qp; - uint32_t max_qp_wr; - uint32_t device_cap_flags; - uint32_t max_sge; - uint32_t max_sge_rd; - uint32_t max_cq; - uint32_t max_cqe; - uint32_t max_mr; - uint32_t max_pd; - uint32_t max_qp_rd_atom; - uint32_t max_ee_rd_atom; - uint32_t max_res_rd_atom; - uint32_t max_qp_init_rd_atom; - uint32_t max_ee_init_rd_atom; - uint32_t max_ee; - uint32_t max_rdd; - uint32_t max_mw; - uint32_t max_raw_ipv6_qp; - uint32_t max_raw_ethy_qp; - uint32_t max_mcast_grp; - uint32_t max_mcast_qp_attach; - uint32_t max_total_mcast_qp_attach; - uint32_t max_ah; - uint32_t max_fmr; - uint32_t max_map_per_fmr; - uint32_t max_srq; - uint32_t max_srq_wr; - uint32_t max_srq_sge; - uint32_t max_uar; - uint32_t gid_tbl_len; - uint16_t max_pkeys; - uint8_t local_ca_ack_delay; - uint8_t phys_port_cnt; - uint8_t mode; /* PVRDMA_DEVICE_MODE_ */ - uint8_t atomic_ops; /* PVRDMA_ATOMIC_OP_* bits */ - uint8_t bmme_flags; /* FRWR Mem Mgmt Extensions */ - uint8_t gid_types; /* PVRDMA_GID_TYPE_FLAG_ */ - uint32_t max_fast_reg_page_list_len; -}; - -struct pvrdma_ring_page_info { - uint32_t num_pages; /* Num pages incl. header. */ - uint32_t reserved; /* Reserved. */ - uint64_t pdir_dma; /* Page directory PA. */ -}; - -#pragma pack(push, 1) - -struct pvrdma_device_shared_region { - uint32_t driver_version; /* W: Driver version. */ - uint32_t pad; /* Pad to 8-byte align. */ - struct pvrdma_gos_info gos_info; /* W: Guest OS information. */ - uint64_t cmd_slot_dma; /* W: Command slot address. */ - uint64_t resp_slot_dma; /* W: Response slot address. */ - struct pvrdma_ring_page_info async_ring_pages; - /* W: Async ring page info. */ - struct pvrdma_ring_page_info cq_ring_pages; - /* W: CQ ring page info. */ - union { - uint32_t uar_pfn; /* W: UAR pageframe. */ - uint64_t uar_pfn64; /* W: 64-bit UAR page frame. */ - }; - struct pvrdma_device_caps caps; /* R: Device capabilities. */ -}; - -#pragma pack(pop) - -/* Event types. Currently a 1:1 mapping with enum ib_event. */ -enum pvrdma_eqe_type { - PVRDMA_EVENT_CQ_ERR, - PVRDMA_EVENT_QP_FATAL, - PVRDMA_EVENT_QP_REQ_ERR, - PVRDMA_EVENT_QP_ACCESS_ERR, - PVRDMA_EVENT_COMM_EST, - PVRDMA_EVENT_SQ_DRAINED, - PVRDMA_EVENT_PATH_MIG, - PVRDMA_EVENT_PATH_MIG_ERR, - PVRDMA_EVENT_DEVICE_FATAL, - PVRDMA_EVENT_PORT_ACTIVE, - PVRDMA_EVENT_PORT_ERR, - PVRDMA_EVENT_LID_CHANGE, - PVRDMA_EVENT_PKEY_CHANGE, - PVRDMA_EVENT_SM_CHANGE, - PVRDMA_EVENT_SRQ_ERR, - PVRDMA_EVENT_SRQ_LIMIT_REACHED, - PVRDMA_EVENT_QP_LAST_WQE_REACHED, - PVRDMA_EVENT_CLIENT_REREGISTER, - PVRDMA_EVENT_GID_CHANGE, -}; - -/* Event queue element. */ -struct pvrdma_eqe { - uint32_t type; /* Event type. */ - uint32_t info; /* Handle, other. */ -}; - -/* CQ notification queue element. */ -struct pvrdma_cqne { - uint32_t info; /* Handle */ -}; - -enum { - PVRDMA_CMD_FIRST, - PVRDMA_CMD_QUERY_PORT = PVRDMA_CMD_FIRST, - PVRDMA_CMD_QUERY_PKEY, - PVRDMA_CMD_CREATE_PD, - PVRDMA_CMD_DESTROY_PD, - PVRDMA_CMD_CREATE_MR, - PVRDMA_CMD_DESTROY_MR, - PVRDMA_CMD_CREATE_CQ, - PVRDMA_CMD_RESIZE_CQ, - PVRDMA_CMD_DESTROY_CQ, - PVRDMA_CMD_CREATE_QP, - PVRDMA_CMD_MODIFY_QP, - PVRDMA_CMD_QUERY_QP, - PVRDMA_CMD_DESTROY_QP, - PVRDMA_CMD_CREATE_UC, - PVRDMA_CMD_DESTROY_UC, - PVRDMA_CMD_CREATE_BIND, - PVRDMA_CMD_DESTROY_BIND, - PVRDMA_CMD_CREATE_SRQ, - PVRDMA_CMD_MODIFY_SRQ, - PVRDMA_CMD_QUERY_SRQ, - PVRDMA_CMD_DESTROY_SRQ, - PVRDMA_CMD_MAX, -}; - -enum { - PVRDMA_CMD_FIRST_RESP = (1 << 31), - PVRDMA_CMD_QUERY_PORT_RESP = PVRDMA_CMD_FIRST_RESP, - PVRDMA_CMD_QUERY_PKEY_RESP, - PVRDMA_CMD_CREATE_PD_RESP, - PVRDMA_CMD_DESTROY_PD_RESP_NOOP, - PVRDMA_CMD_CREATE_MR_RESP, - PVRDMA_CMD_DESTROY_MR_RESP_NOOP, - PVRDMA_CMD_CREATE_CQ_RESP, - PVRDMA_CMD_RESIZE_CQ_RESP, - PVRDMA_CMD_DESTROY_CQ_RESP_NOOP, - PVRDMA_CMD_CREATE_QP_RESP, - PVRDMA_CMD_MODIFY_QP_RESP, - PVRDMA_CMD_QUERY_QP_RESP, - PVRDMA_CMD_DESTROY_QP_RESP, - PVRDMA_CMD_CREATE_UC_RESP, - PVRDMA_CMD_DESTROY_UC_RESP_NOOP, - PVRDMA_CMD_CREATE_BIND_RESP_NOOP, - PVRDMA_CMD_DESTROY_BIND_RESP_NOOP, - PVRDMA_CMD_CREATE_SRQ_RESP, - PVRDMA_CMD_MODIFY_SRQ_RESP, - PVRDMA_CMD_QUERY_SRQ_RESP, - PVRDMA_CMD_DESTROY_SRQ_RESP, - PVRDMA_CMD_MAX_RESP, -}; - -struct pvrdma_cmd_hdr { - uint64_t response; /* Key for response lookup. */ - uint32_t cmd; /* PVRDMA_CMD_ */ - uint32_t reserved; /* Reserved. */ -}; - -struct pvrdma_cmd_resp_hdr { - uint64_t response; /* From cmd hdr. */ - uint32_t ack; /* PVRDMA_CMD_XXX_RESP */ - uint8_t err; /* Error. */ - uint8_t reserved[3]; /* Reserved. */ -}; - -struct pvrdma_cmd_query_port { - struct pvrdma_cmd_hdr hdr; - uint8_t port_num; - uint8_t reserved[7]; -}; - -struct pvrdma_cmd_query_port_resp { - struct pvrdma_cmd_resp_hdr hdr; - struct pvrdma_port_attr attrs; -}; - -struct pvrdma_cmd_query_pkey { - struct pvrdma_cmd_hdr hdr; - uint8_t port_num; - uint8_t index; - uint8_t reserved[6]; -}; - -struct pvrdma_cmd_query_pkey_resp { - struct pvrdma_cmd_resp_hdr hdr; - uint16_t pkey; - uint8_t reserved[6]; -}; - -struct pvrdma_cmd_create_uc { - struct pvrdma_cmd_hdr hdr; - union { - uint32_t pfn; /* UAR page frame number */ - uint64_t pfn64; /* 64-bit UAR page frame number */ - }; -}; - -struct pvrdma_cmd_create_uc_resp { - struct pvrdma_cmd_resp_hdr hdr; - uint32_t ctx_handle; - uint8_t reserved[4]; -}; - -struct pvrdma_cmd_destroy_uc { - struct pvrdma_cmd_hdr hdr; - uint32_t ctx_handle; - uint8_t reserved[4]; -}; - -struct pvrdma_cmd_create_pd { - struct pvrdma_cmd_hdr hdr; - uint32_t ctx_handle; - uint8_t reserved[4]; -}; - -struct pvrdma_cmd_create_pd_resp { - struct pvrdma_cmd_resp_hdr hdr; - uint32_t pd_handle; - uint8_t reserved[4]; -}; - -struct pvrdma_cmd_destroy_pd { - struct pvrdma_cmd_hdr hdr; - uint32_t pd_handle; - uint8_t reserved[4]; -}; - -struct pvrdma_cmd_create_mr { - struct pvrdma_cmd_hdr hdr; - uint64_t start; - uint64_t length; - uint64_t pdir_dma; - uint32_t pd_handle; - uint32_t access_flags; - uint32_t flags; - uint32_t nchunks; -}; - -struct pvrdma_cmd_create_mr_resp { - struct pvrdma_cmd_resp_hdr hdr; - uint32_t mr_handle; - uint32_t lkey; - uint32_t rkey; - uint8_t reserved[4]; -}; - -struct pvrdma_cmd_destroy_mr { - struct pvrdma_cmd_hdr hdr; - uint32_t mr_handle; - uint8_t reserved[4]; -}; - -struct pvrdma_cmd_create_cq { - struct pvrdma_cmd_hdr hdr; - uint64_t pdir_dma; - uint32_t ctx_handle; - uint32_t cqe; - uint32_t nchunks; - uint8_t reserved[4]; -}; - -struct pvrdma_cmd_create_cq_resp { - struct pvrdma_cmd_resp_hdr hdr; - uint32_t cq_handle; - uint32_t cqe; -}; - -struct pvrdma_cmd_resize_cq { - struct pvrdma_cmd_hdr hdr; - uint32_t cq_handle; - uint32_t cqe; -}; - -struct pvrdma_cmd_resize_cq_resp { - struct pvrdma_cmd_resp_hdr hdr; - uint32_t cqe; - uint8_t reserved[4]; -}; - -struct pvrdma_cmd_destroy_cq { - struct pvrdma_cmd_hdr hdr; - uint32_t cq_handle; - uint8_t reserved[4]; -}; - -struct pvrdma_cmd_create_srq { - struct pvrdma_cmd_hdr hdr; - uint64_t pdir_dma; - uint32_t pd_handle; - uint32_t nchunks; - struct pvrdma_srq_attr attrs; - uint8_t srq_type; - uint8_t reserved[7]; -}; - -struct pvrdma_cmd_create_srq_resp { - struct pvrdma_cmd_resp_hdr hdr; - uint32_t srqn; - uint8_t reserved[4]; -}; - -struct pvrdma_cmd_modify_srq { - struct pvrdma_cmd_hdr hdr; - uint32_t srq_handle; - uint32_t attr_mask; - struct pvrdma_srq_attr attrs; -}; - -struct pvrdma_cmd_query_srq { - struct pvrdma_cmd_hdr hdr; - uint32_t srq_handle; - uint8_t reserved[4]; -}; - -struct pvrdma_cmd_query_srq_resp { - struct pvrdma_cmd_resp_hdr hdr; - struct pvrdma_srq_attr attrs; -}; - -struct pvrdma_cmd_destroy_srq { - struct pvrdma_cmd_hdr hdr; - uint32_t srq_handle; - uint8_t reserved[4]; -}; - -struct pvrdma_cmd_create_qp { - struct pvrdma_cmd_hdr hdr; - uint64_t pdir_dma; - uint32_t pd_handle; - uint32_t send_cq_handle; - uint32_t recv_cq_handle; - uint32_t srq_handle; - uint32_t max_send_wr; - uint32_t max_recv_wr; - uint32_t max_send_sge; - uint32_t max_recv_sge; - uint32_t max_inline_data; - uint32_t lkey; - uint32_t access_flags; - uint16_t total_chunks; - uint16_t send_chunks; - uint16_t max_atomic_arg; - uint8_t sq_sig_all; - uint8_t qp_type; - uint8_t is_srq; - uint8_t reserved[3]; -}; - -struct pvrdma_cmd_create_qp_resp { - struct pvrdma_cmd_resp_hdr hdr; - uint32_t qpn; - uint32_t max_send_wr; - uint32_t max_recv_wr; - uint32_t max_send_sge; - uint32_t max_recv_sge; - uint32_t max_inline_data; -}; - -struct pvrdma_cmd_create_qp_resp_v2 { - struct pvrdma_cmd_resp_hdr hdr; - uint32_t qpn; - uint32_t qp_handle; - uint32_t max_send_wr; - uint32_t max_recv_wr; - uint32_t max_send_sge; - uint32_t max_recv_sge; - uint32_t max_inline_data; -}; - -struct pvrdma_cmd_modify_qp { - struct pvrdma_cmd_hdr hdr; - uint32_t qp_handle; - uint32_t attr_mask; - struct pvrdma_qp_attr attrs; -}; - -struct pvrdma_cmd_query_qp { - struct pvrdma_cmd_hdr hdr; - uint32_t qp_handle; - uint32_t attr_mask; -}; - -struct pvrdma_cmd_query_qp_resp { - struct pvrdma_cmd_resp_hdr hdr; - struct pvrdma_qp_attr attrs; -}; - -struct pvrdma_cmd_destroy_qp { - struct pvrdma_cmd_hdr hdr; - uint32_t qp_handle; - uint8_t reserved[4]; -}; - -struct pvrdma_cmd_destroy_qp_resp { - struct pvrdma_cmd_resp_hdr hdr; - uint32_t events_reported; - uint8_t reserved[4]; -}; - -struct pvrdma_cmd_create_bind { - struct pvrdma_cmd_hdr hdr; - uint32_t mtu; - uint32_t vlan; - uint32_t index; - uint8_t new_gid[16]; - uint8_t gid_type; - uint8_t reserved[3]; -}; - -struct pvrdma_cmd_destroy_bind { - struct pvrdma_cmd_hdr hdr; - uint32_t index; - uint8_t dest_gid[16]; - uint8_t reserved[4]; -}; - -union pvrdma_cmd_req { - struct pvrdma_cmd_hdr hdr; - struct pvrdma_cmd_query_port query_port; - struct pvrdma_cmd_query_pkey query_pkey; - struct pvrdma_cmd_create_uc create_uc; - struct pvrdma_cmd_destroy_uc destroy_uc; - struct pvrdma_cmd_create_pd create_pd; - struct pvrdma_cmd_destroy_pd destroy_pd; - struct pvrdma_cmd_create_mr create_mr; - struct pvrdma_cmd_destroy_mr destroy_mr; - struct pvrdma_cmd_create_cq create_cq; - struct pvrdma_cmd_resize_cq resize_cq; - struct pvrdma_cmd_destroy_cq destroy_cq; - struct pvrdma_cmd_create_qp create_qp; - struct pvrdma_cmd_modify_qp modify_qp; - struct pvrdma_cmd_query_qp query_qp; - struct pvrdma_cmd_destroy_qp destroy_qp; - struct pvrdma_cmd_create_bind create_bind; - struct pvrdma_cmd_destroy_bind destroy_bind; - struct pvrdma_cmd_create_srq create_srq; - struct pvrdma_cmd_modify_srq modify_srq; - struct pvrdma_cmd_query_srq query_srq; - struct pvrdma_cmd_destroy_srq destroy_srq; -}; - -union pvrdma_cmd_resp { - struct pvrdma_cmd_resp_hdr hdr; - struct pvrdma_cmd_query_port_resp query_port_resp; - struct pvrdma_cmd_query_pkey_resp query_pkey_resp; - struct pvrdma_cmd_create_uc_resp create_uc_resp; - struct pvrdma_cmd_create_pd_resp create_pd_resp; - struct pvrdma_cmd_create_mr_resp create_mr_resp; - struct pvrdma_cmd_create_cq_resp create_cq_resp; - struct pvrdma_cmd_resize_cq_resp resize_cq_resp; - struct pvrdma_cmd_create_qp_resp create_qp_resp; - struct pvrdma_cmd_create_qp_resp_v2 create_qp_resp_v2; - struct pvrdma_cmd_query_qp_resp query_qp_resp; - struct pvrdma_cmd_destroy_qp_resp destroy_qp_resp; - struct pvrdma_cmd_create_srq_resp create_srq_resp; - struct pvrdma_cmd_query_srq_resp query_srq_resp; -}; - -#endif /* __PVRDMA_DEV_API_H__ */ diff --git a/include/standard-headers/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h b/include/standard-headers/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h deleted file mode 100644 index 94d41b202c..0000000000 --- a/include/standard-headers/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h +++ /dev/null @@ -1,348 +0,0 @@ -/* - * Copyright (c) 2012-2016 VMware, Inc. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of EITHER the GNU General Public License - * version 2 as published by the Free Software Foundation or the BSD - * 2-Clause License. This program is distributed in the hope that it - * will be useful, but WITHOUT ANY WARRANTY; WITHOUT EVEN THE IMPLIED - * WARRANTY OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE. - * See the GNU General Public License version 2 for more details at - * http://www.gnu.org/licenses/old-licenses/gpl-2.0.en.html. - * - * You should have received a copy of the GNU General Public License - * along with this program available in the file COPYING in the main - * directory of this source tree. - * - * The BSD 2-Clause License - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and/or other materials - * provided with the distribution. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS - * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE - * COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, - * INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES - * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR - * SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) - * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, - * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) - * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED - * OF THE POSSIBILITY OF SUCH DAMAGE. - */ - -#ifndef __PVRDMA_VERBS_H__ -#define __PVRDMA_VERBS_H__ - -#include "standard-headers/linux/types.h" - -union pvrdma_gid { - uint8_t raw[16]; - struct { - uint64_t subnet_prefix; - uint64_t interface_id; - } global; -}; - -enum pvrdma_link_layer { - PVRDMA_LINK_LAYER_UNSPECIFIED, - PVRDMA_LINK_LAYER_INFINIBAND, - PVRDMA_LINK_LAYER_ETHERNET, -}; - -enum pvrdma_mtu { - PVRDMA_MTU_256 = 1, - PVRDMA_MTU_512 = 2, - PVRDMA_MTU_1024 = 3, - PVRDMA_MTU_2048 = 4, - PVRDMA_MTU_4096 = 5, -}; - -enum pvrdma_port_state { - PVRDMA_PORT_NOP = 0, - PVRDMA_PORT_DOWN = 1, - PVRDMA_PORT_INIT = 2, - PVRDMA_PORT_ARMED = 3, - PVRDMA_PORT_ACTIVE = 4, - PVRDMA_PORT_ACTIVE_DEFER = 5, -}; - -enum pvrdma_port_cap_flags { - PVRDMA_PORT_SM = 1 << 1, - PVRDMA_PORT_NOTICE_SUP = 1 << 2, - PVRDMA_PORT_TRAP_SUP = 1 << 3, - PVRDMA_PORT_OPT_IPD_SUP = 1 << 4, - PVRDMA_PORT_AUTO_MIGR_SUP = 1 << 5, - PVRDMA_PORT_SL_MAP_SUP = 1 << 6, - PVRDMA_PORT_MKEY_NVRAM = 1 << 7, - PVRDMA_PORT_PKEY_NVRAM = 1 << 8, - PVRDMA_PORT_LED_INFO_SUP = 1 << 9, - PVRDMA_PORT_SM_DISABLED = 1 << 10, - PVRDMA_PORT_SYS_IMAGE_GUID_SUP = 1 << 11, - PVRDMA_PORT_PKEY_SW_EXT_PORT_TRAP_SUP = 1 << 12, - PVRDMA_PORT_EXTENDED_SPEEDS_SUP = 1 << 14, - PVRDMA_PORT_CM_SUP = 1 << 16, - PVRDMA_PORT_SNMP_TUNNEL_SUP = 1 << 17, - PVRDMA_PORT_REINIT_SUP = 1 << 18, - PVRDMA_PORT_DEVICE_MGMT_SUP = 1 << 19, - PVRDMA_PORT_VENDOR_CLASS_SUP = 1 << 20, - PVRDMA_PORT_DR_NOTICE_SUP = 1 << 21, - PVRDMA_PORT_CAP_MASK_NOTICE_SUP = 1 << 22, - PVRDMA_PORT_BOOT_MGMT_SUP = 1 << 23, - PVRDMA_PORT_LINK_LATENCY_SUP = 1 << 24, - PVRDMA_PORT_CLIENT_REG_SUP = 1 << 25, - PVRDMA_PORT_IP_BASED_GIDS = 1 << 26, - PVRDMA_PORT_CAP_FLAGS_MAX = PVRDMA_PORT_IP_BASED_GIDS, -}; - -enum pvrdma_port_width { - PVRDMA_WIDTH_1X = 1, - PVRDMA_WIDTH_4X = 2, - PVRDMA_WIDTH_8X = 4, - PVRDMA_WIDTH_12X = 8, -}; - -enum pvrdma_port_speed { - PVRDMA_SPEED_SDR = 1, - PVRDMA_SPEED_DDR = 2, - PVRDMA_SPEED_QDR = 4, - PVRDMA_SPEED_FDR10 = 8, - PVRDMA_SPEED_FDR = 16, - PVRDMA_SPEED_EDR = 32, -}; - -struct pvrdma_port_attr { - enum pvrdma_port_state state; - enum pvrdma_mtu max_mtu; - enum pvrdma_mtu active_mtu; - uint32_t gid_tbl_len; - uint32_t port_cap_flags; - uint32_t max_msg_sz; - uint32_t bad_pkey_cntr; - uint32_t qkey_viol_cntr; - uint16_t pkey_tbl_len; - uint16_t lid; - uint16_t sm_lid; - uint8_t lmc; - uint8_t max_vl_num; - uint8_t sm_sl; - uint8_t subnet_timeout; - uint8_t init_type_reply; - uint8_t active_width; - uint8_t active_speed; - uint8_t phys_state; - uint8_t reserved[2]; -}; - -struct pvrdma_global_route { - union pvrdma_gid dgid; - uint32_t flow_label; - uint8_t sgid_index; - uint8_t hop_limit; - uint8_t traffic_class; - uint8_t reserved; -}; - -struct pvrdma_grh { - uint32_t version_tclass_flow; - uint16_t paylen; - uint8_t next_hdr; - uint8_t hop_limit; - union pvrdma_gid sgid; - union pvrdma_gid dgid; -}; - -enum pvrdma_ah_flags { - PVRDMA_AH_GRH = 1, -}; - -enum pvrdma_rate { - PVRDMA_RATE_PORT_CURRENT = 0, - PVRDMA_RATE_2_5_GBPS = 2, - PVRDMA_RATE_5_GBPS = 5, - PVRDMA_RATE_10_GBPS = 3, - PVRDMA_RATE_20_GBPS = 6, - PVRDMA_RATE_30_GBPS = 4, - PVRDMA_RATE_40_GBPS = 7, - PVRDMA_RATE_60_GBPS = 8, - PVRDMA_RATE_80_GBPS = 9, - PVRDMA_RATE_120_GBPS = 10, - PVRDMA_RATE_14_GBPS = 11, - PVRDMA_RATE_56_GBPS = 12, - PVRDMA_RATE_112_GBPS = 13, - PVRDMA_RATE_168_GBPS = 14, - PVRDMA_RATE_25_GBPS = 15, - PVRDMA_RATE_100_GBPS = 16, - PVRDMA_RATE_200_GBPS = 17, - PVRDMA_RATE_300_GBPS = 18, -}; - -struct pvrdma_ah_attr { - struct pvrdma_global_route grh; - uint16_t dlid; - uint16_t vlan_id; - uint8_t sl; - uint8_t src_path_bits; - uint8_t static_rate; - uint8_t ah_flags; - uint8_t port_num; - uint8_t dmac[6]; - uint8_t reserved; -}; - -enum pvrdma_cq_notify_flags { - PVRDMA_CQ_SOLICITED = 1 << 0, - PVRDMA_CQ_NEXT_COMP = 1 << 1, - PVRDMA_CQ_SOLICITED_MASK = PVRDMA_CQ_SOLICITED | - PVRDMA_CQ_NEXT_COMP, - PVRDMA_CQ_REPORT_MISSED_EVENTS = 1 << 2, -}; - -struct pvrdma_qp_cap { - uint32_t max_send_wr; - uint32_t max_recv_wr; - uint32_t max_send_sge; - uint32_t max_recv_sge; - uint32_t max_inline_data; - uint32_t reserved; -}; - -enum pvrdma_sig_type { - PVRDMA_SIGNAL_ALL_WR, - PVRDMA_SIGNAL_REQ_WR, -}; - -enum pvrdma_qp_type { - PVRDMA_QPT_SMI, - PVRDMA_QPT_GSI, - PVRDMA_QPT_RC, - PVRDMA_QPT_UC, - PVRDMA_QPT_UD, - PVRDMA_QPT_RAW_IPV6, - PVRDMA_QPT_RAW_ETHERTYPE, - PVRDMA_QPT_RAW_PACKET = 8, - PVRDMA_QPT_XRC_INI = 9, - PVRDMA_QPT_XRC_TGT, - PVRDMA_QPT_MAX, -}; - -enum pvrdma_qp_create_flags { - PVRDMA_QP_CREATE_IPOPVRDMA_UD_LSO = 1 << 0, - PVRDMA_QP_CREATE_BLOCK_MULTICAST_LOOPBACK = 1 << 1, -}; - -enum pvrdma_qp_attr_mask { - PVRDMA_QP_STATE = 1 << 0, - PVRDMA_QP_CUR_STATE = 1 << 1, - PVRDMA_QP_EN_SQD_ASYNC_NOTIFY = 1 << 2, - PVRDMA_QP_ACCESS_FLAGS = 1 << 3, - PVRDMA_QP_PKEY_INDEX = 1 << 4, - PVRDMA_QP_PORT = 1 << 5, - PVRDMA_QP_QKEY = 1 << 6, - PVRDMA_QP_AV = 1 << 7, - PVRDMA_QP_PATH_MTU = 1 << 8, - PVRDMA_QP_TIMEOUT = 1 << 9, - PVRDMA_QP_RETRY_CNT = 1 << 10, - PVRDMA_QP_RNR_RETRY = 1 << 11, - PVRDMA_QP_RQ_PSN = 1 << 12, - PVRDMA_QP_MAX_QP_RD_ATOMIC = 1 << 13, - PVRDMA_QP_ALT_PATH = 1 << 14, - PVRDMA_QP_MIN_RNR_TIMER = 1 << 15, - PVRDMA_QP_SQ_PSN = 1 << 16, - PVRDMA_QP_MAX_DEST_RD_ATOMIC = 1 << 17, - PVRDMA_QP_PATH_MIG_STATE = 1 << 18, - PVRDMA_QP_CAP = 1 << 19, - PVRDMA_QP_DEST_QPN = 1 << 20, - PVRDMA_QP_ATTR_MASK_MAX = PVRDMA_QP_DEST_QPN, -}; - -enum pvrdma_qp_state { - PVRDMA_QPS_RESET, - PVRDMA_QPS_INIT, - PVRDMA_QPS_RTR, - PVRDMA_QPS_RTS, - PVRDMA_QPS_SQD, - PVRDMA_QPS_SQE, - PVRDMA_QPS_ERR, -}; - -enum pvrdma_mig_state { - PVRDMA_MIG_MIGRATED, - PVRDMA_MIG_REARM, - PVRDMA_MIG_ARMED, -}; - -enum pvrdma_mw_type { - PVRDMA_MW_TYPE_1 = 1, - PVRDMA_MW_TYPE_2 = 2, -}; - -struct pvrdma_srq_attr { - uint32_t max_wr; - uint32_t max_sge; - uint32_t srq_limit; - uint32_t reserved; -}; - -struct pvrdma_qp_attr { - enum pvrdma_qp_state qp_state; - enum pvrdma_qp_state cur_qp_state; - enum pvrdma_mtu path_mtu; - enum pvrdma_mig_state path_mig_state; - uint32_t qkey; - uint32_t rq_psn; - uint32_t sq_psn; - uint32_t dest_qp_num; - uint32_t qp_access_flags; - uint16_t pkey_index; - uint16_t alt_pkey_index; - uint8_t en_sqd_async_notify; - uint8_t sq_draining; - uint8_t max_rd_atomic; - uint8_t max_dest_rd_atomic; - uint8_t min_rnr_timer; - uint8_t port_num; - uint8_t timeout; - uint8_t retry_cnt; - uint8_t rnr_retry; - uint8_t alt_port_num; - uint8_t alt_timeout; - uint8_t reserved[5]; - struct pvrdma_qp_cap cap; - struct pvrdma_ah_attr ah_attr; - struct pvrdma_ah_attr alt_ah_attr; -}; - -enum pvrdma_send_flags { - PVRDMA_SEND_FENCE = 1 << 0, - PVRDMA_SEND_SIGNALED = 1 << 1, - PVRDMA_SEND_SOLICITED = 1 << 2, - PVRDMA_SEND_INLINE = 1 << 3, - PVRDMA_SEND_IP_CSUM = 1 << 4, - PVRDMA_SEND_FLAGS_MAX = PVRDMA_SEND_IP_CSUM, -}; - -enum pvrdma_access_flags { - PVRDMA_ACCESS_LOCAL_WRITE = 1 << 0, - PVRDMA_ACCESS_REMOTE_WRITE = 1 << 1, - PVRDMA_ACCESS_REMOTE_READ = 1 << 2, - PVRDMA_ACCESS_REMOTE_ATOMIC = 1 << 3, - PVRDMA_ACCESS_MW_BIND = 1 << 4, - PVRDMA_ZERO_BASED = 1 << 5, - PVRDMA_ACCESS_ON_DEMAND = 1 << 6, - PVRDMA_ACCESS_FLAGS_MAX = PVRDMA_ACCESS_ON_DEMAND, -}; - -#endif /* __PVRDMA_VERBS_H__ */ diff --git a/include/standard-headers/rdma/vmw_pvrdma-abi.h b/include/standard-headers/rdma/vmw_pvrdma-abi.h deleted file mode 100644 index c30182a7ae..0000000000 --- a/include/standard-headers/rdma/vmw_pvrdma-abi.h +++ /dev/null @@ -1,310 +0,0 @@ -/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */ -/* - * Copyright (c) 2012-2016 VMware, Inc. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of EITHER the GNU General Public License - * version 2 as published by the Free Software Foundation or the BSD - * 2-Clause License. This program is distributed in the hope that it - * will be useful, but WITHOUT ANY WARRANTY; WITHOUT EVEN THE IMPLIED - * WARRANTY OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE. - * See the GNU General Public License version 2 for more details at - * http://www.gnu.org/licenses/old-licenses/gpl-2.0.en.html. - * - * You should have received a copy of the GNU General Public License - * along with this program available in the file COPYING in the main - * directory of this source tree. - * - * The BSD 2-Clause License - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and/or other materials - * provided with the distribution. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS - * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE - * COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, - * INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES - * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR - * SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) - * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, - * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) - * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED - * OF THE POSSIBILITY OF SUCH DAMAGE. - */ - -#ifndef __VMW_PVRDMA_ABI_H__ -#define __VMW_PVRDMA_ABI_H__ - -#include "standard-headers/linux/types.h" - -#define PVRDMA_UVERBS_ABI_VERSION 3 /* ABI Version. */ -#define PVRDMA_UAR_HANDLE_MASK 0x00FFFFFF /* Bottom 24 bits. */ -#define PVRDMA_UAR_QP_OFFSET 0 /* QP doorbell. */ -#define PVRDMA_UAR_QP_SEND (1 << 30) /* Send bit. */ -#define PVRDMA_UAR_QP_RECV (1 << 31) /* Recv bit. */ -#define PVRDMA_UAR_CQ_OFFSET 4 /* CQ doorbell. */ -#define PVRDMA_UAR_CQ_ARM_SOL (1 << 29) /* Arm solicited bit. */ -#define PVRDMA_UAR_CQ_ARM (1 << 30) /* Arm bit. */ -#define PVRDMA_UAR_CQ_POLL (1 << 31) /* Poll bit. */ -#define PVRDMA_UAR_SRQ_OFFSET 8 /* SRQ doorbell. */ -#define PVRDMA_UAR_SRQ_RECV (1 << 30) /* Recv bit. */ - -enum pvrdma_wr_opcode { - PVRDMA_WR_RDMA_WRITE, - PVRDMA_WR_RDMA_WRITE_WITH_IMM, - PVRDMA_WR_SEND, - PVRDMA_WR_SEND_WITH_IMM, - PVRDMA_WR_RDMA_READ, - PVRDMA_WR_ATOMIC_CMP_AND_SWP, - PVRDMA_WR_ATOMIC_FETCH_AND_ADD, - PVRDMA_WR_LSO, - PVRDMA_WR_SEND_WITH_INV, - PVRDMA_WR_RDMA_READ_WITH_INV, - PVRDMA_WR_LOCAL_INV, - PVRDMA_WR_FAST_REG_MR, - PVRDMA_WR_MASKED_ATOMIC_CMP_AND_SWP, - PVRDMA_WR_MASKED_ATOMIC_FETCH_AND_ADD, - PVRDMA_WR_BIND_MW, - PVRDMA_WR_REG_SIG_MR, - PVRDMA_WR_ERROR, -}; - -enum pvrdma_wc_status { - PVRDMA_WC_SUCCESS, - PVRDMA_WC_LOC_LEN_ERR, - PVRDMA_WC_LOC_QP_OP_ERR, - PVRDMA_WC_LOC_EEC_OP_ERR, - PVRDMA_WC_LOC_PROT_ERR, - PVRDMA_WC_WR_FLUSH_ERR, - PVRDMA_WC_MW_BIND_ERR, - PVRDMA_WC_BAD_RESP_ERR, - PVRDMA_WC_LOC_ACCESS_ERR, - PVRDMA_WC_REM_INV_REQ_ERR, - PVRDMA_WC_REM_ACCESS_ERR, - PVRDMA_WC_REM_OP_ERR, - PVRDMA_WC_RETRY_EXC_ERR, - PVRDMA_WC_RNR_RETRY_EXC_ERR, - PVRDMA_WC_LOC_RDD_VIOL_ERR, - PVRDMA_WC_REM_INV_RD_REQ_ERR, - PVRDMA_WC_REM_ABORT_ERR, - PVRDMA_WC_INV_EECN_ERR, - PVRDMA_WC_INV_EEC_STATE_ERR, - PVRDMA_WC_FATAL_ERR, - PVRDMA_WC_RESP_TIMEOUT_ERR, - PVRDMA_WC_GENERAL_ERR, -}; - -enum pvrdma_wc_opcode { - PVRDMA_WC_SEND, - PVRDMA_WC_RDMA_WRITE, - PVRDMA_WC_RDMA_READ, - PVRDMA_WC_COMP_SWAP, - PVRDMA_WC_FETCH_ADD, - PVRDMA_WC_BIND_MW, - PVRDMA_WC_LSO, - PVRDMA_WC_LOCAL_INV, - PVRDMA_WC_FAST_REG_MR, - PVRDMA_WC_MASKED_COMP_SWAP, - PVRDMA_WC_MASKED_FETCH_ADD, - PVRDMA_WC_RECV = 1 << 7, - PVRDMA_WC_RECV_RDMA_WITH_IMM, -}; - -enum pvrdma_wc_flags { - PVRDMA_WC_GRH = 1 << 0, - PVRDMA_WC_WITH_IMM = 1 << 1, - PVRDMA_WC_WITH_INVALIDATE = 1 << 2, - PVRDMA_WC_IP_CSUM_OK = 1 << 3, - PVRDMA_WC_WITH_SMAC = 1 << 4, - PVRDMA_WC_WITH_VLAN = 1 << 5, - PVRDMA_WC_WITH_NETWORK_HDR_TYPE = 1 << 6, - PVRDMA_WC_FLAGS_MAX = PVRDMA_WC_WITH_NETWORK_HDR_TYPE, -}; - -enum pvrdma_network_type { - PVRDMA_NETWORK_IB, - PVRDMA_NETWORK_ROCE_V1 = PVRDMA_NETWORK_IB, - PVRDMA_NETWORK_IPV4, - PVRDMA_NETWORK_IPV6 -}; - -struct pvrdma_alloc_ucontext_resp { - uint32_t qp_tab_size; - uint32_t reserved; -}; - -struct pvrdma_alloc_pd_resp { - uint32_t pdn; - uint32_t reserved; -}; - -struct pvrdma_create_cq { - uint64_t __attribute__((aligned(8))) buf_addr; - uint32_t buf_size; - uint32_t reserved; -}; - -struct pvrdma_create_cq_resp { - uint32_t cqn; - uint32_t reserved; -}; - -struct pvrdma_resize_cq { - uint64_t __attribute__((aligned(8))) buf_addr; - uint32_t buf_size; - uint32_t reserved; -}; - -struct pvrdma_create_srq { - uint64_t __attribute__((aligned(8))) buf_addr; - uint32_t buf_size; - uint32_t reserved; -}; - -struct pvrdma_create_srq_resp { - uint32_t srqn; - uint32_t reserved; -}; - -struct pvrdma_create_qp { - uint64_t __attribute__((aligned(8))) rbuf_addr; - uint64_t __attribute__((aligned(8))) sbuf_addr; - uint32_t rbuf_size; - uint32_t sbuf_size; - uint64_t __attribute__((aligned(8))) qp_addr; -}; - -struct pvrdma_create_qp_resp { - uint32_t qpn; - uint32_t qp_handle; -}; - -/* PVRDMA masked atomic compare and swap */ -struct pvrdma_ex_cmp_swap { - uint64_t __attribute__((aligned(8))) swap_val; - uint64_t __attribute__((aligned(8))) compare_val; - uint64_t __attribute__((aligned(8))) swap_mask; - uint64_t __attribute__((aligned(8))) compare_mask; -}; - -/* PVRDMA masked atomic fetch and add */ -struct pvrdma_ex_fetch_add { - uint64_t __attribute__((aligned(8))) add_val; - uint64_t __attribute__((aligned(8))) field_boundary; -}; - -/* PVRDMA address vector. */ -struct pvrdma_av { - uint32_t port_pd; - uint32_t sl_tclass_flowlabel; - uint8_t dgid[16]; - uint8_t src_path_bits; - uint8_t gid_index; - uint8_t stat_rate; - uint8_t hop_limit; - uint8_t dmac[6]; - uint8_t reserved[6]; -}; - -/* PVRDMA scatter/gather entry */ -struct pvrdma_sge { - uint64_t __attribute__((aligned(8))) addr; - uint32_t length; - uint32_t lkey; -}; - -/* PVRDMA receive queue work request */ -struct pvrdma_rq_wqe_hdr { - uint64_t __attribute__((aligned(8))) wr_id; /* wr id */ - uint32_t num_sge; /* size of s/g array */ - uint32_t total_len; /* reserved */ -}; -/* Use pvrdma_sge (ib_sge) for receive queue s/g array elements. */ - -/* PVRDMA send queue work request */ -struct pvrdma_sq_wqe_hdr { - uint64_t __attribute__((aligned(8))) wr_id; /* wr id */ - uint32_t num_sge; /* size of s/g array */ - uint32_t total_len; /* reserved */ - uint32_t opcode; /* operation type */ - uint32_t send_flags; /* wr flags */ - union { - uint32_t imm_data; - uint32_t invalidate_rkey; - } ex; - uint32_t reserved; - union { - struct { - uint64_t __attribute__((aligned(8))) remote_addr; - uint32_t rkey; - uint8_t reserved[4]; - } rdma; - struct { - uint64_t __attribute__((aligned(8))) remote_addr; - uint64_t __attribute__((aligned(8))) compare_add; - uint64_t __attribute__((aligned(8))) swap; - uint32_t rkey; - uint32_t reserved; - } atomic; - struct { - uint64_t __attribute__((aligned(8))) remote_addr; - uint32_t log_arg_sz; - uint32_t rkey; - union { - struct pvrdma_ex_cmp_swap cmp_swap; - struct pvrdma_ex_fetch_add fetch_add; - } wr_data; - } masked_atomics; - struct { - uint64_t __attribute__((aligned(8))) iova_start; - uint64_t __attribute__((aligned(8))) pl_pdir_dma; - uint32_t page_shift; - uint32_t page_list_len; - uint32_t length; - uint32_t access_flags; - uint32_t rkey; - uint32_t reserved; - } fast_reg; - struct { - uint32_t remote_qpn; - uint32_t remote_qkey; - struct pvrdma_av av; - } ud; - } wr; -}; -/* Use pvrdma_sge (ib_sge) for send queue s/g array elements. */ - -/* Completion queue element. */ -struct pvrdma_cqe { - uint64_t __attribute__((aligned(8))) wr_id; - uint64_t __attribute__((aligned(8))) qp; - uint32_t opcode; - uint32_t status; - uint32_t byte_len; - uint32_t imm_data; - uint32_t src_qp; - uint32_t wc_flags; - uint32_t vendor_err; - uint16_t pkey_index; - uint16_t slid; - uint8_t sl; - uint8_t dlid_path_bits; - uint8_t port_num; - uint8_t smac[6]; - uint8_t network_hdr_type; - uint8_t reserved2[6]; /* Pad to next power of 2 (64). */ -}; - -#endif /* __VMW_PVRDMA_ABI_H__ */ diff --git a/migration/migration-stats.h b/migration/migration-stats.h index 05290ade76..817c53559a 100644 --- a/migration/migration-stats.h +++ b/migration/migration-stats.h @@ -93,10 +93,6 @@ typedef struct { * Maximum amount of data we can send in a cycle. */ Stat64 rate_limit_max; - /* - * Number of bytes sent through RDMA. - */ - Stat64 rdma_bytes; /* * Number of pages transferred that were full of zeros. */ @@ -133,7 +129,7 @@ void migration_rate_set(uint64_t new_rate); * * Returns how many bytes have we transferred since the beginning of * the migration. It accounts for bytes sent through any migration - * channel, multifd, qemu_file, rdma, .... + * channel, multifd, qemu_file, .... */ uint64_t migration_transferred_bytes(void); #endif diff --git a/migration/migration.h b/migration/migration.h index 8045e39c26..d097828580 100644 --- a/migration/migration.h +++ b/migration/migration.h @@ -162,13 +162,6 @@ struct MigrationIncomingState { int state; - /* - * The incoming migration coroutine, non-NULL during qemu_loadvm_state(). - * Used to wake the migration incoming coroutine from rdma code. How much is - * it safe - it's a question. - */ - Coroutine *loadvm_co; - /* The coroutine we should enter (back) after failover */ Coroutine *colo_incoming_co; QemuSemaphore colo_incoming_sem; @@ -463,8 +456,6 @@ struct MigrationState { * switchover has been received. */ bool switchover_acked; - /* Is this a rdma migration */ - bool rdma_migration; }; void migrate_set_state(int *state, int old_state, int new_state); diff --git a/migration/options.h b/migration/options.h index ab8199e207..c00213973e 100644 --- a/migration/options.h +++ b/migration/options.h @@ -37,7 +37,6 @@ bool migrate_multifd(void); bool migrate_pause_before_switchover(void); bool migrate_postcopy_blocktime(void); bool migrate_postcopy_preempt(void); -bool migrate_rdma_pin_all(void); bool migrate_release_ram(void); bool migrate_return_path(void); bool migrate_validate_uuid(void); @@ -54,7 +53,6 @@ bool migrate_zero_copy_send(void); bool migrate_multifd_flush_after_each_section(void); bool migrate_postcopy(void); -bool migrate_rdma(void); bool migrate_tls(void); /* capabilities helpers */ diff --git a/migration/rdma.h b/migration/rdma.h deleted file mode 100644 index a8d27f33b8..0000000000 --- a/migration/rdma.h +++ /dev/null @@ -1,69 +0,0 @@ -/* - * RDMA protocol and interfaces - * - * Copyright IBM, Corp. 2010-2013 - * Copyright Red Hat, Inc. 2015-2016 - * - * Authors: - * Michael R. Hines <mrhines(a)us.ibm.com> - * Jiuxing Liu <jl(a)us.ibm.com> - * Daniel P. Berrange <berrange(a)redhat.com> - * - * This work is licensed under the terms of the GNU GPL, version 2 or - * later. See the COPYING file in the top-level directory. - * - */ - -#include "qemu/sockets.h" - -#ifndef QEMU_MIGRATION_RDMA_H -#define QEMU_MIGRATION_RDMA_H - -#include "exec/memory.h" - -void rdma_start_outgoing_migration(void *opaque, InetSocketAddress *host_port, - Error **errp); - -void rdma_start_incoming_migration(InetSocketAddress *host_port, Error **errp); - -/* - * Constants used by rdma return codes - */ -#define RAM_CONTROL_SETUP 0 -#define RAM_CONTROL_ROUND 1 -#define RAM_CONTROL_FINISH 3 - -/* - * Whenever this is found in the data stream, the flags - * will be passed to rdma functions in the incoming-migration - * side. - */ -#define RAM_SAVE_FLAG_HOOK 0x80 - -#define RAM_SAVE_CONTROL_NOT_SUPP -1000 -#define RAM_SAVE_CONTROL_DELAYED -2000 - -#ifdef CONFIG_RDMA -int rdma_registration_handle(QEMUFile *f); -int rdma_registration_start(QEMUFile *f, uint64_t flags); -int rdma_registration_stop(QEMUFile *f, uint64_t flags); -int rdma_block_notification_handle(QEMUFile *f, const char *name); -int rdma_control_save_page(QEMUFile *f, ram_addr_t block_offset, - ram_addr_t offset, size_t size); -#else -static inline -int rdma_registration_handle(QEMUFile *f) { return 0; } -static inline -int rdma_registration_start(QEMUFile *f, uint64_t flags) { return 0; } -static inline -int rdma_registration_stop(QEMUFile *f, uint64_t flags) { return 0; } -static inline -int rdma_block_notification_handle(QEMUFile *f, const char *name) { return 0; } -static inline -int rdma_control_save_page(QEMUFile *f, ram_addr_t block_offset, - ram_addr_t offset, size_t size) -{ - return RAM_SAVE_CONTROL_NOT_SUPP; -} -#endif -#endif diff --git a/block/gluster.c b/block/gluster.c index cc74af06dc..4253c8db5e 100644 --- a/block/gluster.c +++ b/block/gluster.c @@ -371,9 +371,6 @@ static int qemu_gluster_parse_uri(BlockdevOptionsGluster *gconf, } else if (!strcmp(uri->scheme, "gluster+unix")) { gsconf->type = SOCKET_ADDRESS_TYPE_UNIX; is_unix = true; - } else if (!strcmp(uri->scheme, "gluster+rdma")) { - gsconf->type = SOCKET_ADDRESS_TYPE_INET; - warn_report("rdma feature is not supported, falling back to tcp"); } else { ret = -EINVAL; goto out; @@ -1638,44 +1635,8 @@ static BlockDriver bdrv_gluster_unix = { .strong_runtime_opts = gluster_strong_open_opts, }; -/* rdma is deprecated (actually never supported for volfile fetch). - * Let's maintain it for the protocol compatibility, to make sure things - * won't break immediately. For now, gluster+rdma will fall back to gluster+tcp - * protocol with a warning. - * TODO: remove gluster+rdma interface support - */ -static BlockDriver bdrv_gluster_rdma = { - .format_name = "gluster", - .protocol_name = "gluster+rdma", - .instance_size = sizeof(BDRVGlusterState), - .bdrv_file_open = qemu_gluster_open, - .bdrv_reopen_prepare = qemu_gluster_reopen_prepare, - .bdrv_reopen_commit = qemu_gluster_reopen_commit, - .bdrv_reopen_abort = qemu_gluster_reopen_abort, - .bdrv_close = qemu_gluster_close, - .bdrv_co_create = qemu_gluster_co_create, - .bdrv_co_create_opts = qemu_gluster_co_create_opts, - .bdrv_co_getlength = qemu_gluster_co_getlength, - .bdrv_co_get_allocated_file_size = qemu_gluster_co_get_allocated_file_size, - .bdrv_co_truncate = qemu_gluster_co_truncate, - .bdrv_co_readv = qemu_gluster_co_readv, - .bdrv_co_writev = qemu_gluster_co_writev, - .bdrv_co_flush_to_disk = qemu_gluster_co_flush_to_disk, -#ifdef CONFIG_GLUSTERFS_DISCARD - .bdrv_co_pdiscard = qemu_gluster_co_pdiscard, -#endif -#ifdef CONFIG_GLUSTERFS_ZEROFILL - .bdrv_co_pwrite_zeroes = qemu_gluster_co_pwrite_zeroes, -#endif - .bdrv_co_block_status = qemu_gluster_co_block_status, - .bdrv_refresh_limits = qemu_gluster_refresh_limits, - .create_opts = &qemu_gluster_create_opts, - .strong_runtime_opts = gluster_strong_open_opts, -}; - static void bdrv_gluster_init(void) { - bdrv_register(&bdrv_gluster_rdma); bdrv_register(&bdrv_gluster_unix); bdrv_register(&bdrv_gluster_tcp); bdrv_register(&bdrv_gluster); diff --git a/contrib/rdmacm-mux/main.c b/contrib/rdmacm-mux/main.c deleted file mode 100644 index 771ca01e03..0000000000 --- a/contrib/rdmacm-mux/main.c +++ /dev/null @@ -1,831 +0,0 @@ -/* - * QEMU paravirtual RDMA - rdmacm-mux implementation - * - * Copyright (C) 2018 Oracle - * Copyright (C) 2018 Red Hat Inc - * - * Authors: - * Yuval Shaia <yuval.shaia(a)oracle.com> - * Marcel Apfelbaum <marcel(a)redhat.com> - * - * This work is licensed under the terms of the GNU GPL, version 2 or later. - * See the COPYING file in the top-level directory. - * - */ - -#include "qemu/osdep.h" -#include <sys/poll.h> -#include <sys/ioctl.h> -#include <pthread.h> -#include <syslog.h> - -#include <infiniband/verbs.h> -#include <infiniband/umad.h> -#include <infiniband/umad_types.h> -#include <infiniband/umad_sa.h> -#include <infiniband/umad_cm.h> - -#include "rdmacm-mux.h" - -#define SCALE_US 1000 -#define COMMID_TTL 2 /* How many SCALE_US a context of MAD session is saved */ -#define SLEEP_SECS 5 /* This is used both in poll() and thread */ -#define SERVER_LISTEN_BACKLOG 10 -#define MAX_CLIENTS 4096 -#define MAD_RMPP_VERSION 0 -#define MAD_METHOD_MASK0 0x8 - -#define IB_USER_MAD_LONGS_PER_METHOD_MASK (128 / (8 * sizeof(long))) - -#define CM_REQ_DGID_POS 80 -#define CM_SIDR_REQ_DGID_POS 44 - -/* The below can be override by command line parameter */ -#define UNIX_SOCKET_PATH "/var/run/rdmacm-mux" -/* Has format %s-%s-%d" <path>-<rdma-dev--name>-<port> */ -#define SOCKET_PATH_MAX (PATH_MAX - NAME_MAX - sizeof(int) - 2) -#define RDMA_PORT_NUM 1 - -typedef struct RdmaCmServerArgs { - char unix_socket_path[PATH_MAX]; - char rdma_dev_name[NAME_MAX]; - int rdma_port_num; -} RdmaCMServerArgs; - -typedef struct CommId2FdEntry { - int fd; - int ttl; /* Initialized to 2, decrement each timeout, entry delete when 0 */ - __be64 gid_ifid; -} CommId2FdEntry; - -typedef struct RdmaCmUMadAgent { - int port_id; - int agent_id; - GHashTable *gid2fd; /* Used to find fd of a given gid */ - GHashTable *commid2fd; /* Used to find fd on of a given comm_id */ -} RdmaCmUMadAgent; - -typedef struct RdmaCmServer { - bool run; - RdmaCMServerArgs args; - struct pollfd fds[MAX_CLIENTS]; - int nfds; - RdmaCmUMadAgent umad_agent; - pthread_t umad_recv_thread; - pthread_rwlock_t lock; -} RdmaCMServer; - -static RdmaCMServer server = {0}; - -static void usage(const char *progname) -{ - printf("Usage: %s [OPTION]...\n" - "Start a RDMA-CM multiplexer\n" - "\n" - "\t-h Show this help\n" - "\t-d rdma-device-name Name of RDMA device to register with\n" - "\t-s unix-socket-path Path to unix socket to listen on (default %s)\n" - "\t-p rdma-device-port Port number of RDMA device to register with (default %d)\n", - progname, UNIX_SOCKET_PATH, RDMA_PORT_NUM); -} - -static void help(const char *progname) -{ - fprintf(stderr, "Try '%s -h' for more information.\n", progname); -} - -static void parse_args(int argc, char *argv[]) -{ - int c; - char unix_socket_path[SOCKET_PATH_MAX]; - - strcpy(server.args.rdma_dev_name, ""); - strcpy(unix_socket_path, UNIX_SOCKET_PATH); - server.args.rdma_port_num = RDMA_PORT_NUM; - - while ((c = getopt(argc, argv, "hs:d:p:")) != -1) { - switch (c) { - case 'h': - usage(argv[0]); - exit(0); - - case 'd': - strncpy(server.args.rdma_dev_name, optarg, NAME_MAX - 1); - break; - - case 's': - /* This is temporary, final name will build below */ - strncpy(unix_socket_path, optarg, SOCKET_PATH_MAX - 1); - break; - - case 'p': - server.args.rdma_port_num = atoi(optarg); - break; - - default: - help(argv[0]); - exit(1); - } - } - - if (!strcmp(server.args.rdma_dev_name, "")) { - fprintf(stderr, "Missing RDMA device name\n"); - help(argv[0]); - exit(1); - } - - /* Build unique unix-socket file name */ - snprintf(server.args.unix_socket_path, PATH_MAX, "%s-%s-%d", - unix_socket_path, server.args.rdma_dev_name, - server.args.rdma_port_num); - - syslog(LOG_INFO, "unix_socket_path=%s", server.args.unix_socket_path); - syslog(LOG_INFO, "rdma-device-name=%s", server.args.rdma_dev_name); - syslog(LOG_INFO, "rdma-device-port=%d", server.args.rdma_port_num); -} - -static void hash_tbl_alloc(void) -{ - - server.umad_agent.gid2fd = g_hash_table_new_full(g_int64_hash, - g_int64_equal, - g_free, g_free); - server.umad_agent.commid2fd = g_hash_table_new_full(g_int_hash, - g_int_equal, - g_free, g_free); -} - -static void hash_tbl_free(void) -{ - if (server.umad_agent.commid2fd) { - g_hash_table_destroy(server.umad_agent.commid2fd); - } - if (server.umad_agent.gid2fd) { - g_hash_table_destroy(server.umad_agent.gid2fd); - } -} - - -static int _hash_tbl_search_fd_by_ifid(__be64 *gid_ifid) -{ - int *fd; - - fd = g_hash_table_lookup(server.umad_agent.gid2fd, gid_ifid); - if (!fd) { - /* Let's try IPv4 */ - *gid_ifid |= 0x00000000ffff0000; - fd = g_hash_table_lookup(server.umad_agent.gid2fd, gid_ifid); - } - - return fd ? *fd : 0; -} - -static int hash_tbl_search_fd_by_ifid(int *fd, __be64 *gid_ifid) -{ - pthread_rwlock_rdlock(&server.lock); - *fd = _hash_tbl_search_fd_by_ifid(gid_ifid); - pthread_rwlock_unlock(&server.lock); - - if (!*fd) { - syslog(LOG_WARNING, "Can't find matching for ifid 0x%llx\n", *gid_ifid); - return -ENOENT; - } - - return 0; -} - -static int hash_tbl_search_fd_by_comm_id(uint32_t comm_id, int *fd, - __be64 *gid_idid) -{ - CommId2FdEntry *fde; - - pthread_rwlock_rdlock(&server.lock); - fde = g_hash_table_lookup(server.umad_agent.commid2fd, &comm_id); - pthread_rwlock_unlock(&server.lock); - - if (!fde) { - syslog(LOG_WARNING, "Can't find matching for comm_id 0x%x\n", comm_id); - return -ENOENT; - } - - *fd = fde->fd; - *gid_idid = fde->gid_ifid; - - return 0; -} - -static RdmaCmMuxErrCode add_fd_ifid_pair(int fd, __be64 gid_ifid) -{ - int fd1; - - pthread_rwlock_wrlock(&server.lock); - - fd1 = _hash_tbl_search_fd_by_ifid(&gid_ifid); - if (fd1) { /* record already exist - an error */ - pthread_rwlock_unlock(&server.lock); - return fd == fd1 ? RDMACM_MUX_ERR_CODE_EEXIST : - RDMACM_MUX_ERR_CODE_EACCES; - } - - g_hash_table_insert(server.umad_agent.gid2fd, g_memdup(&gid_ifid, - sizeof(gid_ifid)), g_memdup(&fd, sizeof(fd))); - - pthread_rwlock_unlock(&server.lock); - - syslog(LOG_INFO, "0x%lx registered on socket %d", - be64toh((uint64_t)gid_ifid), fd); - - return RDMACM_MUX_ERR_CODE_OK; -} - -static RdmaCmMuxErrCode delete_fd_ifid_pair(int fd, __be64 gid_ifid) -{ - int fd1; - - pthread_rwlock_wrlock(&server.lock); - - fd1 = _hash_tbl_search_fd_by_ifid(&gid_ifid); - if (!fd1) { /* record not exist - an error */ - pthread_rwlock_unlock(&server.lock); - return RDMACM_MUX_ERR_CODE_ENOTFOUND; - } - - g_hash_table_remove(server.umad_agent.gid2fd, g_memdup(&gid_ifid, - sizeof(gid_ifid))); - pthread_rwlock_unlock(&server.lock); - - syslog(LOG_INFO, "0x%lx unregistered on socket %d", - be64toh((uint64_t)gid_ifid), fd); - - return RDMACM_MUX_ERR_CODE_OK; -} - -static void hash_tbl_save_fd_comm_id_pair(int fd, uint32_t comm_id, - uint64_t gid_ifid) -{ - CommId2FdEntry fde = {fd, COMMID_TTL, gid_ifid}; - - pthread_rwlock_wrlock(&server.lock); - g_hash_table_insert(server.umad_agent.commid2fd, - g_memdup(&comm_id, sizeof(comm_id)), - g_memdup(&fde, sizeof(fde))); - pthread_rwlock_unlock(&server.lock); -} - -static gboolean remove_old_comm_ids(gpointer key, gpointer value, - gpointer user_data) -{ - CommId2FdEntry *fde = (CommId2FdEntry *)value; - - return !fde->ttl--; -} - -static gboolean remove_entry_from_gid2fd(gpointer key, gpointer value, - gpointer user_data) -{ - if (*(int *)value == *(int *)user_data) { - syslog(LOG_INFO, "0x%lx unregistered on socket %d", - be64toh(*(uint64_t *)key), *(int *)value); - return true; - } - - return false; -} - -static void hash_tbl_remove_fd_ifid_pair(int fd) -{ - pthread_rwlock_wrlock(&server.lock); - g_hash_table_foreach_remove(server.umad_agent.gid2fd, - remove_entry_from_gid2fd, (gpointer)&fd); - pthread_rwlock_unlock(&server.lock); -} - -static int get_fd(const char *mad, int umad_len, int *fd, __be64 *gid_ifid) -{ - struct umad_hdr *hdr = (struct umad_hdr *)mad; - char *data = (char *)hdr + sizeof(*hdr); - int32_t comm_id = 0; - uint16_t attr_id = be16toh(hdr->attr_id); - int rc = 0; - - if (umad_len <= sizeof(*hdr)) { - rc = -EINVAL; - syslog(LOG_DEBUG, "Ignoring MAD packets with header only\n"); - goto out; - } - - switch (attr_id) { - case UMAD_CM_ATTR_REQ: - if (unlikely(umad_len < sizeof(*hdr) + CM_REQ_DGID_POS + - sizeof(*gid_ifid))) { - rc = -EINVAL; - syslog(LOG_WARNING, - "Invalid MAD packet size (%d) for attr_id 0x%x\n", umad_len, - attr_id); - goto out; - } - memcpy(gid_ifid, data + CM_REQ_DGID_POS, sizeof(*gid_ifid)); - rc = hash_tbl_search_fd_by_ifid(fd, gid_ifid); - break; - - case UMAD_CM_ATTR_SIDR_REQ: - if (unlikely(umad_len < sizeof(*hdr) + CM_SIDR_REQ_DGID_POS + - sizeof(*gid_ifid))) { - rc = -EINVAL; - syslog(LOG_WARNING, - "Invalid MAD packet size (%d) for attr_id 0x%x\n", umad_len, - attr_id); - goto out; - } - memcpy(gid_ifid, data + CM_SIDR_REQ_DGID_POS, sizeof(*gid_ifid)); - rc = hash_tbl_search_fd_by_ifid(fd, gid_ifid); - break; - - case UMAD_CM_ATTR_REP: - /* Fall through */ - case UMAD_CM_ATTR_REJ: - /* Fall through */ - case UMAD_CM_ATTR_DREQ: - /* Fall through */ - case UMAD_CM_ATTR_DREP: - /* Fall through */ - case UMAD_CM_ATTR_RTU: - data += sizeof(comm_id); - /* Fall through */ - case UMAD_CM_ATTR_SIDR_REP: - if (unlikely(umad_len < sizeof(*hdr) + sizeof(comm_id))) { - rc = -EINVAL; - syslog(LOG_WARNING, - "Invalid MAD packet size (%d) for attr_id 0x%x\n", umad_len, - attr_id); - goto out; - } - memcpy(&comm_id, data, sizeof(comm_id)); - if (comm_id) { - rc = hash_tbl_search_fd_by_comm_id(comm_id, fd, gid_ifid); - } - break; - - default: - rc = -EINVAL; - syslog(LOG_WARNING, "Unsupported attr_id 0x%x\n", attr_id); - } - - syslog(LOG_DEBUG, "mad_to_vm: %d 0x%x 0x%x\n", *fd, attr_id, comm_id); - -out: - return rc; -} - -static void *umad_recv_thread_func(void *args) -{ - int rc; - RdmaCmMuxMsg msg = {}; - int fd = -2; - - msg.hdr.msg_type = RDMACM_MUX_MSG_TYPE_REQ; - msg.hdr.op_code = RDMACM_MUX_OP_CODE_MAD; - - while (server.run) { - do { - msg.umad_len = sizeof(msg.umad.mad); - rc = umad_recv(server.umad_agent.port_id, &msg.umad, &msg.umad_len, - SLEEP_SECS * SCALE_US); - if ((rc == -EIO) || (rc == -EINVAL)) { - syslog(LOG_CRIT, "Fatal error while trying to read MAD"); - } - - if (rc == -ETIMEDOUT) { - g_hash_table_foreach_remove(server.umad_agent.commid2fd, - remove_old_comm_ids, NULL); - } - } while (rc && server.run); - - if (server.run) { - rc = get_fd(msg.umad.mad, msg.umad_len, &fd, - &msg.hdr.sgid.global.interface_id); - if (rc) { - continue; - } - - send(fd, &msg, sizeof(msg), 0); - } - } - - return NULL; -} - -static int read_and_process(int fd) -{ - int rc; - RdmaCmMuxMsg msg = {}; - struct umad_hdr *hdr; - uint32_t *comm_id = 0; - uint16_t attr_id; - - rc = recv(fd, &msg, sizeof(msg), 0); - syslog(LOG_DEBUG, "Socket %d, recv %d\n", fd, rc); - - if (rc < 0 && errno != EWOULDBLOCK) { - syslog(LOG_ERR, "Fail to read from socket %d\n", fd); - return -EIO; - } - - if (!rc) { - syslog(LOG_ERR, "Fail to read from socket %d\n", fd); - return -EPIPE; - } - - if (msg.hdr.msg_type != RDMACM_MUX_MSG_TYPE_REQ) { - syslog(LOG_WARNING, "Got non-request message (%d) from socket %d\n", - msg.hdr.msg_type, fd); - return -EPERM; - } - - switch (msg.hdr.op_code) { - case RDMACM_MUX_OP_CODE_REG: - rc = add_fd_ifid_pair(fd, msg.hdr.sgid.global.interface_id); - break; - - case RDMACM_MUX_OP_CODE_UNREG: - rc = delete_fd_ifid_pair(fd, msg.hdr.sgid.global.interface_id); - break; - - case RDMACM_MUX_OP_CODE_MAD: - /* If this is REQ or REP then store the pair comm_id,fd to be later - * used for other messages where gid is unknown */ - hdr = (struct umad_hdr *)msg.umad.mad; - attr_id = be16toh(hdr->attr_id); - if ((attr_id == UMAD_CM_ATTR_REQ) || (attr_id == UMAD_CM_ATTR_DREQ) || - (attr_id == UMAD_CM_ATTR_SIDR_REQ) || - (attr_id == UMAD_CM_ATTR_REP) || (attr_id == UMAD_CM_ATTR_DREP)) { - comm_id = (uint32_t *)(msg.umad.mad + sizeof(*hdr)); - hash_tbl_save_fd_comm_id_pair(fd, *comm_id, - msg.hdr.sgid.global.interface_id); - } - - syslog(LOG_DEBUG, "vm_to_mad: %d 0x%x 0x%x\n", fd, attr_id, - comm_id ? *comm_id : 0); - rc = umad_send(server.umad_agent.port_id, server.umad_agent.agent_id, - &msg.umad, msg.umad_len, 1, 0); - if (rc) { - syslog(LOG_ERR, - "Fail to send MAD message (0x%x) from socket %d, err=%d", - attr_id, fd, rc); - } - break; - - default: - syslog(LOG_ERR, "Got invalid op_code (%d) from socket %d", - msg.hdr.msg_type, fd); - rc = RDMACM_MUX_ERR_CODE_EINVAL; - } - - msg.hdr.msg_type = RDMACM_MUX_MSG_TYPE_RESP; - msg.hdr.err_code = rc; - rc = send(fd, &msg, sizeof(msg), 0); - - return rc == sizeof(msg) ? 0 : -EPIPE; -} - -static int accept_all(void) -{ - int fd, rc = 0; - - pthread_rwlock_wrlock(&server.lock); - - do { - if ((server.nfds + 1) > MAX_CLIENTS) { - syslog(LOG_WARNING, "Too many clients (%d)", server.nfds); - rc = -EIO; - goto out; - } - - fd = accept(server.fds[0].fd, NULL, NULL); - if (fd < 0) { - if (errno != EWOULDBLOCK) { - syslog(LOG_WARNING, "accept() failed"); - rc = -EIO; - goto out; - } - break; - } - - syslog(LOG_INFO, "Client connected on socket %d\n", fd); - server.fds[server.nfds].fd = fd; - server.fds[server.nfds].events = POLLIN; - server.nfds++; - } while (fd != -1); - -out: - pthread_rwlock_unlock(&server.lock); - return rc; -} - -static void compress_fds(void) -{ - int i, j; - int closed = 0; - - pthread_rwlock_wrlock(&server.lock); - - for (i = 1; i < server.nfds; i++) { - if (!server.fds[i].fd) { - closed++; - for (j = i; j < server.nfds - 1; j++) { - server.fds[j] = server.fds[j + 1]; - } - } - } - - server.nfds -= closed; - - pthread_rwlock_unlock(&server.lock); -} - -static void close_fd(int idx) -{ - close(server.fds[idx].fd); - syslog(LOG_INFO, "Socket %d closed\n", server.fds[idx].fd); - hash_tbl_remove_fd_ifid_pair(server.fds[idx].fd); - server.fds[idx].fd = 0; -} - -static void run(void) -{ - int rc, nfds, i; - bool compress = false; - - syslog(LOG_INFO, "Service started"); - - while (server.run) { - rc = poll(server.fds, server.nfds, SLEEP_SECS * SCALE_US); - if (rc < 0) { - if (errno != EINTR) { - syslog(LOG_WARNING, "poll() failed"); - } - continue; - } - - if (rc == 0) { - continue; - } - - nfds = server.nfds; - for (i = 0; i < nfds; i++) { - syslog(LOG_DEBUG, "pollfd[%d]: revents 0x%x, events 0x%x\n", i, - server.fds[i].revents, server.fds[i].events); - if (server.fds[i].revents == 0) { - continue; - } - - if (server.fds[i].revents != POLLIN) { - if (i == 0) { - syslog(LOG_NOTICE, "Unexpected poll() event (0x%x)\n", - server.fds[i].revents); - } else { - close_fd(i); - compress = true; - } - continue; - } - - if (i == 0) { - rc = accept_all(); - if (rc) { - continue; - } - } else { - rc = read_and_process(server.fds[i].fd); - if (rc) { - close_fd(i); - compress = true; - } - } - } - - if (compress) { - compress = false; - compress_fds(); - } - } -} - -static void fini_listener(void) -{ - int i; - - if (server.fds[0].fd <= 0) { - return; - } - - for (i = server.nfds - 1; i >= 0; i--) { - if (server.fds[i].fd) { - close(server.fds[i].fd); - } - } - - unlink(server.args.unix_socket_path); -} - -static void fini_umad(void) -{ - if (server.umad_agent.agent_id) { - umad_unregister(server.umad_agent.port_id, server.umad_agent.agent_id); - } - - if (server.umad_agent.port_id) { - umad_close_port(server.umad_agent.port_id); - } - - hash_tbl_free(); -} - -static void fini(void) -{ - if (server.umad_recv_thread) { - pthread_join(server.umad_recv_thread, NULL); - server.umad_recv_thread = 0; - } - fini_umad(); - fini_listener(); - pthread_rwlock_destroy(&server.lock); - - syslog(LOG_INFO, "Service going down"); -} - -static int init_listener(void) -{ - struct sockaddr_un sun; - int rc, on = 1; - - server.fds[0].fd = socket(AF_UNIX, SOCK_STREAM, 0); - if (server.fds[0].fd < 0) { - syslog(LOG_ALERT, "socket() failed"); - return -EIO; - } - - rc = setsockopt(server.fds[0].fd, SOL_SOCKET, SO_REUSEADDR, (char *)&on, - sizeof(on)); - if (rc < 0) { - syslog(LOG_ALERT, "setsockopt() failed"); - rc = -EIO; - goto err; - } - - rc = ioctl(server.fds[0].fd, FIONBIO, (char *)&on); - if (rc < 0) { - syslog(LOG_ALERT, "ioctl() failed"); - rc = -EIO; - goto err; - } - - if (strlen(server.args.unix_socket_path) >= sizeof(sun.sun_path)) { - syslog(LOG_ALERT, - "Invalid unix_socket_path, size must be less than %ld\n", - sizeof(sun.sun_path)); - rc = -EINVAL; - goto err; - } - - sun.sun_family = AF_UNIX; - rc = snprintf(sun.sun_path, sizeof(sun.sun_path), "%s", - server.args.unix_socket_path); - if (rc < 0 || rc >= sizeof(sun.sun_path)) { - syslog(LOG_ALERT, "Could not copy unix socket path\n"); - rc = -EINVAL; - goto err; - } - - rc = bind(server.fds[0].fd, (struct sockaddr *)&sun, sizeof(sun)); - if (rc < 0) { - syslog(LOG_ALERT, "bind() failed"); - rc = -EIO; - goto err; - } - - rc = listen(server.fds[0].fd, SERVER_LISTEN_BACKLOG); - if (rc < 0) { - syslog(LOG_ALERT, "listen() failed"); - rc = -EIO; - goto err; - } - - server.fds[0].events = POLLIN; - server.nfds = 1; - server.run = true; - - return 0; - -err: - close(server.fds[0].fd); - return rc; -} - -static int init_umad(void) -{ - long method_mask[IB_USER_MAD_LONGS_PER_METHOD_MASK]; - - server.umad_agent.port_id = umad_open_port(server.args.rdma_dev_name, - server.args.rdma_port_num); - - if (server.umad_agent.port_id < 0) { - syslog(LOG_WARNING, "umad_open_port() failed"); - return -EIO; - } - - memset(&method_mask, 0, sizeof(method_mask)); - method_mask[0] = MAD_METHOD_MASK0; - server.umad_agent.agent_id = umad_register(server.umad_agent.port_id, - UMAD_CLASS_CM, - UMAD_SA_CLASS_VERSION, - MAD_RMPP_VERSION, method_mask); - if (server.umad_agent.agent_id < 0) { - syslog(LOG_WARNING, "umad_register() failed"); - return -EIO; - } - - hash_tbl_alloc(); - - return 0; -} - -static void signal_handler(int sig, siginfo_t *siginfo, void *context) -{ - static bool warned; - - /* Prevent stop if clients are connected */ - if (server.nfds != 1) { - if (!warned) { - syslog(LOG_WARNING, - "Can't stop while active client exist, resend SIGINT to overid"); - warned = true; - return; - } - } - - if (sig == SIGINT) { - server.run = false; - fini(); - } - - exit(0); -} - -static int init(void) -{ - int rc; - struct sigaction sig = {}; - - rc = init_listener(); - if (rc) { - return rc; - } - - rc = init_umad(); - if (rc) { - return rc; - } - - pthread_rwlock_init(&server.lock, 0); - - rc = pthread_create(&server.umad_recv_thread, NULL, umad_recv_thread_func, - NULL); - if (rc) { - syslog(LOG_ERR, "Fail to create UMAD receiver thread (%d)\n", rc); - return rc; - } - - sig.sa_sigaction = &signal_handler; - sig.sa_flags = SA_SIGINFO; - rc = sigaction(SIGINT, &sig, NULL); - if (rc < 0) { - syslog(LOG_ERR, "Fail to install SIGINT handler (%d)\n", errno); - return rc; - } - - return 0; -} - -int main(int argc, char *argv[]) -{ - int rc; - - memset(&server, 0, sizeof(server)); - - parse_args(argc, argv); - - rc = init(); - if (rc) { - syslog(LOG_ERR, "Fail to initialize server (%d)\n", rc); - rc = -EAGAIN; - goto out; - } - - run(); - -out: - fini(); - - return rc; -} diff --git a/hw/core/machine-qmp-cmds.c b/hw/core/machine-qmp-cmds.c index 4b72009cd3..c20829b9ae 100644 --- a/hw/core/machine-qmp-cmds.c +++ b/hw/core/machine-qmp-cmds.c @@ -12,7 +12,6 @@ #include "hw/boards.h" #include "hw/intc/intc.h" #include "hw/mem/memory-device.h" -#include "hw/rdma/rdma.h" #include "qapi/error.h" #include "qapi/qapi-builtin-visit.h" #include "qapi/qapi-commands-machine.h" @@ -291,37 +290,6 @@ MemoryInfo *qmp_query_memory_size_summary(Error **errp) return mem_info; } -static int qmp_x_query_rdma_foreach(Object *obj, void *opaque) -{ - RdmaProvider *rdma; - RdmaProviderClass *k; - GString *buf = opaque; - - if (object_dynamic_cast(obj, INTERFACE_RDMA_PROVIDER)) { - rdma = RDMA_PROVIDER(obj); - k = RDMA_PROVIDER_GET_CLASS(obj); - if (k->format_statistics) { - k->format_statistics(rdma, buf); - } else { - g_string_append_printf(buf, - "RDMA statistics not available for %s.\n", - object_get_typename(obj)); - } - } - - return 0; -} - -HumanReadableText *qmp_x_query_rdma(Error **errp) -{ - g_autoptr(GString) buf = g_string_new(""); - - object_child_foreach_recursive(object_get_root(), - qmp_x_query_rdma_foreach, buf); - - return human_readable_text_from_str(buf); -} - HumanReadableText *qmp_x_query_ramblock(Error **errp) { g_autoptr(GString) buf = ram_block_format(); diff --git a/hw/rdma/rdma.c b/hw/rdma/rdma.c deleted file mode 100644 index 7bec0d0d2c..0000000000 --- a/hw/rdma/rdma.c +++ /dev/null @@ -1,30 +0,0 @@ -/* - * RDMA device interface - * - * Copyright (C) 2018 Oracle - * Copyright (C) 2018 Red Hat Inc - * - * Authors: - * Yuval Shaia <yuval.shaia(a)oracle.com> - * - * This work is licensed under the terms of the GNU GPL, version 2 or later. - * See the COPYING file in the top-level directory. - * - */ - -#include "qemu/osdep.h" -#include "hw/rdma/rdma.h" -#include "qemu/module.h" - -static const TypeInfo rdma_hmp_info = { - .name = INTERFACE_RDMA_PROVIDER, - .parent = TYPE_INTERFACE, - .class_size = sizeof(RdmaProviderClass), -}; - -static void rdma_register_types(void) -{ - type_register_static(&rdma_hmp_info); -} - -type_init(rdma_register_types) diff --git a/hw/rdma/rdma_backend.c b/hw/rdma/rdma_backend.c deleted file mode 100644 index 6dcdfbbbe2..0000000000 --- a/hw/rdma/rdma_backend.c +++ /dev/null @@ -1,1401 +0,0 @@ -/* - * QEMU paravirtual RDMA - Generic RDMA backend - * - * Copyright (C) 2018 Oracle - * Copyright (C) 2018 Red Hat Inc - * - * Authors: - * Yuval Shaia <yuval.shaia(a)oracle.com> - * Marcel Apfelbaum <marcel(a)redhat.com> - * - * This work is licensed under the terms of the GNU GPL, version 2 or later. - * See the COPYING file in the top-level directory. - * - */ - -#include "qemu/osdep.h" -#include "qapi/qapi-events-rdma.h" - -#include <infiniband/verbs.h> - -#include "contrib/rdmacm-mux/rdmacm-mux.h" -#include "trace.h" -#include "rdma_utils.h" -#include "rdma_rm.h" -#include "rdma_backend.h" - -#define THR_NAME_LEN 16 -#define THR_POLL_TO 5000 - -#define MAD_HDR_SIZE sizeof(struct ibv_grh) - -typedef struct BackendCtx { - void *up_ctx; - struct ibv_sge sge; /* Used to save MAD recv buffer */ - RdmaBackendQP *backend_qp; /* To maintain recv buffers */ - RdmaBackendSRQ *backend_srq; -} BackendCtx; - -struct backend_umad { - struct ib_user_mad hdr; - char mad[RDMA_MAX_PRIVATE_DATA]; -}; - -static void (*comp_handler)(void *ctx, struct ibv_wc *wc); - -static void dummy_comp_handler(void *ctx, struct ibv_wc *wc) -{ - rdma_error_report("No completion handler is registered"); -} - -static inline void complete_work(enum ibv_wc_status status, uint32_t vendor_err, - void *ctx) -{ - struct ibv_wc wc = {}; - - wc.status = status; - wc.vendor_err = vendor_err; - - comp_handler(ctx, &wc); -} - -static void free_cqe_ctx(gpointer data, gpointer user_data) -{ - BackendCtx *bctx; - RdmaDeviceResources *rdma_dev_res = user_data; - unsigned long cqe_ctx_id = GPOINTER_TO_INT(data); - - bctx = rdma_rm_get_cqe_ctx(rdma_dev_res, cqe_ctx_id); - if (bctx) { - rdma_rm_dealloc_cqe_ctx(rdma_dev_res, cqe_ctx_id); - qatomic_dec(&rdma_dev_res->stats.missing_cqe); - } - g_free(bctx); -} - -static void clean_recv_mads(RdmaBackendDev *backend_dev) -{ - unsigned long cqe_ctx_id; - - do { - cqe_ctx_id = rdma_protected_gqueue_pop_int64(&backend_dev-> - recv_mads_list); - if (cqe_ctx_id != -ENOENT) { - qatomic_inc(&backend_dev->rdma_dev_res->stats.missing_cqe); - free_cqe_ctx(GINT_TO_POINTER(cqe_ctx_id), - backend_dev->rdma_dev_res); - } - } while (cqe_ctx_id != -ENOENT); -} - -static int rdma_poll_cq(RdmaDeviceResources *rdma_dev_res, struct ibv_cq *ibcq) -{ - int i, ne, total_ne = 0; - BackendCtx *bctx; - struct ibv_wc wc[2]; - RdmaProtectedGSList *cqe_ctx_list; - - WITH_QEMU_LOCK_GUARD(&rdma_dev_res->lock) { - do { - ne = ibv_poll_cq(ibcq, ARRAY_SIZE(wc), wc); - - trace_rdma_poll_cq(ne, ibcq); - - for (i = 0; i < ne; i++) { - bctx = rdma_rm_get_cqe_ctx(rdma_dev_res, wc[i].wr_id); - if (unlikely(!bctx)) { - rdma_error_report("No matching ctx for req %"PRId64, - wc[i].wr_id); - continue; - } - - comp_handler(bctx->up_ctx, &wc[i]); - - if (bctx->backend_qp) { - cqe_ctx_list = &bctx->backend_qp->cqe_ctx_list; - } else { - cqe_ctx_list = &bctx->backend_srq->cqe_ctx_list; - } - - rdma_protected_gslist_remove_int32(cqe_ctx_list, wc[i].wr_id); - rdma_rm_dealloc_cqe_ctx(rdma_dev_res, wc[i].wr_id); - g_free(bctx); - } - total_ne += ne; - } while (ne > 0); - qatomic_sub(&rdma_dev_res->stats.missing_cqe, total_ne); - } - - if (ne < 0) { - rdma_error_report("ibv_poll_cq fail, rc=%d, errno=%d", ne, errno); - } - - rdma_dev_res->stats.completions += total_ne; - - return total_ne; -} - -static void *comp_handler_thread(void *arg) -{ - RdmaBackendDev *backend_dev = (RdmaBackendDev *)arg; - int rc; - struct ibv_cq *ev_cq; - void *ev_ctx; - int flags; - GPollFD pfds[1]; - - /* Change to non-blocking mode */ - flags = fcntl(backend_dev->channel->fd, F_GETFL); - rc = fcntl(backend_dev->channel->fd, F_SETFL, flags | O_NONBLOCK); - if (rc < 0) { - rdma_error_report("Failed to change backend channel FD to non-blocking"); - return NULL; - } - - pfds[0].fd = backend_dev->channel->fd; - pfds[0].events = G_IO_IN | G_IO_HUP | G_IO_ERR; - - backend_dev->comp_thread.is_running = true; - - while (backend_dev->comp_thread.run) { - do { - rc = qemu_poll_ns(pfds, 1, THR_POLL_TO * (int64_t)SCALE_MS); - if (!rc) { - backend_dev->rdma_dev_res->stats.poll_cq_ppoll_to++; - } - } while (!rc && backend_dev->comp_thread.run); - - if (backend_dev->comp_thread.run) { - rc = ibv_get_cq_event(backend_dev->channel, &ev_cq, &ev_ctx); - if (unlikely(rc)) { - rdma_error_report("ibv_get_cq_event fail, rc=%d, errno=%d", rc, - errno); - continue; - } - - rc = ibv_req_notify_cq(ev_cq, 0); - if (unlikely(rc)) { - rdma_error_report("ibv_req_notify_cq fail, rc=%d, errno=%d", rc, - errno); - } - - backend_dev->rdma_dev_res->stats.poll_cq_from_bk++; - rdma_poll_cq(backend_dev->rdma_dev_res, ev_cq); - - ibv_ack_cq_events(ev_cq, 1); - } - } - - backend_dev->comp_thread.is_running = false; - - qemu_thread_exit(0); - - return NULL; -} - -static inline void disable_rdmacm_mux_async(RdmaBackendDev *backend_dev) -{ - qatomic_set(&backend_dev->rdmacm_mux.can_receive, 0); -} - -static inline void enable_rdmacm_mux_async(RdmaBackendDev *backend_dev) -{ - qatomic_set(&backend_dev->rdmacm_mux.can_receive, sizeof(RdmaCmMuxMsg)); -} - -static inline int rdmacm_mux_can_process_async(RdmaBackendDev *backend_dev) -{ - return qatomic_read(&backend_dev->rdmacm_mux.can_receive); -} - -static int rdmacm_mux_check_op_status(CharBackend *mad_chr_be) -{ - RdmaCmMuxMsg msg = {}; - int ret; - - ret = qemu_chr_fe_read_all(mad_chr_be, (uint8_t *)&msg, sizeof(msg)); - if (ret != sizeof(msg)) { - rdma_error_report("Got invalid message from mux: size %d, expecting %d", - ret, (int)sizeof(msg)); - return -EIO; - } - - trace_rdmacm_mux_check_op_status(msg.hdr.msg_type, msg.hdr.op_code, - msg.hdr.err_code); - - if (msg.hdr.msg_type != RDMACM_MUX_MSG_TYPE_RESP) { - rdma_error_report("Got invalid message type %d", msg.hdr.msg_type); - return -EIO; - } - - if (msg.hdr.err_code != RDMACM_MUX_ERR_CODE_OK) { - rdma_error_report("Operation failed in mux, error code %d", - msg.hdr.err_code); - return -EIO; - } - - return 0; -} - -static int rdmacm_mux_send(RdmaBackendDev *backend_dev, RdmaCmMuxMsg *msg) -{ - int rc = 0; - - msg->hdr.msg_type = RDMACM_MUX_MSG_TYPE_REQ; - trace_rdmacm_mux("send", msg->hdr.msg_type, msg->hdr.op_code); - disable_rdmacm_mux_async(backend_dev); - rc = qemu_chr_fe_write(backend_dev->rdmacm_mux.chr_be, - (const uint8_t *)msg, sizeof(*msg)); - if (rc != sizeof(*msg)) { - enable_rdmacm_mux_async(backend_dev); - rdma_error_report("Failed to send request to rdmacm_mux (rc=%d)", rc); - return -EIO; - } - - rc = rdmacm_mux_check_op_status(backend_dev->rdmacm_mux.chr_be); - if (rc) { - rdma_error_report("Failed to execute rdmacm_mux request %d (rc=%d)", - msg->hdr.op_code, rc); - } - - enable_rdmacm_mux_async(backend_dev); - - return 0; -} - -static void stop_backend_thread(RdmaBackendThread *thread) -{ - thread->run = false; - while (thread->is_running) { - sleep(THR_POLL_TO / SCALE_US / 2); - } -} - -static void start_comp_thread(RdmaBackendDev *backend_dev) -{ - char thread_name[THR_NAME_LEN] = {}; - - stop_backend_thread(&backend_dev->comp_thread); - - snprintf(thread_name, sizeof(thread_name), "rdma_comp_%s", - ibv_get_device_name(backend_dev->ib_dev)); - backend_dev->comp_thread.run = true; - qemu_thread_create(&backend_dev->comp_thread.thread, thread_name, - comp_handler_thread, backend_dev, QEMU_THREAD_DETACHED); -} - -void rdma_backend_register_comp_handler(void (*handler)(void *ctx, - struct ibv_wc *wc)) -{ - comp_handler = handler; -} - -void rdma_backend_unregister_comp_handler(void) -{ - rdma_backend_register_comp_handler(dummy_comp_handler); -} - -int rdma_backend_query_port(RdmaBackendDev *backend_dev, - struct ibv_port_attr *port_attr) -{ - int rc; - - rc = ibv_query_port(backend_dev->context, backend_dev->port_num, port_attr); - if (rc) { - rdma_error_report("ibv_query_port fail, rc=%d, errno=%d", rc, errno); - return -EIO; - } - - return 0; -} - -void rdma_backend_poll_cq(RdmaDeviceResources *rdma_dev_res, RdmaBackendCQ *cq) -{ - int polled; - - rdma_dev_res->stats.poll_cq_from_guest++; - polled = rdma_poll_cq(rdma_dev_res, cq->ibcq); - if (!polled) { - rdma_dev_res->stats.poll_cq_from_guest_empty++; - } -} - -static GHashTable *ah_hash; - -static struct ibv_ah *create_ah(RdmaBackendDev *backend_dev, struct ibv_pd *pd, - uint8_t sgid_idx, union ibv_gid *dgid) -{ - GBytes *ah_key = g_bytes_new(dgid, sizeof(*dgid)); - struct ibv_ah *ah = g_hash_table_lookup(ah_hash, ah_key); - - if (ah) { - trace_rdma_create_ah_cache_hit(be64_to_cpu(dgid->global.subnet_prefix), - be64_to_cpu(dgid->global.interface_id)); - g_bytes_unref(ah_key); - } else { - struct ibv_ah_attr ah_attr = { - .is_global = 1, - .port_num = backend_dev->port_num, - .grh.hop_limit = 1, - }; - - ah_attr.grh.dgid = *dgid; - ah_attr.grh.sgid_index = sgid_idx; - - ah = ibv_create_ah(pd, &ah_attr); - if (ah) { - g_hash_table_insert(ah_hash, ah_key, ah); - } else { - g_bytes_unref(ah_key); - rdma_error_report("Failed to create AH for gid <0x%" PRIx64", 0x%"PRIx64">", - be64_to_cpu(dgid->global.subnet_prefix), - be64_to_cpu(dgid->global.interface_id)); - } - - trace_rdma_create_ah_cache_miss(be64_to_cpu(dgid->global.subnet_prefix), - be64_to_cpu(dgid->global.interface_id)); - } - - return ah; -} - -static void destroy_ah_hash_key(gpointer data) -{ - g_bytes_unref(data); -} - -static void destroy_ah_hast_data(gpointer data) -{ - struct ibv_ah *ah = data; - - ibv_destroy_ah(ah); -} - -static void ah_cache_init(void) -{ - ah_hash = g_hash_table_new_full(g_bytes_hash, g_bytes_equal, - destroy_ah_hash_key, destroy_ah_hast_data); -} - -#ifdef LEGACY_RDMA_REG_MR -static int build_host_sge_array(RdmaDeviceResources *rdma_dev_res, - struct ibv_sge *sge, uint8_t num_sge, - uint64_t *total_length) -{ - RdmaRmMR *mr; - int idx; - - for (idx = 0; idx < num_sge; idx++) { - mr = rdma_rm_get_mr(rdma_dev_res, sge[idx].lkey); - if (unlikely(!mr)) { - rdma_error_report("Invalid lkey 0x%x", sge[idx].lkey); - return VENDOR_ERR_INVLKEY | sge[idx].lkey; - } - - sge[idx].addr = (uintptr_t)mr->virt + sge[idx].addr - mr->start; - sge[idx].lkey = rdma_backend_mr_lkey(&mr->backend_mr); - - *total_length += sge[idx].length; - } - - return 0; -} -#else -static inline int build_host_sge_array(RdmaDeviceResources *rdma_dev_res, - struct ibv_sge *sge, uint8_t num_sge, - uint64_t *total_length) -{ - int idx; - - for (idx = 0; idx < num_sge; idx++) { - *total_length += sge[idx].length; - } - return 0; -} -#endif - -static void trace_mad_message(const char *title, char *buf, int len) -{ - int i; - char *b = g_malloc0(len * 3 + 1); - char b1[4]; - - for (i = 0; i < len; i++) { - sprintf(b1, "%.2X ", buf[i] & 0x000000FF); - strcat(b, b1); - } - - trace_rdma_mad_message(title, len, b); - - g_free(b); -} - -static int mad_send(RdmaBackendDev *backend_dev, uint8_t sgid_idx, - union ibv_gid *sgid, struct ibv_sge *sge, uint32_t num_sge) -{ - RdmaCmMuxMsg msg = {}; - char *hdr, *data; - int ret; - - if (num_sge != 2) { - return -EINVAL; - } - - msg.hdr.op_code = RDMACM_MUX_OP_CODE_MAD; - memcpy(msg.hdr.sgid.raw, sgid->raw, sizeof(msg.hdr.sgid)); - - msg.umad_len = sge[0].length + sge[1].length; - - if (msg.umad_len > sizeof(msg.umad.mad)) { - return -ENOMEM; - } - - msg.umad.hdr.addr.qpn = htobe32(1); - msg.umad.hdr.addr.grh_present = 1; - msg.umad.hdr.addr.gid_index = sgid_idx; - memcpy(msg.umad.hdr.addr.gid, sgid->raw, sizeof(msg.umad.hdr.addr.gid)); - msg.umad.hdr.addr.hop_limit = 0xFF; - - hdr = rdma_pci_dma_map(backend_dev->dev, sge[0].addr, sge[0].length); - if (!hdr) { - return -ENOMEM; - } - data = rdma_pci_dma_map(backend_dev->dev, sge[1].addr, sge[1].length); - if (!data) { - rdma_pci_dma_unmap(backend_dev->dev, hdr, sge[0].length); - return -ENOMEM; - } - - memcpy(&msg.umad.mad[0], hdr, sge[0].length); - memcpy(&msg.umad.mad[sge[0].length], data, sge[1].length); - - rdma_pci_dma_unmap(backend_dev->dev, data, sge[1].length); - rdma_pci_dma_unmap(backend_dev->dev, hdr, sge[0].length); - - trace_mad_message("send", msg.umad.mad, msg.umad_len); - - ret = rdmacm_mux_send(backend_dev, &msg); - if (ret) { - rdma_error_report("Failed to send MAD to rdma_umadmux (%d)", ret); - return -EIO; - } - - return 0; -} - -void rdma_backend_post_send(RdmaBackendDev *backend_dev, - RdmaBackendQP *qp, uint8_t qp_type, - struct ibv_sge *sge, uint32_t num_sge, - uint8_t sgid_idx, union ibv_gid *sgid, - union ibv_gid *dgid, uint32_t dqpn, uint32_t dqkey, - void *ctx) -{ - BackendCtx *bctx; - uint32_t bctx_id; - int rc; - struct ibv_send_wr wr = {}, *bad_wr; - - if (!qp->ibqp) { /* This field is not initialized for QP0 and QP1 */ - if (qp_type == IBV_QPT_SMI) { - rdma_error_report("Got QP0 request"); - complete_work(IBV_WC_GENERAL_ERR, VENDOR_ERR_QP0, ctx); - } else if (qp_type == IBV_QPT_GSI) { - rc = mad_send(backend_dev, sgid_idx, sgid, sge, num_sge); - if (rc) { - complete_work(IBV_WC_GENERAL_ERR, VENDOR_ERR_MAD_SEND, ctx); - backend_dev->rdma_dev_res->stats.mad_tx_err++; - } else { - complete_work(IBV_WC_SUCCESS, 0, ctx); - backend_dev->rdma_dev_res->stats.mad_tx++; - } - } - return; - } - - bctx = g_malloc0(sizeof(*bctx)); - bctx->up_ctx = ctx; - bctx->backend_qp = qp; - - rc = rdma_rm_alloc_cqe_ctx(backend_dev->rdma_dev_res, &bctx_id, bctx); - if (unlikely(rc)) { - complete_work(IBV_WC_GENERAL_ERR, VENDOR_ERR_NOMEM, ctx); - goto err_free_bctx; - } - - rdma_protected_gslist_append_int32(&qp->cqe_ctx_list, bctx_id); - - rc = build_host_sge_array(backend_dev->rdma_dev_res, sge, num_sge, - &backend_dev->rdma_dev_res->stats.tx_len); - if (rc) { - complete_work(IBV_WC_GENERAL_ERR, rc, ctx); - goto err_dealloc_cqe_ctx; - } - - if (qp_type == IBV_QPT_UD) { - wr.wr.ud.ah = create_ah(backend_dev, qp->ibpd, sgid_idx, dgid); - if (!wr.wr.ud.ah) { - complete_work(IBV_WC_GENERAL_ERR, VENDOR_ERR_FAIL_BACKEND, ctx); - goto err_dealloc_cqe_ctx; - } - wr.wr.ud.remote_qpn = dqpn; - wr.wr.ud.remote_qkey = dqkey; - } - - wr.num_sge = num_sge; - wr.opcode = IBV_WR_SEND; - wr.send_flags = IBV_SEND_SIGNALED; - wr.sg_list = sge; - wr.wr_id = bctx_id; - - rc = ibv_post_send(qp->ibqp, &wr, &bad_wr); - if (rc) { - rdma_error_report("ibv_post_send fail, qpn=0x%x, rc=%d, errno=%d", - qp->ibqp->qp_num, rc, errno); - complete_work(IBV_WC_GENERAL_ERR, VENDOR_ERR_FAIL_BACKEND, ctx); - goto err_dealloc_cqe_ctx; - } - - qatomic_inc(&backend_dev->rdma_dev_res->stats.missing_cqe); - backend_dev->rdma_dev_res->stats.tx++; - - return; - -err_dealloc_cqe_ctx: - backend_dev->rdma_dev_res->stats.tx_err++; - rdma_rm_dealloc_cqe_ctx(backend_dev->rdma_dev_res, bctx_id); - -err_free_bctx: - g_free(bctx); -} - -static unsigned int save_mad_recv_buffer(RdmaBackendDev *backend_dev, - struct ibv_sge *sge, uint32_t num_sge, - void *ctx) -{ - BackendCtx *bctx; - int rc; - uint32_t bctx_id; - - if (num_sge != 1) { - rdma_error_report("Invalid num_sge (%d), expecting 1", num_sge); - return VENDOR_ERR_INV_NUM_SGE; - } - - if (sge[0].length < RDMA_MAX_PRIVATE_DATA + sizeof(struct ibv_grh)) { - rdma_error_report("Too small buffer for MAD"); - return VENDOR_ERR_INV_MAD_BUFF; - } - - bctx = g_malloc0(sizeof(*bctx)); - - rc = rdma_rm_alloc_cqe_ctx(backend_dev->rdma_dev_res, &bctx_id, bctx); - if (unlikely(rc)) { - g_free(bctx); - return VENDOR_ERR_NOMEM; - } - - bctx->up_ctx = ctx; - bctx->sge = *sge; - - rdma_protected_gqueue_append_int64(&backend_dev->recv_mads_list, bctx_id); - - return 0; -} - -void rdma_backend_post_recv(RdmaBackendDev *backend_dev, - RdmaBackendQP *qp, uint8_t qp_type, - struct ibv_sge *sge, uint32_t num_sge, void *ctx) -{ - BackendCtx *bctx; - uint32_t bctx_id; - int rc; - struct ibv_recv_wr wr = {}, *bad_wr; - - if (!qp->ibqp) { /* This field does not get initialized for QP0 and QP1 */ - if (qp_type == IBV_QPT_SMI) { - rdma_error_report("Got QP0 request"); - complete_work(IBV_WC_GENERAL_ERR, VENDOR_ERR_QP0, ctx); - } - if (qp_type == IBV_QPT_GSI) { - rc = save_mad_recv_buffer(backend_dev, sge, num_sge, ctx); - if (rc) { - complete_work(IBV_WC_GENERAL_ERR, rc, ctx); - backend_dev->rdma_dev_res->stats.mad_rx_bufs_err++; - } else { - backend_dev->rdma_dev_res->stats.mad_rx_bufs++; - } - } - return; - } - - bctx = g_malloc0(sizeof(*bctx)); - bctx->up_ctx = ctx; - bctx->backend_qp = qp; - - rc = rdma_rm_alloc_cqe_ctx(backend_dev->rdma_dev_res, &bctx_id, bctx); - if (unlikely(rc)) { - complete_work(IBV_WC_GENERAL_ERR, VENDOR_ERR_NOMEM, ctx); - goto err_free_bctx; - } - - rdma_protected_gslist_append_int32(&qp->cqe_ctx_list, bctx_id); - - rc = build_host_sge_array(backend_dev->rdma_dev_res, sge, num_sge, - &backend_dev->rdma_dev_res->stats.rx_bufs_len); - if (rc) { - complete_work(IBV_WC_GENERAL_ERR, rc, ctx); - goto err_dealloc_cqe_ctx; - } - - wr.num_sge = num_sge; - wr.sg_list = sge; - wr.wr_id = bctx_id; - rc = ibv_post_recv(qp->ibqp, &wr, &bad_wr); - if (rc) { - rdma_error_report("ibv_post_recv fail, qpn=0x%x, rc=%d, errno=%d", - qp->ibqp->qp_num, rc, errno); - complete_work(IBV_WC_GENERAL_ERR, VENDOR_ERR_FAIL_BACKEND, ctx); - goto err_dealloc_cqe_ctx; - } - - qatomic_inc(&backend_dev->rdma_dev_res->stats.missing_cqe); - backend_dev->rdma_dev_res->stats.rx_bufs++; - - return; - -err_dealloc_cqe_ctx: - backend_dev->rdma_dev_res->stats.rx_bufs_err++; - rdma_rm_dealloc_cqe_ctx(backend_dev->rdma_dev_res, bctx_id); - -err_free_bctx: - g_free(bctx); -} - -void rdma_backend_post_srq_recv(RdmaBackendDev *backend_dev, - RdmaBackendSRQ *srq, struct ibv_sge *sge, - uint32_t num_sge, void *ctx) -{ - BackendCtx *bctx; - uint32_t bctx_id; - int rc; - struct ibv_recv_wr wr = {}, *bad_wr; - - bctx = g_malloc0(sizeof(*bctx)); - bctx->up_ctx = ctx; - bctx->backend_srq = srq; - - rc = rdma_rm_alloc_cqe_ctx(backend_dev->rdma_dev_res, &bctx_id, bctx); - if (unlikely(rc)) { - complete_work(IBV_WC_GENERAL_ERR, VENDOR_ERR_NOMEM, ctx); - goto err_free_bctx; - } - - rdma_protected_gslist_append_int32(&srq->cqe_ctx_list, bctx_id); - - rc = build_host_sge_array(backend_dev->rdma_dev_res, sge, num_sge, - &backend_dev->rdma_dev_res->stats.rx_bufs_len); - if (rc) { - complete_work(IBV_WC_GENERAL_ERR, rc, ctx); - goto err_dealloc_cqe_ctx; - } - - wr.num_sge = num_sge; - wr.sg_list = sge; - wr.wr_id = bctx_id; - rc = ibv_post_srq_recv(srq->ibsrq, &wr, &bad_wr); - if (rc) { - rdma_error_report("ibv_post_srq_recv fail, srqn=0x%x, rc=%d, errno=%d", - srq->ibsrq->handle, rc, errno); - complete_work(IBV_WC_GENERAL_ERR, VENDOR_ERR_FAIL_BACKEND, ctx); - goto err_dealloc_cqe_ctx; - } - - qatomic_inc(&backend_dev->rdma_dev_res->stats.missing_cqe); - backend_dev->rdma_dev_res->stats.rx_bufs++; - backend_dev->rdma_dev_res->stats.rx_srq++; - - return; - -err_dealloc_cqe_ctx: - backend_dev->rdma_dev_res->stats.rx_bufs_err++; - rdma_rm_dealloc_cqe_ctx(backend_dev->rdma_dev_res, bctx_id); - -err_free_bctx: - g_free(bctx); -} - -int rdma_backend_create_pd(RdmaBackendDev *backend_dev, RdmaBackendPD *pd) -{ - pd->ibpd = ibv_alloc_pd(backend_dev->context); - - if (!pd->ibpd) { - rdma_error_report("ibv_alloc_pd fail, errno=%d", errno); - return -EIO; - } - - return 0; -} - -void rdma_backend_destroy_pd(RdmaBackendPD *pd) -{ - if (pd->ibpd) { - ibv_dealloc_pd(pd->ibpd); - } -} - -int rdma_backend_create_mr(RdmaBackendMR *mr, RdmaBackendPD *pd, void *addr, - size_t length, uint64_t guest_start, int access) -{ -#ifdef LEGACY_RDMA_REG_MR - mr->ibmr = ibv_reg_mr(pd->ibpd, addr, length, access); -#else - mr->ibmr = ibv_reg_mr_iova(pd->ibpd, addr, length, guest_start, access); -#endif - if (!mr->ibmr) { - rdma_error_report("ibv_reg_mr fail, errno=%d", errno); - return -EIO; - } - - mr->ibpd = pd->ibpd; - - return 0; -} - -void rdma_backend_destroy_mr(RdmaBackendMR *mr) -{ - if (mr->ibmr) { - ibv_dereg_mr(mr->ibmr); - } -} - -int rdma_backend_create_cq(RdmaBackendDev *backend_dev, RdmaBackendCQ *cq, - int cqe) -{ - int rc; - - cq->ibcq = ibv_create_cq(backend_dev->context, cqe + 1, NULL, - backend_dev->channel, 0); - if (!cq->ibcq) { - rdma_error_report("ibv_create_cq fail, errno=%d", errno); - return -EIO; - } - - rc = ibv_req_notify_cq(cq->ibcq, 0); - if (rc) { - rdma_warn_report("ibv_req_notify_cq fail, rc=%d, errno=%d", rc, errno); - } - - cq->backend_dev = backend_dev; - - return 0; -} - -void rdma_backend_destroy_cq(RdmaBackendCQ *cq) -{ - if (cq->ibcq) { - ibv_destroy_cq(cq->ibcq); - } -} - -int rdma_backend_create_qp(RdmaBackendQP *qp, uint8_t qp_type, - RdmaBackendPD *pd, RdmaBackendCQ *scq, - RdmaBackendCQ *rcq, RdmaBackendSRQ *srq, - uint32_t max_send_wr, uint32_t max_recv_wr, - uint32_t max_send_sge, uint32_t max_recv_sge) -{ - struct ibv_qp_init_attr attr = {}; - - qp->ibqp = 0; - - switch (qp_type) { - case IBV_QPT_GSI: - return 0; - - case IBV_QPT_RC: - /* fall through */ - case IBV_QPT_UD: - /* do nothing */ - break; - - default: - rdma_error_report("Unsupported QP type %d", qp_type); - return -EIO; - } - - attr.qp_type = qp_type; - attr.send_cq = scq->ibcq; - attr.recv_cq = rcq->ibcq; - attr.cap.max_send_wr = max_send_wr; - attr.cap.max_recv_wr = max_recv_wr; - attr.cap.max_send_sge = max_send_sge; - attr.cap.max_recv_sge = max_recv_sge; - if (srq) { - attr.srq = srq->ibsrq; - } - - qp->ibqp = ibv_create_qp(pd->ibpd, &attr); - if (!qp->ibqp) { - rdma_error_report("ibv_create_qp fail, errno=%d", errno); - return -EIO; - } - - rdma_protected_gslist_init(&qp->cqe_ctx_list); - - qp->ibpd = pd->ibpd; - - /* TODO: Query QP to get max_inline_data and save it to be used in send */ - - return 0; -} - -int rdma_backend_qp_state_init(RdmaBackendDev *backend_dev, RdmaBackendQP *qp, - uint8_t qp_type, uint32_t qkey) -{ - struct ibv_qp_attr attr = {}; - int rc, attr_mask; - - attr_mask = IBV_QP_STATE | IBV_QP_PKEY_INDEX | IBV_QP_PORT; - attr.qp_state = IBV_QPS_INIT; - attr.pkey_index = 0; - attr.port_num = backend_dev->port_num; - - switch (qp_type) { - case IBV_QPT_RC: - attr_mask |= IBV_QP_ACCESS_FLAGS; - trace_rdma_backend_rc_qp_state_init(qp->ibqp->qp_num); - break; - - case IBV_QPT_UD: - attr.qkey = qkey; - attr_mask |= IBV_QP_QKEY; - trace_rdma_backend_ud_qp_state_init(qp->ibqp->qp_num, qkey); - break; - - default: - rdma_error_report("Unsupported QP type %d", qp_type); - return -EIO; - } - - rc = ibv_modify_qp(qp->ibqp, &attr, attr_mask); - if (rc) { - rdma_error_report("ibv_modify_qp fail, rc=%d, errno=%d", rc, errno); - return -EIO; - } - - return 0; -} - -int rdma_backend_qp_state_rtr(RdmaBackendDev *backend_dev, RdmaBackendQP *qp, - uint8_t qp_type, uint8_t sgid_idx, - union ibv_gid *dgid, uint32_t dqpn, - uint32_t rq_psn, uint32_t qkey, bool use_qkey) -{ - struct ibv_qp_attr attr = {}; - union ibv_gid ibv_gid = { - .global.interface_id = dgid->global.interface_id, - .global.subnet_prefix = dgid->global.subnet_prefix - }; - int rc, attr_mask; - - attr.qp_state = IBV_QPS_RTR; - attr_mask = IBV_QP_STATE; - - qp->sgid_idx = sgid_idx; - - switch (qp_type) { - case IBV_QPT_RC: - attr.path_mtu = IBV_MTU_1024; - attr.dest_qp_num = dqpn; - attr.max_dest_rd_atomic = 1; - attr.min_rnr_timer = 12; - attr.ah_attr.port_num = backend_dev->port_num; - attr.ah_attr.is_global = 1; - attr.ah_attr.grh.hop_limit = 1; - attr.ah_attr.grh.dgid = ibv_gid; - attr.ah_attr.grh.sgid_index = qp->sgid_idx; - attr.rq_psn = rq_psn; - - attr_mask |= IBV_QP_AV | IBV_QP_PATH_MTU | IBV_QP_DEST_QPN | - IBV_QP_RQ_PSN | IBV_QP_MAX_DEST_RD_ATOMIC | - IBV_QP_MIN_RNR_TIMER; - - trace_rdma_backend_rc_qp_state_rtr(qp->ibqp->qp_num, - be64_to_cpu(ibv_gid.global. - subnet_prefix), - be64_to_cpu(ibv_gid.global. - interface_id), - qp->sgid_idx, dqpn, rq_psn); - break; - - case IBV_QPT_UD: - if (use_qkey) { - attr.qkey = qkey; - attr_mask |= IBV_QP_QKEY; - } - trace_rdma_backend_ud_qp_state_rtr(qp->ibqp->qp_num, use_qkey ? qkey : - 0); - break; - } - - rc = ibv_modify_qp(qp->ibqp, &attr, attr_mask); - if (rc) { - rdma_error_report("ibv_modify_qp fail, rc=%d, errno=%d", rc, errno); - return -EIO; - } - - return 0; -} - -int rdma_backend_qp_state_rts(RdmaBackendQP *qp, uint8_t qp_type, - uint32_t sq_psn, uint32_t qkey, bool use_qkey) -{ - struct ibv_qp_attr attr = {}; - int rc, attr_mask; - - attr.qp_state = IBV_QPS_RTS; - attr.sq_psn = sq_psn; - attr_mask = IBV_QP_STATE | IBV_QP_SQ_PSN; - - switch (qp_type) { - case IBV_QPT_RC: - attr.timeout = 14; - attr.retry_cnt = 7; - attr.rnr_retry = 7; - attr.max_rd_atomic = 1; - - attr_mask |= IBV_QP_TIMEOUT | IBV_QP_RETRY_CNT | IBV_QP_RNR_RETRY | - IBV_QP_MAX_QP_RD_ATOMIC; - trace_rdma_backend_rc_qp_state_rts(qp->ibqp->qp_num, sq_psn); - break; - - case IBV_QPT_UD: - if (use_qkey) { - attr.qkey = qkey; - attr_mask |= IBV_QP_QKEY; - } - trace_rdma_backend_ud_qp_state_rts(qp->ibqp->qp_num, sq_psn, - use_qkey ? qkey : 0); - break; - } - - rc = ibv_modify_qp(qp->ibqp, &attr, attr_mask); - if (rc) { - rdma_error_report("ibv_modify_qp fail, rc=%d, errno=%d", rc, errno); - return -EIO; - } - - return 0; -} - -int rdma_backend_query_qp(RdmaBackendQP *qp, struct ibv_qp_attr *attr, - int attr_mask, struct ibv_qp_init_attr *init_attr) -{ - if (!qp->ibqp) { - attr->qp_state = IBV_QPS_RTS; - return 0; - } - - return ibv_query_qp(qp->ibqp, attr, attr_mask, init_attr); -} - -void rdma_backend_destroy_qp(RdmaBackendQP *qp, RdmaDeviceResources *dev_res) -{ - if (qp->ibqp) { - ibv_destroy_qp(qp->ibqp); - } - g_slist_foreach(qp->cqe_ctx_list.list, free_cqe_ctx, dev_res); - rdma_protected_gslist_destroy(&qp->cqe_ctx_list); -} - -int rdma_backend_create_srq(RdmaBackendSRQ *srq, RdmaBackendPD *pd, - uint32_t max_wr, uint32_t max_sge, - uint32_t srq_limit) -{ - struct ibv_srq_init_attr srq_init_attr = {}; - - srq_init_attr.attr.max_wr = max_wr; - srq_init_attr.attr.max_sge = max_sge; - srq_init_attr.attr.srq_limit = srq_limit; - - srq->ibsrq = ibv_create_srq(pd->ibpd, &srq_init_attr); - if (!srq->ibsrq) { - rdma_error_report("ibv_create_srq failed, errno=%d", errno); - return -EIO; - } - - rdma_protected_gslist_init(&srq->cqe_ctx_list); - - return 0; -} - -int rdma_backend_query_srq(RdmaBackendSRQ *srq, struct ibv_srq_attr *srq_attr) -{ - if (!srq->ibsrq) { - return -EINVAL; - } - - return ibv_query_srq(srq->ibsrq, srq_attr); -} - -int rdma_backend_modify_srq(RdmaBackendSRQ *srq, struct ibv_srq_attr *srq_attr, - int srq_attr_mask) -{ - if (!srq->ibsrq) { - return -EINVAL; - } - - return ibv_modify_srq(srq->ibsrq, srq_attr, srq_attr_mask); -} - -void rdma_backend_destroy_srq(RdmaBackendSRQ *srq, RdmaDeviceResources *dev_res) -{ - if (srq->ibsrq) { - ibv_destroy_srq(srq->ibsrq); - } - g_slist_foreach(srq->cqe_ctx_list.list, free_cqe_ctx, dev_res); - rdma_protected_gslist_destroy(&srq->cqe_ctx_list); -} - -#define CHK_ATTR(req, dev, member, fmt) ({ \ - trace_rdma_check_dev_attr(#member, dev.member, req->member); \ - if (req->member > dev.member) { \ - rdma_warn_report("%s = "fmt" is higher than host device capability "fmt, \ - #member, req->member, dev.member); \ - req->member = dev.member; \ - } \ -}) - -static int init_device_caps(RdmaBackendDev *backend_dev, - struct ibv_device_attr *dev_attr) -{ - struct ibv_device_attr bk_dev_attr; - int rc; - - rc = ibv_query_device(backend_dev->context, &bk_dev_attr); - if (rc) { - rdma_error_report("ibv_query_device fail, rc=%d, errno=%d", rc, errno); - return -EIO; - } - - dev_attr->max_sge = MAX_SGE; - dev_attr->max_srq_sge = MAX_SGE; - - CHK_ATTR(dev_attr, bk_dev_attr, max_mr_size, "%" PRId64); - CHK_ATTR(dev_attr, bk_dev_attr, max_qp, "%d"); - CHK_ATTR(dev_attr, bk_dev_attr, max_sge, "%d"); - CHK_ATTR(dev_attr, bk_dev_attr, max_cq, "%d"); - CHK_ATTR(dev_attr, bk_dev_attr, max_mr, "%d"); - CHK_ATTR(dev_attr, bk_dev_attr, max_pd, "%d"); - CHK_ATTR(dev_attr, bk_dev_attr, max_qp_rd_atom, "%d"); - CHK_ATTR(dev_attr, bk_dev_attr, max_qp_init_rd_atom, "%d"); - CHK_ATTR(dev_attr, bk_dev_attr, max_ah, "%d"); - CHK_ATTR(dev_attr, bk_dev_attr, max_srq, "%d"); - - return 0; -} - -static inline void build_mad_hdr(struct ibv_grh *grh, union ibv_gid *sgid, - union ibv_gid *my_gid, int paylen) -{ - grh->paylen = htons(paylen); - grh->sgid = *sgid; - grh->dgid = *my_gid; -} - -static void process_incoming_mad_req(RdmaBackendDev *backend_dev, - RdmaCmMuxMsg *msg) -{ - unsigned long cqe_ctx_id; - BackendCtx *bctx; - char *mad; - - trace_mad_message("recv", msg->umad.mad, msg->umad_len); - - cqe_ctx_id = rdma_protected_gqueue_pop_int64(&backend_dev->recv_mads_list); - if (cqe_ctx_id == -ENOENT) { - rdma_warn_report("No more free MADs buffers, waiting for a while"); - sleep(THR_POLL_TO); - return; - } - - bctx = rdma_rm_get_cqe_ctx(backend_dev->rdma_dev_res, cqe_ctx_id); - if (unlikely(!bctx)) { - rdma_error_report("No matching ctx for req %ld", cqe_ctx_id); - backend_dev->rdma_dev_res->stats.mad_rx_err++; - return; - } - - mad = rdma_pci_dma_map(backend_dev->dev, bctx->sge.addr, - bctx->sge.length); - if (!mad || bctx->sge.length < msg->umad_len + MAD_HDR_SIZE) { - backend_dev->rdma_dev_res->stats.mad_rx_err++; - complete_work(IBV_WC_GENERAL_ERR, VENDOR_ERR_INV_MAD_BUFF, - bctx->up_ctx); - } else { - struct ibv_wc wc = {}; - memset(mad, 0, bctx->sge.length); - build_mad_hdr((struct ibv_grh *)mad, - (union ibv_gid *)&msg->umad.hdr.addr.gid, &msg->hdr.sgid, - msg->umad_len); - memcpy(&mad[MAD_HDR_SIZE], msg->umad.mad, msg->umad_len); - rdma_pci_dma_unmap(backend_dev->dev, mad, bctx->sge.length); - - wc.byte_len = msg->umad_len; - wc.status = IBV_WC_SUCCESS; - wc.wc_flags = IBV_WC_GRH; - backend_dev->rdma_dev_res->stats.mad_rx++; - comp_handler(bctx->up_ctx, &wc); - } - - g_free(bctx); - rdma_rm_dealloc_cqe_ctx(backend_dev->rdma_dev_res, cqe_ctx_id); -} - -static inline int rdmacm_mux_can_receive(void *opaque) -{ - RdmaBackendDev *backend_dev = (RdmaBackendDev *)opaque; - - return rdmacm_mux_can_process_async(backend_dev); -} - -static void rdmacm_mux_read(void *opaque, const uint8_t *buf, int size) -{ - RdmaBackendDev *backend_dev = (RdmaBackendDev *)opaque; - RdmaCmMuxMsg *msg = (RdmaCmMuxMsg *)buf; - - trace_rdmacm_mux("read", msg->hdr.msg_type, msg->hdr.op_code); - - if (msg->hdr.msg_type != RDMACM_MUX_MSG_TYPE_REQ && - msg->hdr.op_code != RDMACM_MUX_OP_CODE_MAD) { - rdma_error_report("Error: Not a MAD request, skipping"); - return; - } - process_incoming_mad_req(backend_dev, msg); -} - -static int mad_init(RdmaBackendDev *backend_dev, CharBackend *mad_chr_be) -{ - int ret; - - backend_dev->rdmacm_mux.chr_be = mad_chr_be; - - ret = qemu_chr_fe_backend_connected(backend_dev->rdmacm_mux.chr_be); - if (!ret) { - rdma_error_report("Missing chardev for MAD multiplexer"); - return -EIO; - } - - rdma_protected_gqueue_init(&backend_dev->recv_mads_list); - - enable_rdmacm_mux_async(backend_dev); - - qemu_chr_fe_set_handlers(backend_dev->rdmacm_mux.chr_be, - rdmacm_mux_can_receive, rdmacm_mux_read, NULL, - NULL, backend_dev, NULL, true); - - return 0; -} - -static void mad_stop(RdmaBackendDev *backend_dev) -{ - clean_recv_mads(backend_dev); -} - -static void mad_fini(RdmaBackendDev *backend_dev) -{ - disable_rdmacm_mux_async(backend_dev); - qemu_chr_fe_disconnect(backend_dev->rdmacm_mux.chr_be); - rdma_protected_gqueue_destroy(&backend_dev->recv_mads_list); -} - -int rdma_backend_get_gid_index(RdmaBackendDev *backend_dev, - union ibv_gid *gid) -{ - union ibv_gid sgid; - int ret; - int i = 0; - - do { - ret = ibv_query_gid(backend_dev->context, backend_dev->port_num, i, - &sgid); - i++; - } while (!ret && (memcmp(&sgid, gid, sizeof(*gid)))); - - trace_rdma_backend_get_gid_index(be64_to_cpu(gid->global.subnet_prefix), - be64_to_cpu(gid->global.interface_id), - i - 1); - - return ret ? ret : i - 1; -} - -int rdma_backend_add_gid(RdmaBackendDev *backend_dev, const char *ifname, - union ibv_gid *gid) -{ - RdmaCmMuxMsg msg = {}; - int ret; - - trace_rdma_backend_gid_change("add", be64_to_cpu(gid->global.subnet_prefix), - be64_to_cpu(gid->global.interface_id)); - - msg.hdr.op_code = RDMACM_MUX_OP_CODE_REG; - memcpy(msg.hdr.sgid.raw, gid->raw, sizeof(msg.hdr.sgid)); - - ret = rdmacm_mux_send(backend_dev, &msg); - if (ret) { - rdma_error_report("Failed to register GID to rdma_umadmux (%d)", ret); - return -EIO; - } - - qapi_event_send_rdma_gid_status_changed(ifname, true, - gid->global.subnet_prefix, - gid->global.interface_id); - - return ret; -} - -int rdma_backend_del_gid(RdmaBackendDev *backend_dev, const char *ifname, - union ibv_gid *gid) -{ - RdmaCmMuxMsg msg = {}; - int ret; - - trace_rdma_backend_gid_change("del", be64_to_cpu(gid->global.subnet_prefix), - be64_to_cpu(gid->global.interface_id)); - - msg.hdr.op_code = RDMACM_MUX_OP_CODE_UNREG; - memcpy(msg.hdr.sgid.raw, gid->raw, sizeof(msg.hdr.sgid)); - - ret = rdmacm_mux_send(backend_dev, &msg); - if (ret) { - rdma_error_report("Failed to unregister GID from rdma_umadmux (%d)", - ret); - return -EIO; - } - - qapi_event_send_rdma_gid_status_changed(ifname, false, - gid->global.subnet_prefix, - gid->global.interface_id); - - return 0; -} - -int rdma_backend_init(RdmaBackendDev *backend_dev, PCIDevice *pdev, - RdmaDeviceResources *rdma_dev_res, - const char *backend_device_name, uint8_t port_num, - struct ibv_device_attr *dev_attr, CharBackend *mad_chr_be) -{ - int i; - int ret = 0; - int num_ibv_devices; - struct ibv_device **dev_list; - - memset(backend_dev, 0, sizeof(*backend_dev)); - - backend_dev->dev = pdev; - backend_dev->port_num = port_num; - backend_dev->rdma_dev_res = rdma_dev_res; - - rdma_backend_register_comp_handler(dummy_comp_handler); - - dev_list = ibv_get_device_list(&num_ibv_devices); - if (!dev_list) { - rdma_error_report("Failed to get IB devices list"); - return -EIO; - } - - if (num_ibv_devices == 0) { - rdma_error_report("No IB devices were found"); - ret = -ENXIO; - goto out_free_dev_list; - } - - if (backend_device_name) { - for (i = 0; dev_list[i]; ++i) { - if (!strcmp(ibv_get_device_name(dev_list[i]), - backend_device_name)) { - break; - } - } - - backend_dev->ib_dev = dev_list[i]; - if (!backend_dev->ib_dev) { - rdma_error_report("Failed to find IB device %s", - backend_device_name); - ret = -EIO; - goto out_free_dev_list; - } - } else { - backend_dev->ib_dev = *dev_list; - } - - rdma_info_report("uverb device %s", backend_dev->ib_dev->dev_name); - - backend_dev->context = ibv_open_device(backend_dev->ib_dev); - if (!backend_dev->context) { - rdma_error_report("Failed to open IB device %s", - ibv_get_device_name(backend_dev->ib_dev)); - ret = -EIO; - goto out; - } - - backend_dev->channel = ibv_create_comp_channel(backend_dev->context); - if (!backend_dev->channel) { - rdma_error_report("Failed to create IB communication channel"); - ret = -EIO; - goto out_close_device; - } - - ret = init_device_caps(backend_dev, dev_attr); - if (ret) { - rdma_error_report("Failed to initialize device capabilities"); - ret = -EIO; - goto out_destroy_comm_channel; - } - - - ret = mad_init(backend_dev, mad_chr_be); - if (ret) { - rdma_error_report("Failed to initialize mad"); - ret = -EIO; - goto out_destroy_comm_channel; - } - - backend_dev->comp_thread.run = false; - backend_dev->comp_thread.is_running = false; - - ah_cache_init(); - - goto out_free_dev_list; - -out_destroy_comm_channel: - ibv_destroy_comp_channel(backend_dev->channel); - -out_close_device: - ibv_close_device(backend_dev->context); - -out_free_dev_list: - ibv_free_device_list(dev_list); - -out: - return ret; -} - - -void rdma_backend_start(RdmaBackendDev *backend_dev) -{ - start_comp_thread(backend_dev); -} - -void rdma_backend_stop(RdmaBackendDev *backend_dev) -{ - mad_stop(backend_dev); - stop_backend_thread(&backend_dev->comp_thread); -} - -void rdma_backend_fini(RdmaBackendDev *backend_dev) -{ - mad_fini(backend_dev); - g_hash_table_destroy(ah_hash); - ibv_destroy_comp_channel(backend_dev->channel); - ibv_close_device(backend_dev->context); -} diff --git a/hw/rdma/rdma_rm.c b/hw/rdma/rdma_rm.c deleted file mode 100644 index 038d564433..0000000000 --- a/hw/rdma/rdma_rm.c +++ /dev/null @@ -1,812 +0,0 @@ -/* - * QEMU paravirtual RDMA - Resource Manager Implementation - * - * Copyright (C) 2018 Oracle - * Copyright (C) 2018 Red Hat Inc - * - * Authors: - * Yuval Shaia <yuval.shaia(a)oracle.com> - * Marcel Apfelbaum <marcel(a)redhat.com> - * - * This work is licensed under the terms of the GNU GPL, version 2 or later. - * See the COPYING file in the top-level directory. - * - */ - -#include "qemu/osdep.h" -#include "qapi/error.h" -#include "cpu.h" -#include "monitor/monitor.h" - -#include "trace.h" -#include "rdma_utils.h" -#include "rdma_backend.h" -#include "rdma_rm.h" - -void rdma_format_device_counters(RdmaDeviceResources *dev_res, GString *buf) -{ - g_string_append_printf(buf, "\ttx : %" PRId64 "\n", - dev_res->stats.tx); - g_string_append_printf(buf, "\ttx_len : %" PRId64 "\n", - dev_res->stats.tx_len); - g_string_append_printf(buf, "\ttx_err : %" PRId64 "\n", - dev_res->stats.tx_err); - g_string_append_printf(buf, "\trx_bufs : %" PRId64 "\n", - dev_res->stats.rx_bufs); - g_string_append_printf(buf, "\trx_srq : %" PRId64 "\n", - dev_res->stats.rx_srq); - g_string_append_printf(buf, "\trx_bufs_len : %" PRId64 "\n", - dev_res->stats.rx_bufs_len); - g_string_append_printf(buf, "\trx_bufs_err : %" PRId64 "\n", - dev_res->stats.rx_bufs_err); - g_string_append_printf(buf, "\tcomps : %" PRId64 "\n", - dev_res->stats.completions); - g_string_append_printf(buf, "\tmissing_comps : %" PRId32 "\n", - dev_res->stats.missing_cqe); - g_string_append_printf(buf, "\tpoll_cq (bk) : %" PRId64 "\n", - dev_res->stats.poll_cq_from_bk); - g_string_append_printf(buf, "\tpoll_cq_ppoll_to : %" PRId64 "\n", - dev_res->stats.poll_cq_ppoll_to); - g_string_append_printf(buf, "\tpoll_cq (fe) : %" PRId64 "\n", - dev_res->stats.poll_cq_from_guest); - g_string_append_printf(buf, "\tpoll_cq_empty : %" PRId64 "\n", - dev_res->stats.poll_cq_from_guest_empty); - g_string_append_printf(buf, "\tmad_tx : %" PRId64 "\n", - dev_res->stats.mad_tx); - g_string_append_printf(buf, "\tmad_tx_err : %" PRId64 "\n", - dev_res->stats.mad_tx_err); - g_string_append_printf(buf, "\tmad_rx : %" PRId64 "\n", - dev_res->stats.mad_rx); - g_string_append_printf(buf, "\tmad_rx_err : %" PRId64 "\n", - dev_res->stats.mad_rx_err); - g_string_append_printf(buf, "\tmad_rx_bufs : %" PRId64 "\n", - dev_res->stats.mad_rx_bufs); - g_string_append_printf(buf, "\tmad_rx_bufs_err : %" PRId64 "\n", - dev_res->stats.mad_rx_bufs_err); - g_string_append_printf(buf, "\tPDs : %" PRId32 "\n", - dev_res->pd_tbl.used); - g_string_append_printf(buf, "\tMRs : %" PRId32 "\n", - dev_res->mr_tbl.used); - g_string_append_printf(buf, "\tUCs : %" PRId32 "\n", - dev_res->uc_tbl.used); - g_string_append_printf(buf, "\tQPs : %" PRId32 "\n", - dev_res->qp_tbl.used); - g_string_append_printf(buf, "\tCQs : %" PRId32 "\n", - dev_res->cq_tbl.used); - g_string_append_printf(buf, "\tCEQ_CTXs : %" PRId32 "\n", - dev_res->cqe_ctx_tbl.used); -} - -static inline void res_tbl_init(const char *name, RdmaRmResTbl *tbl, - uint32_t tbl_sz, uint32_t res_sz) -{ - tbl->tbl = g_malloc(tbl_sz * res_sz); - - strncpy(tbl->name, name, MAX_RM_TBL_NAME); - tbl->name[MAX_RM_TBL_NAME - 1] = 0; - - tbl->bitmap = bitmap_new(tbl_sz); - tbl->tbl_sz = tbl_sz; - tbl->res_sz = res_sz; - tbl->used = 0; - qemu_mutex_init(&tbl->lock); -} - -static inline void res_tbl_free(RdmaRmResTbl *tbl) -{ - if (!tbl->bitmap) { - return; - } - qemu_mutex_destroy(&tbl->lock); - g_free(tbl->tbl); - g_free(tbl->bitmap); -} - -static inline void *rdma_res_tbl_get(RdmaRmResTbl *tbl, uint32_t handle) -{ - trace_rdma_res_tbl_get(tbl->name, handle); - - if ((handle < tbl->tbl_sz) && (test_bit(handle, tbl->bitmap))) { - return tbl->tbl + handle * tbl->res_sz; - } else { - rdma_error_report("Table %s, invalid handle %d", tbl->name, handle); - return NULL; - } -} - -static inline void *rdma_res_tbl_alloc(RdmaRmResTbl *tbl, uint32_t *handle) -{ - qemu_mutex_lock(&tbl->lock); - - *handle = find_first_zero_bit(tbl->bitmap, tbl->tbl_sz); - if (*handle > tbl->tbl_sz) { - rdma_error_report("Table %s, failed to allocate, bitmap is full", - tbl->name); - qemu_mutex_unlock(&tbl->lock); - return NULL; - } - - set_bit(*handle, tbl->bitmap); - - tbl->used++; - - qemu_mutex_unlock(&tbl->lock); - - memset(tbl->tbl + *handle * tbl->res_sz, 0, tbl->res_sz); - - trace_rdma_res_tbl_alloc(tbl->name, *handle); - - return tbl->tbl + *handle * tbl->res_sz; -} - -static inline void rdma_res_tbl_dealloc(RdmaRmResTbl *tbl, uint32_t handle) -{ - trace_rdma_res_tbl_dealloc(tbl->name, handle); - - QEMU_LOCK_GUARD(&tbl->lock); - - if (handle < tbl->tbl_sz) { - clear_bit(handle, tbl->bitmap); - tbl->used--; - } - -} - -int rdma_rm_alloc_pd(RdmaDeviceResources *dev_res, RdmaBackendDev *backend_dev, - uint32_t *pd_handle, uint32_t ctx_handle) -{ - RdmaRmPD *pd; - int ret = -ENOMEM; - - pd = rdma_res_tbl_alloc(&dev_res->pd_tbl, pd_handle); - if (!pd) { - goto out; - } - - ret = rdma_backend_create_pd(backend_dev, &pd->backend_pd); - if (ret) { - ret = -EIO; - goto out_tbl_dealloc; - } - - pd->ctx_handle = ctx_handle; - - return 0; - -out_tbl_dealloc: - rdma_res_tbl_dealloc(&dev_res->pd_tbl, *pd_handle); - -out: - return ret; -} - -RdmaRmPD *rdma_rm_get_pd(RdmaDeviceResources *dev_res, uint32_t pd_handle) -{ - return rdma_res_tbl_get(&dev_res->pd_tbl, pd_handle); -} - -void rdma_rm_dealloc_pd(RdmaDeviceResources *dev_res, uint32_t pd_handle) -{ - RdmaRmPD *pd = rdma_rm_get_pd(dev_res, pd_handle); - - if (pd) { - rdma_backend_destroy_pd(&pd->backend_pd); - rdma_res_tbl_dealloc(&dev_res->pd_tbl, pd_handle); - } -} - -int rdma_rm_alloc_mr(RdmaDeviceResources *dev_res, uint32_t pd_handle, - uint64_t guest_start, uint64_t guest_length, - void *host_virt, int access_flags, uint32_t *mr_handle, - uint32_t *lkey, uint32_t *rkey) -{ - RdmaRmMR *mr; - int ret = 0; - RdmaRmPD *pd; - - pd = rdma_rm_get_pd(dev_res, pd_handle); - if (!pd) { - return -EINVAL; - } - - mr = rdma_res_tbl_alloc(&dev_res->mr_tbl, mr_handle); - if (!mr) { - return -ENOMEM; - } - trace_rdma_rm_alloc_mr(*mr_handle, host_virt, guest_start, guest_length, - access_flags); - - if (host_virt) { - mr->virt = host_virt; - mr->start = guest_start; - mr->length = guest_length; - mr->virt += (mr->start & (TARGET_PAGE_SIZE - 1)); - - ret = rdma_backend_create_mr(&mr->backend_mr, &pd->backend_pd, mr->virt, - mr->length, guest_start, access_flags); - if (ret) { - ret = -EIO; - goto out_dealloc_mr; - } -#ifdef LEGACY_RDMA_REG_MR - /* We keep mr_handle in lkey so send and recv get get mr ptr */ - *lkey = *mr_handle; -#else - *lkey = rdma_backend_mr_lkey(&mr->backend_mr); -#endif - } - - *rkey = -1; - - mr->pd_handle = pd_handle; - - return 0; - -out_dealloc_mr: - rdma_res_tbl_dealloc(&dev_res->mr_tbl, *mr_handle); - - return ret; -} - -RdmaRmMR *rdma_rm_get_mr(RdmaDeviceResources *dev_res, uint32_t mr_handle) -{ - return rdma_res_tbl_get(&dev_res->mr_tbl, mr_handle); -} - -void rdma_rm_dealloc_mr(RdmaDeviceResources *dev_res, uint32_t mr_handle) -{ - RdmaRmMR *mr = rdma_rm_get_mr(dev_res, mr_handle); - - if (mr) { - rdma_backend_destroy_mr(&mr->backend_mr); - trace_rdma_rm_dealloc_mr(mr_handle, mr->start); - if (mr->start) { - mr->virt -= (mr->start & (TARGET_PAGE_SIZE - 1)); - munmap(mr->virt, mr->length); - } - rdma_res_tbl_dealloc(&dev_res->mr_tbl, mr_handle); - } -} - -int rdma_rm_alloc_uc(RdmaDeviceResources *dev_res, uint32_t pfn, - uint32_t *uc_handle) -{ - RdmaRmUC *uc; - - /* TODO: Need to make sure pfn is between bar start address and - * bsd+RDMA_BAR2_UAR_SIZE - if (pfn > RDMA_BAR2_UAR_SIZE) { - rdma_error_report("pfn out of range (%d > %d)", pfn, - RDMA_BAR2_UAR_SIZE); - return -ENOMEM; - } - */ - - uc = rdma_res_tbl_alloc(&dev_res->uc_tbl, uc_handle); - if (!uc) { - return -ENOMEM; - } - - return 0; -} - -RdmaRmUC *rdma_rm_get_uc(RdmaDeviceResources *dev_res, uint32_t uc_handle) -{ - return rdma_res_tbl_get(&dev_res->uc_tbl, uc_handle); -} - -void rdma_rm_dealloc_uc(RdmaDeviceResources *dev_res, uint32_t uc_handle) -{ - RdmaRmUC *uc = rdma_rm_get_uc(dev_res, uc_handle); - - if (uc) { - rdma_res_tbl_dealloc(&dev_res->uc_tbl, uc_handle); - } -} - -RdmaRmCQ *rdma_rm_get_cq(RdmaDeviceResources *dev_res, uint32_t cq_handle) -{ - return rdma_res_tbl_get(&dev_res->cq_tbl, cq_handle); -} - -int rdma_rm_alloc_cq(RdmaDeviceResources *dev_res, RdmaBackendDev *backend_dev, - uint32_t cqe, uint32_t *cq_handle, void *opaque) -{ - int rc; - RdmaRmCQ *cq; - - cq = rdma_res_tbl_alloc(&dev_res->cq_tbl, cq_handle); - if (!cq) { - return -ENOMEM; - } - - cq->opaque = opaque; - cq->notify = CNT_CLEAR; - - rc = rdma_backend_create_cq(backend_dev, &cq->backend_cq, cqe); - if (rc) { - rc = -EIO; - goto out_dealloc_cq; - } - - return 0; - -out_dealloc_cq: - rdma_rm_dealloc_cq(dev_res, *cq_handle); - - return rc; -} - -void rdma_rm_req_notify_cq(RdmaDeviceResources *dev_res, uint32_t cq_handle, - bool notify) -{ - RdmaRmCQ *cq; - - cq = rdma_rm_get_cq(dev_res, cq_handle); - if (!cq) { - return; - } - - if (cq->notify != CNT_SET) { - cq->notify = notify ? CNT_ARM : CNT_CLEAR; - } -} - -void rdma_rm_dealloc_cq(RdmaDeviceResources *dev_res, uint32_t cq_handle) -{ - RdmaRmCQ *cq; - - cq = rdma_rm_get_cq(dev_res, cq_handle); - if (!cq) { - return; - } - - rdma_backend_destroy_cq(&cq->backend_cq); - - rdma_res_tbl_dealloc(&dev_res->cq_tbl, cq_handle); -} - -RdmaRmQP *rdma_rm_get_qp(RdmaDeviceResources *dev_res, uint32_t qpn) -{ - GBytes *key = g_bytes_new(&qpn, sizeof(qpn)); - - RdmaRmQP *qp = g_hash_table_lookup(dev_res->qp_hash, key); - - g_bytes_unref(key); - - if (!qp) { - rdma_error_report("Invalid QP handle %d", qpn); - } - - return qp; -} - -int rdma_rm_alloc_qp(RdmaDeviceResources *dev_res, uint32_t pd_handle, - uint8_t qp_type, uint32_t max_send_wr, - uint32_t max_send_sge, uint32_t send_cq_handle, - uint32_t max_recv_wr, uint32_t max_recv_sge, - uint32_t recv_cq_handle, void *opaque, uint32_t *qpn, - uint8_t is_srq, uint32_t srq_handle) -{ - int rc; - RdmaRmQP *qp; - RdmaRmCQ *scq, *rcq; - RdmaRmPD *pd; - RdmaRmSRQ *srq = NULL; - uint32_t rm_qpn; - - pd = rdma_rm_get_pd(dev_res, pd_handle); - if (!pd) { - return -EINVAL; - } - - scq = rdma_rm_get_cq(dev_res, send_cq_handle); - rcq = rdma_rm_get_cq(dev_res, recv_cq_handle); - - if (!scq || !rcq) { - rdma_error_report("Invalid send_cqn or recv_cqn (%d, %d)", - send_cq_handle, recv_cq_handle); - return -EINVAL; - } - - if (is_srq) { - srq = rdma_rm_get_srq(dev_res, srq_handle); - if (!srq) { - rdma_error_report("Invalid srqn %d", srq_handle); - return -EINVAL; - } - - srq->recv_cq_handle = recv_cq_handle; - } - - if (qp_type == IBV_QPT_GSI) { - scq->notify = CNT_SET; - rcq->notify = CNT_SET; - } - - qp = rdma_res_tbl_alloc(&dev_res->qp_tbl, &rm_qpn); - if (!qp) { - return -ENOMEM; - } - - qp->qpn = rm_qpn; - qp->qp_state = IBV_QPS_RESET; - qp->qp_type = qp_type; - qp->send_cq_handle = send_cq_handle; - qp->recv_cq_handle = recv_cq_handle; - qp->opaque = opaque; - qp->is_srq = is_srq; - - rc = rdma_backend_create_qp(&qp->backend_qp, qp_type, &pd->backend_pd, - &scq->backend_cq, &rcq->backend_cq, - is_srq ? &srq->backend_srq : NULL, - max_send_wr, max_recv_wr, max_send_sge, - max_recv_sge); - - if (rc) { - rc = -EIO; - goto out_dealloc_qp; - } - - *qpn = rdma_backend_qpn(&qp->backend_qp); - trace_rdma_rm_alloc_qp(rm_qpn, *qpn, qp_type); - g_hash_table_insert(dev_res->qp_hash, g_bytes_new(qpn, sizeof(*qpn)), qp); - - return 0; - -out_dealloc_qp: - rdma_res_tbl_dealloc(&dev_res->qp_tbl, qp->qpn); - - return rc; -} - -int rdma_rm_modify_qp(RdmaDeviceResources *dev_res, RdmaBackendDev *backend_dev, - uint32_t qp_handle, uint32_t attr_mask, uint8_t sgid_idx, - union ibv_gid *dgid, uint32_t dqpn, - enum ibv_qp_state qp_state, uint32_t qkey, - uint32_t rq_psn, uint32_t sq_psn) -{ - RdmaRmQP *qp; - int ret; - - qp = rdma_rm_get_qp(dev_res, qp_handle); - if (!qp) { - return -EINVAL; - } - - if (qp->qp_type == IBV_QPT_SMI) { - rdma_error_report("Got QP0 request"); - return -EPERM; - } else if (qp->qp_type == IBV_QPT_GSI) { - return 0; - } - - trace_rdma_rm_modify_qp(qp_handle, attr_mask, qp_state, sgid_idx); - - if (attr_mask & IBV_QP_STATE) { - qp->qp_state = qp_state; - - if (qp->qp_state == IBV_QPS_INIT) { - ret = rdma_backend_qp_state_init(backend_dev, &qp->backend_qp, - qp->qp_type, qkey); - if (ret) { - return -EIO; - } - } - - if (qp->qp_state == IBV_QPS_RTR) { - /* Get backend gid index */ - sgid_idx = rdma_rm_get_backend_gid_index(dev_res, backend_dev, - sgid_idx); - if (sgid_idx <= 0) { /* TODO check also less than bk.max_sgid */ - rdma_error_report("Failed to get bk sgid_idx for sgid_idx %d", - sgid_idx); - return -EIO; - } - - ret = rdma_backend_qp_state_rtr(backend_dev, &qp->backend_qp, - qp->qp_type, sgid_idx, dgid, dqpn, - rq_psn, qkey, - attr_mask & IBV_QP_QKEY); - if (ret) { - return -EIO; - } - } - - if (qp->qp_state == IBV_QPS_RTS) { - ret = rdma_backend_qp_state_rts(&qp->backend_qp, qp->qp_type, - sq_psn, qkey, - attr_mask & IBV_QP_QKEY); - if (ret) { - return -EIO; - } - } - } - - return 0; -} - -int rdma_rm_query_qp(RdmaDeviceResources *dev_res, RdmaBackendDev *backend_dev, - uint32_t qp_handle, struct ibv_qp_attr *attr, - int attr_mask, struct ibv_qp_init_attr *init_attr) -{ - RdmaRmQP *qp; - - qp = rdma_rm_get_qp(dev_res, qp_handle); - if (!qp) { - return -EINVAL; - } - - return rdma_backend_query_qp(&qp->backend_qp, attr, attr_mask, init_attr); -} - -void rdma_rm_dealloc_qp(RdmaDeviceResources *dev_res, uint32_t qp_handle) -{ - RdmaRmQP *qp; - GBytes *key; - - key = g_bytes_new(&qp_handle, sizeof(qp_handle)); - qp = g_hash_table_lookup(dev_res->qp_hash, key); - g_hash_table_remove(dev_res->qp_hash, key); - g_bytes_unref(key); - - if (!qp) { - return; - } - - rdma_backend_destroy_qp(&qp->backend_qp, dev_res); - - rdma_res_tbl_dealloc(&dev_res->qp_tbl, qp->qpn); -} - -RdmaRmSRQ *rdma_rm_get_srq(RdmaDeviceResources *dev_res, uint32_t srq_handle) -{ - return rdma_res_tbl_get(&dev_res->srq_tbl, srq_handle); -} - -int rdma_rm_alloc_srq(RdmaDeviceResources *dev_res, uint32_t pd_handle, - uint32_t max_wr, uint32_t max_sge, uint32_t srq_limit, - uint32_t *srq_handle, void *opaque) -{ - RdmaRmSRQ *srq; - RdmaRmPD *pd; - int rc; - - pd = rdma_rm_get_pd(dev_res, pd_handle); - if (!pd) { - return -EINVAL; - } - - srq = rdma_res_tbl_alloc(&dev_res->srq_tbl, srq_handle); - if (!srq) { - return -ENOMEM; - } - - rc = rdma_backend_create_srq(&srq->backend_srq, &pd->backend_pd, - max_wr, max_sge, srq_limit); - if (rc) { - rc = -EIO; - goto out_dealloc_srq; - } - - srq->opaque = opaque; - - return 0; - -out_dealloc_srq: - rdma_res_tbl_dealloc(&dev_res->srq_tbl, *srq_handle); - - return rc; -} - -int rdma_rm_query_srq(RdmaDeviceResources *dev_res, uint32_t srq_handle, - struct ibv_srq_attr *srq_attr) -{ - RdmaRmSRQ *srq; - - srq = rdma_rm_get_srq(dev_res, srq_handle); - if (!srq) { - return -EINVAL; - } - - return rdma_backend_query_srq(&srq->backend_srq, srq_attr); -} - -int rdma_rm_modify_srq(RdmaDeviceResources *dev_res, uint32_t srq_handle, - struct ibv_srq_attr *srq_attr, int srq_attr_mask) -{ - RdmaRmSRQ *srq; - - srq = rdma_rm_get_srq(dev_res, srq_handle); - if (!srq) { - return -EINVAL; - } - - if ((srq_attr_mask & IBV_SRQ_LIMIT) && - (srq_attr->srq_limit == 0)) { - return -EINVAL; - } - - if ((srq_attr_mask & IBV_SRQ_MAX_WR) && - (srq_attr->max_wr == 0)) { - return -EINVAL; - } - - return rdma_backend_modify_srq(&srq->backend_srq, srq_attr, - srq_attr_mask); -} - -void rdma_rm_dealloc_srq(RdmaDeviceResources *dev_res, uint32_t srq_handle) -{ - RdmaRmSRQ *srq; - - srq = rdma_rm_get_srq(dev_res, srq_handle); - if (!srq) { - return; - } - - rdma_backend_destroy_srq(&srq->backend_srq, dev_res); - rdma_res_tbl_dealloc(&dev_res->srq_tbl, srq_handle); -} - -void *rdma_rm_get_cqe_ctx(RdmaDeviceResources *dev_res, uint32_t cqe_ctx_id) -{ - void **cqe_ctx; - - cqe_ctx = rdma_res_tbl_get(&dev_res->cqe_ctx_tbl, cqe_ctx_id); - if (!cqe_ctx) { - return NULL; - } - - return *cqe_ctx; -} - -int rdma_rm_alloc_cqe_ctx(RdmaDeviceResources *dev_res, uint32_t *cqe_ctx_id, - void *ctx) -{ - void **cqe_ctx; - - cqe_ctx = rdma_res_tbl_alloc(&dev_res->cqe_ctx_tbl, cqe_ctx_id); - if (!cqe_ctx) { - return -ENOMEM; - } - - *cqe_ctx = ctx; - - return 0; -} - -void rdma_rm_dealloc_cqe_ctx(RdmaDeviceResources *dev_res, uint32_t cqe_ctx_id) -{ - rdma_res_tbl_dealloc(&dev_res->cqe_ctx_tbl, cqe_ctx_id); -} - -int rdma_rm_add_gid(RdmaDeviceResources *dev_res, RdmaBackendDev *backend_dev, - const char *ifname, union ibv_gid *gid, int gid_idx) -{ - int rc; - - rc = rdma_backend_add_gid(backend_dev, ifname, gid); - if (rc) { - return -EINVAL; - } - - memcpy(&dev_res->port.gid_tbl[gid_idx].gid, gid, sizeof(*gid)); - - return 0; -} - -int rdma_rm_del_gid(RdmaDeviceResources *dev_res, RdmaBackendDev *backend_dev, - const char *ifname, int gid_idx) -{ - int rc; - - if (!dev_res->port.gid_tbl[gid_idx].gid.global.interface_id) { - return 0; - } - - rc = rdma_backend_del_gid(backend_dev, ifname, - &dev_res->port.gid_tbl[gid_idx].gid); - if (rc) { - return -EINVAL; - } - - memset(dev_res->port.gid_tbl[gid_idx].gid.raw, 0, - sizeof(dev_res->port.gid_tbl[gid_idx].gid)); - dev_res->port.gid_tbl[gid_idx].backend_gid_index = -1; - - return 0; -} - -int rdma_rm_get_backend_gid_index(RdmaDeviceResources *dev_res, - RdmaBackendDev *backend_dev, int sgid_idx) -{ - if (unlikely(sgid_idx < 0 || sgid_idx >= MAX_PORT_GIDS)) { - rdma_error_report("Got invalid sgid_idx %d", sgid_idx); - return -EINVAL; - } - - if (unlikely(dev_res->port.gid_tbl[sgid_idx].backend_gid_index == -1)) { - dev_res->port.gid_tbl[sgid_idx].backend_gid_index = - rdma_backend_get_gid_index(backend_dev, - &dev_res->port.gid_tbl[sgid_idx].gid); - } - - return dev_res->port.gid_tbl[sgid_idx].backend_gid_index; -} - -static void destroy_qp_hash_key(gpointer data) -{ - g_bytes_unref(data); -} - -static void init_ports(RdmaDeviceResources *dev_res) -{ - int i; - - memset(&dev_res->port, 0, sizeof(dev_res->port)); - - dev_res->port.state = IBV_PORT_DOWN; - for (i = 0; i < MAX_PORT_GIDS; i++) { - dev_res->port.gid_tbl[i].backend_gid_index = -1; - } -} - -static void fini_ports(RdmaDeviceResources *dev_res, - RdmaBackendDev *backend_dev, const char *ifname) -{ - int i; - - dev_res->port.state = IBV_PORT_DOWN; - for (i = 0; i < MAX_PORT_GIDS; i++) { - rdma_rm_del_gid(dev_res, backend_dev, ifname, i); - } -} - -int rdma_rm_init(RdmaDeviceResources *dev_res, struct ibv_device_attr *dev_attr) -{ - dev_res->qp_hash = g_hash_table_new_full(g_bytes_hash, g_bytes_equal, - destroy_qp_hash_key, NULL); - if (!dev_res->qp_hash) { - return -ENOMEM; - } - - res_tbl_init("PD", &dev_res->pd_tbl, dev_attr->max_pd, sizeof(RdmaRmPD)); - res_tbl_init("CQ", &dev_res->cq_tbl, dev_attr->max_cq, sizeof(RdmaRmCQ)); - res_tbl_init("MR", &dev_res->mr_tbl, dev_attr->max_mr, sizeof(RdmaRmMR)); - res_tbl_init("QP", &dev_res->qp_tbl, dev_attr->max_qp, sizeof(RdmaRmQP)); - res_tbl_init("CQE_CTX", &dev_res->cqe_ctx_tbl, dev_attr->max_qp * - dev_attr->max_qp_wr, sizeof(void *)); - res_tbl_init("UC", &dev_res->uc_tbl, MAX_UCS, sizeof(RdmaRmUC)); - res_tbl_init("SRQ", &dev_res->srq_tbl, dev_attr->max_srq, - sizeof(RdmaRmSRQ)); - - init_ports(dev_res); - - qemu_mutex_init(&dev_res->lock); - - memset(&dev_res->stats, 0, sizeof(dev_res->stats)); - qatomic_set(&dev_res->stats.missing_cqe, 0); - - return 0; -} - -void rdma_rm_fini(RdmaDeviceResources *dev_res, RdmaBackendDev *backend_dev, - const char *ifname) -{ - qemu_mutex_destroy(&dev_res->lock); - - fini_ports(dev_res, backend_dev, ifname); - - res_tbl_free(&dev_res->srq_tbl); - res_tbl_free(&dev_res->uc_tbl); - res_tbl_free(&dev_res->cqe_ctx_tbl); - res_tbl_free(&dev_res->qp_tbl); - res_tbl_free(&dev_res->mr_tbl); - res_tbl_free(&dev_res->cq_tbl); - res_tbl_free(&dev_res->pd_tbl); - - if (dev_res->qp_hash) { - g_hash_table_destroy(dev_res->qp_hash); - } -} diff --git a/hw/rdma/rdma_utils.c b/hw/rdma/rdma_utils.c deleted file mode 100644 index c948baf052..0000000000 --- a/hw/rdma/rdma_utils.c +++ /dev/null @@ -1,126 +0,0 @@ -/* - * QEMU paravirtual RDMA - Generic RDMA backend - * - * Copyright (C) 2018 Oracle - * Copyright (C) 2018 Red Hat Inc - * - * Authors: - * Yuval Shaia <yuval.shaia(a)oracle.com> - * Marcel Apfelbaum <marcel(a)redhat.com> - * - * This work is licensed under the terms of the GNU GPL, version 2 or later. - * See the COPYING file in the top-level directory. - * - */ - -#include "qemu/osdep.h" -#include "hw/pci/pci_device.h" -#include "trace.h" -#include "rdma_utils.h" - -void *rdma_pci_dma_map(PCIDevice *dev, dma_addr_t addr, dma_addr_t len) -{ - void *p; - dma_addr_t pci_len = len; - - if (!addr) { - rdma_error_report("addr is NULL"); - return NULL; - } - - p = pci_dma_map(dev, addr, &pci_len, DMA_DIRECTION_TO_DEVICE); - if (!p) { - rdma_error_report("pci_dma_map fail, addr=0x%"PRIx64", len=%"PRId64, - addr, pci_len); - return NULL; - } - - if (pci_len != len) { - rdma_pci_dma_unmap(dev, p, pci_len); - return NULL; - } - - trace_rdma_pci_dma_map(addr, p, pci_len); - - return p; -} - -void rdma_pci_dma_unmap(PCIDevice *dev, void *buffer, dma_addr_t len) -{ - trace_rdma_pci_dma_unmap(buffer); - if (buffer) { - pci_dma_unmap(dev, buffer, len, DMA_DIRECTION_TO_DEVICE, 0); - } -} - -void rdma_protected_gqueue_init(RdmaProtectedGQueue *list) -{ - qemu_mutex_init(&list->lock); - list->list = g_queue_new(); -} - -void rdma_protected_gqueue_destroy(RdmaProtectedGQueue *list) -{ - if (list->list) { - g_queue_free_full(list->list, g_free); - qemu_mutex_destroy(&list->lock); - list->list = NULL; - } -} - -void rdma_protected_gqueue_append_int64(RdmaProtectedGQueue *list, - int64_t value) -{ - qemu_mutex_lock(&list->lock); - g_queue_push_tail(list->list, g_memdup(&value, sizeof(value))); - qemu_mutex_unlock(&list->lock); -} - -int64_t rdma_protected_gqueue_pop_int64(RdmaProtectedGQueue *list) -{ - int64_t *valp; - int64_t val; - - qemu_mutex_lock(&list->lock); - - valp = g_queue_pop_head(list->list); - qemu_mutex_unlock(&list->lock); - - if (!valp) { - return -ENOENT; - } - - val = *valp; - g_free(valp); - return val; -} - -void rdma_protected_gslist_init(RdmaProtectedGSList *list) -{ - qemu_mutex_init(&list->lock); -} - -void rdma_protected_gslist_destroy(RdmaProtectedGSList *list) -{ - if (list->list) { - g_slist_free(list->list); - qemu_mutex_destroy(&list->lock); - list->list = NULL; - } -} - -void rdma_protected_gslist_append_int32(RdmaProtectedGSList *list, - int32_t value) -{ - qemu_mutex_lock(&list->lock); - list->list = g_slist_prepend(list->list, GINT_TO_POINTER(value)); - qemu_mutex_unlock(&list->lock); -} - -void rdma_protected_gslist_remove_int32(RdmaProtectedGSList *list, - int32_t value) -{ - qemu_mutex_lock(&list->lock); - list->list = g_slist_remove(list->list, GINT_TO_POINTER(value)); - qemu_mutex_unlock(&list->lock); -} diff --git a/hw/rdma/vmw/pvrdma_cmd.c b/hw/rdma/vmw/pvrdma_cmd.c deleted file mode 100644 index d385d18d9c..0000000000 --- a/hw/rdma/vmw/pvrdma_cmd.c +++ /dev/null @@ -1,815 +0,0 @@ -/* - * QEMU paravirtual RDMA - Command channel - * - * Copyright (C) 2018 Oracle - * Copyright (C) 2018 Red Hat Inc - * - * Authors: - * Yuval Shaia <yuval.shaia(a)oracle.com> - * Marcel Apfelbaum <marcel(a)redhat.com> - * - * This work is licensed under the terms of the GNU GPL, version 2 or later. - * See the COPYING file in the top-level directory. - * - */ - -#include "qemu/osdep.h" -#include "cpu.h" -#include "hw/pci/pci.h" -#include "hw/pci/pci_ids.h" - -#include "../rdma_backend.h" -#include "../rdma_rm.h" -#include "../rdma_utils.h" - -#include "trace.h" -#include "pvrdma.h" -#include "standard-headers/rdma/vmw_pvrdma-abi.h" - -static void *pvrdma_map_to_pdir(PCIDevice *pdev, uint64_t pdir_dma, - uint32_t nchunks, size_t length) -{ - uint64_t *dir, *tbl; - int tbl_idx, dir_idx, addr_idx; - void *host_virt = NULL, *curr_page; - - if (!nchunks) { - rdma_error_report("Got nchunks=0"); - return NULL; - } - - length = ROUND_UP(length, TARGET_PAGE_SIZE); - if (nchunks * TARGET_PAGE_SIZE != length) { - rdma_error_report("Invalid nchunks/length (%u, %lu)", nchunks, - (unsigned long)length); - return NULL; - } - - dir = rdma_pci_dma_map(pdev, pdir_dma, TARGET_PAGE_SIZE); - if (!dir) { - rdma_error_report("Failed to map to page directory"); - return NULL; - } - - tbl = rdma_pci_dma_map(pdev, dir[0], TARGET_PAGE_SIZE); - if (!tbl) { - rdma_error_report("Failed to map to page table 0"); - goto out_unmap_dir; - } - - curr_page = rdma_pci_dma_map(pdev, (dma_addr_t)tbl[0], TARGET_PAGE_SIZE); - if (!curr_page) { - rdma_error_report("Failed to map the page 0"); - goto out_unmap_tbl; - } - - host_virt = mremap(curr_page, 0, length, MREMAP_MAYMOVE); - if (host_virt == MAP_FAILED) { - host_virt = NULL; - rdma_error_report("Failed to remap memory for host_virt"); - goto out_unmap_tbl; - } - trace_pvrdma_map_to_pdir_host_virt(curr_page, host_virt); - - rdma_pci_dma_unmap(pdev, curr_page, TARGET_PAGE_SIZE); - - dir_idx = 0; - tbl_idx = 1; - addr_idx = 1; - while (addr_idx < nchunks) { - if (tbl_idx == TARGET_PAGE_SIZE / sizeof(uint64_t)) { - tbl_idx = 0; - dir_idx++; - rdma_pci_dma_unmap(pdev, tbl, TARGET_PAGE_SIZE); - tbl = rdma_pci_dma_map(pdev, dir[dir_idx], TARGET_PAGE_SIZE); - if (!tbl) { - rdma_error_report("Failed to map to page table %d", dir_idx); - goto out_unmap_host_virt; - } - } - - curr_page = rdma_pci_dma_map(pdev, (dma_addr_t)tbl[tbl_idx], - TARGET_PAGE_SIZE); - if (!curr_page) { - rdma_error_report("Failed to map to page %d, dir %d", tbl_idx, - dir_idx); - goto out_unmap_host_virt; - } - - mremap(curr_page, 0, TARGET_PAGE_SIZE, MREMAP_MAYMOVE | MREMAP_FIXED, - host_virt + TARGET_PAGE_SIZE * addr_idx); - - trace_pvrdma_map_to_pdir_next_page(addr_idx, curr_page, host_virt + - TARGET_PAGE_SIZE * addr_idx); - - rdma_pci_dma_unmap(pdev, curr_page, TARGET_PAGE_SIZE); - - addr_idx++; - - tbl_idx++; - } - - goto out_unmap_tbl; - -out_unmap_host_virt: - munmap(host_virt, length); - host_virt = NULL; - -out_unmap_tbl: - rdma_pci_dma_unmap(pdev, tbl, TARGET_PAGE_SIZE); - -out_unmap_dir: - rdma_pci_dma_unmap(pdev, dir, TARGET_PAGE_SIZE); - - return host_virt; -} - -static int query_port(PVRDMADev *dev, union pvrdma_cmd_req *req, - union pvrdma_cmd_resp *rsp) -{ - struct pvrdma_cmd_query_port *cmd = &req->query_port; - struct pvrdma_cmd_query_port_resp *resp = &rsp->query_port_resp; - struct ibv_port_attr attrs = {}; - - if (cmd->port_num > MAX_PORTS) { - return -EINVAL; - } - - if (rdma_backend_query_port(&dev->backend_dev, &attrs)) { - return -ENOMEM; - } - - memset(resp, 0, sizeof(*resp)); - - /* - * The state, max_mtu and active_mtu fields are enums; the values - * for pvrdma_port_state and pvrdma_mtu match those for - * ibv_port_state and ibv_mtu, so we can cast them safely. - */ - resp->attrs.state = dev->func0->device_active ? - (enum pvrdma_port_state)attrs.state : PVRDMA_PORT_DOWN; - resp->attrs.max_mtu = (enum pvrdma_mtu)attrs.max_mtu; - resp->attrs.active_mtu = (enum pvrdma_mtu)attrs.active_mtu; - resp->attrs.phys_state = attrs.phys_state; - resp->attrs.gid_tbl_len = MIN(MAX_PORT_GIDS, attrs.gid_tbl_len); - resp->attrs.max_msg_sz = 1024; - resp->attrs.pkey_tbl_len = MIN(MAX_PORT_PKEYS, attrs.pkey_tbl_len); - resp->attrs.active_width = 1; - resp->attrs.active_speed = 1; - - return 0; -} - -static int query_pkey(PVRDMADev *dev, union pvrdma_cmd_req *req, - union pvrdma_cmd_resp *rsp) -{ - struct pvrdma_cmd_query_pkey *cmd = &req->query_pkey; - struct pvrdma_cmd_query_pkey_resp *resp = &rsp->query_pkey_resp; - - if (cmd->port_num > MAX_PORTS) { - return -EINVAL; - } - - if (cmd->index > MAX_PKEYS) { - return -EINVAL; - } - - memset(resp, 0, sizeof(*resp)); - - resp->pkey = PVRDMA_PKEY; - - return 0; -} - -static int create_pd(PVRDMADev *dev, union pvrdma_cmd_req *req, - union pvrdma_cmd_resp *rsp) -{ - struct pvrdma_cmd_create_pd *cmd = &req->create_pd; - struct pvrdma_cmd_create_pd_resp *resp = &rsp->create_pd_resp; - - memset(resp, 0, sizeof(*resp)); - return rdma_rm_alloc_pd(&dev->rdma_dev_res, &dev->backend_dev, - &resp->pd_handle, cmd->ctx_handle); -} - -static int destroy_pd(PVRDMADev *dev, union pvrdma_cmd_req *req, - union pvrdma_cmd_resp *rsp) -{ - struct pvrdma_cmd_destroy_pd *cmd = &req->destroy_pd; - - rdma_rm_dealloc_pd(&dev->rdma_dev_res, cmd->pd_handle); - - return 0; -} - -static int create_mr(PVRDMADev *dev, union pvrdma_cmd_req *req, - union pvrdma_cmd_resp *rsp) -{ - struct pvrdma_cmd_create_mr *cmd = &req->create_mr; - struct pvrdma_cmd_create_mr_resp *resp = &rsp->create_mr_resp; - PCIDevice *pci_dev = PCI_DEVICE(dev); - void *host_virt = NULL; - int rc = 0; - - memset(resp, 0, sizeof(*resp)); - - if (!(cmd->flags & PVRDMA_MR_FLAG_DMA)) { - host_virt = pvrdma_map_to_pdir(pci_dev, cmd->pdir_dma, cmd->nchunks, - cmd->length); - if (!host_virt) { - rdma_error_report("Failed to map to pdir"); - return -EINVAL; - } - } - - rc = rdma_rm_alloc_mr(&dev->rdma_dev_res, cmd->pd_handle, cmd->start, - cmd->length, host_virt, cmd->access_flags, - &resp->mr_handle, &resp->lkey, &resp->rkey); - if (rc && host_virt) { - munmap(host_virt, cmd->length); - } - - return rc; -} - -static int destroy_mr(PVRDMADev *dev, union pvrdma_cmd_req *req, - union pvrdma_cmd_resp *rsp) -{ - struct pvrdma_cmd_destroy_mr *cmd = &req->destroy_mr; - - rdma_rm_dealloc_mr(&dev->rdma_dev_res, cmd->mr_handle); - - return 0; -} - -static int create_cq_ring(PCIDevice *pci_dev , PvrdmaRing **ring, - uint64_t pdir_dma, uint32_t nchunks, uint32_t cqe) -{ - uint64_t *dir = NULL, *tbl = NULL; - PvrdmaRing *r; - int rc = -EINVAL; - char ring_name[MAX_RING_NAME_SZ]; - - if (!nchunks || nchunks > PVRDMA_MAX_FAST_REG_PAGES) { - rdma_error_report("Got invalid nchunks: %d", nchunks); - return rc; - } - - dir = rdma_pci_dma_map(pci_dev, pdir_dma, TARGET_PAGE_SIZE); - if (!dir) { - rdma_error_report("Failed to map to CQ page directory"); - goto out; - } - - tbl = rdma_pci_dma_map(pci_dev, dir[0], TARGET_PAGE_SIZE); - if (!tbl) { - rdma_error_report("Failed to map to CQ page table"); - goto out; - } - - r = g_malloc(sizeof(*r)); - *ring = r; - - r->ring_state = rdma_pci_dma_map(pci_dev, tbl[0], TARGET_PAGE_SIZE); - - if (!r->ring_state) { - rdma_error_report("Failed to map to CQ ring state"); - goto out_free_ring; - } - - sprintf(ring_name, "cq_ring_%" PRIx64, pdir_dma); - rc = pvrdma_ring_init(r, ring_name, pci_dev, &r->ring_state[1], - cqe, sizeof(struct pvrdma_cqe), - /* first page is ring state */ - (dma_addr_t *)&tbl[1], nchunks - 1); - if (rc) { - goto out_unmap_ring_state; - } - - goto out; - -out_unmap_ring_state: - /* ring_state was in slot 1, not 0 so need to jump back */ - rdma_pci_dma_unmap(pci_dev, --r->ring_state, TARGET_PAGE_SIZE); - -out_free_ring: - g_free(r); - -out: - rdma_pci_dma_unmap(pci_dev, tbl, TARGET_PAGE_SIZE); - rdma_pci_dma_unmap(pci_dev, dir, TARGET_PAGE_SIZE); - - return rc; -} - -static void destroy_cq_ring(PvrdmaRing *ring) -{ - pvrdma_ring_free(ring); - /* ring_state was in slot 1, not 0 so need to jump back */ - rdma_pci_dma_unmap(ring->dev, --ring->ring_state, TARGET_PAGE_SIZE); - g_free(ring); -} - -static int create_cq(PVRDMADev *dev, union pvrdma_cmd_req *req, - union pvrdma_cmd_resp *rsp) -{ - struct pvrdma_cmd_create_cq *cmd = &req->create_cq; - struct pvrdma_cmd_create_cq_resp *resp = &rsp->create_cq_resp; - PvrdmaRing *ring = NULL; - int rc; - - memset(resp, 0, sizeof(*resp)); - - resp->cqe = cmd->cqe; - - rc = create_cq_ring(PCI_DEVICE(dev), &ring, cmd->pdir_dma, cmd->nchunks, - cmd->cqe); - if (rc) { - return rc; - } - - rc = rdma_rm_alloc_cq(&dev->rdma_dev_res, &dev->backend_dev, cmd->cqe, - &resp->cq_handle, ring); - if (rc) { - destroy_cq_ring(ring); - } - - resp->cqe = cmd->cqe; - - return rc; -} - -static int destroy_cq(PVRDMADev *dev, union pvrdma_cmd_req *req, - union pvrdma_cmd_resp *rsp) -{ - struct pvrdma_cmd_destroy_cq *cmd = &req->destroy_cq; - RdmaRmCQ *cq; - PvrdmaRing *ring; - - cq = rdma_rm_get_cq(&dev->rdma_dev_res, cmd->cq_handle); - if (!cq) { - rdma_error_report("Got invalid CQ handle"); - return -EINVAL; - } - - ring = (PvrdmaRing *)cq->opaque; - destroy_cq_ring(ring); - - rdma_rm_dealloc_cq(&dev->rdma_dev_res, cmd->cq_handle); - - return 0; -} - -static int create_qp_rings(PCIDevice *pci_dev, uint64_t pdir_dma, - PvrdmaRing **rings, uint32_t scqe, uint32_t smax_sge, - uint32_t spages, uint32_t rcqe, uint32_t rmax_sge, - uint32_t rpages, uint8_t is_srq) -{ - uint64_t *dir = NULL, *tbl = NULL; - PvrdmaRing *sr, *rr; - int rc = -EINVAL; - char ring_name[MAX_RING_NAME_SZ]; - uint32_t wqe_sz; - - if (!spages || spages > PVRDMA_MAX_FAST_REG_PAGES) { - rdma_error_report("Got invalid send page count for QP ring: %d", - spages); - return rc; - } - - if (!is_srq && (!rpages || rpages > PVRDMA_MAX_FAST_REG_PAGES)) { - rdma_error_report("Got invalid recv page count for QP ring: %d", - rpages); - return rc; - } - - dir = rdma_pci_dma_map(pci_dev, pdir_dma, TARGET_PAGE_SIZE); - if (!dir) { - rdma_error_report("Failed to map to QP page directory"); - goto out; - } - - tbl = rdma_pci_dma_map(pci_dev, dir[0], TARGET_PAGE_SIZE); - if (!tbl) { - rdma_error_report("Failed to map to QP page table"); - goto out; - } - - if (!is_srq) { - sr = g_malloc(2 * sizeof(*rr)); - rr = &sr[1]; - } else { - sr = g_malloc(sizeof(*sr)); - } - - *rings = sr; - - /* Create send ring */ - sr->ring_state = rdma_pci_dma_map(pci_dev, tbl[0], TARGET_PAGE_SIZE); - if (!sr->ring_state) { - rdma_error_report("Failed to map to QP ring state"); - goto out_free_sr_mem; - } - - wqe_sz = pow2ceil(sizeof(struct pvrdma_sq_wqe_hdr) + - sizeof(struct pvrdma_sge) * smax_sge - 1); - - sprintf(ring_name, "qp_sring_%" PRIx64, pdir_dma); - rc = pvrdma_ring_init(sr, ring_name, pci_dev, sr->ring_state, - scqe, wqe_sz, (dma_addr_t *)&tbl[1], spages); - if (rc) { - goto out_unmap_ring_state; - } - - if (!is_srq) { - /* Create recv ring */ - rr->ring_state = &sr->ring_state[1]; - wqe_sz = pow2ceil(sizeof(struct pvrdma_rq_wqe_hdr) + - sizeof(struct pvrdma_sge) * rmax_sge - 1); - sprintf(ring_name, "qp_rring_%" PRIx64, pdir_dma); - rc = pvrdma_ring_init(rr, ring_name, pci_dev, rr->ring_state, - rcqe, wqe_sz, (dma_addr_t *)&tbl[1 + spages], - rpages); - if (rc) { - goto out_free_sr; - } - } - - goto out; - -out_free_sr: - pvrdma_ring_free(sr); - -out_unmap_ring_state: - rdma_pci_dma_unmap(pci_dev, sr->ring_state, TARGET_PAGE_SIZE); - -out_free_sr_mem: - g_free(sr); - -out: - rdma_pci_dma_unmap(pci_dev, tbl, TARGET_PAGE_SIZE); - rdma_pci_dma_unmap(pci_dev, dir, TARGET_PAGE_SIZE); - - return rc; -} - -static void destroy_qp_rings(PvrdmaRing *ring, uint8_t is_srq) -{ - pvrdma_ring_free(&ring[0]); - if (!is_srq) { - pvrdma_ring_free(&ring[1]); - } - - rdma_pci_dma_unmap(ring->dev, ring->ring_state, TARGET_PAGE_SIZE); - g_free(ring); -} - -static int create_qp(PVRDMADev *dev, union pvrdma_cmd_req *req, - union pvrdma_cmd_resp *rsp) -{ - struct pvrdma_cmd_create_qp *cmd = &req->create_qp; - struct pvrdma_cmd_create_qp_resp *resp = &rsp->create_qp_resp; - PvrdmaRing *rings = NULL; - int rc; - - memset(resp, 0, sizeof(*resp)); - - rc = create_qp_rings(PCI_DEVICE(dev), cmd->pdir_dma, &rings, - cmd->max_send_wr, cmd->max_send_sge, cmd->send_chunks, - cmd->max_recv_wr, cmd->max_recv_sge, - cmd->total_chunks - cmd->send_chunks - 1, cmd->is_srq); - if (rc) { - return rc; - } - - rc = rdma_rm_alloc_qp(&dev->rdma_dev_res, cmd->pd_handle, cmd->qp_type, - cmd->max_send_wr, cmd->max_send_sge, - cmd->send_cq_handle, cmd->max_recv_wr, - cmd->max_recv_sge, cmd->recv_cq_handle, rings, - &resp->qpn, cmd->is_srq, cmd->srq_handle); - if (rc) { - destroy_qp_rings(rings, cmd->is_srq); - return rc; - } - - resp->max_send_wr = cmd->max_send_wr; - resp->max_recv_wr = cmd->max_recv_wr; - resp->max_send_sge = cmd->max_send_sge; - resp->max_recv_sge = cmd->max_recv_sge; - resp->max_inline_data = cmd->max_inline_data; - - return 0; -} - -static int modify_qp(PVRDMADev *dev, union pvrdma_cmd_req *req, - union pvrdma_cmd_resp *rsp) -{ - struct pvrdma_cmd_modify_qp *cmd = &req->modify_qp; - - /* No need to verify sgid_index since it is u8 */ - - return rdma_rm_modify_qp(&dev->rdma_dev_res, &dev->backend_dev, - cmd->qp_handle, cmd->attr_mask, - cmd->attrs.ah_attr.grh.sgid_index, - (union ibv_gid *)&cmd->attrs.ah_attr.grh.dgid, - cmd->attrs.dest_qp_num, - (enum ibv_qp_state)cmd->attrs.qp_state, - cmd->attrs.qkey, cmd->attrs.rq_psn, - cmd->attrs.sq_psn); -} - -static int query_qp(PVRDMADev *dev, union pvrdma_cmd_req *req, - union pvrdma_cmd_resp *rsp) -{ - struct pvrdma_cmd_query_qp *cmd = &req->query_qp; - struct pvrdma_cmd_query_qp_resp *resp = &rsp->query_qp_resp; - struct ibv_qp_init_attr init_attr; - - memset(resp, 0, sizeof(*resp)); - - return rdma_rm_query_qp(&dev->rdma_dev_res, &dev->backend_dev, - cmd->qp_handle, - (struct ibv_qp_attr *)&resp->attrs, - cmd->attr_mask, - &init_attr); -} - -static int destroy_qp(PVRDMADev *dev, union pvrdma_cmd_req *req, - union pvrdma_cmd_resp *rsp) -{ - struct pvrdma_cmd_destroy_qp *cmd = &req->destroy_qp; - RdmaRmQP *qp; - PvrdmaRing *ring; - - qp = rdma_rm_get_qp(&dev->rdma_dev_res, cmd->qp_handle); - if (!qp) { - return -EINVAL; - } - - ring = (PvrdmaRing *)qp->opaque; - destroy_qp_rings(ring, qp->is_srq); - rdma_rm_dealloc_qp(&dev->rdma_dev_res, cmd->qp_handle); - - return 0; -} - -static int create_bind(PVRDMADev *dev, union pvrdma_cmd_req *req, - union pvrdma_cmd_resp *rsp) -{ - struct pvrdma_cmd_create_bind *cmd = &req->create_bind; - union ibv_gid *gid = (union ibv_gid *)&cmd->new_gid; - - if (cmd->index >= MAX_PORT_GIDS) { - return -EINVAL; - } - - return rdma_rm_add_gid(&dev->rdma_dev_res, &dev->backend_dev, - dev->backend_eth_device_name, gid, cmd->index); -} - -static int destroy_bind(PVRDMADev *dev, union pvrdma_cmd_req *req, - union pvrdma_cmd_resp *rsp) -{ - struct pvrdma_cmd_destroy_bind *cmd = &req->destroy_bind; - - if (cmd->index >= MAX_PORT_GIDS) { - return -EINVAL; - } - - return rdma_rm_del_gid(&dev->rdma_dev_res, &dev->backend_dev, - dev->backend_eth_device_name, cmd->index); -} - -static int create_uc(PVRDMADev *dev, union pvrdma_cmd_req *req, - union pvrdma_cmd_resp *rsp) -{ - struct pvrdma_cmd_create_uc *cmd = &req->create_uc; - struct pvrdma_cmd_create_uc_resp *resp = &rsp->create_uc_resp; - - memset(resp, 0, sizeof(*resp)); - return rdma_rm_alloc_uc(&dev->rdma_dev_res, cmd->pfn, &resp->ctx_handle); -} - -static int destroy_uc(PVRDMADev *dev, union pvrdma_cmd_req *req, - union pvrdma_cmd_resp *rsp) -{ - struct pvrdma_cmd_destroy_uc *cmd = &req->destroy_uc; - - rdma_rm_dealloc_uc(&dev->rdma_dev_res, cmd->ctx_handle); - - return 0; -} - -static int create_srq_ring(PCIDevice *pci_dev, PvrdmaRing **ring, - uint64_t pdir_dma, uint32_t max_wr, - uint32_t max_sge, uint32_t nchunks) -{ - uint64_t *dir = NULL, *tbl = NULL; - PvrdmaRing *r; - int rc = -EINVAL; - char ring_name[MAX_RING_NAME_SZ]; - uint32_t wqe_sz; - - if (!nchunks || nchunks > PVRDMA_MAX_FAST_REG_PAGES) { - rdma_error_report("Got invalid page count for SRQ ring: %d", - nchunks); - return rc; - } - - dir = rdma_pci_dma_map(pci_dev, pdir_dma, TARGET_PAGE_SIZE); - if (!dir) { - rdma_error_report("Failed to map to SRQ page directory"); - goto out; - } - - tbl = rdma_pci_dma_map(pci_dev, dir[0], TARGET_PAGE_SIZE); - if (!tbl) { - rdma_error_report("Failed to map to SRQ page table"); - goto out; - } - - r = g_malloc(sizeof(*r)); - *ring = r; - - r->ring_state = rdma_pci_dma_map(pci_dev, tbl[0], TARGET_PAGE_SIZE); - if (!r->ring_state) { - rdma_error_report("Failed to map tp SRQ ring state"); - goto out_free_ring_mem; - } - - wqe_sz = pow2ceil(sizeof(struct pvrdma_rq_wqe_hdr) + - sizeof(struct pvrdma_sge) * max_sge - 1); - sprintf(ring_name, "srq_ring_%" PRIx64, pdir_dma); - rc = pvrdma_ring_init(r, ring_name, pci_dev, &r->ring_state[1], max_wr, - wqe_sz, (dma_addr_t *)&tbl[1], nchunks - 1); - if (rc) { - goto out_unmap_ring_state; - } - - goto out; - -out_unmap_ring_state: - rdma_pci_dma_unmap(pci_dev, r->ring_state, TARGET_PAGE_SIZE); - -out_free_ring_mem: - g_free(r); - -out: - rdma_pci_dma_unmap(pci_dev, tbl, TARGET_PAGE_SIZE); - rdma_pci_dma_unmap(pci_dev, dir, TARGET_PAGE_SIZE); - - return rc; -} - -static void destroy_srq_ring(PvrdmaRing *ring) -{ - pvrdma_ring_free(ring); - rdma_pci_dma_unmap(ring->dev, ring->ring_state, TARGET_PAGE_SIZE); - g_free(ring); -} - -static int create_srq(PVRDMADev *dev, union pvrdma_cmd_req *req, - union pvrdma_cmd_resp *rsp) -{ - struct pvrdma_cmd_create_srq *cmd = &req->create_srq; - struct pvrdma_cmd_create_srq_resp *resp = &rsp->create_srq_resp; - PvrdmaRing *ring = NULL; - int rc; - - memset(resp, 0, sizeof(*resp)); - - rc = create_srq_ring(PCI_DEVICE(dev), &ring, cmd->pdir_dma, - cmd->attrs.max_wr, cmd->attrs.max_sge, - cmd->nchunks); - if (rc) { - return rc; - } - - rc = rdma_rm_alloc_srq(&dev->rdma_dev_res, cmd->pd_handle, - cmd->attrs.max_wr, cmd->attrs.max_sge, - cmd->attrs.srq_limit, &resp->srqn, ring); - if (rc) { - destroy_srq_ring(ring); - return rc; - } - - return 0; -} - -static int query_srq(PVRDMADev *dev, union pvrdma_cmd_req *req, - union pvrdma_cmd_resp *rsp) -{ - struct pvrdma_cmd_query_srq *cmd = &req->query_srq; - struct pvrdma_cmd_query_srq_resp *resp = &rsp->query_srq_resp; - - memset(resp, 0, sizeof(*resp)); - - return rdma_rm_query_srq(&dev->rdma_dev_res, cmd->srq_handle, - (struct ibv_srq_attr *)&resp->attrs); -} - -static int modify_srq(PVRDMADev *dev, union pvrdma_cmd_req *req, - union pvrdma_cmd_resp *rsp) -{ - struct pvrdma_cmd_modify_srq *cmd = &req->modify_srq; - - /* Only support SRQ limit */ - if (!(cmd->attr_mask & IBV_SRQ_LIMIT) || - (cmd->attr_mask & IBV_SRQ_MAX_WR)) - return -EINVAL; - - return rdma_rm_modify_srq(&dev->rdma_dev_res, cmd->srq_handle, - (struct ibv_srq_attr *)&cmd->attrs, - cmd->attr_mask); -} - -static int destroy_srq(PVRDMADev *dev, union pvrdma_cmd_req *req, - union pvrdma_cmd_resp *rsp) -{ - struct pvrdma_cmd_destroy_srq *cmd = &req->destroy_srq; - RdmaRmSRQ *srq; - PvrdmaRing *ring; - - srq = rdma_rm_get_srq(&dev->rdma_dev_res, cmd->srq_handle); - if (!srq) { - return -EINVAL; - } - - ring = (PvrdmaRing *)srq->opaque; - destroy_srq_ring(ring); - rdma_rm_dealloc_srq(&dev->rdma_dev_res, cmd->srq_handle); - - return 0; -} - -struct cmd_handler { - uint32_t cmd; - uint32_t ack; - int (*exec)(PVRDMADev *dev, union pvrdma_cmd_req *req, - union pvrdma_cmd_resp *rsp); -}; - -static struct cmd_handler cmd_handlers[] = { - {PVRDMA_CMD_QUERY_PORT, PVRDMA_CMD_QUERY_PORT_RESP, query_port}, - {PVRDMA_CMD_QUERY_PKEY, PVRDMA_CMD_QUERY_PKEY_RESP, query_pkey}, - {PVRDMA_CMD_CREATE_PD, PVRDMA_CMD_CREATE_PD_RESP, create_pd}, - {PVRDMA_CMD_DESTROY_PD, PVRDMA_CMD_DESTROY_PD_RESP_NOOP, destroy_pd}, - {PVRDMA_CMD_CREATE_MR, PVRDMA_CMD_CREATE_MR_RESP, create_mr}, - {PVRDMA_CMD_DESTROY_MR, PVRDMA_CMD_DESTROY_MR_RESP_NOOP, destroy_mr}, - {PVRDMA_CMD_CREATE_CQ, PVRDMA_CMD_CREATE_CQ_RESP, create_cq}, - {PVRDMA_CMD_RESIZE_CQ, PVRDMA_CMD_RESIZE_CQ_RESP, NULL}, - {PVRDMA_CMD_DESTROY_CQ, PVRDMA_CMD_DESTROY_CQ_RESP_NOOP, destroy_cq}, - {PVRDMA_CMD_CREATE_QP, PVRDMA_CMD_CREATE_QP_RESP, create_qp}, - {PVRDMA_CMD_MODIFY_QP, PVRDMA_CMD_MODIFY_QP_RESP, modify_qp}, - {PVRDMA_CMD_QUERY_QP, PVRDMA_CMD_QUERY_QP_RESP, query_qp}, - {PVRDMA_CMD_DESTROY_QP, PVRDMA_CMD_DESTROY_QP_RESP, destroy_qp}, - {PVRDMA_CMD_CREATE_UC, PVRDMA_CMD_CREATE_UC_RESP, create_uc}, - {PVRDMA_CMD_DESTROY_UC, PVRDMA_CMD_DESTROY_UC_RESP_NOOP, destroy_uc}, - {PVRDMA_CMD_CREATE_BIND, PVRDMA_CMD_CREATE_BIND_RESP_NOOP, create_bind}, - {PVRDMA_CMD_DESTROY_BIND, PVRDMA_CMD_DESTROY_BIND_RESP_NOOP, destroy_bind}, - {PVRDMA_CMD_CREATE_SRQ, PVRDMA_CMD_CREATE_SRQ_RESP, create_srq}, - {PVRDMA_CMD_QUERY_SRQ, PVRDMA_CMD_QUERY_SRQ_RESP, query_srq}, - {PVRDMA_CMD_MODIFY_SRQ, PVRDMA_CMD_MODIFY_SRQ_RESP, modify_srq}, - {PVRDMA_CMD_DESTROY_SRQ, PVRDMA_CMD_DESTROY_SRQ_RESP, destroy_srq}, -}; - -int pvrdma_exec_cmd(PVRDMADev *dev) -{ - int err = 0xFFFF; - DSRInfo *dsr_info; - - dsr_info = &dev->dsr_info; - - if (!dsr_info->dsr) { - /* Buggy or malicious guest driver */ - rdma_error_report("Exec command without dsr, req or rsp buffers"); - goto out; - } - - if (dsr_info->req->hdr.cmd >= sizeof(cmd_handlers) / - sizeof(struct cmd_handler)) { - rdma_error_report("Unsupported command"); - goto out; - } - - if (!cmd_handlers[dsr_info->req->hdr.cmd].exec) { - rdma_error_report("Unsupported command (not implemented yet)"); - goto out; - } - - err = cmd_handlers[dsr_info->req->hdr.cmd].exec(dev, dsr_info->req, - dsr_info->rsp); - dsr_info->rsp->hdr.response = dsr_info->req->hdr.response; - dsr_info->rsp->hdr.ack = cmd_handlers[dsr_info->req->hdr.cmd].ack; - dsr_info->rsp->hdr.err = err < 0 ? -err : 0; - - trace_pvrdma_exec_cmd(dsr_info->req->hdr.cmd, dsr_info->rsp->hdr.err); - - dev->stats.commands++; - -out: - set_reg_val(dev, PVRDMA_REG_ERR, err); - post_interrupt(dev, INTR_VEC_CMD_RING); - - return (err == 0) ? 0 : -EINVAL; -} diff --git a/hw/rdma/vmw/pvrdma_dev_ring.c b/hw/rdma/vmw/pvrdma_dev_ring.c deleted file mode 100644 index 30ce22a5be..0000000000 --- a/hw/rdma/vmw/pvrdma_dev_ring.c +++ /dev/null @@ -1,141 +0,0 @@ -/* - * QEMU paravirtual RDMA - Device rings - * - * Copyright (C) 2018 Oracle - * Copyright (C) 2018 Red Hat Inc - * - * Authors: - * Yuval Shaia <yuval.shaia(a)oracle.com> - * Marcel Apfelbaum <marcel(a)redhat.com> - * - * This work is licensed under the terms of the GNU GPL, version 2 or later. - * See the COPYING file in the top-level directory. - * - */ - -#include "qemu/osdep.h" -#include "hw/pci/pci.h" -#include "cpu.h" -#include "qemu/cutils.h" - -#include "trace.h" - -#include "../rdma_utils.h" -#include "pvrdma_dev_ring.h" - -int pvrdma_ring_init(PvrdmaRing *ring, const char *name, PCIDevice *dev, - PvrdmaRingState *ring_state, uint32_t max_elems, - size_t elem_sz, dma_addr_t *tbl, uint32_t npages) -{ - int i; - int rc = 0; - - pstrcpy(ring->name, MAX_RING_NAME_SZ, name); - ring->dev = dev; - ring->ring_state = ring_state; - ring->max_elems = max_elems; - ring->elem_sz = elem_sz; - /* TODO: Give a moment to think if we want to redo driver settings - qatomic_set(&ring->ring_state->prod_tail, 0); - qatomic_set(&ring->ring_state->cons_head, 0); - */ - ring->npages = npages; - ring->pages = g_new0(void *, npages); - - for (i = 0; i < npages; i++) { - if (!tbl[i]) { - rdma_error_report("npages=%d but tbl[%d] is NULL", npages, i); - continue; - } - - ring->pages[i] = rdma_pci_dma_map(dev, tbl[i], TARGET_PAGE_SIZE); - if (!ring->pages[i]) { - rc = -ENOMEM; - rdma_error_report("Failed to map to page %d in ring %s", i, name); - goto out_free; - } - memset(ring->pages[i], 0, TARGET_PAGE_SIZE); - } - - goto out; - -out_free: - while (i--) { - rdma_pci_dma_unmap(dev, ring->pages[i], TARGET_PAGE_SIZE); - } - g_free(ring->pages); - -out: - return rc; -} - -void *pvrdma_ring_next_elem_read(PvrdmaRing *ring) -{ - unsigned int idx, offset; - const uint32_t tail = qatomic_read(&ring->ring_state->prod_tail); - const uint32_t head = qatomic_read(&ring->ring_state->cons_head); - - if (tail & ~((ring->max_elems << 1) - 1) || - head & ~((ring->max_elems << 1) - 1) || - tail == head) { - trace_pvrdma_ring_next_elem_read_no_data(ring->name); - return NULL; - } - - idx = head & (ring->max_elems - 1); - offset = idx * ring->elem_sz; - return ring->pages[offset / TARGET_PAGE_SIZE] + (offset % TARGET_PAGE_SIZE); -} - -void pvrdma_ring_read_inc(PvrdmaRing *ring) -{ - uint32_t idx = qatomic_read(&ring->ring_state->cons_head); - - idx = (idx + 1) & ((ring->max_elems << 1) - 1); - qatomic_set(&ring->ring_state->cons_head, idx); -} - -void *pvrdma_ring_next_elem_write(PvrdmaRing *ring) -{ - unsigned int idx, offset; - const uint32_t tail = qatomic_read(&ring->ring_state->prod_tail); - const uint32_t head = qatomic_read(&ring->ring_state->cons_head); - - if (tail & ~((ring->max_elems << 1) - 1) || - head & ~((ring->max_elems << 1) - 1) || - tail == (head ^ ring->max_elems)) { - rdma_error_report("CQ is full"); - return NULL; - } - - idx = tail & (ring->max_elems - 1); - offset = idx * ring->elem_sz; - return ring->pages[offset / TARGET_PAGE_SIZE] + (offset % TARGET_PAGE_SIZE); -} - -void pvrdma_ring_write_inc(PvrdmaRing *ring) -{ - uint32_t idx = qatomic_read(&ring->ring_state->prod_tail); - - idx = (idx + 1) & ((ring->max_elems << 1) - 1); - qatomic_set(&ring->ring_state->prod_tail, idx); -} - -void pvrdma_ring_free(PvrdmaRing *ring) -{ - if (!ring) { - return; - } - - if (!ring->pages) { - return; - } - - while (ring->npages--) { - rdma_pci_dma_unmap(ring->dev, ring->pages[ring->npages], - TARGET_PAGE_SIZE); - } - - g_free(ring->pages); - ring->pages = NULL; -} diff --git a/hw/rdma/vmw/pvrdma_main.c b/hw/rdma/vmw/pvrdma_main.c deleted file mode 100644 index e735ff97eb..0000000000 --- a/hw/rdma/vmw/pvrdma_main.c +++ /dev/null @@ -1,735 +0,0 @@ -/* - * QEMU paravirtual RDMA - * - * Copyright (C) 2018 Oracle - * Copyright (C) 2018 Red Hat Inc - * - * Authors: - * Yuval Shaia <yuval.shaia(a)oracle.com> - * Marcel Apfelbaum <marcel(a)redhat.com> - * - * This work is licensed under the terms of the GNU GPL, version 2 or later. - * See the COPYING file in the top-level directory. - * - */ - -#include "qemu/osdep.h" -#include "qapi/error.h" -#include "qemu/module.h" -#include "hw/pci/pci.h" -#include "hw/pci/pci_ids.h" -#include "hw/pci/msi.h" -#include "hw/pci/msix.h" -#include "hw/qdev-properties.h" -#include "hw/qdev-properties-system.h" -#include "cpu.h" -#include "trace.h" -#include "monitor/monitor.h" -#include "hw/rdma/rdma.h" - -#include "../rdma_rm.h" -#include "../rdma_backend.h" -#include "../rdma_utils.h" - -#include <infiniband/verbs.h> -#include "pvrdma.h" -#include "standard-headers/rdma/vmw_pvrdma-abi.h" -#include "sysemu/runstate.h" -#include "standard-headers/drivers/infiniband/hw/vmw_pvrdma/pvrdma_dev_api.h" -#include "pvrdma_qp_ops.h" - -static Property pvrdma_dev_properties[] = { - DEFINE_PROP_STRING("netdev", PVRDMADev, backend_eth_device_name), - DEFINE_PROP_STRING("ibdev", PVRDMADev, backend_device_name), - DEFINE_PROP_UINT8("ibport", PVRDMADev, backend_port_num, 1), - DEFINE_PROP_UINT64("dev-caps-max-mr-size", PVRDMADev, dev_attr.max_mr_size, - MAX_MR_SIZE), - DEFINE_PROP_INT32("dev-caps-max-qp", PVRDMADev, dev_attr.max_qp, MAX_QP), - DEFINE_PROP_INT32("dev-caps-max-cq", PVRDMADev, dev_attr.max_cq, MAX_CQ), - DEFINE_PROP_INT32("dev-caps-max-mr", PVRDMADev, dev_attr.max_mr, MAX_MR), - DEFINE_PROP_INT32("dev-caps-max-pd", PVRDMADev, dev_attr.max_pd, MAX_PD), - DEFINE_PROP_INT32("dev-caps-qp-rd-atom", PVRDMADev, dev_attr.max_qp_rd_atom, - MAX_QP_RD_ATOM), - DEFINE_PROP_INT32("dev-caps-max-qp-init-rd-atom", PVRDMADev, - dev_attr.max_qp_init_rd_atom, MAX_QP_INIT_RD_ATOM), - DEFINE_PROP_INT32("dev-caps-max-ah", PVRDMADev, dev_attr.max_ah, MAX_AH), - DEFINE_PROP_INT32("dev-caps-max-srq", PVRDMADev, dev_attr.max_srq, MAX_SRQ), - DEFINE_PROP_CHR("mad-chardev", PVRDMADev, mad_chr), - DEFINE_PROP_END_OF_LIST(), -}; - -static void pvrdma_format_statistics(RdmaProvider *obj, GString *buf) -{ - PVRDMADev *dev = PVRDMA_DEV(obj); - PCIDevice *pdev = PCI_DEVICE(dev); - - g_string_append_printf(buf, "%s, %x.%x\n", - pdev->name, PCI_SLOT(pdev->devfn), - PCI_FUNC(pdev->devfn)); - g_string_append_printf(buf, "\tcommands : %" PRId64 "\n", - dev->stats.commands); - g_string_append_printf(buf, "\tregs_reads : %" PRId64 "\n", - dev->stats.regs_reads); - g_string_append_printf(buf, "\tregs_writes : %" PRId64 "\n", - dev->stats.regs_writes); - g_string_append_printf(buf, "\tuar_writes : %" PRId64 "\n", - dev->stats.uar_writes); - g_string_append_printf(buf, "\tinterrupts : %" PRId64 "\n", - dev->stats.interrupts); - rdma_format_device_counters(&dev->rdma_dev_res, buf); -} - -static void free_dev_ring(PCIDevice *pci_dev, PvrdmaRing *ring, - void *ring_state) -{ - pvrdma_ring_free(ring); - rdma_pci_dma_unmap(pci_dev, ring_state, TARGET_PAGE_SIZE); -} - -static int init_dev_ring(PvrdmaRing *ring, PvrdmaRingState **ring_state, - const char *name, PCIDevice *pci_dev, - dma_addr_t dir_addr, uint32_t num_pages) -{ - uint64_t *dir, *tbl; - int max_pages, rc = 0; - - if (!num_pages) { - rdma_error_report("Ring pages count must be strictly positive"); - return -EINVAL; - } - - /* - * Make sure we can satisfy the requested number of pages in a single - * TARGET_PAGE_SIZE sized page table (taking into account that first entry - * is reserved for ring-state) - */ - max_pages = TARGET_PAGE_SIZE / sizeof(dma_addr_t) - 1; - if (num_pages > max_pages) { - rdma_error_report("Maximum pages on a single directory must not exceed %d\n", - max_pages); - return -EINVAL; - } - - dir = rdma_pci_dma_map(pci_dev, dir_addr, TARGET_PAGE_SIZE); - if (!dir) { - rdma_error_report("Failed to map to page directory (ring %s)", name); - rc = -ENOMEM; - goto out; - } - - /* We support only one page table for a ring */ - tbl = rdma_pci_dma_map(pci_dev, dir[0], TARGET_PAGE_SIZE); - if (!tbl) { - rdma_error_report("Failed to map to page table (ring %s)", name); - rc = -ENOMEM; - goto out_free_dir; - } - - *ring_state = rdma_pci_dma_map(pci_dev, tbl[0], TARGET_PAGE_SIZE); - if (!*ring_state) { - rdma_error_report("Failed to map to ring state (ring %s)", name); - rc = -ENOMEM; - goto out_free_tbl; - } - /* RX ring is the second */ - (*ring_state)++; - rc = pvrdma_ring_init(ring, name, pci_dev, - (PvrdmaRingState *)*ring_state, - (num_pages - 1) * TARGET_PAGE_SIZE / - sizeof(struct pvrdma_cqne), - sizeof(struct pvrdma_cqne), - (dma_addr_t *)&tbl[1], (dma_addr_t)num_pages - 1); - if (rc) { - rc = -ENOMEM; - goto out_free_ring_state; - } - - goto out_free_tbl; - -out_free_ring_state: - rdma_pci_dma_unmap(pci_dev, *ring_state, TARGET_PAGE_SIZE); - -out_free_tbl: - rdma_pci_dma_unmap(pci_dev, tbl, TARGET_PAGE_SIZE); - -out_free_dir: - rdma_pci_dma_unmap(pci_dev, dir, TARGET_PAGE_SIZE); - -out: - return rc; -} - -static void free_dsr(PVRDMADev *dev) -{ - PCIDevice *pci_dev = PCI_DEVICE(dev); - - if (!dev->dsr_info.dsr) { - return; - } - - free_dev_ring(pci_dev, &dev->dsr_info.async, - dev->dsr_info.async_ring_state); - - free_dev_ring(pci_dev, &dev->dsr_info.cq, dev->dsr_info.cq_ring_state); - - rdma_pci_dma_unmap(pci_dev, dev->dsr_info.req, - sizeof(union pvrdma_cmd_req)); - - rdma_pci_dma_unmap(pci_dev, dev->dsr_info.rsp, - sizeof(union pvrdma_cmd_resp)); - - rdma_pci_dma_unmap(pci_dev, dev->dsr_info.dsr, - sizeof(struct pvrdma_device_shared_region)); - - dev->dsr_info.dsr = NULL; -} - -static int load_dsr(PVRDMADev *dev) -{ - int rc = 0; - PCIDevice *pci_dev = PCI_DEVICE(dev); - DSRInfo *dsr_info; - struct pvrdma_device_shared_region *dsr; - - free_dsr(dev); - - /* Map to DSR */ - dev->dsr_info.dsr = rdma_pci_dma_map(pci_dev, dev->dsr_info.dma, - sizeof(struct pvrdma_device_shared_region)); - if (!dev->dsr_info.dsr) { - rdma_error_report("Failed to map to DSR"); - rc = -ENOMEM; - goto out; - } - - /* Shortcuts */ - dsr_info = &dev->dsr_info; - dsr = dsr_info->dsr; - - /* Map to command slot */ - dsr_info->req = rdma_pci_dma_map(pci_dev, dsr->cmd_slot_dma, - sizeof(union pvrdma_cmd_req)); - if (!dsr_info->req) { - rdma_error_report("Failed to map to command slot address"); - rc = -ENOMEM; - goto out_free_dsr; - } - - /* Map to response slot */ - dsr_info->rsp = rdma_pci_dma_map(pci_dev, dsr->resp_slot_dma, - sizeof(union pvrdma_cmd_resp)); - if (!dsr_info->rsp) { - rdma_error_report("Failed to map to response slot address"); - rc = -ENOMEM; - goto out_free_req; - } - - /* Map to CQ notification ring */ - rc = init_dev_ring(&dsr_info->cq, &dsr_info->cq_ring_state, "dev_cq", - pci_dev, dsr->cq_ring_pages.pdir_dma, - dsr->cq_ring_pages.num_pages); - if (rc) { - rc = -ENOMEM; - goto out_free_rsp; - } - - /* Map to event notification ring */ - rc = init_dev_ring(&dsr_info->async, &dsr_info->async_ring_state, - "dev_async", pci_dev, dsr->async_ring_pages.pdir_dma, - dsr->async_ring_pages.num_pages); - if (rc) { - rc = -ENOMEM; - goto out_free_rsp; - } - - goto out; - -out_free_rsp: - rdma_pci_dma_unmap(pci_dev, dsr_info->rsp, sizeof(union pvrdma_cmd_resp)); - -out_free_req: - rdma_pci_dma_unmap(pci_dev, dsr_info->req, sizeof(union pvrdma_cmd_req)); - -out_free_dsr: - rdma_pci_dma_unmap(pci_dev, dsr_info->dsr, - sizeof(struct pvrdma_device_shared_region)); - dsr_info->dsr = NULL; - -out: - return rc; -} - -static void init_dsr_dev_caps(PVRDMADev *dev) -{ - struct pvrdma_device_shared_region *dsr; - - if (!dev->dsr_info.dsr) { - /* Buggy or malicious guest driver */ - rdma_error_report("Can't initialized DSR"); - return; - } - - dsr = dev->dsr_info.dsr; - dsr->caps.fw_ver = PVRDMA_FW_VERSION; - dsr->caps.mode = PVRDMA_DEVICE_MODE_ROCE; - dsr->caps.gid_types |= PVRDMA_GID_TYPE_FLAG_ROCE_V1; - dsr->caps.max_uar = RDMA_BAR2_UAR_SIZE; - dsr->caps.max_mr_size = dev->dev_attr.max_mr_size; - dsr->caps.max_qp = dev->dev_attr.max_qp; - dsr->caps.max_qp_wr = dev->dev_attr.max_qp_wr; - dsr->caps.max_sge = dev->dev_attr.max_sge; - dsr->caps.max_cq = dev->dev_attr.max_cq; - dsr->caps.max_cqe = dev->dev_attr.max_cqe; - dsr->caps.max_mr = dev->dev_attr.max_mr; - dsr->caps.max_pd = dev->dev_attr.max_pd; - dsr->caps.max_ah = dev->dev_attr.max_ah; - dsr->caps.max_srq = dev->dev_attr.max_srq; - dsr->caps.max_srq_wr = dev->dev_attr.max_srq_wr; - dsr->caps.max_srq_sge = dev->dev_attr.max_srq_sge; - dsr->caps.gid_tbl_len = MAX_GIDS; - dsr->caps.sys_image_guid = 0; - dsr->caps.node_guid = dev->node_guid; - dsr->caps.phys_port_cnt = MAX_PORTS; - dsr->caps.max_pkeys = MAX_PKEYS; -} - -static void uninit_msix(PCIDevice *pdev, int used_vectors) -{ - PVRDMADev *dev = PVRDMA_DEV(pdev); - int i; - - for (i = 0; i < used_vectors; i++) { - msix_vector_unuse(pdev, i); - } - - msix_uninit(pdev, &dev->msix, &dev->msix); -} - -static int init_msix(PCIDevice *pdev) -{ - PVRDMADev *dev = PVRDMA_DEV(pdev); - int i; - int rc; - - rc = msix_init(pdev, RDMA_MAX_INTRS, &dev->msix, RDMA_MSIX_BAR_IDX, - RDMA_MSIX_TABLE, &dev->msix, RDMA_MSIX_BAR_IDX, - RDMA_MSIX_PBA, 0, NULL); - - if (rc < 0) { - rdma_error_report("Failed to initialize MSI-X"); - return rc; - } - - for (i = 0; i < RDMA_MAX_INTRS; i++) { - msix_vector_use(PCI_DEVICE(dev), i); - } - - return 0; -} - -static void pvrdma_fini(PCIDevice *pdev) -{ - PVRDMADev *dev = PVRDMA_DEV(pdev); - - notifier_remove(&dev->shutdown_notifier); - - pvrdma_qp_ops_fini(); - - rdma_backend_stop(&dev->backend_dev); - - rdma_rm_fini(&dev->rdma_dev_res, &dev->backend_dev, - dev->backend_eth_device_name); - - rdma_backend_fini(&dev->backend_dev); - - free_dsr(dev); - - if (msix_enabled(pdev)) { - uninit_msix(pdev, RDMA_MAX_INTRS); - } - - rdma_info_report("Device %s %x.%x is down", pdev->name, - PCI_SLOT(pdev->devfn), PCI_FUNC(pdev->devfn)); -} - -static void pvrdma_stop(PVRDMADev *dev) -{ - rdma_backend_stop(&dev->backend_dev); -} - -static void pvrdma_start(PVRDMADev *dev) -{ - rdma_backend_start(&dev->backend_dev); -} - -static void activate_device(PVRDMADev *dev) -{ - pvrdma_start(dev); - set_reg_val(dev, PVRDMA_REG_ERR, 0); -} - -static int unquiesce_device(PVRDMADev *dev) -{ - return 0; -} - -static void reset_device(PVRDMADev *dev) -{ - pvrdma_stop(dev); -} - -static uint64_t pvrdma_regs_read(void *opaque, hwaddr addr, unsigned size) -{ - PVRDMADev *dev = opaque; - uint32_t val; - - dev->stats.regs_reads++; - - if (get_reg_val(dev, addr, &val)) { - rdma_error_report("Failed to read REG value from address 0x%x", - (uint32_t)addr); - return -EINVAL; - } - - trace_pvrdma_regs_read(addr, val); - - return val; -} - -static void pvrdma_regs_write(void *opaque, hwaddr addr, uint64_t val, - unsigned size) -{ - PVRDMADev *dev = opaque; - - dev->stats.regs_writes++; - - if (set_reg_val(dev, addr, val)) { - rdma_error_report("Failed to set REG value, addr=0x%"PRIx64 ", val=0x%"PRIx64, - addr, val); - return; - } - - switch (addr) { - case PVRDMA_REG_DSRLOW: - trace_pvrdma_regs_write(addr, val, "DSRLOW", ""); - dev->dsr_info.dma = val; - break; - case PVRDMA_REG_DSRHIGH: - trace_pvrdma_regs_write(addr, val, "DSRHIGH", ""); - dev->dsr_info.dma |= val << 32; - load_dsr(dev); - init_dsr_dev_caps(dev); - break; - case PVRDMA_REG_CTL: - switch (val) { - case PVRDMA_DEVICE_CTL_ACTIVATE: - trace_pvrdma_regs_write(addr, val, "CTL", "ACTIVATE"); - activate_device(dev); - break; - case PVRDMA_DEVICE_CTL_UNQUIESCE: - trace_pvrdma_regs_write(addr, val, "CTL", "UNQUIESCE"); - unquiesce_device(dev); - break; - case PVRDMA_DEVICE_CTL_RESET: - trace_pvrdma_regs_write(addr, val, "CTL", "URESET"); - reset_device(dev); - break; - } - break; - case PVRDMA_REG_IMR: - trace_pvrdma_regs_write(addr, val, "INTR_MASK", ""); - dev->interrupt_mask = val; - break; - case PVRDMA_REG_REQUEST: - if (val == 0) { - trace_pvrdma_regs_write(addr, val, "REQUEST", ""); - pvrdma_exec_cmd(dev); - } - break; - default: - break; - } -} - -static const MemoryRegionOps regs_ops = { - .read = pvrdma_regs_read, - .write = pvrdma_regs_write, - .endianness = DEVICE_LITTLE_ENDIAN, - .impl = { - .min_access_size = sizeof(uint32_t), - .max_access_size = sizeof(uint32_t), - }, -}; - -static uint64_t pvrdma_uar_read(void *opaque, hwaddr addr, unsigned size) -{ - return 0xffffffff; -} - -static void pvrdma_uar_write(void *opaque, hwaddr addr, uint64_t val, - unsigned size) -{ - PVRDMADev *dev = opaque; - - dev->stats.uar_writes++; - - switch (addr & 0xFFF) { /* Mask with 0xFFF as each UC gets page */ - case PVRDMA_UAR_QP_OFFSET: - if (val & PVRDMA_UAR_QP_SEND) { - trace_pvrdma_uar_write(addr, val, "QP", "SEND", - val & PVRDMA_UAR_HANDLE_MASK, 0); - pvrdma_qp_send(dev, val & PVRDMA_UAR_HANDLE_MASK); - } - if (val & PVRDMA_UAR_QP_RECV) { - trace_pvrdma_uar_write(addr, val, "QP", "RECV", - val & PVRDMA_UAR_HANDLE_MASK, 0); - pvrdma_qp_recv(dev, val & PVRDMA_UAR_HANDLE_MASK); - } - break; - case PVRDMA_UAR_CQ_OFFSET: - if (val & PVRDMA_UAR_CQ_ARM) { - trace_pvrdma_uar_write(addr, val, "CQ", "ARM", - val & PVRDMA_UAR_HANDLE_MASK, - !!(val & PVRDMA_UAR_CQ_ARM_SOL)); - rdma_rm_req_notify_cq(&dev->rdma_dev_res, - val & PVRDMA_UAR_HANDLE_MASK, - !!(val & PVRDMA_UAR_CQ_ARM_SOL)); - } - if (val & PVRDMA_UAR_CQ_ARM_SOL) { - trace_pvrdma_uar_write(addr, val, "CQ", "ARMSOL - not supported", 0, - 0); - } - if (val & PVRDMA_UAR_CQ_POLL) { - trace_pvrdma_uar_write(addr, val, "CQ", "POLL", - val & PVRDMA_UAR_HANDLE_MASK, 0); - pvrdma_cq_poll(&dev->rdma_dev_res, val & PVRDMA_UAR_HANDLE_MASK); - } - break; - case PVRDMA_UAR_SRQ_OFFSET: - if (val & PVRDMA_UAR_SRQ_RECV) { - trace_pvrdma_uar_write(addr, val, "QP", "SRQ", - val & PVRDMA_UAR_HANDLE_MASK, 0); - pvrdma_srq_recv(dev, val & PVRDMA_UAR_HANDLE_MASK); - } - break; - default: - rdma_error_report("Unsupported command, addr=0x%"PRIx64", val=0x%"PRIx64, - addr, val); - break; - } -} - -static const MemoryRegionOps uar_ops = { - .read = pvrdma_uar_read, - .write = pvrdma_uar_write, - .endianness = DEVICE_LITTLE_ENDIAN, - .impl = { - .min_access_size = sizeof(uint32_t), - .max_access_size = sizeof(uint32_t), - }, -}; - -static void init_pci_config(PCIDevice *pdev) -{ - pdev->config[PCI_INTERRUPT_PIN] = 1; -} - -static void init_bars(PCIDevice *pdev) -{ - PVRDMADev *dev = PVRDMA_DEV(pdev); - - /* BAR 0 - MSI-X */ - memory_region_init(&dev->msix, OBJECT(dev), "pvrdma-msix", - RDMA_BAR0_MSIX_SIZE); - pci_register_bar(pdev, RDMA_MSIX_BAR_IDX, PCI_BASE_ADDRESS_SPACE_MEMORY, - &dev->msix); - - /* BAR 1 - Registers */ - memset(&dev->regs_data, 0, sizeof(dev->regs_data)); - memory_region_init_io(&dev->regs, OBJECT(dev), &regs_ops, dev, - "pvrdma-regs", sizeof(dev->regs_data)); - pci_register_bar(pdev, RDMA_REG_BAR_IDX, PCI_BASE_ADDRESS_SPACE_MEMORY, - &dev->regs); - - /* BAR 2 - UAR */ - memset(&dev->uar_data, 0, sizeof(dev->uar_data)); - memory_region_init_io(&dev->uar, OBJECT(dev), &uar_ops, dev, "rdma-uar", - sizeof(dev->uar_data)); - pci_register_bar(pdev, RDMA_UAR_BAR_IDX, PCI_BASE_ADDRESS_SPACE_MEMORY, - &dev->uar); -} - -static void init_regs(PCIDevice *pdev) -{ - PVRDMADev *dev = PVRDMA_DEV(pdev); - - set_reg_val(dev, PVRDMA_REG_VERSION, PVRDMA_HW_VERSION); - set_reg_val(dev, PVRDMA_REG_ERR, 0xFFFF); -} - -static void init_dev_caps(PVRDMADev *dev) -{ - size_t pg_tbl_bytes = TARGET_PAGE_SIZE * - (TARGET_PAGE_SIZE / sizeof(uint64_t)); - size_t wr_sz = MAX(sizeof(struct pvrdma_sq_wqe_hdr), - sizeof(struct pvrdma_rq_wqe_hdr)); - - dev->dev_attr.max_qp_wr = pg_tbl_bytes / - (wr_sz + sizeof(struct pvrdma_sge) * - dev->dev_attr.max_sge) - TARGET_PAGE_SIZE; - /* First page is ring state ^^^^ */ - - dev->dev_attr.max_cqe = pg_tbl_bytes / sizeof(struct pvrdma_cqe) - - TARGET_PAGE_SIZE; /* First page is ring state */ - - dev->dev_attr.max_srq_wr = pg_tbl_bytes / - ((sizeof(struct pvrdma_rq_wqe_hdr) + - sizeof(struct pvrdma_sge)) * - dev->dev_attr.max_sge) - TARGET_PAGE_SIZE; -} - -static int pvrdma_check_ram_shared(Object *obj, void *opaque) -{ - bool *shared = opaque; - - if (object_dynamic_cast(obj, "memory-backend-ram")) { - *shared = object_property_get_bool(obj, "share", NULL); - } - - return 0; -} - -static void pvrdma_shutdown_notifier(Notifier *n, void *opaque) -{ - PVRDMADev *dev = container_of(n, PVRDMADev, shutdown_notifier); - PCIDevice *pci_dev = PCI_DEVICE(dev); - - pvrdma_fini(pci_dev); -} - -static void pvrdma_realize(PCIDevice *pdev, Error **errp) -{ - int rc = 0; - PVRDMADev *dev = PVRDMA_DEV(pdev); - Object *memdev_root; - bool ram_shared = false; - PCIDevice *func0; - - warn_report_once("pvrdma is deprecated and will be removed in a future release"); - - rdma_info_report("Initializing device %s %x.%x", pdev->name, - PCI_SLOT(pdev->devfn), PCI_FUNC(pdev->devfn)); - - if (TARGET_PAGE_SIZE != qemu_real_host_page_size()) { - error_setg(errp, "Target page size must be the same as host page size"); - return; - } - - func0 = pci_get_function_0(pdev); - /* Break if not vmxnet3 device in slot 0 */ - if (strcmp(object_get_typename(OBJECT(func0)), TYPE_VMXNET3)) { - error_setg(errp, "Device on %x.0 must be %s", PCI_SLOT(pdev->devfn), - TYPE_VMXNET3); - return; - } - dev->func0 = VMXNET3(func0); - - addrconf_addr_eui48((unsigned char *)&dev->node_guid, - (const char *)&dev->func0->conf.macaddr.a); - - memdev_root = object_resolve_path("/objects", NULL); - if (memdev_root) { - object_child_foreach(memdev_root, pvrdma_check_ram_shared, &ram_shared); - } - if (!ram_shared) { - error_setg(errp, "Only shared memory backed ram is supported"); - return; - } - - dev->dsr_info.dsr = NULL; - - init_pci_config(pdev); - - init_bars(pdev); - - init_regs(pdev); - - rc = init_msix(pdev); - if (rc) { - goto out; - } - - rc = rdma_backend_init(&dev->backend_dev, pdev, &dev->rdma_dev_res, - dev->backend_device_name, dev->backend_port_num, - &dev->dev_attr, &dev->mad_chr); - if (rc) { - goto out; - } - - init_dev_caps(dev); - - rc = rdma_rm_init(&dev->rdma_dev_res, &dev->dev_attr); - if (rc) { - goto out; - } - - rc = pvrdma_qp_ops_init(); - if (rc) { - goto out; - } - - memset(&dev->stats, 0, sizeof(dev->stats)); - - dev->shutdown_notifier.notify = pvrdma_shutdown_notifier; - qemu_register_shutdown_notifier(&dev->shutdown_notifier); - -#ifdef LEGACY_RDMA_REG_MR - rdma_info_report("Using legacy reg_mr"); -#else - rdma_info_report("Using iova reg_mr"); -#endif - -out: - if (rc) { - pvrdma_fini(pdev); - error_append_hint(errp, "Device failed to load\n"); - } -} - -static void pvrdma_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - PCIDeviceClass *k = PCI_DEVICE_CLASS(klass); - RdmaProviderClass *ir = RDMA_PROVIDER_CLASS(klass); - - k->realize = pvrdma_realize; - k->vendor_id = PCI_VENDOR_ID_VMWARE; - k->device_id = PCI_DEVICE_ID_VMWARE_PVRDMA; - k->revision = 0x00; - k->class_id = PCI_CLASS_NETWORK_OTHER; - - dc->desc = "RDMA Device"; - device_class_set_props(dc, pvrdma_dev_properties); - set_bit(DEVICE_CATEGORY_NETWORK, dc->categories); - - ir->format_statistics = pvrdma_format_statistics; -} - -static const TypeInfo pvrdma_info = { - .name = PVRDMA_HW_NAME, - .parent = TYPE_PCI_DEVICE, - .instance_size = sizeof(PVRDMADev), - .class_init = pvrdma_class_init, - .interfaces = (InterfaceInfo[]) { - { INTERFACE_CONVENTIONAL_PCI_DEVICE }, - { INTERFACE_RDMA_PROVIDER }, - { } - } -}; - -static void register_types(void) -{ - type_register_static(&pvrdma_info); -} - -type_init(register_types) diff --git a/hw/rdma/vmw/pvrdma_qp_ops.c b/hw/rdma/vmw/pvrdma_qp_ops.c deleted file mode 100644 index c30c8344f6..0000000000 --- a/hw/rdma/vmw/pvrdma_qp_ops.c +++ /dev/null @@ -1,298 +0,0 @@ -/* - * QEMU paravirtual RDMA - QP implementation - * - * Copyright (C) 2018 Oracle - * Copyright (C) 2018 Red Hat Inc - * - * Authors: - * Yuval Shaia <yuval.shaia(a)oracle.com> - * Marcel Apfelbaum <marcel(a)redhat.com> - * - * This work is licensed under the terms of the GNU GPL, version 2 or later. - * See the COPYING file in the top-level directory. - * - */ - -#include "qemu/osdep.h" - -#include "../rdma_utils.h" -#include "../rdma_rm.h" -#include "../rdma_backend.h" - -#include "trace.h" - -#include "pvrdma.h" -#include "standard-headers/rdma/vmw_pvrdma-abi.h" -#include "pvrdma_qp_ops.h" - -typedef struct CompHandlerCtx { - PVRDMADev *dev; - uint32_t cq_handle; - struct pvrdma_cqe cqe; -} CompHandlerCtx; - -/* Send Queue WQE */ -typedef struct PvrdmaSqWqe { - struct pvrdma_sq_wqe_hdr hdr; - struct pvrdma_sge sge[]; -} PvrdmaSqWqe; - -/* Recv Queue WQE */ -typedef struct PvrdmaRqWqe { - struct pvrdma_rq_wqe_hdr hdr; - struct pvrdma_sge sge[]; -} PvrdmaRqWqe; - -/* - * 1. Put CQE on send CQ ring - * 2. Put CQ number on dsr completion ring - * 3. Interrupt host - */ -static int pvrdma_post_cqe(PVRDMADev *dev, uint32_t cq_handle, - struct pvrdma_cqe *cqe, struct ibv_wc *wc) -{ - struct pvrdma_cqe *cqe1; - struct pvrdma_cqne *cqne; - PvrdmaRing *ring; - RdmaRmCQ *cq = rdma_rm_get_cq(&dev->rdma_dev_res, cq_handle); - - if (unlikely(!cq)) { - return -EINVAL; - } - - ring = (PvrdmaRing *)cq->opaque; - - /* Step #1: Put CQE on CQ ring */ - cqe1 = pvrdma_ring_next_elem_write(ring); - if (unlikely(!cqe1)) { - return -EINVAL; - } - - memset(cqe1, 0, sizeof(*cqe1)); - cqe1->wr_id = cqe->wr_id; - cqe1->qp = cqe->qp ? cqe->qp : wc->qp_num; - cqe1->opcode = cqe->opcode; - cqe1->status = wc->status; - cqe1->byte_len = wc->byte_len; - cqe1->src_qp = wc->src_qp; - cqe1->wc_flags = wc->wc_flags; - cqe1->vendor_err = wc->vendor_err; - - trace_pvrdma_post_cqe(cq_handle, cq->notify, cqe1->wr_id, cqe1->qp, - cqe1->opcode, cqe1->status, cqe1->byte_len, - cqe1->src_qp, cqe1->wc_flags, cqe1->vendor_err); - - pvrdma_ring_write_inc(ring); - - /* Step #2: Put CQ number on dsr completion ring */ - cqne = pvrdma_ring_next_elem_write(&dev->dsr_info.cq); - if (unlikely(!cqne)) { - return -EINVAL; - } - - cqne->info = cq_handle; - pvrdma_ring_write_inc(&dev->dsr_info.cq); - - if (cq->notify != CNT_CLEAR) { - if (cq->notify == CNT_ARM) { - cq->notify = CNT_CLEAR; - } - post_interrupt(dev, INTR_VEC_CMD_COMPLETION_Q); - } - - return 0; -} - -static void pvrdma_qp_ops_comp_handler(void *ctx, struct ibv_wc *wc) -{ - CompHandlerCtx *comp_ctx = (CompHandlerCtx *)ctx; - - pvrdma_post_cqe(comp_ctx->dev, comp_ctx->cq_handle, &comp_ctx->cqe, wc); - - g_free(ctx); -} - -static void complete_with_error(uint32_t vendor_err, void *ctx) -{ - struct ibv_wc wc = {}; - - wc.status = IBV_WC_GENERAL_ERR; - wc.vendor_err = vendor_err; - - pvrdma_qp_ops_comp_handler(ctx, &wc); -} - -void pvrdma_qp_ops_fini(void) -{ - rdma_backend_unregister_comp_handler(); -} - -int pvrdma_qp_ops_init(void) -{ - rdma_backend_register_comp_handler(pvrdma_qp_ops_comp_handler); - - return 0; -} - -void pvrdma_qp_send(PVRDMADev *dev, uint32_t qp_handle) -{ - RdmaRmQP *qp; - PvrdmaSqWqe *wqe; - PvrdmaRing *ring; - int sgid_idx; - union ibv_gid *sgid; - - qp = rdma_rm_get_qp(&dev->rdma_dev_res, qp_handle); - if (unlikely(!qp)) { - return; - } - - ring = (PvrdmaRing *)qp->opaque; - - wqe = pvrdma_ring_next_elem_read(ring); - while (wqe) { - CompHandlerCtx *comp_ctx; - - /* Prepare CQE */ - comp_ctx = g_new(CompHandlerCtx, 1); - comp_ctx->dev = dev; - comp_ctx->cq_handle = qp->send_cq_handle; - comp_ctx->cqe.wr_id = wqe->hdr.wr_id; - comp_ctx->cqe.qp = qp_handle; - comp_ctx->cqe.opcode = IBV_WC_SEND; - - sgid = rdma_rm_get_gid(&dev->rdma_dev_res, wqe->hdr.wr.ud.av.gid_index); - if (!sgid) { - rdma_error_report("Failed to get gid for idx %d", - wqe->hdr.wr.ud.av.gid_index); - complete_with_error(VENDOR_ERR_INV_GID_IDX, comp_ctx); - continue; - } - - sgid_idx = rdma_rm_get_backend_gid_index(&dev->rdma_dev_res, - &dev->backend_dev, - wqe->hdr.wr.ud.av.gid_index); - if (sgid_idx <= 0) { - rdma_error_report("Failed to get bk sgid_idx for sgid_idx %d", - wqe->hdr.wr.ud.av.gid_index); - complete_with_error(VENDOR_ERR_INV_GID_IDX, comp_ctx); - continue; - } - - if (wqe->hdr.num_sge > dev->dev_attr.max_sge) { - rdma_error_report("Invalid num_sge=%d (max %d)", wqe->hdr.num_sge, - dev->dev_attr.max_sge); - complete_with_error(VENDOR_ERR_INV_NUM_SGE, comp_ctx); - continue; - } - - rdma_backend_post_send(&dev->backend_dev, &qp->backend_qp, qp->qp_type, - (struct ibv_sge *)&wqe->sge[0], wqe->hdr.num_sge, - sgid_idx, sgid, - (union ibv_gid *)wqe->hdr.wr.ud.av.dgid, - wqe->hdr.wr.ud.remote_qpn, - wqe->hdr.wr.ud.remote_qkey, comp_ctx); - - pvrdma_ring_read_inc(ring); - - wqe = pvrdma_ring_next_elem_read(ring); - } -} - -void pvrdma_qp_recv(PVRDMADev *dev, uint32_t qp_handle) -{ - RdmaRmQP *qp; - PvrdmaRqWqe *wqe; - PvrdmaRing *ring; - - qp = rdma_rm_get_qp(&dev->rdma_dev_res, qp_handle); - if (unlikely(!qp)) { - return; - } - - ring = &((PvrdmaRing *)qp->opaque)[1]; - - wqe = pvrdma_ring_next_elem_read(ring); - while (wqe) { - CompHandlerCtx *comp_ctx; - - /* Prepare CQE */ - comp_ctx = g_new(CompHandlerCtx, 1); - comp_ctx->dev = dev; - comp_ctx->cq_handle = qp->recv_cq_handle; - comp_ctx->cqe.wr_id = wqe->hdr.wr_id; - comp_ctx->cqe.qp = qp_handle; - comp_ctx->cqe.opcode = IBV_WC_RECV; - - if (wqe->hdr.num_sge > dev->dev_attr.max_sge) { - rdma_error_report("Invalid num_sge=%d (max %d)", wqe->hdr.num_sge, - dev->dev_attr.max_sge); - complete_with_error(VENDOR_ERR_INV_NUM_SGE, comp_ctx); - continue; - } - - rdma_backend_post_recv(&dev->backend_dev, &qp->backend_qp, qp->qp_type, - (struct ibv_sge *)&wqe->sge[0], wqe->hdr.num_sge, - comp_ctx); - - pvrdma_ring_read_inc(ring); - - wqe = pvrdma_ring_next_elem_read(ring); - } -} - -void pvrdma_srq_recv(PVRDMADev *dev, uint32_t srq_handle) -{ - RdmaRmSRQ *srq; - PvrdmaRqWqe *wqe; - PvrdmaRing *ring; - - srq = rdma_rm_get_srq(&dev->rdma_dev_res, srq_handle); - if (unlikely(!srq)) { - return; - } - - ring = (PvrdmaRing *)srq->opaque; - - wqe = pvrdma_ring_next_elem_read(ring); - while (wqe) { - CompHandlerCtx *comp_ctx; - - /* Prepare CQE */ - comp_ctx = g_new(CompHandlerCtx, 1); - comp_ctx->dev = dev; - comp_ctx->cq_handle = srq->recv_cq_handle; - comp_ctx->cqe.wr_id = wqe->hdr.wr_id; - comp_ctx->cqe.qp = 0; - comp_ctx->cqe.opcode = IBV_WC_RECV; - - if (wqe->hdr.num_sge > dev->dev_attr.max_sge) { - rdma_error_report("Invalid num_sge=%d (max %d)", wqe->hdr.num_sge, - dev->dev_attr.max_sge); - complete_with_error(VENDOR_ERR_INV_NUM_SGE, comp_ctx); - continue; - } - - rdma_backend_post_srq_recv(&dev->backend_dev, &srq->backend_srq, - (struct ibv_sge *)&wqe->sge[0], - wqe->hdr.num_sge, - comp_ctx); - - pvrdma_ring_read_inc(ring); - - wqe = pvrdma_ring_next_elem_read(ring); - } - -} - -void pvrdma_cq_poll(RdmaDeviceResources *dev_res, uint32_t cq_handle) -{ - RdmaRmCQ *cq; - - cq = rdma_rm_get_cq(dev_res, cq_handle); - if (!cq) { - return; - } - - rdma_backend_poll_cq(dev_res, &cq->backend_cq); -} diff --git a/migration/migration-stats.c b/migration/migration-stats.c index f690b98a03..9bc8d7018f 100644 --- a/migration/migration-stats.c +++ b/migration/migration-stats.c @@ -62,9 +62,8 @@ void migration_rate_reset(void) uint64_t migration_transferred_bytes(void) { uint64_t multifd = stat64_get(&mig_stats.multifd_bytes); - uint64_t rdma = stat64_get(&mig_stats.rdma_bytes); uint64_t qemu_file = stat64_get(&mig_stats.qemu_file_transferred); - trace_migration_transferred_bytes(qemu_file, multifd, rdma); - return qemu_file + multifd + rdma; + trace_migration_transferred_bytes(qemu_file, multifd); + return qemu_file + multifd; } diff --git a/migration/migration.c b/migration/migration.c index 9fe8fd2afd..8e17914c8b 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -25,7 +25,6 @@ #include "sysemu/runstate.h" #include "sysemu/sysemu.h" #include "sysemu/cpu-throttle.h" -#include "rdma.h" #include "ram.h" #include "ram-compress.h" #include "migration/global_state.h" @@ -545,7 +544,6 @@ bool migrate_uri_parse(const char *uri, MigrationChannel **channel, { g_autoptr(MigrationChannel) val = g_new0(MigrationChannel, 1); g_autoptr(MigrationAddress) addr = g_new0(MigrationAddress, 1); - InetSocketAddress *isock = &addr->u.rdma; strList **tail = &addr->u.exec.args; if (strstart(uri, "exec:", NULL)) { @@ -558,12 +556,6 @@ bool migrate_uri_parse(const char *uri, MigrationChannel **channel, QAPI_LIST_APPEND(tail, g_strdup("-c")); #endif QAPI_LIST_APPEND(tail, g_strdup(uri + strlen("exec:"))); - } else if (strstart(uri, "rdma:", NULL)) { - if (inet_parse(isock, uri + strlen("rdma:"), errp)) { - qapi_free_InetSocketAddress(isock); - return false; - } - addr->transport = MIGRATION_ADDRESS_TYPE_RDMA; } else if (strstart(uri, "tcp:", NULL) || strstart(uri, "unix:", NULL) || strstart(uri, "vsock:", NULL) || @@ -645,22 +637,6 @@ static void qemu_start_incoming_migration(const char *uri, bool has_channels, } else if (saddr->type == SOCKET_ADDRESS_TYPE_FD) { fd_start_incoming_migration(saddr->u.fd.str, errp); } -#ifdef CONFIG_RDMA - } else if (addr->transport == MIGRATION_ADDRESS_TYPE_RDMA) { - if (migrate_compress()) { - error_setg(errp, "RDMA and compression can't be used together"); - return; - } - if (migrate_xbzrle()) { - error_setg(errp, "RDMA and XBZRLE can't be used together"); - return; - } - if (migrate_multifd()) { - error_setg(errp, "RDMA and multifd can't be used together"); - return; - } - rdma_start_incoming_migration(&addr->u.rdma, errp); -#endif } else if (addr->transport == MIGRATION_ADDRESS_TYPE_EXEC) { exec_start_incoming_migration(addr->u.exec.args, errp); } else if (addr->transport == MIGRATION_ADDRESS_TYPE_FILE) { @@ -751,9 +727,7 @@ process_incoming_migration_co(void *opaque) migrate_set_state(&mis->state, MIGRATION_STATUS_SETUP, MIGRATION_STATUS_ACTIVE); - mis->loadvm_co = qemu_coroutine_self(); ret = qemu_loadvm_state(mis->from_src_file); - mis->loadvm_co = NULL; trace_vmstate_downtime_checkpoint("dst-precopy-loadvm-completed"); @@ -1679,7 +1653,6 @@ int migrate_init(MigrationState *s, Error **errp) s->iteration_initial_bytes = 0; s->threshold_size = 0; s->switchover_acked = false; - s->rdma_migration = false; /* * set mig_stats memory to zero for a new migration */ @@ -2100,10 +2073,6 @@ void qmp_migrate(const char *uri, bool has_channels, } else if (saddr->type == SOCKET_ADDRESS_TYPE_FD) { fd_start_outgoing_migration(s, saddr->u.fd.str, &local_err); } -#ifdef CONFIG_RDMA - } else if (addr->transport == MIGRATION_ADDRESS_TYPE_RDMA) { - rdma_start_outgoing_migration(s, &addr->u.rdma, &local_err); -#endif } else if (addr->transport == MIGRATION_ADDRESS_TYPE_EXEC) { exec_start_outgoing_migration(s, addr->u.exec.args, &local_err); } else if (addr->transport == MIGRATION_ADDRESS_TYPE_FILE) { diff --git a/migration/options.c b/migration/options.c index bfd7753b69..02fc0b9ae8 100644 --- a/migration/options.c +++ b/migration/options.c @@ -185,7 +185,6 @@ Property migration_properties[] = { /* Migration capabilities */ DEFINE_PROP_MIG_CAP("x-xbzrle", MIGRATION_CAPABILITY_XBZRLE), - DEFINE_PROP_MIG_CAP("x-rdma-pin-all", MIGRATION_CAPABILITY_RDMA_PIN_ALL), DEFINE_PROP_MIG_CAP("x-auto-converge", MIGRATION_CAPABILITY_AUTO_CONVERGE), DEFINE_PROP_MIG_CAP("x-zero-blocks", MIGRATION_CAPABILITY_ZERO_BLOCKS), DEFINE_PROP_MIG_CAP("x-compress", MIGRATION_CAPABILITY_COMPRESS), @@ -323,13 +322,6 @@ bool migrate_postcopy_ram(void) return s->capabilities[MIGRATION_CAPABILITY_POSTCOPY_RAM]; } -bool migrate_rdma_pin_all(void) -{ - MigrationState *s = migrate_get_current(); - - return s->capabilities[MIGRATION_CAPABILITY_RDMA_PIN_ALL]; -} - bool migrate_release_ram(void) { MigrationState *s = migrate_get_current(); @@ -393,13 +385,6 @@ bool migrate_postcopy(void) return migrate_postcopy_ram() || migrate_dirty_bitmaps(); } -bool migrate_rdma(void) -{ - MigrationState *s = migrate_get_current(); - - return s->rdma_migration; -} - bool migrate_tls(void) { MigrationState *s = migrate_get_current(); @@ -458,7 +443,6 @@ INITIALIZE_MIGRATE_CAPS_SET(check_caps_background_snapshot, MIGRATION_CAPABILITY_PAUSE_BEFORE_SWITCHOVER, MIGRATION_CAPABILITY_AUTO_CONVERGE, MIGRATION_CAPABILITY_RELEASE_RAM, - MIGRATION_CAPABILITY_RDMA_PIN_ALL, MIGRATION_CAPABILITY_COMPRESS, MIGRATION_CAPABILITY_XBZRLE, MIGRATION_CAPABILITY_X_COLO, diff --git a/migration/qemu-file.c b/migration/qemu-file.c index a10882d47f..ad2efb332e 100644 --- a/migration/qemu-file.c +++ b/migration/qemu-file.c @@ -32,7 +32,6 @@ #include "trace.h" #include "options.h" #include "qapi/error.h" -#include "rdma.h" #include "io/channel-file.h" #define IO_BUF_SIZE 32768 diff --git a/migration/ram.c b/migration/ram.c index 8deb84984f..c81c8a7cff 100644 --- a/migration/ram.c +++ b/migration/ram.c @@ -59,7 +59,6 @@ #include "qemu/iov.h" #include "multifd.h" #include "sysemu/runstate.h" -#include "rdma.h" #include "options.h" #include "sysemu/dirtylimit.h" #include "sysemu/kvm.h" @@ -89,7 +88,7 @@ #define RAM_SAVE_FLAG_EOS 0x10 #define RAM_SAVE_FLAG_CONTINUE 0x20 #define RAM_SAVE_FLAG_XBZRLE 0x40 -/* 0x80 is reserved in rdma.h for RAM_SAVE_FLAG_HOOK */ +#define RAM_SAVE_FLAG_HOOK 0x80 /* was reserved by RDMA */ #define RAM_SAVE_FLAG_COMPRESS_PAGE 0x100 #define RAM_SAVE_FLAG_MULTIFD_FLUSH 0x200 /* We can't use any flag that is bigger than 0x200 */ @@ -1175,32 +1174,6 @@ static int save_zero_page(RAMState *rs, PageSearchStatus *pss, return len; } -/* - * @pages: the number of pages written by the control path, - * < 0 - error - * > 0 - number of pages written - * - * Return true if the pages has been saved, otherwise false is returned. - */ -static bool control_save_page(PageSearchStatus *pss, - ram_addr_t offset, int *pages) -{ - int ret; - - ret = rdma_control_save_page(pss->pss_channel, pss->block->offset, offset, - TARGET_PAGE_SIZE); - if (ret == RAM_SAVE_CONTROL_NOT_SUPP) { - return false; - } - - if (ret == RAM_SAVE_CONTROL_DELAYED) { - *pages = 1; - return true; - } - *pages = ret; - return true; -} - /* * directly send the page to the stream * @@ -2080,11 +2053,6 @@ static bool save_compress_page(RAMState *rs, PageSearchStatus *pss, static int ram_save_target_page_legacy(RAMState *rs, PageSearchStatus *pss) { ram_addr_t offset = ((ram_addr_t)pss->page) << TARGET_PAGE_BITS; - int res; - - if (control_save_page(pss, offset, &res)) { - return res; - } if (save_compress_page(rs, pss, offset)) { return 1; @@ -3114,18 +3082,6 @@ static int ram_save_setup(QEMUFile *f, void *opaque) } } - ret = rdma_registration_start(f, RAM_CONTROL_SETUP); - if (ret < 0) { - qemu_file_set_error(f, ret); - return ret; - } - - ret = rdma_registration_stop(f, RAM_CONTROL_SETUP); - if (ret < 0) { - qemu_file_set_error(f, ret); - return ret; - } - migration_ops = g_malloc0(sizeof(MigrationOps)); if (migrate_multifd()) { @@ -3221,12 +3177,6 @@ static int ram_save_iterate(QEMUFile *f, void *opaque) /* Read version before ram_list.blocks */ smp_rmb(); - ret = rdma_registration_start(f, RAM_CONTROL_ROUND); - if (ret < 0) { - qemu_file_set_error(f, ret); - goto out; - } - t0 = qemu_clock_get_ns(QEMU_CLOCK_REALTIME); i = 0; while ((ret = migration_rate_exceeded(f)) == 0 || @@ -3278,15 +3228,6 @@ static int ram_save_iterate(QEMUFile *f, void *opaque) } } - /* - * Must occur before EOS (or any QEMUFile operation) - * because of RDMA protocol. - */ - ret = rdma_registration_stop(f, RAM_CONTROL_ROUND); - if (ret < 0) { - qemu_file_set_error(f, ret); - } - out: if (ret >= 0 && migration_is_setup_or_active()) { @@ -3332,12 +3273,6 @@ static int ram_save_complete(QEMUFile *f, void *opaque) migration_bitmap_sync_precopy(rs, true); } - ret = rdma_registration_start(f, RAM_CONTROL_FINISH); - if (ret < 0) { - qemu_file_set_error(f, ret); - return ret; - } - /* try transferring iterative blocks of memory */ /* flush all remaining blocks regardless of rate limiting */ @@ -3358,12 +3293,6 @@ static int ram_save_complete(QEMUFile *f, void *opaque) qemu_mutex_unlock(&rs->bitmap_mutex); compress_flush_data(); - - ret = rdma_registration_stop(f, RAM_CONTROL_FINISH); - if (ret < 0) { - qemu_file_set_error(f, ret); - return ret; - } } ret = multifd_send_sync_main(); @@ -3576,8 +3505,7 @@ static inline void *colo_cache_from_block_offset(RAMBlock *block, /** * ram_handle_zero: handle the zero page case * - * If a page (or a whole RDMA chunk) has been - * determined to be zero, then zap it. + * If a page has been determined to be zero, then zap it. * * @host: host address for the zero page * @ch: what the page is filled from. We only support zero @@ -4161,10 +4089,6 @@ static int parse_ramblock(QEMUFile *f, RAMBlock *block, ram_addr_t length) return -EINVAL; } } - ret = rdma_block_notification_handle(f, block->idstr); - if (ret < 0) { - qemu_file_set_error(f, ret); - } return ret; } @@ -4363,12 +4287,6 @@ static int ram_load_precopy(QEMUFile *f) multifd_recv_sync_main(); } break; - case RAM_SAVE_FLAG_HOOK: - ret = rdma_registration_handle(f); - if (ret < 0) { - qemu_file_set_error(f, ret); - } - break; default: error_report("Unknown combination of migration flags: 0x%x", flags); ret = -EINVAL; diff --git a/migration/rdma.c b/migration/rdma.c deleted file mode 100644 index 855753c671..0000000000 --- a/migration/rdma.c +++ /dev/null @@ -1,4184 +0,0 @@ -/* - * RDMA protocol and interfaces - * - * Copyright IBM, Corp. 2010-2013 - * Copyright Red Hat, Inc. 2015-2016 - * - * Authors: - * Michael R. Hines <mrhines(a)us.ibm.com> - * Jiuxing Liu <jl(a)us.ibm.com> - * Daniel P. Berrange <berrange(a)redhat.com> - * - * This work is licensed under the terms of the GNU GPL, version 2 or - * later. See the COPYING file in the top-level directory. - * - */ - -#include "qemu/osdep.h" -#include "qapi/error.h" -#include "qemu/cutils.h" -#include "exec/target_page.h" -#include "rdma.h" -#include "migration.h" -#include "migration-stats.h" -#include "qemu-file.h" -#include "ram.h" -#include "qemu/error-report.h" -#include "qemu/main-loop.h" -#include "qemu/module.h" -#include "qemu/rcu.h" -#include "qemu/sockets.h" -#include "qemu/bitmap.h" -#include "qemu/coroutine.h" -#include "exec/memory.h" -#include <sys/socket.h> -#include <netdb.h> -#include <arpa/inet.h> -#include <rdma/rdma_cma.h> -#include "trace.h" -#include "qom/object.h" -#include "options.h" -#include <poll.h> - -#define RDMA_RESOLVE_TIMEOUT_MS 10000 - -/* Do not merge data if larger than this. */ -#define RDMA_MERGE_MAX (2 * 1024 * 1024) -#define RDMA_SIGNALED_SEND_MAX (RDMA_MERGE_MAX / 4096) - -#define RDMA_REG_CHUNK_SHIFT 20 /* 1 MB */ - -/* - * This is only for non-live state being migrated. - * Instead of RDMA_WRITE messages, we use RDMA_SEND - * messages for that state, which requires a different - * delivery design than main memory. - */ -#define RDMA_SEND_INCREMENT 32768 - -/* - * Maximum size infiniband SEND message - */ -#define RDMA_CONTROL_MAX_BUFFER (512 * 1024) -#define RDMA_CONTROL_MAX_COMMANDS_PER_MESSAGE 4096 - -#define RDMA_CONTROL_VERSION_CURRENT 1 -/* - * Capabilities for negotiation. - */ -#define RDMA_CAPABILITY_PIN_ALL 0x01 - -/* - * Add the other flags above to this list of known capabilities - * as they are introduced. - */ -static uint32_t known_capabilities = RDMA_CAPABILITY_PIN_ALL; - -/* - * A work request ID is 64-bits and we split up these bits - * into 3 parts: - * - * bits 0-15 : type of control message, 2^16 - * bits 16-29: ram block index, 2^14 - * bits 30-63: ram block chunk number, 2^34 - * - * The last two bit ranges are only used for RDMA writes, - * in order to track their completion and potentially - * also track unregistration status of the message. - */ -#define RDMA_WRID_TYPE_SHIFT 0UL -#define RDMA_WRID_BLOCK_SHIFT 16UL -#define RDMA_WRID_CHUNK_SHIFT 30UL - -#define RDMA_WRID_TYPE_MASK \ - ((1UL << RDMA_WRID_BLOCK_SHIFT) - 1UL) - -#define RDMA_WRID_BLOCK_MASK \ - (~RDMA_WRID_TYPE_MASK & ((1UL << RDMA_WRID_CHUNK_SHIFT) - 1UL)) - -#define RDMA_WRID_CHUNK_MASK (~RDMA_WRID_BLOCK_MASK & ~RDMA_WRID_TYPE_MASK) - -/* - * RDMA migration protocol: - * 1. RDMA Writes (data messages, i.e. RAM) - * 2. IB Send/Recv (control channel messages) - */ -enum { - RDMA_WRID_NONE = 0, - RDMA_WRID_RDMA_WRITE = 1, - RDMA_WRID_SEND_CONTROL = 2000, - RDMA_WRID_RECV_CONTROL = 4000, -}; - -/* - * Work request IDs for IB SEND messages only (not RDMA writes). - * This is used by the migration protocol to transmit - * control messages (such as device state and registration commands) - * - * We could use more WRs, but we have enough for now. - */ -enum { - RDMA_WRID_READY = 0, - RDMA_WRID_DATA, - RDMA_WRID_CONTROL, - RDMA_WRID_MAX, -}; - -/* - * SEND/RECV IB Control Messages. - */ -enum { - RDMA_CONTROL_NONE = 0, - RDMA_CONTROL_ERROR, - RDMA_CONTROL_READY, /* ready to receive */ - RDMA_CONTROL_QEMU_FILE, /* QEMUFile-transmitted bytes */ - RDMA_CONTROL_RAM_BLOCKS_REQUEST, /* RAMBlock synchronization */ - RDMA_CONTROL_RAM_BLOCKS_RESULT, /* RAMBlock synchronization */ - RDMA_CONTROL_COMPRESS, /* page contains repeat values */ - RDMA_CONTROL_REGISTER_REQUEST, /* dynamic page registration */ - RDMA_CONTROL_REGISTER_RESULT, /* key to use after registration */ - RDMA_CONTROL_REGISTER_FINISHED, /* current iteration finished */ - RDMA_CONTROL_UNREGISTER_REQUEST, /* dynamic UN-registration */ - RDMA_CONTROL_UNREGISTER_FINISHED, /* unpinning finished */ -}; - - -/* - * Memory and MR structures used to represent an IB Send/Recv work request. - * This is *not* used for RDMA writes, only IB Send/Recv. - */ -typedef struct { - uint8_t control[RDMA_CONTROL_MAX_BUFFER]; /* actual buffer to register */ - struct ibv_mr *control_mr; /* registration metadata */ - size_t control_len; /* length of the message */ - uint8_t *control_curr; /* start of unconsumed bytes */ -} RDMAWorkRequestData; - -/* - * Negotiate RDMA capabilities during connection-setup time. - */ -typedef struct { - uint32_t version; - uint32_t flags; -} RDMACapabilities; - -static void caps_to_network(RDMACapabilities *cap) -{ - cap->version = htonl(cap->version); - cap->flags = htonl(cap->flags); -} - -static void network_to_caps(RDMACapabilities *cap) -{ - cap->version = ntohl(cap->version); - cap->flags = ntohl(cap->flags); -} - -/* - * Representation of a RAMBlock from an RDMA perspective. - * This is not transmitted, only local. - * This and subsequent structures cannot be linked lists - * because we're using a single IB message to transmit - * the information. It's small anyway, so a list is overkill. - */ -typedef struct RDMALocalBlock { - char *block_name; - uint8_t *local_host_addr; /* local virtual address */ - uint64_t remote_host_addr; /* remote virtual address */ - uint64_t offset; - uint64_t length; - struct ibv_mr **pmr; /* MRs for chunk-level registration */ - struct ibv_mr *mr; /* MR for non-chunk-level registration */ - uint32_t *remote_keys; /* rkeys for chunk-level registration */ - uint32_t remote_rkey; /* rkeys for non-chunk-level registration */ - int index; /* which block are we */ - unsigned int src_index; /* (Only used on dest) */ - bool is_ram_block; - int nb_chunks; - unsigned long *transit_bitmap; - unsigned long *unregister_bitmap; -} RDMALocalBlock; - -/* - * Also represents a RAMblock, but only on the dest. - * This gets transmitted by the dest during connection-time - * to the source VM and then is used to populate the - * corresponding RDMALocalBlock with - * the information needed to perform the actual RDMA. - */ -typedef struct QEMU_PACKED RDMADestBlock { - uint64_t remote_host_addr; - uint64_t offset; - uint64_t length; - uint32_t remote_rkey; - uint32_t padding; -} RDMADestBlock; - -static const char *control_desc(unsigned int rdma_control) -{ - static const char *strs[] = { - [RDMA_CONTROL_NONE] = "NONE", - [RDMA_CONTROL_ERROR] = "ERROR", - [RDMA_CONTROL_READY] = "READY", - [RDMA_CONTROL_QEMU_FILE] = "QEMU FILE", - [RDMA_CONTROL_RAM_BLOCKS_REQUEST] = "RAM BLOCKS REQUEST", - [RDMA_CONTROL_RAM_BLOCKS_RESULT] = "RAM BLOCKS RESULT", - [RDMA_CONTROL_COMPRESS] = "COMPRESS", - [RDMA_CONTROL_REGISTER_REQUEST] = "REGISTER REQUEST", - [RDMA_CONTROL_REGISTER_RESULT] = "REGISTER RESULT", - [RDMA_CONTROL_REGISTER_FINISHED] = "REGISTER FINISHED", - [RDMA_CONTROL_UNREGISTER_REQUEST] = "UNREGISTER REQUEST", - [RDMA_CONTROL_UNREGISTER_FINISHED] = "UNREGISTER FINISHED", - }; - - if (rdma_control > RDMA_CONTROL_UNREGISTER_FINISHED) { - return "??BAD CONTROL VALUE??"; - } - - return strs[rdma_control]; -} - -#if !defined(htonll) -static uint64_t htonll(uint64_t v) -{ - union { uint32_t lv[2]; uint64_t llv; } u; - u.lv[0] = htonl(v >> 32); - u.lv[1] = htonl(v & 0xFFFFFFFFULL); - return u.llv; -} -#endif - -#if !defined(ntohll) -static uint64_t ntohll(uint64_t v) -{ - union { uint32_t lv[2]; uint64_t llv; } u; - u.llv = v; - return ((uint64_t)ntohl(u.lv[0]) << 32) | (uint64_t) ntohl(u.lv[1]); -} -#endif - -static void dest_block_to_network(RDMADestBlock *db) -{ - db->remote_host_addr = htonll(db->remote_host_addr); - db->offset = htonll(db->offset); - db->length = htonll(db->length); - db->remote_rkey = htonl(db->remote_rkey); -} - -static void network_to_dest_block(RDMADestBlock *db) -{ - db->remote_host_addr = ntohll(db->remote_host_addr); - db->offset = ntohll(db->offset); - db->length = ntohll(db->length); - db->remote_rkey = ntohl(db->remote_rkey); -} - -/* - * Virtual address of the above structures used for transmitting - * the RAMBlock descriptions at connection-time. - * This structure is *not* transmitted. - */ -typedef struct RDMALocalBlocks { - int nb_blocks; - bool init; /* main memory init complete */ - RDMALocalBlock *block; -} RDMALocalBlocks; - -/* - * Main data structure for RDMA state. - * While there is only one copy of this structure being allocated right now, - * this is the place where one would start if you wanted to consider - * having more than one RDMA connection open at the same time. - */ -typedef struct RDMAContext { - char *host; - int port; - - RDMAWorkRequestData wr_data[RDMA_WRID_MAX]; - - /* - * This is used by *_exchange_send() to figure out whether or not - * the initial "READY" message has already been received or not. - * This is because other functions may potentially poll() and detect - * the READY message before send() does, in which case we need to - * know if it completed. - */ - int control_ready_expected; - - /* number of outstanding writes */ - int nb_sent; - - /* store info about current buffer so that we can - merge it with future sends */ - uint64_t current_addr; - uint64_t current_length; - /* index of ram block the current buffer belongs to */ - int current_index; - /* index of the chunk in the current ram block */ - int current_chunk; - - bool pin_all; - - /* - * infiniband-specific variables for opening the device - * and maintaining connection state and so forth. - * - * cm_id also has ibv_context, rdma_event_channel, and ibv_qp in - * cm_id->verbs, cm_id->channel, and cm_id->qp. - */ - struct rdma_cm_id *cm_id; /* connection manager ID */ - struct rdma_cm_id *listen_id; - bool connected; - - struct ibv_context *verbs; - struct rdma_event_channel *channel; - struct ibv_qp *qp; /* queue pair */ - struct ibv_comp_channel *recv_comp_channel; /* recv completion channel */ - struct ibv_comp_channel *send_comp_channel; /* send completion channel */ - struct ibv_pd *pd; /* protection domain */ - struct ibv_cq *recv_cq; /* recvieve completion queue */ - struct ibv_cq *send_cq; /* send completion queue */ - - /* - * If a previous write failed (perhaps because of a failed - * memory registration, then do not attempt any future work - * and remember the error state. - */ - bool errored; - bool error_reported; - bool received_error; - - /* - * Description of ram blocks used throughout the code. - */ - RDMALocalBlocks local_ram_blocks; - RDMADestBlock *dest_blocks; - - /* Index of the next RAMBlock received during block registration */ - unsigned int next_src_index; - - /* - * Migration on *destination* started. - * Then use coroutine yield function. - * Source runs in a thread, so we don't care. - */ - int migration_started_on_destination; - - int total_registrations; - int total_writes; - - int unregister_current, unregister_next; - uint64_t unregistrations[RDMA_SIGNALED_SEND_MAX]; - - GHashTable *blockmap; - - /* the RDMAContext for return path */ - struct RDMAContext *return_path; - bool is_return_path; -} RDMAContext; - -#define TYPE_QIO_CHANNEL_RDMA "qio-channel-rdma" -OBJECT_DECLARE_SIMPLE_TYPE(QIOChannelRDMA, QIO_CHANNEL_RDMA) - - - -struct QIOChannelRDMA { - QIOChannel parent; - RDMAContext *rdmain; - RDMAContext *rdmaout; - QEMUFile *file; - bool blocking; /* XXX we don't actually honour this yet */ -}; - -/* - * Main structure for IB Send/Recv control messages. - * This gets prepended at the beginning of every Send/Recv. - */ -typedef struct QEMU_PACKED { - uint32_t len; /* Total length of data portion */ - uint32_t type; /* which control command to perform */ - uint32_t repeat; /* number of commands in data portion of same type */ - uint32_t padding; -} RDMAControlHeader; - -static void control_to_network(RDMAControlHeader *control) -{ - control->type = htonl(control->type); - control->len = htonl(control->len); - control->repeat = htonl(control->repeat); -} - -static void network_to_control(RDMAControlHeader *control) -{ - control->type = ntohl(control->type); - control->len = ntohl(control->len); - control->repeat = ntohl(control->repeat); -} - -/* - * Register a single Chunk. - * Information sent by the source VM to inform the dest - * to register an single chunk of memory before we can perform - * the actual RDMA operation. - */ -typedef struct QEMU_PACKED { - union QEMU_PACKED { - uint64_t current_addr; /* offset into the ram_addr_t space */ - uint64_t chunk; /* chunk to lookup if unregistering */ - } key; - uint32_t current_index; /* which ramblock the chunk belongs to */ - uint32_t padding; - uint64_t chunks; /* how many sequential chunks to register */ -} RDMARegister; - -static bool rdma_errored(RDMAContext *rdma) -{ - if (rdma->errored && !rdma->error_reported) { - error_report("RDMA is in an error state waiting migration" - " to abort!"); - rdma->error_reported = true; - } - return rdma->errored; -} - -static void register_to_network(RDMAContext *rdma, RDMARegister *reg) -{ - RDMALocalBlock *local_block; - local_block = &rdma->local_ram_blocks.block[reg->current_index]; - - if (local_block->is_ram_block) { - /* - * current_addr as passed in is an address in the local ram_addr_t - * space, we need to translate this for the destination - */ - reg->key.current_addr -= local_block->offset; - reg->key.current_addr += rdma->dest_blocks[reg->current_index].offset; - } - reg->key.current_addr = htonll(reg->key.current_addr); - reg->current_index = htonl(reg->current_index); - reg->chunks = htonll(reg->chunks); -} - -static void network_to_register(RDMARegister *reg) -{ - reg->key.current_addr = ntohll(reg->key.current_addr); - reg->current_index = ntohl(reg->current_index); - reg->chunks = ntohll(reg->chunks); -} - -typedef struct QEMU_PACKED { - uint32_t value; /* if zero, we will madvise() */ - uint32_t block_idx; /* which ram block index */ - uint64_t offset; /* Address in remote ram_addr_t space */ - uint64_t length; /* length of the chunk */ -} RDMACompress; - -static void compress_to_network(RDMAContext *rdma, RDMACompress *comp) -{ - comp->value = htonl(comp->value); - /* - * comp->offset as passed in is an address in the local ram_addr_t - * space, we need to translate this for the destination - */ - comp->offset -= rdma->local_ram_blocks.block[comp->block_idx].offset; - comp->offset += rdma->dest_blocks[comp->block_idx].offset; - comp->block_idx = htonl(comp->block_idx); - comp->offset = htonll(comp->offset); - comp->length = htonll(comp->length); -} - -static void network_to_compress(RDMACompress *comp) -{ - comp->value = ntohl(comp->value); - comp->block_idx = ntohl(comp->block_idx); - comp->offset = ntohll(comp->offset); - comp->length = ntohll(comp->length); -} - -/* - * The result of the dest's memory registration produces an "rkey" - * which the source VM must reference in order to perform - * the RDMA operation. - */ -typedef struct QEMU_PACKED { - uint32_t rkey; - uint32_t padding; - uint64_t host_addr; -} RDMARegisterResult; - -static void result_to_network(RDMARegisterResult *result) -{ - result->rkey = htonl(result->rkey); - result->host_addr = htonll(result->host_addr); -}; - -static void network_to_result(RDMARegisterResult *result) -{ - result->rkey = ntohl(result->rkey); - result->host_addr = ntohll(result->host_addr); -}; - -static int qemu_rdma_exchange_send(RDMAContext *rdma, RDMAControlHeader *head, - uint8_t *data, RDMAControlHeader *resp, - int *resp_idx, - int (*callback)(RDMAContext *rdma, - Error **errp), - Error **errp); - -static inline uint64_t ram_chunk_index(const uint8_t *start, - const uint8_t *host) -{ - return ((uintptr_t) host - (uintptr_t) start) >> RDMA_REG_CHUNK_SHIFT; -} - -static inline uint8_t *ram_chunk_start(const RDMALocalBlock *rdma_ram_block, - uint64_t i) -{ - return (uint8_t *)(uintptr_t)(rdma_ram_block->local_host_addr + - (i << RDMA_REG_CHUNK_SHIFT)); -} - -static inline uint8_t *ram_chunk_end(const RDMALocalBlock *rdma_ram_block, - uint64_t i) -{ - uint8_t *result = ram_chunk_start(rdma_ram_block, i) + - (1UL << RDMA_REG_CHUNK_SHIFT); - - if (result > (rdma_ram_block->local_host_addr + rdma_ram_block->length)) { - result = rdma_ram_block->local_host_addr + rdma_ram_block->length; - } - - return result; -} - -static void rdma_add_block(RDMAContext *rdma, const char *block_name, - void *host_addr, - ram_addr_t block_offset, uint64_t length) -{ - RDMALocalBlocks *local = &rdma->local_ram_blocks; - RDMALocalBlock *block; - RDMALocalBlock *old = local->block; - - local->block = g_new0(RDMALocalBlock, local->nb_blocks + 1); - - if (local->nb_blocks) { - if (rdma->blockmap) { - for (int x = 0; x < local->nb_blocks; x++) { - g_hash_table_remove(rdma->blockmap, - (void *)(uintptr_t)old[x].offset); - g_hash_table_insert(rdma->blockmap, - (void *)(uintptr_t)old[x].offset, - &local->block[x]); - } - } - memcpy(local->block, old, sizeof(RDMALocalBlock) * local->nb_blocks); - g_free(old); - } - - block = &local->block[local->nb_blocks]; - - block->block_name = g_strdup(block_name); - block->local_host_addr = host_addr; - block->offset = block_offset; - block->length = length; - block->index = local->nb_blocks; - block->src_index = ~0U; /* Filled in by the receipt of the block list */ - block->nb_chunks = ram_chunk_index(host_addr, host_addr + length) + 1UL; - block->transit_bitmap = bitmap_new(block->nb_chunks); - bitmap_clear(block->transit_bitmap, 0, block->nb_chunks); - block->unregister_bitmap = bitmap_new(block->nb_chunks); - bitmap_clear(block->unregister_bitmap, 0, block->nb_chunks); - block->remote_keys = g_new0(uint32_t, block->nb_chunks); - - block->is_ram_block = local->init ? false : true; - - if (rdma->blockmap) { - g_hash_table_insert(rdma->blockmap, (void *)(uintptr_t)block_offset, block); - } - - trace_rdma_add_block(block_name, local->nb_blocks, - (uintptr_t) block->local_host_addr, - block->offset, block->length, - (uintptr_t) (block->local_host_addr + block->length), - BITS_TO_LONGS(block->nb_chunks) * - sizeof(unsigned long) * 8, - block->nb_chunks); - - local->nb_blocks++; -} - -/* - * Memory regions need to be registered with the device and queue pairs setup - * in advanced before the migration starts. This tells us where the RAM blocks - * are so that we can register them individually. - */ -static int qemu_rdma_init_one_block(RAMBlock *rb, void *opaque) -{ - const char *block_name = qemu_ram_get_idstr(rb); - void *host_addr = qemu_ram_get_host_addr(rb); - ram_addr_t block_offset = qemu_ram_get_offset(rb); - ram_addr_t length = qemu_ram_get_used_length(rb); - rdma_add_block(opaque, block_name, host_addr, block_offset, length); - return 0; -} - -/* - * Identify the RAMBlocks and their quantity. They will be references to - * identify chunk boundaries inside each RAMBlock and also be referenced - * during dynamic page registration. - */ -static void qemu_rdma_init_ram_blocks(RDMAContext *rdma) -{ - RDMALocalBlocks *local = &rdma->local_ram_blocks; - int ret; - - assert(rdma->blockmap == NULL); - memset(local, 0, sizeof *local); - ret = foreach_not_ignored_block(qemu_rdma_init_one_block, rdma); - assert(!ret); - trace_qemu_rdma_init_ram_blocks(local->nb_blocks); - rdma->dest_blocks = g_new0(RDMADestBlock, - rdma->local_ram_blocks.nb_blocks); - local->init = true; -} - -/* - * Note: If used outside of cleanup, the caller must ensure that the destination - * block structures are also updated - */ -static void rdma_delete_block(RDMAContext *rdma, RDMALocalBlock *block) -{ - RDMALocalBlocks *local = &rdma->local_ram_blocks; - RDMALocalBlock *old = local->block; - - if (rdma->blockmap) { - g_hash_table_remove(rdma->blockmap, (void *)(uintptr_t)block->offset); - } - if (block->pmr) { - for (int j = 0; j < block->nb_chunks; j++) { - if (!block->pmr[j]) { - continue; - } - ibv_dereg_mr(block->pmr[j]); - rdma->total_registrations--; - } - g_free(block->pmr); - block->pmr = NULL; - } - - if (block->mr) { - ibv_dereg_mr(block->mr); - rdma->total_registrations--; - block->mr = NULL; - } - - g_free(block->transit_bitmap); - block->transit_bitmap = NULL; - - g_free(block->unregister_bitmap); - block->unregister_bitmap = NULL; - - g_free(block->remote_keys); - block->remote_keys = NULL; - - g_free(block->block_name); - block->block_name = NULL; - - if (rdma->blockmap) { - for (int x = 0; x < local->nb_blocks; x++) { - g_hash_table_remove(rdma->blockmap, - (void *)(uintptr_t)old[x].offset); - } - } - - if (local->nb_blocks > 1) { - - local->block = g_new0(RDMALocalBlock, local->nb_blocks - 1); - - if (block->index) { - memcpy(local->block, old, sizeof(RDMALocalBlock) * block->index); - } - - if (block->index < (local->nb_blocks - 1)) { - memcpy(local->block + block->index, old + (block->index + 1), - sizeof(RDMALocalBlock) * - (local->nb_blocks - (block->index + 1))); - for (int x = block->index; x < local->nb_blocks - 1; x++) { - local->block[x].index--; - } - } - } else { - assert(block == local->block); - local->block = NULL; - } - - trace_rdma_delete_block(block, (uintptr_t)block->local_host_addr, - block->offset, block->length, - (uintptr_t)(block->local_host_addr + block->length), - BITS_TO_LONGS(block->nb_chunks) * - sizeof(unsigned long) * 8, block->nb_chunks); - - g_free(old); - - local->nb_blocks--; - - if (local->nb_blocks && rdma->blockmap) { - for (int x = 0; x < local->nb_blocks; x++) { - g_hash_table_insert(rdma->blockmap, - (void *)(uintptr_t)local->block[x].offset, - &local->block[x]); - } - } -} - -/* - * Trace RDMA device open, with device details. - */ -static void qemu_rdma_dump_id(const char *who, struct ibv_context *verbs) -{ - struct ibv_port_attr port; - - if (ibv_query_port(verbs, 1, &port)) { - trace_qemu_rdma_dump_id_failed(who); - return; - } - - trace_qemu_rdma_dump_id(who, - verbs->device->name, - verbs->device->dev_name, - verbs->device->dev_path, - verbs->device->ibdev_path, - port.link_layer, - port.link_layer == IBV_LINK_LAYER_INFINIBAND ? "Infiniband" - : port.link_layer == IBV_LINK_LAYER_ETHERNET ? "Ethernet" - : "Unknown"); -} - -/* - * Trace RDMA gid addressing information. - * Useful for understanding the RDMA device hierarchy in the kernel. - */ -static void qemu_rdma_dump_gid(const char *who, struct rdma_cm_id *id) -{ - char sgid[33]; - char dgid[33]; - inet_ntop(AF_INET6, &id->route.addr.addr.ibaddr.sgid, sgid, sizeof sgid); - inet_ntop(AF_INET6, &id->route.addr.addr.ibaddr.dgid, dgid, sizeof dgid); - trace_qemu_rdma_dump_gid(who, sgid, dgid); -} - -/* - * As of now, IPv6 over RoCE / iWARP is not supported by linux. - * We will try the next addrinfo struct, and fail if there are - * no other valid addresses to bind against. - * - * If user is listening on '[::]', then we will not have a opened a device - * yet and have no way of verifying if the device is RoCE or not. - * - * In this case, the source VM will throw an error for ALL types of - * connections (both IPv4 and IPv6) if the destination machine does not have - * a regular infiniband network available for use. - * - * The only way to guarantee that an error is thrown for broken kernels is - * for the management software to choose a *specific* interface at bind time - * and validate what time of hardware it is. - * - * Unfortunately, this puts the user in a fix: - * - * If the source VM connects with an IPv4 address without knowing that the - * destination has bound to '[::]' the migration will unconditionally fail - * unless the management software is explicitly listening on the IPv4 - * address while using a RoCE-based device. - * - * If the source VM connects with an IPv6 address, then we're OK because we can - * throw an error on the source (and similarly on the destination). - * - * But in mixed environments, this will be broken for a while until it is fixed - * inside linux. - * - * We do provide a *tiny* bit of help in this function: We can list all of the - * devices in the system and check to see if all the devices are RoCE or - * Infiniband. - * - * If we detect that we have a *pure* RoCE environment, then we can safely - * thrown an error even if the management software has specified '[::]' as the - * bind address. - * - * However, if there is are multiple hetergeneous devices, then we cannot make - * this assumption and the user just has to be sure they know what they are - * doing. - * - * Patches are being reviewed on linux-rdma. - */ -static int qemu_rdma_broken_ipv6_kernel(struct ibv_context *verbs, Error **errp) -{ - /* This bug only exists in linux, to our knowledge. */ -#ifdef CONFIG_LINUX - struct ibv_port_attr port_attr; - - /* - * Verbs are only NULL if management has bound to '[::]'. - * - * Let's iterate through all the devices and see if there any pure IB - * devices (non-ethernet). - * - * If not, then we can safely proceed with the migration. - * Otherwise, there are no guarantees until the bug is fixed in linux. - */ - if (!verbs) { - int num_devices; - struct ibv_device **dev_list = ibv_get_device_list(&num_devices); - bool roce_found = false; - bool ib_found = false; - - for (int x = 0; x < num_devices; x++) { - verbs = ibv_open_device(dev_list[x]); - /* - * ibv_open_device() is not documented to set errno. If - * it does, it's somebody else's doc bug. If it doesn't, - * the use of errno below is wrong. - * TODO Find out whether ibv_open_device() sets errno. - */ - if (!verbs) { - if (errno == EPERM) { - continue; - } else { - error_setg_errno(errp, errno, - "could not open RDMA device context"); - return -1; - } - } - - if (ibv_query_port(verbs, 1, &port_attr)) { - ibv_close_device(verbs); - error_setg(errp, - "RDMA ERROR: Could not query initial IB port"); - return -1; - } - - if (port_attr.link_layer == IBV_LINK_LAYER_INFINIBAND) { - ib_found = true; - } else if (port_attr.link_layer == IBV_LINK_LAYER_ETHERNET) { - roce_found = true; - } - - ibv_close_device(verbs); - - } - - if (roce_found) { - if (ib_found) { - warn_report("migrations may fail:" - " IPv6 over RoCE / iWARP in linux" - " is broken. But since you appear to have a" - " mixed RoCE / IB environment, be sure to only" - " migrate over the IB fabric until the kernel " - " fixes the bug."); - } else { - error_setg(errp, "RDMA ERROR: " - "You only have RoCE / iWARP devices in your systems" - " and your management software has specified '[::]'" - ", but IPv6 over RoCE / iWARP is not supported in Linux."); - return -1; - } - } - - return 0; - } - - /* - * If we have a verbs context, that means that some other than '[::]' was - * used by the management software for binding. In which case we can - * actually warn the user about a potentially broken kernel. - */ - - /* IB ports start with 1, not 0 */ - if (ibv_query_port(verbs, 1, &port_attr)) { - error_setg(errp, "RDMA ERROR: Could not query initial IB port"); - return -1; - } - - if (port_attr.link_layer == IBV_LINK_LAYER_ETHERNET) { - error_setg(errp, "RDMA ERROR: " - "Linux kernel's RoCE / iWARP does not support IPv6 " - "(but patches on linux-rdma in progress)"); - return -1; - } - -#endif - - return 0; -} - -/* - * Figure out which RDMA device corresponds to the requested IP hostname - * Also create the initial connection manager identifiers for opening - * the connection. - */ -static int qemu_rdma_resolve_host(RDMAContext *rdma, Error **errp) -{ - Error *err = NULL; - int ret; - struct rdma_addrinfo *res; - char port_str[16]; - struct rdma_cm_event *cm_event; - char ip[40] = "unknown"; - - if (rdma->host == NULL || !strcmp(rdma->host, "")) { - error_setg(errp, "RDMA ERROR: RDMA hostname has not been set"); - return -1; - } - - /* create CM channel */ - rdma->channel = rdma_create_event_channel(); - if (!rdma->channel) { - error_setg(errp, "RDMA ERROR: could not create CM channel"); - return -1; - } - - /* create CM id */ - ret = rdma_create_id(rdma->channel, &rdma->cm_id, NULL, RDMA_PS_TCP); - if (ret < 0) { - error_setg(errp, "RDMA ERROR: could not create channel id"); - goto err_resolve_create_id; - } - - snprintf(port_str, 16, "%d", rdma->port); - port_str[15] = '\0'; - - ret = rdma_getaddrinfo(rdma->host, port_str, NULL, &res); - if (ret) { - error_setg(errp, "RDMA ERROR: could not rdma_getaddrinfo address %s", - rdma->host); - goto err_resolve_get_addr; - } - - /* Try all addresses, saving the first error in @err */ - for (struct rdma_addrinfo *e = res; e != NULL; e = e->ai_next) { - Error **local_errp = err ? NULL : &err; - - inet_ntop(e->ai_family, - &((struct sockaddr_in *) e->ai_dst_addr)->sin_addr, ip, sizeof ip); - trace_qemu_rdma_resolve_host_trying(rdma->host, ip); - - ret = rdma_resolve_addr(rdma->cm_id, NULL, e->ai_dst_addr, - RDMA_RESOLVE_TIMEOUT_MS); - if (ret >= 0) { - if (e->ai_family == AF_INET6) { - ret = qemu_rdma_broken_ipv6_kernel(rdma->cm_id->verbs, - local_errp); - if (ret < 0) { - continue; - } - } - error_free(err); - goto route; - } - } - - rdma_freeaddrinfo(res); - if (err) { - error_propagate(errp, err); - } else { - error_setg(errp, "RDMA ERROR: could not resolve address %s", - rdma->host); - } - goto err_resolve_get_addr; - -route: - rdma_freeaddrinfo(res); - qemu_rdma_dump_gid("source_resolve_addr", rdma->cm_id); - - ret = rdma_get_cm_event(rdma->channel, &cm_event); - if (ret < 0) { - error_setg(errp, "RDMA ERROR: could not perform event_addr_resolved"); - goto err_resolve_get_addr; - } - - if (cm_event->event != RDMA_CM_EVENT_ADDR_RESOLVED) { - error_setg(errp, - "RDMA ERROR: result not equal to event_addr_resolved %s", - rdma_event_str(cm_event->event)); - rdma_ack_cm_event(cm_event); - goto err_resolve_get_addr; - } - rdma_ack_cm_event(cm_event); - - /* resolve route */ - ret = rdma_resolve_route(rdma->cm_id, RDMA_RESOLVE_TIMEOUT_MS); - if (ret < 0) { - error_setg(errp, "RDMA ERROR: could not resolve rdma route"); - goto err_resolve_get_addr; - } - - ret = rdma_get_cm_event(rdma->channel, &cm_event); - if (ret < 0) { - error_setg(errp, "RDMA ERROR: could not perform event_route_resolved"); - goto err_resolve_get_addr; - } - if (cm_event->event != RDMA_CM_EVENT_ROUTE_RESOLVED) { - error_setg(errp, "RDMA ERROR: " - "result not equal to event_route_resolved: %s", - rdma_event_str(cm_event->event)); - rdma_ack_cm_event(cm_event); - goto err_resolve_get_addr; - } - rdma_ack_cm_event(cm_event); - rdma->verbs = rdma->cm_id->verbs; - qemu_rdma_dump_id("source_resolve_host", rdma->cm_id->verbs); - qemu_rdma_dump_gid("source_resolve_host", rdma->cm_id); - return 0; - -err_resolve_get_addr: - rdma_destroy_id(rdma->cm_id); - rdma->cm_id = NULL; -err_resolve_create_id: - rdma_destroy_event_channel(rdma->channel); - rdma->channel = NULL; - return -1; -} - -/* - * Create protection domain and completion queues - */ -static int qemu_rdma_alloc_pd_cq(RDMAContext *rdma, Error **errp) -{ - /* allocate pd */ - rdma->pd = ibv_alloc_pd(rdma->verbs); - if (!rdma->pd) { - error_setg(errp, "failed to allocate protection domain"); - return -1; - } - - /* create receive completion channel */ - rdma->recv_comp_channel = ibv_create_comp_channel(rdma->verbs); - if (!rdma->recv_comp_channel) { - error_setg(errp, "failed to allocate receive completion channel"); - goto err_alloc_pd_cq; - } - - /* - * Completion queue can be filled by read work requests. - */ - rdma->recv_cq = ibv_create_cq(rdma->verbs, (RDMA_SIGNALED_SEND_MAX * 3), - NULL, rdma->recv_comp_channel, 0); - if (!rdma->recv_cq) { - error_setg(errp, "failed to allocate receive completion queue"); - goto err_alloc_pd_cq; - } - - /* create send completion channel */ - rdma->send_comp_channel = ibv_create_comp_channel(rdma->verbs); - if (!rdma->send_comp_channel) { - error_setg(errp, "failed to allocate send completion channel"); - goto err_alloc_pd_cq; - } - - rdma->send_cq = ibv_create_cq(rdma->verbs, (RDMA_SIGNALED_SEND_MAX * 3), - NULL, rdma->send_comp_channel, 0); - if (!rdma->send_cq) { - error_setg(errp, "failed to allocate send completion queue"); - goto err_alloc_pd_cq; - } - - return 0; - -err_alloc_pd_cq: - if (rdma->pd) { - ibv_dealloc_pd(rdma->pd); - } - if (rdma->recv_comp_channel) { - ibv_destroy_comp_channel(rdma->recv_comp_channel); - } - if (rdma->send_comp_channel) { - ibv_destroy_comp_channel(rdma->send_comp_channel); - } - if (rdma->recv_cq) { - ibv_destroy_cq(rdma->recv_cq); - rdma->recv_cq = NULL; - } - rdma->pd = NULL; - rdma->recv_comp_channel = NULL; - rdma->send_comp_channel = NULL; - return -1; - -} - -/* - * Create queue pairs. - */ -static int qemu_rdma_alloc_qp(RDMAContext *rdma) -{ - struct ibv_qp_init_attr attr = { 0 }; - - attr.cap.max_send_wr = RDMA_SIGNALED_SEND_MAX; - attr.cap.max_recv_wr = 3; - attr.cap.max_send_sge = 1; - attr.cap.max_recv_sge = 1; - attr.send_cq = rdma->send_cq; - attr.recv_cq = rdma->recv_cq; - attr.qp_type = IBV_QPT_RC; - - if (rdma_create_qp(rdma->cm_id, rdma->pd, &attr) < 0) { - return -1; - } - - rdma->qp = rdma->cm_id->qp; - return 0; -} - -/* Check whether On-Demand Paging is supported by RDAM device */ -static bool rdma_support_odp(struct ibv_context *dev) -{ - struct ibv_device_attr_ex attr = {0}; - - if (ibv_query_device_ex(dev, NULL, &attr)) { - return false; - } - - if (attr.odp_caps.general_caps & IBV_ODP_SUPPORT) { - return true; - } - - return false; -} - -/* - * ibv_advise_mr to avoid RNR NAK error as far as possible. - * The responder mr registering with ODP will sent RNR NAK back to - * the requester in the face of the page fault. - */ -static void qemu_rdma_advise_prefetch_mr(struct ibv_pd *pd, uint64_t addr, - uint32_t len, uint32_t lkey, - const char *name, bool wr) -{ -#ifdef HAVE_IBV_ADVISE_MR - int ret; - int advice = wr ? IBV_ADVISE_MR_ADVICE_PREFETCH_WRITE : - IBV_ADVISE_MR_ADVICE_PREFETCH; - struct ibv_sge sg_list = {.lkey = lkey, .addr = addr, .length = len}; - - ret = ibv_advise_mr(pd, advice, - IBV_ADVISE_MR_FLAG_FLUSH, &sg_list, 1); - /* ignore the error */ - trace_qemu_rdma_advise_mr(name, len, addr, strerror(ret)); -#endif -} - -static int qemu_rdma_reg_whole_ram_blocks(RDMAContext *rdma, Error **errp) -{ - int i; - RDMALocalBlocks *local = &rdma->local_ram_blocks; - - for (i = 0; i < local->nb_blocks; i++) { - int access = IBV_ACCESS_LOCAL_WRITE | IBV_ACCESS_REMOTE_WRITE; - - local->block[i].mr = - ibv_reg_mr(rdma->pd, - local->block[i].local_host_addr, - local->block[i].length, access - ); - /* - * ibv_reg_mr() is not documented to set errno. If it does, - * it's somebody else's doc bug. If it doesn't, the use of - * errno below is wrong. - * TODO Find out whether ibv_reg_mr() sets errno. - */ - if (!local->block[i].mr && - errno == ENOTSUP && rdma_support_odp(rdma->verbs)) { - access |= IBV_ACCESS_ON_DEMAND; - /* register ODP mr */ - local->block[i].mr = - ibv_reg_mr(rdma->pd, - local->block[i].local_host_addr, - local->block[i].length, access); - trace_qemu_rdma_register_odp_mr(local->block[i].block_name); - - if (local->block[i].mr) { - qemu_rdma_advise_prefetch_mr(rdma->pd, - (uintptr_t)local->block[i].local_host_addr, - local->block[i].length, - local->block[i].mr->lkey, - local->block[i].block_name, - true); - } - } - - if (!local->block[i].mr) { - error_setg_errno(errp, errno, - "Failed to register local dest ram block!"); - goto err; - } - rdma->total_registrations++; - } - - return 0; - -err: - for (i--; i >= 0; i--) { - ibv_dereg_mr(local->block[i].mr); - local->block[i].mr = NULL; - rdma->total_registrations--; - } - - return -1; - -} - -/* - * Find the ram block that corresponds to the page requested to be - * transmitted by QEMU. - * - * Once the block is found, also identify which 'chunk' within that - * block that the page belongs to. - */ -static void qemu_rdma_search_ram_block(RDMAContext *rdma, - uintptr_t block_offset, - uint64_t offset, - uint64_t length, - uint64_t *block_index, - uint64_t *chunk_index) -{ - uint64_t current_addr = block_offset + offset; - RDMALocalBlock *block = g_hash_table_lookup(rdma->blockmap, - (void *) block_offset); - assert(block); - assert(current_addr >= block->offset); - assert((current_addr + length) <= (block->offset + block->length)); - - *block_index = block->index; - *chunk_index = ram_chunk_index(block->local_host_addr, - block->local_host_addr + (current_addr - block->offset)); -} - -/* - * Register a chunk with IB. If the chunk was already registered - * previously, then skip. - * - * Also return the keys associated with the registration needed - * to perform the actual RDMA operation. - */ -static int qemu_rdma_register_and_get_keys(RDMAContext *rdma, - RDMALocalBlock *block, uintptr_t host_addr, - uint32_t *lkey, uint32_t *rkey, int chunk, - uint8_t *chunk_start, uint8_t *chunk_end) -{ - if (block->mr) { - if (lkey) { - *lkey = block->mr->lkey; - } - if (rkey) { - *rkey = block->mr->rkey; - } - return 0; - } - - /* allocate memory to store chunk MRs */ - if (!block->pmr) { - block->pmr = g_new0(struct ibv_mr *, block->nb_chunks); - } - - /* - * If 'rkey', then we're the destination, so grant access to the source. - * - * If 'lkey', then we're the source VM, so grant access only to ourselves. - */ - if (!block->pmr[chunk]) { - uint64_t len = chunk_end - chunk_start; - int access = rkey ? IBV_ACCESS_LOCAL_WRITE | IBV_ACCESS_REMOTE_WRITE : - 0; - - trace_qemu_rdma_register_and_get_keys(len, chunk_start); - - block->pmr[chunk] = ibv_reg_mr(rdma->pd, chunk_start, len, access); - /* - * ibv_reg_mr() is not documented to set errno. If it does, - * it's somebody else's doc bug. If it doesn't, the use of - * errno below is wrong. - * TODO Find out whether ibv_reg_mr() sets errno. - */ - if (!block->pmr[chunk] && - errno == ENOTSUP && rdma_support_odp(rdma->verbs)) { - access |= IBV_ACCESS_ON_DEMAND; - /* register ODP mr */ - block->pmr[chunk] = ibv_reg_mr(rdma->pd, chunk_start, len, access); - trace_qemu_rdma_register_odp_mr(block->block_name); - - if (block->pmr[chunk]) { - qemu_rdma_advise_prefetch_mr(rdma->pd, (uintptr_t)chunk_start, - len, block->pmr[chunk]->lkey, - block->block_name, rkey); - - } - } - } - if (!block->pmr[chunk]) { - return -1; - } - rdma->total_registrations++; - - if (lkey) { - *lkey = block->pmr[chunk]->lkey; - } - if (rkey) { - *rkey = block->pmr[chunk]->rkey; - } - return 0; -} - -/* - * Register (at connection time) the memory used for control - * channel messages. - */ -static int qemu_rdma_reg_control(RDMAContext *rdma, int idx) -{ - rdma->wr_data[idx].control_mr = ibv_reg_mr(rdma->pd, - rdma->wr_data[idx].control, RDMA_CONTROL_MAX_BUFFER, - IBV_ACCESS_LOCAL_WRITE | IBV_ACCESS_REMOTE_WRITE); - if (rdma->wr_data[idx].control_mr) { - rdma->total_registrations++; - return 0; - } - return -1; -} - -/* - * Perform a non-optimized memory unregistration after every transfer - * for demonstration purposes, only if pin-all is not requested. - * - * Potential optimizations: - * 1. Start a new thread to run this function continuously - - for bit clearing - - and for receipt of unregister messages - * 2. Use an LRU. - * 3. Use workload hints. - */ -static int qemu_rdma_unregister_waiting(RDMAContext *rdma) -{ - Error *err = NULL; - - while (rdma->unregistrations[rdma->unregister_current]) { - int ret; - uint64_t wr_id = rdma->unregistrations[rdma->unregister_current]; - uint64_t chunk = - (wr_id & RDMA_WRID_CHUNK_MASK) >> RDMA_WRID_CHUNK_SHIFT; - uint64_t index = - (wr_id & RDMA_WRID_BLOCK_MASK) >> RDMA_WRID_BLOCK_SHIFT; - RDMALocalBlock *block = - &(rdma->local_ram_blocks.block[index]); - RDMARegister reg = { .current_index = index }; - RDMAControlHeader resp = { .type = RDMA_CONTROL_UNREGISTER_FINISHED, - }; - RDMAControlHeader head = { .len = sizeof(RDMARegister), - .type = RDMA_CONTROL_UNREGISTER_REQUEST, - .repeat = 1, - }; - - trace_qemu_rdma_unregister_waiting_proc(chunk, - rdma->unregister_current); - - rdma->unregistrations[rdma->unregister_current] = 0; - rdma->unregister_current++; - - if (rdma->unregister_current == RDMA_SIGNALED_SEND_MAX) { - rdma->unregister_current = 0; - } - - - /* - * Unregistration is speculative (because migration is single-threaded - * and we cannot break the protocol's inifinband message ordering). - * Thus, if the memory is currently being used for transmission, - * then abort the attempt to unregister and try again - * later the next time a completion is received for this memory. - */ - clear_bit(chunk, block->unregister_bitmap); - - if (test_bit(chunk, block->transit_bitmap)) { - trace_qemu_rdma_unregister_waiting_inflight(chunk); - continue; - } - - trace_qemu_rdma_unregister_waiting_send(chunk); - - ret = ibv_dereg_mr(block->pmr[chunk]); - block->pmr[chunk] = NULL; - block->remote_keys[chunk] = 0; - - if (ret != 0) { - error_report("unregistration chunk failed: %s", - strerror(ret)); - return -1; - } - rdma->total_registrations--; - - reg.key.chunk = chunk; - register_to_network(rdma, &reg); - ret = qemu_rdma_exchange_send(rdma, &head, (uint8_t *) &reg, - &resp, NULL, NULL, &err); - if (ret < 0) { - error_report_err(err); - return -1; - } - - trace_qemu_rdma_unregister_waiting_complete(chunk); - } - - return 0; -} - -static uint64_t qemu_rdma_make_wrid(uint64_t wr_id, uint64_t index, - uint64_t chunk) -{ - uint64_t result = wr_id & RDMA_WRID_TYPE_MASK; - - result |= (index << RDMA_WRID_BLOCK_SHIFT); - result |= (chunk << RDMA_WRID_CHUNK_SHIFT); - - return result; -} - -/* - * Consult the connection manager to see a work request - * (of any kind) has completed. - * Return the work request ID that completed. - */ -static int qemu_rdma_poll(RDMAContext *rdma, struct ibv_cq *cq, - uint64_t *wr_id_out, uint32_t *byte_len) -{ - int ret; - struct ibv_wc wc; - uint64_t wr_id; - - ret = ibv_poll_cq(cq, 1, &wc); - - if (!ret) { - *wr_id_out = RDMA_WRID_NONE; - return 0; - } - - if (ret < 0) { - return -1; - } - - wr_id = wc.wr_id & RDMA_WRID_TYPE_MASK; - - if (wc.status != IBV_WC_SUCCESS) { - return -1; - } - - if (rdma->control_ready_expected && - (wr_id >= RDMA_WRID_RECV_CONTROL)) { - trace_qemu_rdma_poll_recv(wr_id - RDMA_WRID_RECV_CONTROL, wr_id, - rdma->nb_sent); - rdma->control_ready_expected = 0; - } - - if (wr_id == RDMA_WRID_RDMA_WRITE) { - uint64_t chunk = - (wc.wr_id & RDMA_WRID_CHUNK_MASK) >> RDMA_WRID_CHUNK_SHIFT; - uint64_t index = - (wc.wr_id & RDMA_WRID_BLOCK_MASK) >> RDMA_WRID_BLOCK_SHIFT; - RDMALocalBlock *block = &(rdma->local_ram_blocks.block[index]); - - trace_qemu_rdma_poll_write(wr_id, rdma->nb_sent, - index, chunk, block->local_host_addr, - (void *)(uintptr_t)block->remote_host_addr); - - clear_bit(chunk, block->transit_bitmap); - - if (rdma->nb_sent > 0) { - rdma->nb_sent--; - } - } else { - trace_qemu_rdma_poll_other(wr_id, rdma->nb_sent); - } - - *wr_id_out = wc.wr_id; - if (byte_len) { - *byte_len = wc.byte_len; - } - - return 0; -} - -/* Wait for activity on the completion channel. - * Returns 0 on success, none-0 on error. - */ -static int qemu_rdma_wait_comp_channel(RDMAContext *rdma, - struct ibv_comp_channel *comp_channel) -{ - struct rdma_cm_event *cm_event; - - /* - * Coroutine doesn't start until migration_fd_process_incoming() - * so don't yield unless we know we're running inside of a coroutine. - */ - if (rdma->migration_started_on_destination && - migration_incoming_get_current()->state == MIGRATION_STATUS_ACTIVE) { - yield_until_fd_readable(comp_channel->fd); - } else { - /* This is the source side, we're in a separate thread - * or destination prior to migration_fd_process_incoming() - * after postcopy, the destination also in a separate thread. - * we can't yield; so we have to poll the fd. - * But we need to be able to handle 'cancel' or an error - * without hanging forever. - */ - while (!rdma->errored && !rdma->received_error) { - GPollFD pfds[2]; - pfds[0].fd = comp_channel->fd; - pfds[0].events = G_IO_IN | G_IO_HUP | G_IO_ERR; - pfds[0].revents = 0; - - pfds[1].fd = rdma->channel->fd; - pfds[1].events = G_IO_IN | G_IO_HUP | G_IO_ERR; - pfds[1].revents = 0; - - /* 0.1s timeout, should be fine for a 'cancel' */ - switch (qemu_poll_ns(pfds, 2, 100 * 1000 * 1000)) { - case 2: - case 1: /* fd active */ - if (pfds[0].revents) { - return 0; - } - - if (pfds[1].revents) { - if (rdma_get_cm_event(rdma->channel, &cm_event) < 0) { - return -1; - } - - if (cm_event->event == RDMA_CM_EVENT_DISCONNECTED || - cm_event->event == RDMA_CM_EVENT_DEVICE_REMOVAL) { - rdma_ack_cm_event(cm_event); - return -1; - } - rdma_ack_cm_event(cm_event); - } - break; - - case 0: /* Timeout, go around again */ - break; - - default: /* Error of some type - - * I don't trust errno from qemu_poll_ns - */ - return -1; - } - - if (migrate_get_current()->state == MIGRATION_STATUS_CANCELLING) { - /* Bail out and let the cancellation happen */ - return -1; - } - } - } - - if (rdma->received_error) { - return -1; - } - return -rdma->errored; -} - -static struct ibv_comp_channel *to_channel(RDMAContext *rdma, uint64_t wrid) -{ - return wrid < RDMA_WRID_RECV_CONTROL ? rdma->send_comp_channel : - rdma->recv_comp_channel; -} - -static struct ibv_cq *to_cq(RDMAContext *rdma, uint64_t wrid) -{ - return wrid < RDMA_WRID_RECV_CONTROL ? rdma->send_cq : rdma->recv_cq; -} - -/* - * Block until the next work request has completed. - * - * First poll to see if a work request has already completed, - * otherwise block. - * - * If we encounter completed work requests for IDs other than - * the one we're interested in, then that's generally an error. - * - * The only exception is actual RDMA Write completions. These - * completions only need to be recorded, but do not actually - * need further processing. - */ -static int qemu_rdma_block_for_wrid(RDMAContext *rdma, - uint64_t wrid_requested, - uint32_t *byte_len) -{ - int num_cq_events = 0, ret; - struct ibv_cq *cq; - void *cq_ctx; - uint64_t wr_id = RDMA_WRID_NONE, wr_id_in; - struct ibv_comp_channel *ch = to_channel(rdma, wrid_requested); - struct ibv_cq *poll_cq = to_cq(rdma, wrid_requested); - - if (ibv_req_notify_cq(poll_cq, 0)) { - return -1; - } - /* poll cq first */ - while (wr_id != wrid_requested) { - ret = qemu_rdma_poll(rdma, poll_cq, &wr_id_in, byte_len); - if (ret < 0) { - return -1; - } - - wr_id = wr_id_in & RDMA_WRID_TYPE_MASK; - - if (wr_id == RDMA_WRID_NONE) { - break; - } - if (wr_id != wrid_requested) { - trace_qemu_rdma_block_for_wrid_miss(wrid_requested, wr_id); - } - } - - if (wr_id == wrid_requested) { - return 0; - } - - while (1) { - ret = qemu_rdma_wait_comp_channel(rdma, ch); - if (ret < 0) { - goto err_block_for_wrid; - } - - ret = ibv_get_cq_event(ch, &cq, &cq_ctx); - if (ret < 0) { - goto err_block_for_wrid; - } - - num_cq_events++; - - if (ibv_req_notify_cq(cq, 0)) { - goto err_block_for_wrid; - } - - while (wr_id != wrid_requested) { - ret = qemu_rdma_poll(rdma, poll_cq, &wr_id_in, byte_len); - if (ret < 0) { - goto err_block_for_wrid; - } - - wr_id = wr_id_in & RDMA_WRID_TYPE_MASK; - - if (wr_id == RDMA_WRID_NONE) { - break; - } - if (wr_id != wrid_requested) { - trace_qemu_rdma_block_for_wrid_miss(wrid_requested, wr_id); - } - } - - if (wr_id == wrid_requested) { - goto success_block_for_wrid; - } - } - -success_block_for_wrid: - if (num_cq_events) { - ibv_ack_cq_events(cq, num_cq_events); - } - return 0; - -err_block_for_wrid: - if (num_cq_events) { - ibv_ack_cq_events(cq, num_cq_events); - } - - rdma->errored = true; - return -1; -} - -/* - * Post a SEND message work request for the control channel - * containing some data and block until the post completes. - */ -static int qemu_rdma_post_send_control(RDMAContext *rdma, uint8_t *buf, - RDMAControlHeader *head, - Error **errp) -{ - int ret; - RDMAWorkRequestData *wr = &rdma->wr_data[RDMA_WRID_CONTROL]; - struct ibv_send_wr *bad_wr; - struct ibv_sge sge = { - .addr = (uintptr_t)(wr->control), - .length = head->len + sizeof(RDMAControlHeader), - .lkey = wr->control_mr->lkey, - }; - struct ibv_send_wr send_wr = { - .wr_id = RDMA_WRID_SEND_CONTROL, - .opcode = IBV_WR_SEND, - .send_flags = IBV_SEND_SIGNALED, - .sg_list = &sge, - .num_sge = 1, - }; - - trace_qemu_rdma_post_send_control(control_desc(head->type)); - - /* - * We don't actually need to do a memcpy() in here if we used - * the "sge" properly, but since we're only sending control messages - * (not RAM in a performance-critical path), then its OK for now. - * - * The copy makes the RDMAControlHeader simpler to manipulate - * for the time being. - */ - assert(head->len <= RDMA_CONTROL_MAX_BUFFER - sizeof(*head)); - memcpy(wr->control, head, sizeof(RDMAControlHeader)); - control_to_network((void *) wr->control); - - if (buf) { - memcpy(wr->control + sizeof(RDMAControlHeader), buf, head->len); - } - - - ret = ibv_post_send(rdma->qp, &send_wr, &bad_wr); - - if (ret > 0) { - error_setg(errp, "Failed to use post IB SEND for control"); - return -1; - } - - ret = qemu_rdma_block_for_wrid(rdma, RDMA_WRID_SEND_CONTROL, NULL); - if (ret < 0) { - error_setg(errp, "rdma migration: send polling control error"); - return -1; - } - - return 0; -} - -/* - * Post a RECV work request in anticipation of some future receipt - * of data on the control channel. - */ -static int qemu_rdma_post_recv_control(RDMAContext *rdma, int idx, - Error **errp) -{ - struct ibv_recv_wr *bad_wr; - struct ibv_sge sge = { - .addr = (uintptr_t)(rdma->wr_data[idx].control), - .length = RDMA_CONTROL_MAX_BUFFER, - .lkey = rdma->wr_data[idx].control_mr->lkey, - }; - - struct ibv_recv_wr recv_wr = { - .wr_id = RDMA_WRID_RECV_CONTROL + idx, - .sg_list = &sge, - .num_sge = 1, - }; - - - if (ibv_post_recv(rdma->qp, &recv_wr, &bad_wr)) { - error_setg(errp, "error posting control recv"); - return -1; - } - - return 0; -} - -/* - * Block and wait for a RECV control channel message to arrive. - */ -static int qemu_rdma_exchange_get_response(RDMAContext *rdma, - RDMAControlHeader *head, uint32_t expecting, int idx, - Error **errp) -{ - uint32_t byte_len; - int ret = qemu_rdma_block_for_wrid(rdma, RDMA_WRID_RECV_CONTROL + idx, - &byte_len); - - if (ret < 0) { - error_setg(errp, "rdma migration: recv polling control error!"); - return -1; - } - - network_to_control((void *) rdma->wr_data[idx].control); - memcpy(head, rdma->wr_data[idx].control, sizeof(RDMAControlHeader)); - - trace_qemu_rdma_exchange_get_response_start(control_desc(expecting)); - - if (expecting == RDMA_CONTROL_NONE) { - trace_qemu_rdma_exchange_get_response_none(control_desc(head->type), - head->type); - } else if (head->type != expecting || head->type == RDMA_CONTROL_ERROR) { - error_setg(errp, "Was expecting a %s (%d) control message" - ", but got: %s (%d), length: %d", - control_desc(expecting), expecting, - control_desc(head->type), head->type, head->len); - if (head->type == RDMA_CONTROL_ERROR) { - rdma->received_error = true; - } - return -1; - } - if (head->len > RDMA_CONTROL_MAX_BUFFER - sizeof(*head)) { - error_setg(errp, "too long length: %d", head->len); - return -1; - } - if (sizeof(*head) + head->len != byte_len) { - error_setg(errp, "Malformed length: %d byte_len %d", - head->len, byte_len); - return -1; - } - - return 0; -} - -/* - * When a RECV work request has completed, the work request's - * buffer is pointed at the header. - * - * This will advance the pointer to the data portion - * of the control message of the work request's buffer that - * was populated after the work request finished. - */ -static void qemu_rdma_move_header(RDMAContext *rdma, int idx, - RDMAControlHeader *head) -{ - rdma->wr_data[idx].control_len = head->len; - rdma->wr_data[idx].control_curr = - rdma->wr_data[idx].control + sizeof(RDMAControlHeader); -} - -/* - * This is an 'atomic' high-level operation to deliver a single, unified - * control-channel message. - * - * Additionally, if the user is expecting some kind of reply to this message, - * they can request a 'resp' response message be filled in by posting an - * additional work request on behalf of the user and waiting for an additional - * completion. - * - * The extra (optional) response is used during registration to us from having - * to perform an *additional* exchange of message just to provide a response by - * instead piggy-backing on the acknowledgement. - */ -static int qemu_rdma_exchange_send(RDMAContext *rdma, RDMAControlHeader *head, - uint8_t *data, RDMAControlHeader *resp, - int *resp_idx, - int (*callback)(RDMAContext *rdma, - Error **errp), - Error **errp) -{ - int ret; - - /* - * Wait until the dest is ready before attempting to deliver the message - * by waiting for a READY message. - */ - if (rdma->control_ready_expected) { - RDMAControlHeader resp_ignored; - - ret = qemu_rdma_exchange_get_response(rdma, &resp_ignored, - RDMA_CONTROL_READY, - RDMA_WRID_READY, errp); - if (ret < 0) { - return -1; - } - } - - /* - * If the user is expecting a response, post a WR in anticipation of it. - */ - if (resp) { - ret = qemu_rdma_post_recv_control(rdma, RDMA_WRID_DATA, errp); - if (ret < 0) { - return -1; - } - } - - /* - * Post a WR to replace the one we just consumed for the READY message. - */ - ret = qemu_rdma_post_recv_control(rdma, RDMA_WRID_READY, errp); - if (ret < 0) { - return -1; - } - - /* - * Deliver the control message that was requested. - */ - ret = qemu_rdma_post_send_control(rdma, data, head, errp); - - if (ret < 0) { - return -1; - } - - /* - * If we're expecting a response, block and wait for it. - */ - if (resp) { - if (callback) { - trace_qemu_rdma_exchange_send_issue_callback(); - ret = callback(rdma, errp); - if (ret < 0) { - return -1; - } - } - - trace_qemu_rdma_exchange_send_waiting(control_desc(resp->type)); - ret = qemu_rdma_exchange_get_response(rdma, resp, - resp->type, RDMA_WRID_DATA, - errp); - - if (ret < 0) { - return -1; - } - - qemu_rdma_move_header(rdma, RDMA_WRID_DATA, resp); - if (resp_idx) { - *resp_idx = RDMA_WRID_DATA; - } - trace_qemu_rdma_exchange_send_received(control_desc(resp->type)); - } - - rdma->control_ready_expected = 1; - - return 0; -} - -/* - * This is an 'atomic' high-level operation to receive a single, unified - * control-channel message. - */ -static int qemu_rdma_exchange_recv(RDMAContext *rdma, RDMAControlHeader *head, - uint32_t expecting, Error **errp) -{ - RDMAControlHeader ready = { - .len = 0, - .type = RDMA_CONTROL_READY, - .repeat = 1, - }; - int ret; - - /* - * Inform the source that we're ready to receive a message. - */ - ret = qemu_rdma_post_send_control(rdma, NULL, &ready, errp); - - if (ret < 0) { - return -1; - } - - /* - * Block and wait for the message. - */ - ret = qemu_rdma_exchange_get_response(rdma, head, - expecting, RDMA_WRID_READY, errp); - - if (ret < 0) { - return -1; - } - - qemu_rdma_move_header(rdma, RDMA_WRID_READY, head); - - /* - * Post a new RECV work request to replace the one we just consumed. - */ - ret = qemu_rdma_post_recv_control(rdma, RDMA_WRID_READY, errp); - if (ret < 0) { - return -1; - } - - return 0; -} - -/* - * Write an actual chunk of memory using RDMA. - * - * If we're using dynamic registration on the dest-side, we have to - * send a registration command first. - */ -static int qemu_rdma_write_one(RDMAContext *rdma, - int current_index, uint64_t current_addr, - uint64_t length, Error **errp) -{ - struct ibv_sge sge; - struct ibv_send_wr send_wr = { 0 }; - struct ibv_send_wr *bad_wr; - int reg_result_idx, ret, count = 0; - uint64_t chunk, chunks; - uint8_t *chunk_start, *chunk_end; - RDMALocalBlock *block = &(rdma->local_ram_blocks.block[current_index]); - RDMARegister reg; - RDMARegisterResult *reg_result; - RDMAControlHeader resp = { .type = RDMA_CONTROL_REGISTER_RESULT }; - RDMAControlHeader head = { .len = sizeof(RDMARegister), - .type = RDMA_CONTROL_REGISTER_REQUEST, - .repeat = 1, - }; - -retry: - sge.addr = (uintptr_t)(block->local_host_addr + - (current_addr - block->offset)); - sge.length = length; - - chunk = ram_chunk_index(block->local_host_addr, - (uint8_t *)(uintptr_t)sge.addr); - chunk_start = ram_chunk_start(block, chunk); - - if (block->is_ram_block) { - chunks = length / (1UL << RDMA_REG_CHUNK_SHIFT); - - if (chunks && ((length % (1UL << RDMA_REG_CHUNK_SHIFT)) == 0)) { - chunks--; - } - } else { - chunks = block->length / (1UL << RDMA_REG_CHUNK_SHIFT); - - if (chunks && ((block->length % (1UL << RDMA_REG_CHUNK_SHIFT)) == 0)) { - chunks--; - } - } - - trace_qemu_rdma_write_one_top(chunks + 1, - (chunks + 1) * - (1UL << RDMA_REG_CHUNK_SHIFT) / 1024 / 1024); - - chunk_end = ram_chunk_end(block, chunk + chunks); - - - while (test_bit(chunk, block->transit_bitmap)) { - (void)count; - trace_qemu_rdma_write_one_block(count++, current_index, chunk, - sge.addr, length, rdma->nb_sent, block->nb_chunks); - - ret = qemu_rdma_block_for_wrid(rdma, RDMA_WRID_RDMA_WRITE, NULL); - - if (ret < 0) { - error_setg(errp, "Failed to Wait for previous write to complete " - "block %d chunk %" PRIu64 - " current %" PRIu64 " len %" PRIu64 " %d", - current_index, chunk, sge.addr, length, rdma->nb_sent); - return -1; - } - } - - if (!rdma->pin_all || !block->is_ram_block) { - if (!block->remote_keys[chunk]) { - /* - * This chunk has not yet been registered, so first check to see - * if the entire chunk is zero. If so, tell the other size to - * memset() + madvise() the entire chunk without RDMA. - */ - - if (buffer_is_zero((void *)(uintptr_t)sge.addr, length)) { - RDMACompress comp = { - .offset = current_addr, - .value = 0, - .block_idx = current_index, - .length = length, - }; - - head.len = sizeof(comp); - head.type = RDMA_CONTROL_COMPRESS; - - trace_qemu_rdma_write_one_zero(chunk, sge.length, - current_index, current_addr); - - compress_to_network(rdma, &comp); - ret = qemu_rdma_exchange_send(rdma, &head, - (uint8_t *) &comp, NULL, NULL, NULL, errp); - - if (ret < 0) { - return -1; - } - - /* - * TODO: Here we are sending something, but we are not - * accounting for anything transferred. The following is wrong: - * - * stat64_add(&mig_stats.rdma_bytes, sge.length); - * - * because we are using some kind of compression. I - * would think that head.len would be the more similar - * thing to a correct value. - */ - stat64_add(&mig_stats.zero_pages, - sge.length / qemu_target_page_size()); - return 1; - } - - /* - * Otherwise, tell other side to register. - */ - reg.current_index = current_index; - if (block->is_ram_block) { - reg.key.current_addr = current_addr; - } else { - reg.key.chunk = chunk; - } - reg.chunks = chunks; - - trace_qemu_rdma_write_one_sendreg(chunk, sge.length, current_index, - current_addr); - - register_to_network(rdma, &reg); - ret = qemu_rdma_exchange_send(rdma, &head, (uint8_t *) &reg, - &resp, &reg_result_idx, NULL, errp); - if (ret < 0) { - return -1; - } - - /* try to overlap this single registration with the one we sent. */ - if (qemu_rdma_register_and_get_keys(rdma, block, sge.addr, - &sge.lkey, NULL, chunk, - chunk_start, chunk_end)) { - error_setg(errp, "cannot get lkey"); - return -1; - } - - reg_result = (RDMARegisterResult *) - rdma->wr_data[reg_result_idx].control_curr; - - network_to_result(reg_result); - - trace_qemu_rdma_write_one_recvregres(block->remote_keys[chunk], - reg_result->rkey, chunk); - - block->remote_keys[chunk] = reg_result->rkey; - block->remote_host_addr = reg_result->host_addr; - } else { - /* already registered before */ - if (qemu_rdma_register_and_get_keys(rdma, block, sge.addr, - &sge.lkey, NULL, chunk, - chunk_start, chunk_end)) { - error_setg(errp, "cannot get lkey!"); - return -1; - } - } - - send_wr.wr.rdma.rkey = block->remote_keys[chunk]; - } else { - send_wr.wr.rdma.rkey = block->remote_rkey; - - if (qemu_rdma_register_and_get_keys(rdma, block, sge.addr, - &sge.lkey, NULL, chunk, - chunk_start, chunk_end)) { - error_setg(errp, "cannot get lkey!"); - return -1; - } - } - - /* - * Encode the ram block index and chunk within this wrid. - * We will use this information at the time of completion - * to figure out which bitmap to check against and then which - * chunk in the bitmap to look for. - */ - send_wr.wr_id = qemu_rdma_make_wrid(RDMA_WRID_RDMA_WRITE, - current_index, chunk); - - send_wr.opcode = IBV_WR_RDMA_WRITE; - send_wr.send_flags = IBV_SEND_SIGNALED; - send_wr.sg_list = &sge; - send_wr.num_sge = 1; - send_wr.wr.rdma.remote_addr = block->remote_host_addr + - (current_addr - block->offset); - - trace_qemu_rdma_write_one_post(chunk, sge.addr, send_wr.wr.rdma.remote_addr, - sge.length); - - /* - * ibv_post_send() does not return negative error numbers, - * per the specification they are positive - no idea why. - */ - ret = ibv_post_send(rdma->qp, &send_wr, &bad_wr); - - if (ret == ENOMEM) { - trace_qemu_rdma_write_one_queue_full(); - ret = qemu_rdma_block_for_wrid(rdma, RDMA_WRID_RDMA_WRITE, NULL); - if (ret < 0) { - error_setg(errp, "rdma migration: failed to make " - "room in full send queue!"); - return -1; - } - - goto retry; - - } else if (ret > 0) { - error_setg_errno(errp, ret, - "rdma migration: post rdma write failed"); - return -1; - } - - set_bit(chunk, block->transit_bitmap); - stat64_add(&mig_stats.normal_pages, sge.length / qemu_target_page_size()); - /* - * We are adding to transferred the amount of data written, but no - * overhead at all. I will assume that RDMA is magicaly and don't - * need to transfer (at least) the addresses where it wants to - * write the pages. Here it looks like it should be something - * like: - * sizeof(send_wr) + sge.length - * but this being RDMA, who knows. - */ - stat64_add(&mig_stats.rdma_bytes, sge.length); - ram_transferred_add(sge.length); - rdma->total_writes++; - - return 0; -} - -/* - * Push out any unwritten RDMA operations. - * - * We support sending out multiple chunks at the same time. - * Not all of them need to get signaled in the completion queue. - */ -static int qemu_rdma_write_flush(RDMAContext *rdma, Error **errp) -{ - int ret; - - if (!rdma->current_length) { - return 0; - } - - ret = qemu_rdma_write_one(rdma, rdma->current_index, rdma->current_addr, - rdma->current_length, errp); - - if (ret < 0) { - return -1; - } - - if (ret == 0) { - rdma->nb_sent++; - trace_qemu_rdma_write_flush(rdma->nb_sent); - } - - rdma->current_length = 0; - rdma->current_addr = 0; - - return 0; -} - -static inline bool qemu_rdma_buffer_mergeable(RDMAContext *rdma, - uint64_t offset, uint64_t len) -{ - RDMALocalBlock *block; - uint8_t *host_addr; - uint8_t *chunk_end; - - if (rdma->current_index < 0) { - return false; - } - - if (rdma->current_chunk < 0) { - return false; - } - - block = &(rdma->local_ram_blocks.block[rdma->current_index]); - host_addr = block->local_host_addr + (offset - block->offset); - chunk_end = ram_chunk_end(block, rdma->current_chunk); - - if (rdma->current_length == 0) { - return false; - } - - /* - * Only merge into chunk sequentially. - */ - if (offset != (rdma->current_addr + rdma->current_length)) { - return false; - } - - if (offset < block->offset) { - return false; - } - - if ((offset + len) > (block->offset + block->length)) { - return false; - } - - if ((host_addr + len) > chunk_end) { - return false; - } - - return true; -} - -/* - * We're not actually writing here, but doing three things: - * - * 1. Identify the chunk the buffer belongs to. - * 2. If the chunk is full or the buffer doesn't belong to the current - * chunk, then start a new chunk and flush() the old chunk. - * 3. To keep the hardware busy, we also group chunks into batches - * and only require that a batch gets acknowledged in the completion - * queue instead of each individual chunk. - */ -static int qemu_rdma_write(RDMAContext *rdma, - uint64_t block_offset, uint64_t offset, - uint64_t len, Error **errp) -{ - uint64_t current_addr = block_offset + offset; - uint64_t index = rdma->current_index; - uint64_t chunk = rdma->current_chunk; - - /* If we cannot merge it, we flush the current buffer first. */ - if (!qemu_rdma_buffer_mergeable(rdma, current_addr, len)) { - if (qemu_rdma_write_flush(rdma, errp) < 0) { - return -1; - } - rdma->current_length = 0; - rdma->current_addr = current_addr; - - qemu_rdma_search_ram_block(rdma, block_offset, - offset, len, &index, &chunk); - rdma->current_index = index; - rdma->current_chunk = chunk; - } - - /* merge it */ - rdma->current_length += len; - - /* flush it if buffer is too large */ - if (rdma->current_length >= RDMA_MERGE_MAX) { - return qemu_rdma_write_flush(rdma, errp); - } - - return 0; -} - -static void qemu_rdma_cleanup(RDMAContext *rdma) -{ - Error *err = NULL; - - if (rdma->cm_id && rdma->connected) { - if ((rdma->errored || - migrate_get_current()->state == MIGRATION_STATUS_CANCELLING) && - !rdma->received_error) { - RDMAControlHeader head = { .len = 0, - .type = RDMA_CONTROL_ERROR, - .repeat = 1, - }; - warn_report("Early error. Sending error."); - if (qemu_rdma_post_send_control(rdma, NULL, &head, &err) < 0) { - warn_report_err(err); - } - } - - rdma_disconnect(rdma->cm_id); - trace_qemu_rdma_cleanup_disconnect(); - rdma->connected = false; - } - - if (rdma->channel) { - qemu_set_fd_handler(rdma->channel->fd, NULL, NULL, NULL); - } - g_free(rdma->dest_blocks); - rdma->dest_blocks = NULL; - - for (int i = 0; i < RDMA_WRID_MAX; i++) { - if (rdma->wr_data[i].control_mr) { - rdma->total_registrations--; - ibv_dereg_mr(rdma->wr_data[i].control_mr); - } - rdma->wr_data[i].control_mr = NULL; - } - - if (rdma->local_ram_blocks.block) { - while (rdma->local_ram_blocks.nb_blocks) { - rdma_delete_block(rdma, &rdma->local_ram_blocks.block[0]); - } - } - - if (rdma->qp) { - rdma_destroy_qp(rdma->cm_id); - rdma->qp = NULL; - } - if (rdma->recv_cq) { - ibv_destroy_cq(rdma->recv_cq); - rdma->recv_cq = NULL; - } - if (rdma->send_cq) { - ibv_destroy_cq(rdma->send_cq); - rdma->send_cq = NULL; - } - if (rdma->recv_comp_channel) { - ibv_destroy_comp_channel(rdma->recv_comp_channel); - rdma->recv_comp_channel = NULL; - } - if (rdma->send_comp_channel) { - ibv_destroy_comp_channel(rdma->send_comp_channel); - rdma->send_comp_channel = NULL; - } - if (rdma->pd) { - ibv_dealloc_pd(rdma->pd); - rdma->pd = NULL; - } - if (rdma->cm_id) { - rdma_destroy_id(rdma->cm_id); - rdma->cm_id = NULL; - } - - /* the destination side, listen_id and channel is shared */ - if (rdma->listen_id) { - if (!rdma->is_return_path) { - rdma_destroy_id(rdma->listen_id); - } - rdma->listen_id = NULL; - - if (rdma->channel) { - if (!rdma->is_return_path) { - rdma_destroy_event_channel(rdma->channel); - } - rdma->channel = NULL; - } - } - - if (rdma->channel) { - rdma_destroy_event_channel(rdma->channel); - rdma->channel = NULL; - } - g_free(rdma->host); - rdma->host = NULL; -} - - -static int qemu_rdma_source_init(RDMAContext *rdma, bool pin_all, Error **errp) -{ - int ret; - - /* - * Will be validated against destination's actual capabilities - * after the connect() completes. - */ - rdma->pin_all = pin_all; - - ret = qemu_rdma_resolve_host(rdma, errp); - if (ret < 0) { - goto err_rdma_source_init; - } - - ret = qemu_rdma_alloc_pd_cq(rdma, errp); - if (ret < 0) { - goto err_rdma_source_init; - } - - ret = qemu_rdma_alloc_qp(rdma); - if (ret < 0) { - error_setg(errp, "RDMA ERROR: rdma migration: error allocating qp!"); - goto err_rdma_source_init; - } - - qemu_rdma_init_ram_blocks(rdma); - - /* Build the hash that maps from offset to RAMBlock */ - rdma->blockmap = g_hash_table_new(g_direct_hash, g_direct_equal); - for (int i = 0; i < rdma->local_ram_blocks.nb_blocks; i++) { - g_hash_table_insert(rdma->blockmap, - (void *)(uintptr_t)rdma->local_ram_blocks.block[i].offset, - &rdma->local_ram_blocks.block[i]); - } - - for (int i = 0; i < RDMA_WRID_MAX; i++) { - ret = qemu_rdma_reg_control(rdma, i); - if (ret < 0) { - error_setg(errp, "RDMA ERROR: rdma migration: error " - "registering %d control!", i); - goto err_rdma_source_init; - } - } - - return 0; - -err_rdma_source_init: - qemu_rdma_cleanup(rdma); - return -1; -} - -static int qemu_get_cm_event_timeout(RDMAContext *rdma, - struct rdma_cm_event **cm_event, - long msec, Error **errp) -{ - int ret; - struct pollfd poll_fd = { - .fd = rdma->channel->fd, - .events = POLLIN, - .revents = 0 - }; - - do { - ret = poll(&poll_fd, 1, msec); - } while (ret < 0 && errno == EINTR); - - if (ret == 0) { - error_setg(errp, "RDMA ERROR: poll cm event timeout"); - return -1; - } else if (ret < 0) { - error_setg(errp, "RDMA ERROR: failed to poll cm event, errno=%i", - errno); - return -1; - } else if (poll_fd.revents & POLLIN) { - if (rdma_get_cm_event(rdma->channel, cm_event) < 0) { - error_setg(errp, "RDMA ERROR: failed to get cm event"); - return -1; - } - return 0; - } else { - error_setg(errp, "RDMA ERROR: no POLLIN event, revent=%x", - poll_fd.revents); - return -1; - } -} - -static int qemu_rdma_connect(RDMAContext *rdma, bool return_path, - Error **errp) -{ - RDMACapabilities cap = { - .version = RDMA_CONTROL_VERSION_CURRENT, - .flags = 0, - }; - struct rdma_conn_param conn_param = { .initiator_depth = 2, - .retry_count = 5, - .private_data = &cap, - .private_data_len = sizeof(cap), - }; - struct rdma_cm_event *cm_event; - int ret; - - /* - * Only negotiate the capability with destination if the user - * on the source first requested the capability. - */ - if (rdma->pin_all) { - trace_qemu_rdma_connect_pin_all_requested(); - cap.flags |= RDMA_CAPABILITY_PIN_ALL; - } - - caps_to_network(&cap); - - ret = qemu_rdma_post_recv_control(rdma, RDMA_WRID_READY, errp); - if (ret < 0) { - goto err_rdma_source_connect; - } - - ret = rdma_connect(rdma->cm_id, &conn_param); - if (ret < 0) { - error_setg_errno(errp, errno, - "RDMA ERROR: connecting to destination!"); - goto err_rdma_source_connect; - } - - if (return_path) { - ret = qemu_get_cm_event_timeout(rdma, &cm_event, 5000, errp); - } else { - ret = rdma_get_cm_event(rdma->channel, &cm_event); - if (ret < 0) { - error_setg_errno(errp, errno, - "RDMA ERROR: failed to get cm event"); - } - } - if (ret < 0) { - goto err_rdma_source_connect; - } - - if (cm_event->event != RDMA_CM_EVENT_ESTABLISHED) { - error_setg(errp, "RDMA ERROR: connecting to destination!"); - rdma_ack_cm_event(cm_event); - goto err_rdma_source_connect; - } - rdma->connected = true; - - memcpy(&cap, cm_event->param.conn.private_data, sizeof(cap)); - network_to_caps(&cap); - - /* - * Verify that the *requested* capabilities are supported by the destination - * and disable them otherwise. - */ - if (rdma->pin_all && !(cap.flags & RDMA_CAPABILITY_PIN_ALL)) { - warn_report("RDMA: Server cannot support pinning all memory. " - "Will register memory dynamically."); - rdma->pin_all = false; - } - - trace_qemu_rdma_connect_pin_all_outcome(rdma->pin_all); - - rdma_ack_cm_event(cm_event); - - rdma->control_ready_expected = 1; - rdma->nb_sent = 0; - return 0; - -err_rdma_source_connect: - qemu_rdma_cleanup(rdma); - return -1; -} - -static int qemu_rdma_dest_init(RDMAContext *rdma, Error **errp) -{ - Error *err = NULL; - int ret; - struct rdma_cm_id *listen_id; - char ip[40] = "unknown"; - struct rdma_addrinfo *res, *e; - char port_str[16]; - int reuse = 1; - - for (int i = 0; i < RDMA_WRID_MAX; i++) { - rdma->wr_data[i].control_len = 0; - rdma->wr_data[i].control_curr = NULL; - } - - if (!rdma->host || !rdma->host[0]) { - error_setg(errp, "RDMA ERROR: RDMA host is not set!"); - rdma->errored = true; - return -1; - } - /* create CM channel */ - rdma->channel = rdma_create_event_channel(); - if (!rdma->channel) { - error_setg(errp, "RDMA ERROR: could not create rdma event channel"); - rdma->errored = true; - return -1; - } - - /* create CM id */ - ret = rdma_create_id(rdma->channel, &listen_id, NULL, RDMA_PS_TCP); - if (ret < 0) { - error_setg(errp, "RDMA ERROR: could not create cm_id!"); - goto err_dest_init_create_listen_id; - } - - snprintf(port_str, 16, "%d", rdma->port); - port_str[15] = '\0'; - - ret = rdma_getaddrinfo(rdma->host, port_str, NULL, &res); - if (ret) { - error_setg(errp, "RDMA ERROR: could not rdma_getaddrinfo address %s", - rdma->host); - goto err_dest_init_bind_addr; - } - - ret = rdma_set_option(listen_id, RDMA_OPTION_ID, RDMA_OPTION_ID_REUSEADDR, - &reuse, sizeof reuse); - if (ret < 0) { - error_setg(errp, "RDMA ERROR: Error: could not set REUSEADDR option"); - goto err_dest_init_bind_addr; - } - - /* Try all addresses, saving the first error in @err */ - for (e = res; e != NULL; e = e->ai_next) { - Error **local_errp = err ? NULL : &err; - - inet_ntop(e->ai_family, - &((struct sockaddr_in *) e->ai_dst_addr)->sin_addr, ip, sizeof ip); - trace_qemu_rdma_dest_init_trying(rdma->host, ip); - ret = rdma_bind_addr(listen_id, e->ai_dst_addr); - if (ret < 0) { - continue; - } - if (e->ai_family == AF_INET6) { - ret = qemu_rdma_broken_ipv6_kernel(listen_id->verbs, - local_errp); - if (ret < 0) { - continue; - } - } - error_free(err); - break; - } - - rdma_freeaddrinfo(res); - if (!e) { - if (err) { - error_propagate(errp, err); - } else { - error_setg(errp, "RDMA ERROR: Error: could not rdma_bind_addr!"); - } - goto err_dest_init_bind_addr; - } - - rdma->listen_id = listen_id; - qemu_rdma_dump_gid("dest_init", listen_id); - return 0; - -err_dest_init_bind_addr: - rdma_destroy_id(listen_id); -err_dest_init_create_listen_id: - rdma_destroy_event_channel(rdma->channel); - rdma->channel = NULL; - rdma->errored = true; - return -1; - -} - -static void qemu_rdma_return_path_dest_init(RDMAContext *rdma_return_path, - RDMAContext *rdma) -{ - for (int i = 0; i < RDMA_WRID_MAX; i++) { - rdma_return_path->wr_data[i].control_len = 0; - rdma_return_path->wr_data[i].control_curr = NULL; - } - - /*the CM channel and CM id is shared*/ - rdma_return_path->channel = rdma->channel; - rdma_return_path->listen_id = rdma->listen_id; - - rdma->return_path = rdma_return_path; - rdma_return_path->return_path = rdma; - rdma_return_path->is_return_path = true; -} - -static RDMAContext *qemu_rdma_data_init(InetSocketAddress *saddr, Error **errp) -{ - RDMAContext *rdma = NULL; - - rdma = g_new0(RDMAContext, 1); - rdma->current_index = -1; - rdma->current_chunk = -1; - - rdma->host = g_strdup(saddr->host); - rdma->port = atoi(saddr->port); - return rdma; -} - -/* - * QEMUFile interface to the control channel. - * SEND messages for control only. - * VM's ram is handled with regular RDMA messages. - */ -static ssize_t qio_channel_rdma_writev(QIOChannel *ioc, - const struct iovec *iov, - size_t niov, - int *fds, - size_t nfds, - int flags, - Error **errp) -{ - QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(ioc); - RDMAContext *rdma; - int ret; - ssize_t done = 0; - size_t len; - - RCU_READ_LOCK_GUARD(); - rdma = qatomic_rcu_read(&rioc->rdmaout); - - if (!rdma) { - error_setg(errp, "RDMA control channel output is not set"); - return -1; - } - - if (rdma->errored) { - error_setg(errp, - "RDMA is in an error state waiting migration to abort!"); - return -1; - } - - /* - * Push out any writes that - * we're queued up for VM's ram. - */ - ret = qemu_rdma_write_flush(rdma, errp); - if (ret < 0) { - rdma->errored = true; - return -1; - } - - for (int i = 0; i < niov; i++) { - size_t remaining = iov[i].iov_len; - uint8_t * data = (void *)iov[i].iov_base; - while (remaining) { - RDMAControlHeader head = {}; - - len = MIN(remaining, RDMA_SEND_INCREMENT); - remaining -= len; - - head.len = len; - head.type = RDMA_CONTROL_QEMU_FILE; - - ret = qemu_rdma_exchange_send(rdma, &head, - data, NULL, NULL, NULL, errp); - - if (ret < 0) { - rdma->errored = true; - return -1; - } - - data += len; - done += len; - } - } - - return done; -} - -static size_t qemu_rdma_fill(RDMAContext *rdma, uint8_t *buf, - size_t size, int idx) -{ - size_t len = 0; - - if (rdma->wr_data[idx].control_len) { - trace_qemu_rdma_fill(rdma->wr_data[idx].control_len, size); - - len = MIN(size, rdma->wr_data[idx].control_len); - memcpy(buf, rdma->wr_data[idx].control_curr, len); - rdma->wr_data[idx].control_curr += len; - rdma->wr_data[idx].control_len -= len; - } - - return len; -} - -/* - * QEMUFile interface to the control channel. - * RDMA links don't use bytestreams, so we have to - * return bytes to QEMUFile opportunistically. - */ -static ssize_t qio_channel_rdma_readv(QIOChannel *ioc, - const struct iovec *iov, - size_t niov, - int **fds, - size_t *nfds, - int flags, - Error **errp) -{ - QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(ioc); - RDMAContext *rdma; - RDMAControlHeader head; - int ret; - ssize_t done = 0; - size_t len; - - RCU_READ_LOCK_GUARD(); - rdma = qatomic_rcu_read(&rioc->rdmain); - - if (!rdma) { - error_setg(errp, "RDMA control channel input is not set"); - return -1; - } - - if (rdma->errored) { - error_setg(errp, - "RDMA is in an error state waiting migration to abort!"); - return -1; - } - - for (int i = 0; i < niov; i++) { - size_t want = iov[i].iov_len; - uint8_t *data = (void *)iov[i].iov_base; - - /* - * First, we hold on to the last SEND message we - * were given and dish out the bytes until we run - * out of bytes. - */ - len = qemu_rdma_fill(rdma, data, want, 0); - done += len; - want -= len; - /* Got what we needed, so go to next iovec */ - if (want == 0) { - continue; - } - - /* If we got any data so far, then don't wait - * for more, just return what we have */ - if (done > 0) { - break; - } - - - /* We've got nothing at all, so lets wait for - * more to arrive - */ - ret = qemu_rdma_exchange_recv(rdma, &head, RDMA_CONTROL_QEMU_FILE, - errp); - - if (ret < 0) { - rdma->errored = true; - return -1; - } - - /* - * SEND was received with new bytes, now try again. - */ - len = qemu_rdma_fill(rdma, data, want, 0); - done += len; - want -= len; - - /* Still didn't get enough, so lets just return */ - if (want) { - if (done == 0) { - return QIO_CHANNEL_ERR_BLOCK; - } else { - break; - } - } - } - return done; -} - -/* - * Block until all the outstanding chunks have been delivered by the hardware. - */ -static int qemu_rdma_drain_cq(RDMAContext *rdma) -{ - Error *err = NULL; - - if (qemu_rdma_write_flush(rdma, &err) < 0) { - error_report_err(err); - return -1; - } - - while (rdma->nb_sent) { - if (qemu_rdma_block_for_wrid(rdma, RDMA_WRID_RDMA_WRITE, NULL) < 0) { - error_report("rdma migration: complete polling error!"); - return -1; - } - } - - qemu_rdma_unregister_waiting(rdma); - - return 0; -} - - -static int qio_channel_rdma_set_blocking(QIOChannel *ioc, - bool blocking, - Error **errp) -{ - QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(ioc); - /* XXX we should make readv/writev actually honour this :-) */ - rioc->blocking = blocking; - return 0; -} - - -typedef struct QIOChannelRDMASource QIOChannelRDMASource; -struct QIOChannelRDMASource { - GSource parent; - QIOChannelRDMA *rioc; - GIOCondition condition; -}; - -static gboolean -qio_channel_rdma_source_prepare(GSource *source, - gint *timeout) -{ - QIOChannelRDMASource *rsource = (QIOChannelRDMASource *)source; - RDMAContext *rdma; - GIOCondition cond = 0; - *timeout = -1; - - RCU_READ_LOCK_GUARD(); - if (rsource->condition == G_IO_IN) { - rdma = qatomic_rcu_read(&rsource->rioc->rdmain); - } else { - rdma = qatomic_rcu_read(&rsource->rioc->rdmaout); - } - - if (!rdma) { - error_report("RDMAContext is NULL when prepare Gsource"); - return FALSE; - } - - if (rdma->wr_data[0].control_len) { - cond |= G_IO_IN; - } - cond |= G_IO_OUT; - - return cond & rsource->condition; -} - -static gboolean -qio_channel_rdma_source_check(GSource *source) -{ - QIOChannelRDMASource *rsource = (QIOChannelRDMASource *)source; - RDMAContext *rdma; - GIOCondition cond = 0; - - RCU_READ_LOCK_GUARD(); - if (rsource->condition == G_IO_IN) { - rdma = qatomic_rcu_read(&rsource->rioc->rdmain); - } else { - rdma = qatomic_rcu_read(&rsource->rioc->rdmaout); - } - - if (!rdma) { - error_report("RDMAContext is NULL when check Gsource"); - return FALSE; - } - - if (rdma->wr_data[0].control_len) { - cond |= G_IO_IN; - } - cond |= G_IO_OUT; - - return cond & rsource->condition; -} - -static gboolean -qio_channel_rdma_source_dispatch(GSource *source, - GSourceFunc callback, - gpointer user_data) -{ - QIOChannelFunc func = (QIOChannelFunc)callback; - QIOChannelRDMASource *rsource = (QIOChannelRDMASource *)source; - RDMAContext *rdma; - GIOCondition cond = 0; - - RCU_READ_LOCK_GUARD(); - if (rsource->condition == G_IO_IN) { - rdma = qatomic_rcu_read(&rsource->rioc->rdmain); - } else { - rdma = qatomic_rcu_read(&rsource->rioc->rdmaout); - } - - if (!rdma) { - error_report("RDMAContext is NULL when dispatch Gsource"); - return FALSE; - } - - if (rdma->wr_data[0].control_len) { - cond |= G_IO_IN; - } - cond |= G_IO_OUT; - - return (*func)(QIO_CHANNEL(rsource->rioc), - (cond & rsource->condition), - user_data); -} - -static void -qio_channel_rdma_source_finalize(GSource *source) -{ - QIOChannelRDMASource *ssource = (QIOChannelRDMASource *)source; - - object_unref(OBJECT(ssource->rioc)); -} - -static GSourceFuncs qio_channel_rdma_source_funcs = { - qio_channel_rdma_source_prepare, - qio_channel_rdma_source_check, - qio_channel_rdma_source_dispatch, - qio_channel_rdma_source_finalize -}; - -static GSource *qio_channel_rdma_create_watch(QIOChannel *ioc, - GIOCondition condition) -{ - QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(ioc); - QIOChannelRDMASource *ssource; - GSource *source; - - source = g_source_new(&qio_channel_rdma_source_funcs, - sizeof(QIOChannelRDMASource)); - ssource = (QIOChannelRDMASource *)source; - - ssource->rioc = rioc; - object_ref(OBJECT(rioc)); - - ssource->condition = condition; - - return source; -} - -static void qio_channel_rdma_set_aio_fd_handler(QIOChannel *ioc, - AioContext *read_ctx, - IOHandler *io_read, - AioContext *write_ctx, - IOHandler *io_write, - void *opaque) -{ - QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(ioc); - if (io_read) { - aio_set_fd_handler(read_ctx, rioc->rdmain->recv_comp_channel->fd, - io_read, io_write, NULL, NULL, opaque); - aio_set_fd_handler(read_ctx, rioc->rdmain->send_comp_channel->fd, - io_read, io_write, NULL, NULL, opaque); - } else { - aio_set_fd_handler(write_ctx, rioc->rdmaout->recv_comp_channel->fd, - io_read, io_write, NULL, NULL, opaque); - aio_set_fd_handler(write_ctx, rioc->rdmaout->send_comp_channel->fd, - io_read, io_write, NULL, NULL, opaque); - } -} - -struct rdma_close_rcu { - struct rcu_head rcu; - RDMAContext *rdmain; - RDMAContext *rdmaout; -}; - -/* callback from qio_channel_rdma_close via call_rcu */ -static void qio_channel_rdma_close_rcu(struct rdma_close_rcu *rcu) -{ - if (rcu->rdmain) { - qemu_rdma_cleanup(rcu->rdmain); - } - - if (rcu->rdmaout) { - qemu_rdma_cleanup(rcu->rdmaout); - } - - g_free(rcu->rdmain); - g_free(rcu->rdmaout); - g_free(rcu); -} - -static int qio_channel_rdma_close(QIOChannel *ioc, - Error **errp) -{ - QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(ioc); - RDMAContext *rdmain, *rdmaout; - struct rdma_close_rcu *rcu = g_new(struct rdma_close_rcu, 1); - - trace_qemu_rdma_close(); - - rdmain = rioc->rdmain; - if (rdmain) { - qatomic_rcu_set(&rioc->rdmain, NULL); - } - - rdmaout = rioc->rdmaout; - if (rdmaout) { - qatomic_rcu_set(&rioc->rdmaout, NULL); - } - - rcu->rdmain = rdmain; - rcu->rdmaout = rdmaout; - call_rcu(rcu, qio_channel_rdma_close_rcu, rcu); - - return 0; -} - -static int -qio_channel_rdma_shutdown(QIOChannel *ioc, - QIOChannelShutdown how, - Error **errp) -{ - QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(ioc); - RDMAContext *rdmain, *rdmaout; - - RCU_READ_LOCK_GUARD(); - - rdmain = qatomic_rcu_read(&rioc->rdmain); - rdmaout = qatomic_rcu_read(&rioc->rdmain); - - switch (how) { - case QIO_CHANNEL_SHUTDOWN_READ: - if (rdmain) { - rdmain->errored = true; - } - break; - case QIO_CHANNEL_SHUTDOWN_WRITE: - if (rdmaout) { - rdmaout->errored = true; - } - break; - case QIO_CHANNEL_SHUTDOWN_BOTH: - default: - if (rdmain) { - rdmain->errored = true; - } - if (rdmaout) { - rdmaout->errored = true; - } - break; - } - - return 0; -} - -/* - * Parameters: - * @offset == 0 : - * This means that 'block_offset' is a full virtual address that does not - * belong to a RAMBlock of the virtual machine and instead - * represents a private malloc'd memory area that the caller wishes to - * transfer. - * - * @offset != 0 : - * Offset is an offset to be added to block_offset and used - * to also lookup the corresponding RAMBlock. - * - * @size : Number of bytes to transfer - * - * @pages_sent : User-specificed pointer to indicate how many pages were - * sent. Usually, this will not be more than a few bytes of - * the protocol because most transfers are sent asynchronously. - */ -static int qemu_rdma_save_page(QEMUFile *f, ram_addr_t block_offset, - ram_addr_t offset, size_t size) -{ - QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(qemu_file_get_ioc(f)); - Error *err = NULL; - RDMAContext *rdma; - int ret; - - RCU_READ_LOCK_GUARD(); - rdma = qatomic_rcu_read(&rioc->rdmaout); - - if (!rdma) { - return -1; - } - - if (rdma_errored(rdma)) { - return -1; - } - - qemu_fflush(f); - - /* - * Add this page to the current 'chunk'. If the chunk - * is full, or the page doesn't belong to the current chunk, - * an actual RDMA write will occur and a new chunk will be formed. - */ - ret = qemu_rdma_write(rdma, block_offset, offset, size, &err); - if (ret < 0) { - error_report_err(err); - goto err; - } - - /* - * Drain the Completion Queue if possible, but do not block, - * just poll. - * - * If nothing to poll, the end of the iteration will do this - * again to make sure we don't overflow the request queue. - */ - while (1) { - uint64_t wr_id, wr_id_in; - ret = qemu_rdma_poll(rdma, rdma->recv_cq, &wr_id_in, NULL); - - if (ret < 0) { - error_report("rdma migration: polling error"); - goto err; - } - - wr_id = wr_id_in & RDMA_WRID_TYPE_MASK; - - if (wr_id == RDMA_WRID_NONE) { - break; - } - } - - while (1) { - uint64_t wr_id, wr_id_in; - ret = qemu_rdma_poll(rdma, rdma->send_cq, &wr_id_in, NULL); - - if (ret < 0) { - error_report("rdma migration: polling error"); - goto err; - } - - wr_id = wr_id_in & RDMA_WRID_TYPE_MASK; - - if (wr_id == RDMA_WRID_NONE) { - break; - } - } - - return RAM_SAVE_CONTROL_DELAYED; - -err: - rdma->errored = true; - return -1; -} - -int rdma_control_save_page(QEMUFile *f, ram_addr_t block_offset, - ram_addr_t offset, size_t size) -{ - if (!migrate_rdma() || migration_in_postcopy()) { - return RAM_SAVE_CONTROL_NOT_SUPP; - } - - int ret = qemu_rdma_save_page(f, block_offset, offset, size); - - if (ret != RAM_SAVE_CONTROL_DELAYED && - ret != RAM_SAVE_CONTROL_NOT_SUPP) { - if (ret < 0) { - qemu_file_set_error(f, ret); - } - } - return ret; -} - -static void rdma_accept_incoming_migration(void *opaque); - -static void rdma_cm_poll_handler(void *opaque) -{ - RDMAContext *rdma = opaque; - struct rdma_cm_event *cm_event; - MigrationIncomingState *mis = migration_incoming_get_current(); - - if (rdma_get_cm_event(rdma->channel, &cm_event) < 0) { - error_report("get_cm_event failed %d", errno); - return; - } - - if (cm_event->event == RDMA_CM_EVENT_DISCONNECTED || - cm_event->event == RDMA_CM_EVENT_DEVICE_REMOVAL) { - if (!rdma->errored && - migration_incoming_get_current()->state != - MIGRATION_STATUS_COMPLETED) { - error_report("receive cm event, cm event is %d", cm_event->event); - rdma->errored = true; - if (rdma->return_path) { - rdma->return_path->errored = true; - } - } - rdma_ack_cm_event(cm_event); - if (mis->loadvm_co) { - qemu_coroutine_enter(mis->loadvm_co); - } - return; - } - rdma_ack_cm_event(cm_event); -} - -static int qemu_rdma_accept(RDMAContext *rdma) -{ - Error *err = NULL; - RDMACapabilities cap; - struct rdma_conn_param conn_param = { - .responder_resources = 2, - .private_data = &cap, - .private_data_len = sizeof(cap), - }; - RDMAContext *rdma_return_path = NULL; - g_autoptr(InetSocketAddress) isock = g_new0(InetSocketAddress, 1); - struct rdma_cm_event *cm_event; - struct ibv_context *verbs; - int ret; - - ret = rdma_get_cm_event(rdma->channel, &cm_event); - if (ret < 0) { - goto err_rdma_dest_wait; - } - - if (cm_event->event != RDMA_CM_EVENT_CONNECT_REQUEST) { - rdma_ack_cm_event(cm_event); - goto err_rdma_dest_wait; - } - - isock->host = g_strdup(rdma->host); - isock->port = g_strdup_printf("%d", rdma->port); - - /* - * initialize the RDMAContext for return path for postcopy after first - * connection request reached. - */ - if ((migrate_postcopy() || migrate_return_path()) - && !rdma->is_return_path) { - rdma_return_path = qemu_rdma_data_init(isock, NULL); - if (rdma_return_path == NULL) { - rdma_ack_cm_event(cm_event); - goto err_rdma_dest_wait; - } - - qemu_rdma_return_path_dest_init(rdma_return_path, rdma); - } - - memcpy(&cap, cm_event->param.conn.private_data, sizeof(cap)); - - network_to_caps(&cap); - - if (cap.version < 1 || cap.version > RDMA_CONTROL_VERSION_CURRENT) { - error_report("Unknown source RDMA version: %d, bailing...", - cap.version); - rdma_ack_cm_event(cm_event); - goto err_rdma_dest_wait; - } - - /* - * Respond with only the capabilities this version of QEMU knows about. - */ - cap.flags &= known_capabilities; - - /* - * Enable the ones that we do know about. - * Add other checks here as new ones are introduced. - */ - if (cap.flags & RDMA_CAPABILITY_PIN_ALL) { - rdma->pin_all = true; - } - - rdma->cm_id = cm_event->id; - verbs = cm_event->id->verbs; - - rdma_ack_cm_event(cm_event); - - trace_qemu_rdma_accept_pin_state(rdma->pin_all); - - caps_to_network(&cap); - - trace_qemu_rdma_accept_pin_verbsc(verbs); - - if (!rdma->verbs) { - rdma->verbs = verbs; - } else if (rdma->verbs != verbs) { - error_report("ibv context not matching %p, %p!", rdma->verbs, - verbs); - goto err_rdma_dest_wait; - } - - qemu_rdma_dump_id("dest_init", verbs); - - ret = qemu_rdma_alloc_pd_cq(rdma, &err); - if (ret < 0) { - error_report_err(err); - goto err_rdma_dest_wait; - } - - ret = qemu_rdma_alloc_qp(rdma); - if (ret < 0) { - error_report("rdma migration: error allocating qp!"); - goto err_rdma_dest_wait; - } - - qemu_rdma_init_ram_blocks(rdma); - - for (int i = 0; i < RDMA_WRID_MAX; i++) { - ret = qemu_rdma_reg_control(rdma, i); - if (ret < 0) { - error_report("rdma: error registering %d control", i); - goto err_rdma_dest_wait; - } - } - - /* Accept the second connection request for return path */ - if ((migrate_postcopy() || migrate_return_path()) - && !rdma->is_return_path) { - qemu_set_fd_handler(rdma->channel->fd, rdma_accept_incoming_migration, - NULL, - (void *)(intptr_t)rdma->return_path); - } else { - qemu_set_fd_handler(rdma->channel->fd, rdma_cm_poll_handler, - NULL, rdma); - } - - ret = rdma_accept(rdma->cm_id, &conn_param); - if (ret < 0) { - error_report("rdma_accept failed"); - goto err_rdma_dest_wait; - } - - ret = rdma_get_cm_event(rdma->channel, &cm_event); - if (ret < 0) { - error_report("rdma_accept get_cm_event failed"); - goto err_rdma_dest_wait; - } - - if (cm_event->event != RDMA_CM_EVENT_ESTABLISHED) { - error_report("rdma_accept not event established"); - rdma_ack_cm_event(cm_event); - goto err_rdma_dest_wait; - } - - rdma_ack_cm_event(cm_event); - rdma->connected = true; - - ret = qemu_rdma_post_recv_control(rdma, RDMA_WRID_READY, &err); - if (ret < 0) { - error_report_err(err); - goto err_rdma_dest_wait; - } - - qemu_rdma_dump_gid("dest_connect", rdma->cm_id); - - return 0; - -err_rdma_dest_wait: - rdma->errored = true; - qemu_rdma_cleanup(rdma); - g_free(rdma_return_path); - return -1; -} - -static int dest_ram_sort_func(const void *a, const void *b) -{ - unsigned int a_index = ((const RDMALocalBlock *)a)->src_index; - unsigned int b_index = ((const RDMALocalBlock *)b)->src_index; - - return (a_index < b_index) ? -1 : (a_index != b_index); -} - -/* - * During each iteration of the migration, we listen for instructions - * by the source VM to perform dynamic page registrations before they - * can perform RDMA operations. - * - * We respond with the 'rkey'. - * - * Keep doing this until the source tells us to stop. - */ -int rdma_registration_handle(QEMUFile *f) -{ - RDMAControlHeader reg_resp = { .len = sizeof(RDMARegisterResult), - .type = RDMA_CONTROL_REGISTER_RESULT, - .repeat = 0, - }; - RDMAControlHeader unreg_resp = { .len = 0, - .type = RDMA_CONTROL_UNREGISTER_FINISHED, - .repeat = 0, - }; - RDMAControlHeader blocks = { .type = RDMA_CONTROL_RAM_BLOCKS_RESULT, - .repeat = 1 }; - QIOChannelRDMA *rioc; - Error *err = NULL; - RDMAContext *rdma; - RDMALocalBlocks *local; - RDMAControlHeader head; - RDMARegister *reg, *registers; - RDMACompress *comp; - RDMARegisterResult *reg_result; - static RDMARegisterResult results[RDMA_CONTROL_MAX_COMMANDS_PER_MESSAGE]; - RDMALocalBlock *block; - void *host_addr; - int ret; - int idx = 0; - - if (!migrate_rdma()) { - return 0; - } - - RCU_READ_LOCK_GUARD(); - rioc = QIO_CHANNEL_RDMA(qemu_file_get_ioc(f)); - rdma = qatomic_rcu_read(&rioc->rdmain); - - if (!rdma) { - return -1; - } - - if (rdma_errored(rdma)) { - return -1; - } - - local = &rdma->local_ram_blocks; - do { - trace_rdma_registration_handle_wait(); - - ret = qemu_rdma_exchange_recv(rdma, &head, RDMA_CONTROL_NONE, &err); - - if (ret < 0) { - error_report_err(err); - break; - } - - if (head.repeat > RDMA_CONTROL_MAX_COMMANDS_PER_MESSAGE) { - error_report("rdma: Too many requests in this message (%d)." - "Bailing.", head.repeat); - break; - } - - switch (head.type) { - case RDMA_CONTROL_COMPRESS: - comp = (RDMACompress *) rdma->wr_data[idx].control_curr; - network_to_compress(comp); - - trace_rdma_registration_handle_compress(comp->length, - comp->block_idx, - comp->offset); - if (comp->block_idx >= rdma->local_ram_blocks.nb_blocks) { - error_report("rdma: 'compress' bad block index %u (vs %d)", - (unsigned int)comp->block_idx, - rdma->local_ram_blocks.nb_blocks); - goto err; - } - block = &(rdma->local_ram_blocks.block[comp->block_idx]); - - host_addr = block->local_host_addr + - (comp->offset - block->offset); - if (comp->value) { - error_report("rdma: Zero page with non-zero (%d) value", - comp->value); - goto err; - } - ram_handle_zero(host_addr, comp->length); - break; - - case RDMA_CONTROL_REGISTER_FINISHED: - trace_rdma_registration_handle_finished(); - return 0; - - case RDMA_CONTROL_RAM_BLOCKS_REQUEST: - trace_rdma_registration_handle_ram_blocks(); - - /* Sort our local RAM Block list so it's the same as the source, - * we can do this since we've filled in a src_index in the list - * as we received the RAMBlock list earlier. - */ - qsort(rdma->local_ram_blocks.block, - rdma->local_ram_blocks.nb_blocks, - sizeof(RDMALocalBlock), dest_ram_sort_func); - for (int i = 0; i < local->nb_blocks; i++) { - local->block[i].index = i; - } - - if (rdma->pin_all) { - ret = qemu_rdma_reg_whole_ram_blocks(rdma, &err); - if (ret < 0) { - error_report_err(err); - goto err; - } - } - - /* - * Dest uses this to prepare to transmit the RAMBlock descriptions - * to the source VM after connection setup. - * Both sides use the "remote" structure to communicate and update - * their "local" descriptions with what was sent. - */ - for (int i = 0; i < local->nb_blocks; i++) { - rdma->dest_blocks[i].remote_host_addr = - (uintptr_t)(local->block[i].local_host_addr); - - if (rdma->pin_all) { - rdma->dest_blocks[i].remote_rkey = local->block[i].mr->rkey; - } - - rdma->dest_blocks[i].offset = local->block[i].offset; - rdma->dest_blocks[i].length = local->block[i].length; - - dest_block_to_network(&rdma->dest_blocks[i]); - trace_rdma_registration_handle_ram_blocks_loop( - local->block[i].block_name, - local->block[i].offset, - local->block[i].length, - local->block[i].local_host_addr, - local->block[i].src_index); - } - - blocks.len = rdma->local_ram_blocks.nb_blocks - * sizeof(RDMADestBlock); - - - ret = qemu_rdma_post_send_control(rdma, - (uint8_t *) rdma->dest_blocks, &blocks, - &err); - - if (ret < 0) { - error_report_err(err); - goto err; - } - - break; - case RDMA_CONTROL_REGISTER_REQUEST: - trace_rdma_registration_handle_register(head.repeat); - - reg_resp.repeat = head.repeat; - registers = (RDMARegister *) rdma->wr_data[idx].control_curr; - - for (int count = 0; count < head.repeat; count++) { - uint64_t chunk; - uint8_t *chunk_start, *chunk_end; - - reg = &registers[count]; - network_to_register(reg); - - reg_result = &results[count]; - - trace_rdma_registration_handle_register_loop(count, - reg->current_index, reg->key.current_addr, reg->chunks); - - if (reg->current_index >= rdma->local_ram_blocks.nb_blocks) { - error_report("rdma: 'register' bad block index %u (vs %d)", - (unsigned int)reg->current_index, - rdma->local_ram_blocks.nb_blocks); - goto err; - } - block = &(rdma->local_ram_blocks.block[reg->current_index]); - if (block->is_ram_block) { - if (block->offset > reg->key.current_addr) { - error_report("rdma: bad register address for block %s" - " offset: %" PRIx64 " current_addr: %" PRIx64, - block->block_name, block->offset, - reg->key.current_addr); - goto err; - } - host_addr = (block->local_host_addr + - (reg->key.current_addr - block->offset)); - chunk = ram_chunk_index(block->local_host_addr, - (uint8_t *) host_addr); - } else { - chunk = reg->key.chunk; - host_addr = block->local_host_addr + - (reg->key.chunk * (1UL << RDMA_REG_CHUNK_SHIFT)); - /* Check for particularly bad chunk value */ - if (host_addr < (void *)block->local_host_addr) { - error_report("rdma: bad chunk for block %s" - " chunk: %" PRIx64, - block->block_name, reg->key.chunk); - goto err; - } - } - chunk_start = ram_chunk_start(block, chunk); - chunk_end = ram_chunk_end(block, chunk + reg->chunks); - /* avoid "-Waddress-of-packed-member" warning */ - uint32_t tmp_rkey = 0; - if (qemu_rdma_register_and_get_keys(rdma, block, - (uintptr_t)host_addr, NULL, &tmp_rkey, - chunk, chunk_start, chunk_end)) { - error_report("cannot get rkey"); - goto err; - } - reg_result->rkey = tmp_rkey; - - reg_result->host_addr = (uintptr_t)block->local_host_addr; - - trace_rdma_registration_handle_register_rkey(reg_result->rkey); - - result_to_network(reg_result); - } - - ret = qemu_rdma_post_send_control(rdma, - (uint8_t *) results, &reg_resp, &err); - - if (ret < 0) { - error_report_err(err); - goto err; - } - break; - case RDMA_CONTROL_UNREGISTER_REQUEST: - trace_rdma_registration_handle_unregister(head.repeat); - unreg_resp.repeat = head.repeat; - registers = (RDMARegister *) rdma->wr_data[idx].control_curr; - - for (int count = 0; count < head.repeat; count++) { - reg = &registers[count]; - network_to_register(reg); - - trace_rdma_registration_handle_unregister_loop(count, - reg->current_index, reg->key.chunk); - - block = &(rdma->local_ram_blocks.block[reg->current_index]); - - ret = ibv_dereg_mr(block->pmr[reg->key.chunk]); - block->pmr[reg->key.chunk] = NULL; - - if (ret != 0) { - error_report("rdma unregistration chunk failed: %s", - strerror(errno)); - goto err; - } - - rdma->total_registrations--; - - trace_rdma_registration_handle_unregister_success(reg->key.chunk); - } - - ret = qemu_rdma_post_send_control(rdma, NULL, &unreg_resp, &err); - - if (ret < 0) { - error_report_err(err); - goto err; - } - break; - case RDMA_CONTROL_REGISTER_RESULT: - error_report("Invalid RESULT message at dest."); - goto err; - default: - error_report("Unknown control message %s", control_desc(head.type)); - goto err; - } - } while (1); - -err: - rdma->errored = true; - return -1; -} - -/* Destination: - * Called during the initial RAM load section which lists the - * RAMBlocks by name. This lets us know the order of the RAMBlocks on - * the source. We've already built our local RAMBlock list, but not - * yet sent the list to the source. - */ -int rdma_block_notification_handle(QEMUFile *f, const char *name) -{ - int curr; - int found = -1; - - if (!migrate_rdma()) { - return 0; - } - - RCU_READ_LOCK_GUARD(); - QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(qemu_file_get_ioc(f)); - RDMAContext *rdma = qatomic_rcu_read(&rioc->rdmain); - - if (!rdma) { - return -1; - } - - /* Find the matching RAMBlock in our local list */ - for (curr = 0; curr < rdma->local_ram_blocks.nb_blocks; curr++) { - if (!strcmp(rdma->local_ram_blocks.block[curr].block_name, name)) { - found = curr; - break; - } - } - - if (found == -1) { - error_report("RAMBlock '%s' not found on destination", name); - return -1; - } - - rdma->local_ram_blocks.block[curr].src_index = rdma->next_src_index; - trace_rdma_block_notification_handle(name, rdma->next_src_index); - rdma->next_src_index++; - - return 0; -} - -int rdma_registration_start(QEMUFile *f, uint64_t flags) -{ - if (!migrate_rdma() || migration_in_postcopy()) { - return 0; - } - - QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(qemu_file_get_ioc(f)); - RCU_READ_LOCK_GUARD(); - RDMAContext *rdma = qatomic_rcu_read(&rioc->rdmaout); - if (!rdma) { - return -1; - } - - if (rdma_errored(rdma)) { - return -1; - } - - trace_rdma_registration_start(flags); - qemu_put_be64(f, RAM_SAVE_FLAG_HOOK); - return qemu_fflush(f); -} - -/* - * Inform dest that dynamic registrations are done for now. - * First, flush writes, if any. - */ -int rdma_registration_stop(QEMUFile *f, uint64_t flags) -{ - QIOChannelRDMA *rioc; - Error *err = NULL; - RDMAContext *rdma; - RDMAControlHeader head = { .len = 0, .repeat = 1 }; - int ret; - - if (!migrate_rdma() || migration_in_postcopy()) { - return 0; - } - - RCU_READ_LOCK_GUARD(); - rioc = QIO_CHANNEL_RDMA(qemu_file_get_ioc(f)); - rdma = qatomic_rcu_read(&rioc->rdmaout); - if (!rdma) { - return -1; - } - - if (rdma_errored(rdma)) { - return -1; - } - - qemu_fflush(f); - ret = qemu_rdma_drain_cq(rdma); - - if (ret < 0) { - goto err; - } - - if (flags == RAM_CONTROL_SETUP) { - RDMAControlHeader resp = {.type = RDMA_CONTROL_RAM_BLOCKS_RESULT }; - RDMALocalBlocks *local = &rdma->local_ram_blocks; - int reg_result_idx, nb_dest_blocks; - - head.type = RDMA_CONTROL_RAM_BLOCKS_REQUEST; - trace_rdma_registration_stop_ram(); - - /* - * Make sure that we parallelize the pinning on both sides. - * For very large guests, doing this serially takes a really - * long time, so we have to 'interleave' the pinning locally - * with the control messages by performing the pinning on this - * side before we receive the control response from the other - * side that the pinning has completed. - */ - ret = qemu_rdma_exchange_send(rdma, &head, NULL, &resp, - &reg_result_idx, rdma->pin_all ? - qemu_rdma_reg_whole_ram_blocks : NULL, - &err); - if (ret < 0) { - error_report_err(err); - return -1; - } - - nb_dest_blocks = resp.len / sizeof(RDMADestBlock); - - /* - * The protocol uses two different sets of rkeys (mutually exclusive): - * 1. One key to represent the virtual address of the entire ram block. - * (dynamic chunk registration disabled - pin everything with one rkey.) - * 2. One to represent individual chunks within a ram block. - * (dynamic chunk registration enabled - pin individual chunks.) - * - * Once the capability is successfully negotiated, the destination transmits - * the keys to use (or sends them later) including the virtual addresses - * and then propagates the remote ram block descriptions to his local copy. - */ - - if (local->nb_blocks != nb_dest_blocks) { - error_report("ram blocks mismatch (Number of blocks %d vs %d)", - local->nb_blocks, nb_dest_blocks); - error_printf("Your QEMU command line parameters are probably " - "not identical on both the source and destination."); - rdma->errored = true; - return -1; - } - - qemu_rdma_move_header(rdma, reg_result_idx, &resp); - memcpy(rdma->dest_blocks, - rdma->wr_data[reg_result_idx].control_curr, resp.len); - for (int i = 0; i < nb_dest_blocks; i++) { - network_to_dest_block(&rdma->dest_blocks[i]); - - /* We require that the blocks are in the same order */ - if (rdma->dest_blocks[i].length != local->block[i].length) { - error_report("Block %s/%d has a different length %" PRIu64 - "vs %" PRIu64, - local->block[i].block_name, i, - local->block[i].length, - rdma->dest_blocks[i].length); - rdma->errored = true; - return -1; - } - local->block[i].remote_host_addr = - rdma->dest_blocks[i].remote_host_addr; - local->block[i].remote_rkey = rdma->dest_blocks[i].remote_rkey; - } - } - - trace_rdma_registration_stop(flags); - - head.type = RDMA_CONTROL_REGISTER_FINISHED; - ret = qemu_rdma_exchange_send(rdma, &head, NULL, NULL, NULL, NULL, &err); - - if (ret < 0) { - error_report_err(err); - goto err; - } - - return 0; -err: - rdma->errored = true; - return -1; -} - -static void qio_channel_rdma_finalize(Object *obj) -{ - QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(obj); - if (rioc->rdmain) { - qemu_rdma_cleanup(rioc->rdmain); - g_free(rioc->rdmain); - rioc->rdmain = NULL; - } - if (rioc->rdmaout) { - qemu_rdma_cleanup(rioc->rdmaout); - g_free(rioc->rdmaout); - rioc->rdmaout = NULL; - } -} - -static void qio_channel_rdma_class_init(ObjectClass *klass, - void *class_data G_GNUC_UNUSED) -{ - QIOChannelClass *ioc_klass = QIO_CHANNEL_CLASS(klass); - - ioc_klass->io_writev = qio_channel_rdma_writev; - ioc_klass->io_readv = qio_channel_rdma_readv; - ioc_klass->io_set_blocking = qio_channel_rdma_set_blocking; - ioc_klass->io_close = qio_channel_rdma_close; - ioc_klass->io_create_watch = qio_channel_rdma_create_watch; - ioc_klass->io_set_aio_fd_handler = qio_channel_rdma_set_aio_fd_handler; - ioc_klass->io_shutdown = qio_channel_rdma_shutdown; -} - -static const TypeInfo qio_channel_rdma_info = { - .parent = TYPE_QIO_CHANNEL, - .name = TYPE_QIO_CHANNEL_RDMA, - .instance_size = sizeof(QIOChannelRDMA), - .instance_finalize = qio_channel_rdma_finalize, - .class_init = qio_channel_rdma_class_init, -}; - -static void qio_channel_rdma_register_types(void) -{ - type_register_static(&qio_channel_rdma_info); -} - -type_init(qio_channel_rdma_register_types); - -static QEMUFile *rdma_new_input(RDMAContext *rdma) -{ - QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(object_new(TYPE_QIO_CHANNEL_RDMA)); - - rioc->file = qemu_file_new_input(QIO_CHANNEL(rioc)); - rioc->rdmain = rdma; - rioc->rdmaout = rdma->return_path; - - return rioc->file; -} - -static QEMUFile *rdma_new_output(RDMAContext *rdma) -{ - QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(object_new(TYPE_QIO_CHANNEL_RDMA)); - - rioc->file = qemu_file_new_output(QIO_CHANNEL(rioc)); - rioc->rdmaout = rdma; - rioc->rdmain = rdma->return_path; - - return rioc->file; -} - -static void rdma_accept_incoming_migration(void *opaque) -{ - RDMAContext *rdma = opaque; - QEMUFile *f; - - trace_qemu_rdma_accept_incoming_migration(); - if (qemu_rdma_accept(rdma) < 0) { - error_report("RDMA ERROR: Migration initialization failed"); - return; - } - - trace_qemu_rdma_accept_incoming_migration_accepted(); - - if (rdma->is_return_path) { - return; - } - - f = rdma_new_input(rdma); - if (f == NULL) { - error_report("RDMA ERROR: could not open RDMA for input"); - qemu_rdma_cleanup(rdma); - return; - } - - rdma->migration_started_on_destination = 1; - migration_fd_process_incoming(f); -} - -void rdma_start_incoming_migration(InetSocketAddress *host_port, - Error **errp) -{ - MigrationState *s = migrate_get_current(); - int ret; - RDMAContext *rdma; - - trace_rdma_start_incoming_migration(); - - /* Avoid ram_block_discard_disable(), cannot change during migration. */ - if (ram_block_discard_is_required()) { - error_setg(errp, "RDMA: cannot disable RAM discard"); - return; - } - - rdma = qemu_rdma_data_init(host_port, errp); - if (rdma == NULL) { - goto err; - } - - ret = qemu_rdma_dest_init(rdma, errp); - if (ret < 0) { - goto err; - } - - trace_rdma_start_incoming_migration_after_dest_init(); - - ret = rdma_listen(rdma->listen_id, 5); - - if (ret < 0) { - error_setg(errp, "RDMA ERROR: listening on socket!"); - goto cleanup_rdma; - } - - trace_rdma_start_incoming_migration_after_rdma_listen(); - s->rdma_migration = true; - qemu_set_fd_handler(rdma->channel->fd, rdma_accept_incoming_migration, - NULL, (void *)(intptr_t)rdma); - return; - -cleanup_rdma: - qemu_rdma_cleanup(rdma); -err: - if (rdma) { - g_free(rdma->host); - } - g_free(rdma); -} - -void rdma_start_outgoing_migration(void *opaque, - InetSocketAddress *host_port, Error **errp) -{ - MigrationState *s = opaque; - RDMAContext *rdma_return_path = NULL; - RDMAContext *rdma; - int ret; - - /* Avoid ram_block_discard_disable(), cannot change during migration. */ - if (ram_block_discard_is_required()) { - error_setg(errp, "RDMA: cannot disable RAM discard"); - return; - } - - rdma = qemu_rdma_data_init(host_port, errp); - if (rdma == NULL) { - goto err; - } - - ret = qemu_rdma_source_init(rdma, migrate_rdma_pin_all(), errp); - - if (ret < 0) { - goto err; - } - - trace_rdma_start_outgoing_migration_after_rdma_source_init(); - ret = qemu_rdma_connect(rdma, false, errp); - - if (ret < 0) { - goto err; - } - - /* RDMA postcopy need a separate queue pair for return path */ - if (migrate_postcopy() || migrate_return_path()) { - rdma_return_path = qemu_rdma_data_init(host_port, errp); - - if (rdma_return_path == NULL) { - goto return_path_err; - } - - ret = qemu_rdma_source_init(rdma_return_path, - migrate_rdma_pin_all(), errp); - - if (ret < 0) { - goto return_path_err; - } - - ret = qemu_rdma_connect(rdma_return_path, true, errp); - - if (ret < 0) { - goto return_path_err; - } - - rdma->return_path = rdma_return_path; - rdma_return_path->return_path = rdma; - rdma_return_path->is_return_path = true; - } - - trace_rdma_start_outgoing_migration_after_rdma_connect(); - - s->to_dst_file = rdma_new_output(rdma); - s->rdma_migration = true; - migrate_fd_connect(s, NULL); - return; -return_path_err: - qemu_rdma_cleanup(rdma); -err: - g_free(rdma); - g_free(rdma_return_path); -} diff --git a/migration/savevm.c b/migration/savevm.c index 388d7af7cd..939d35d69e 100644 --- a/migration/savevm.c +++ b/migration/savevm.c @@ -2970,7 +2970,7 @@ int qemu_loadvm_state(QEMUFile *f) /* We've got to be careful; if we don't read the data and just shut the fd * then the sender can error if we close while it's still sending. - * We also mustn't read data that isn't there; some transports (RDMA) + * We also mustn't read data that isn't there; some transports * will stall waiting for that data when the source has already closed. */ if (ret == 0 && should_send_vmdesc()) { diff --git a/monitor/qmp-cmds.c b/monitor/qmp-cmds.c index b0f948d337..f84a0dc523 100644 --- a/monitor/qmp-cmds.c +++ b/monitor/qmp-cmds.c @@ -31,7 +31,6 @@ #include "qapi/type-helpers.h" #include "hw/mem/memory-device.h" #include "hw/intc/intc.h" -#include "hw/rdma/rdma.h" NameInfo *qmp_query_name(Error **errp) { diff --git a/Kconfig.host b/Kconfig.host index f496475f8e..f6a2a131e6 100644 --- a/Kconfig.host +++ b/Kconfig.host @@ -35,9 +35,6 @@ config VHOST_KERNEL config VIRTFS bool -config PVRDMA - bool - config MULTIPROCESS_ALLOWED bool imply MULTIPROCESS diff --git a/contrib/rdmacm-mux/meson.build b/contrib/rdmacm-mux/meson.build deleted file mode 100644 index 36c9c89630..0000000000 --- a/contrib/rdmacm-mux/meson.build +++ /dev/null @@ -1,7 +0,0 @@ -if have_pvrdma - # FIXME: broken on big endian architectures - executable('rdmacm-mux', files('main.c'), genh, - dependencies: [glib, libumad], - build_by_default: false, - install: false) -endif diff --git a/hmp-commands-info.hx b/hmp-commands-info.hx index ad1b1306e3..20a9835ea8 100644 --- a/hmp-commands-info.hx +++ b/hmp-commands-info.hx @@ -182,19 +182,6 @@ SRST Show PIC state. ERST - { - .name = "rdma", - .args_type = "", - .params = "", - .help = "show RDMA state", - .cmd_info_hrt = qmp_x_query_rdma, - }, - -SRST - ``info rdma`` - Show RDMA state. -ERST - { .name = "pci", .args_type = "", diff --git a/hw/Kconfig b/hw/Kconfig index 2c00936c28..32f876deb0 100644 --- a/hw/Kconfig +++ b/hw/Kconfig @@ -29,7 +29,6 @@ source pci-bridge/Kconfig source pci-host/Kconfig source pcmcia/Kconfig source pci/Kconfig -source rdma/Kconfig source remote/Kconfig source rtc/Kconfig source scsi/Kconfig diff --git a/hw/meson.build b/hw/meson.build index 463d702683..3049a6fab0 100644 --- a/hw/meson.build +++ b/hw/meson.build @@ -28,7 +28,6 @@ subdir('pci') subdir('pci-bridge') subdir('pci-host') subdir('pcmcia') -subdir('rdma') subdir('rtc') subdir('scsi') subdir('sd') diff --git a/hw/rdma/Kconfig b/hw/rdma/Kconfig deleted file mode 100644 index 840320bdc0..0000000000 --- a/hw/rdma/Kconfig +++ /dev/null @@ -1,3 +0,0 @@ -config VMW_PVRDMA - default y if PCI_DEVICES - depends on PVRDMA && MSI_NONBROKEN && VMXNET3_PCI diff --git a/hw/rdma/meson.build b/hw/rdma/meson.build deleted file mode 100644 index 363c9b8c83..0000000000 --- a/hw/rdma/meson.build +++ /dev/null @@ -1,12 +0,0 @@ -system_ss.add(when: 'CONFIG_VMW_PVRDMA', if_true: files( - 'rdma.c', - 'rdma_backend.c', - 'rdma_utils.c', - 'vmw/pvrdma_qp_ops.c', -)) -specific_ss.add(when: 'CONFIG_VMW_PVRDMA', if_true: files( - 'rdma_rm.c', - 'vmw/pvrdma_cmd.c', - 'vmw/pvrdma_dev_ring.c', - 'vmw/pvrdma_main.c', -)) diff --git a/hw/rdma/trace-events b/hw/rdma/trace-events deleted file mode 100644 index c23175120e..0000000000 --- a/hw/rdma/trace-events +++ /dev/null @@ -1,31 +0,0 @@ -# See docs/devel/tracing.rst for syntax documentation. - -# rdma_backend.c -rdma_check_dev_attr(const char *name, int max_bk, int max_fe) "%s: be=%d, fe=%d" -rdma_create_ah_cache_hit(uint64_t subnet, uint64_t if_id) "subnet=0x%"PRIx64",if_id=0x%"PRIx64 -rdma_create_ah_cache_miss(uint64_t subnet, uint64_t if_id) "subnet=0x%"PRIx64",if_id=0x%"PRIx64 -rdma_poll_cq(int ne, void *ibcq) "Got %d completion(s) from cq %p" -rdmacm_mux(const char *title, int msg_type, int op_code) "%s: msg_type=%d, op_code=%d" -rdmacm_mux_check_op_status(int msg_type, int op_code, int err_code) "resp: msg_type=%d, op_code=%d, err_code=%d" -rdma_mad_message(const char *title, int len, char *data) "mad %s (%d): %s" -rdma_backend_rc_qp_state_init(uint32_t qpn) "RC QP 0x%x switch to INIT" -rdma_backend_ud_qp_state_init(uint32_t qpn, uint32_t qkey) "UD QP 0x%x switch to INIT, qkey=0x%x" -rdma_backend_rc_qp_state_rtr(uint32_t qpn, uint64_t subnet, uint64_t ifid, uint8_t sgid_idx, uint32_t dqpn, uint32_t rq_psn) "RC QP 0x%x switch to RTR, subnet = 0x%"PRIx64", ifid = 0x%"PRIx64 ", sgid_idx=%d, dqpn=0x%x, rq_psn=0x%x" -rdma_backend_ud_qp_state_rtr(uint32_t qpn, uint32_t qkey) "UD QP 0x%x switch to RTR, qkey=0x%x" -rdma_backend_rc_qp_state_rts(uint32_t qpn, uint32_t sq_psn) "RC QP 0x%x switch to RTS, sq_psn=0x%x, " -rdma_backend_ud_qp_state_rts(uint32_t qpn, uint32_t sq_psn, uint32_t qkey) "UD QP 0x%x switch to RTS, sq_psn=0x%x, qkey=0x%x" -rdma_backend_get_gid_index(uint64_t subnet, uint64_t ifid, int gid_idx) "subnet=0x%"PRIx64", ifid=0x%"PRIx64 ", gid_idx=%d" -rdma_backend_gid_change(const char *op, uint64_t subnet, uint64_t ifid) "%s subnet=0x%"PRIx64", ifid=0x%"PRIx64 - -# rdma_rm.c -rdma_res_tbl_get(char *name, uint32_t handle) "tbl %s, handle %d" -rdma_res_tbl_alloc(char *name, uint32_t handle) "tbl %s, handle %d" -rdma_res_tbl_dealloc(char *name, uint32_t handle) "tbl %s, handle %d" -rdma_rm_alloc_mr(uint32_t mr_handle, void *host_virt, uint64_t guest_start, uint64_t guest_length, int access_flags) "mr_handle=%d, host_virt=%p, guest_start=0x%"PRIx64", length=%" PRId64", access_flags=0x%x" -rdma_rm_dealloc_mr(uint32_t mr_handle, uint64_t guest_start) "mr_handle=%d, guest_start=0x%"PRIx64 -rdma_rm_alloc_qp(uint32_t rm_qpn, uint32_t backend_qpn, uint8_t qp_type) "rm_qpn=%d, backend_qpn=0x%x, qp_type=%d" -rdma_rm_modify_qp(uint32_t qpn, uint32_t attr_mask, int qp_state, uint8_t sgid_idx) "qpn=0x%x, attr_mask=0x%x, qp_state=%d, sgid_idx=%d" - -# rdma_utils.c -rdma_pci_dma_map(uint64_t addr, void *vaddr, uint64_t len) "0x%"PRIx64" -> %p (len=%" PRIu64")" -rdma_pci_dma_unmap(void *vaddr) "%p" diff --git a/hw/rdma/vmw/trace-events b/hw/rdma/vmw/trace-events deleted file mode 100644 index a6c77e1e10..0000000000 --- a/hw/rdma/vmw/trace-events +++ /dev/null @@ -1,17 +0,0 @@ -# See docs/devel/tracing.rst for syntax documentation. - -# pvrdma_main.c -pvrdma_regs_read(uint64_t addr, uint64_t val) "pvrdma.regs[0x%"PRIx64"]=0x%"PRIx64 -pvrdma_regs_write(uint64_t addr, uint64_t val, const char *reg_name, const char *val_name) "pvrdma.regs[0x%"PRIx64"]=0x%"PRIx64" (%s %s)" -pvrdma_uar_write(uint64_t addr, uint64_t val, const char *reg_name, const char *val_name, int val1, int val2) "uar[0x%"PRIx64"]=0x%"PRIx64" (cls=%s, op=%s, obj=%d, val=%d)" - -# pvrdma_cmd.c -pvrdma_map_to_pdir_host_virt(void *vfirst, void *vremaped) "mremap %p -> %p" -pvrdma_map_to_pdir_next_page(int page_idx, void *vnext, void *vremaped) "mremap [%d] %p -> %p" -pvrdma_exec_cmd(int cmd, int err) "cmd=%d, err=%d" - -# pvrdma_dev_ring.c -pvrdma_ring_next_elem_read_no_data(char *ring_name) "pvrdma_ring %s is empty" - -# pvrdma_qp_ops.c -pvrdma_post_cqe(uint32_t cq_handle, int notify, uint64_t wr_id, uint64_t qpn, uint32_t op_code, uint32_t status, uint32_t byte_len, uint32_t src_qp, uint32_t wc_flags, uint32_t vendor_err) "cq_handle=%d, notify=%d, wr_id=0x%"PRIx64", qpn=0x%"PRIx64", opcode=%d, status=%d, byte_len=%d, src_qp=%d, wc_flags=%d, vendor_err=%d" diff --git a/meson_options.txt b/meson_options.txt index 0a99a059ec..79b69d4286 100644 --- a/meson_options.txt +++ b/meson_options.txt @@ -196,10 +196,6 @@ option('rbd', type : 'feature', value : 'auto', description: 'Ceph block device driver') option('opengl', type : 'feature', value : 'auto', description: 'OpenGL support') -option('rdma', type : 'feature', value : 'auto', - description: 'Enable RDMA-based migration') -option('pvrdma', type : 'feature', value : 'auto', - description: 'Enable PVRDMA support') option('gtk', type : 'feature', value : 'auto', description: 'GTK+ user interface') option('sdl', type : 'feature', value : 'auto', diff --git a/migration/meson.build b/migration/meson.build index 1eeb915ff6..e2cd92c01f 100644 --- a/migration/meson.build +++ b/migration/meson.build @@ -36,7 +36,6 @@ if get_option('replication').allowed() system_ss.add(files('colo-failover.c', 'colo.c')) endif -system_ss.add(when: rdma, if_true: files('rdma.c')) if get_option('live_block_migration').allowed() system_ss.add(files('block.c')) endif diff --git a/migration/trace-events b/migration/trace-events index f0e1cb80c7..7db3a5194f 100644 --- a/migration/trace-events +++ b/migration/trace-events @@ -193,7 +193,7 @@ process_incoming_migration_co_postcopy_end_main(void) "" postcopy_preempt_enabled(bool value) "%d" # migration-stats -migration_transferred_bytes(uint64_t qemu_file, uint64_t multifd, uint64_t rdma) "qemu_file %" PRIu64 " multifd %" PRIu64 " RDMA %" PRIu64 +migration_transferred_bytes(uint64_t qemu_file, uint64_t multifd) "qemu_file %" PRIu64 " multifd %" PRIu64 # channel.c migration_set_incoming_channel(void *ioc, const char *ioctype) "ioc=%p ioctype=%s" @@ -204,72 +204,6 @@ migrate_state_too_big(void) "" migrate_global_state_post_load(const char *state) "loaded state: %s" migrate_global_state_pre_save(const char *state) "saved state: %s" -# rdma.c -qemu_rdma_accept_incoming_migration(void) "" -qemu_rdma_accept_incoming_migration_accepted(void) "" -qemu_rdma_accept_pin_state(bool pin) "%d" -qemu_rdma_accept_pin_verbsc(void *verbs) "Verbs context after listen: %p" -qemu_rdma_block_for_wrid_miss(uint64_t wcomp, uint64_t req) "A Wanted wrid %" PRIu64 " but got %" PRIu64 -qemu_rdma_cleanup_disconnect(void) "" -qemu_rdma_close(void) "" -qemu_rdma_connect_pin_all_requested(void) "" -qemu_rdma_connect_pin_all_outcome(bool pin) "%d" -qemu_rdma_dest_init_trying(const char *host, const char *ip) "%s => %s" -qemu_rdma_dump_id_failed(const char *who) "%s RDMA Device opened, but can't query port information" -qemu_rdma_dump_id(const char *who, const char *name, const char *dev_name, const char *dev_path, const char *ibdev_path, int transport, const char *transport_name) "%s RDMA Device opened: kernel name %s uverbs device name %s, infiniband_verbs class device path %s, infiniband class device path %s, transport: (%d) %s" -qemu_rdma_dump_gid(const char *who, const char *src, const char *dst) "%s Source GID: %s, Dest GID: %s" -qemu_rdma_exchange_get_response_start(const char *desc) "CONTROL: %s receiving..." -qemu_rdma_exchange_get_response_none(const char *desc, int type) "Surprise: got %s (%d)" -qemu_rdma_exchange_send_issue_callback(void) "" -qemu_rdma_exchange_send_waiting(const char *desc) "Waiting for response %s" -qemu_rdma_exchange_send_received(const char *desc) "Response %s received." -qemu_rdma_fill(size_t control_len, size_t size) "RDMA %zd of %zd bytes already in buffer" -qemu_rdma_init_ram_blocks(int blocks) "Allocated %d local ram block structures" -qemu_rdma_poll_recv(uint64_t comp, int64_t id, int sent) "completion %" PRIu64 " received (%" PRId64 ") left %d" -qemu_rdma_poll_write(uint64_t comp, int left, uint64_t block, uint64_t chunk, void *local, void *remote) "completions %" PRIu64 " left %d, block %" PRIu64 ", chunk: %" PRIu64 " %p %p" -qemu_rdma_poll_other(uint64_t comp, int left) "other completion %" PRIu64 " received left %d" -qemu_rdma_post_send_control(const char *desc) "CONTROL: sending %s.." -qemu_rdma_register_and_get_keys(uint64_t len, void *start) "Registering %" PRIu64 " bytes @ %p" -qemu_rdma_register_odp_mr(const char *name) "Try to register On-Demand Paging memory region: %s" -qemu_rdma_advise_mr(const char *name, uint32_t len, uint64_t addr, const char *res) "Try to advise block %s prefetch at %" PRIu32 "@0x%" PRIx64 ": %s" -qemu_rdma_resolve_host_trying(const char *host, const char *ip) "Trying %s => %s" -qemu_rdma_signal_unregister_append(uint64_t chunk, int pos) "Appending unregister chunk %" PRIu64 " at position %d" -qemu_rdma_signal_unregister_already(uint64_t chunk) "Unregister chunk %" PRIu64 " already in queue" -qemu_rdma_unregister_waiting_inflight(uint64_t chunk) "Cannot unregister inflight chunk: %" PRIu64 -qemu_rdma_unregister_waiting_proc(uint64_t chunk, int pos) "Processing unregister for chunk: %" PRIu64 " at position %d" -qemu_rdma_unregister_waiting_send(uint64_t chunk) "Sending unregister for chunk: %" PRIu64 -qemu_rdma_unregister_waiting_complete(uint64_t chunk) "Unregister for chunk: %" PRIu64 " complete." -qemu_rdma_write_flush(int sent) "sent total: %d" -qemu_rdma_write_one_block(int count, int block, uint64_t chunk, uint64_t current, uint64_t len, int nb_sent, int nb_chunks) "(%d) Not clobbering: block: %d chunk %" PRIu64 " current %" PRIu64 " len %" PRIu64 " %d %d" -qemu_rdma_write_one_post(uint64_t chunk, long addr, long remote, uint32_t len) "Posting chunk: %" PRIu64 ", addr: 0x%lx remote: 0x%lx, bytes %" PRIu32 -qemu_rdma_write_one_queue_full(void) "" -qemu_rdma_write_one_recvregres(int mykey, int theirkey, uint64_t chunk) "Received registration result: my key: 0x%x their key 0x%x, chunk %" PRIu64 -qemu_rdma_write_one_sendreg(uint64_t chunk, int len, int index, int64_t offset) "Sending registration request chunk %" PRIu64 " for %d bytes, index: %d, offset: %" PRId64 -qemu_rdma_write_one_top(uint64_t chunks, uint64_t size) "Writing %" PRIu64 " chunks, (%" PRIu64 " MB)" -qemu_rdma_write_one_zero(uint64_t chunk, int len, int index, int64_t offset) "Entire chunk is zero, sending compress: %" PRIu64 " for %d bytes, index: %d, offset: %" PRId64 -rdma_add_block(const char *block_name, int block, uint64_t addr, uint64_t offset, uint64_t len, uint64_t end, uint64_t bits, int chunks) "Added Block: '%s':%d, addr: %" PRIu64 ", offset: %" PRIu64 " length: %" PRIu64 " end: %" PRIu64 " bits %" PRIu64 " chunks %d" -rdma_block_notification_handle(const char *name, int index) "%s at %d" -rdma_delete_block(void *block, uint64_t addr, uint64_t offset, uint64_t len, uint64_t end, uint64_t bits, int chunks) "Deleted Block: %p, addr: %" PRIu64 ", offset: %" PRIu64 " length: %" PRIu64 " end: %" PRIu64 " bits %" PRIu64 " chunks %d" -rdma_registration_handle_compress(int64_t length, int index, int64_t offset) "Zapping zero chunk: %" PRId64 " bytes, index %d, offset %" PRId64 -rdma_registration_handle_finished(void) "" -rdma_registration_handle_ram_blocks(void) "" -rdma_registration_handle_ram_blocks_loop(const char *name, uint64_t offset, uint64_t length, void *local_host_addr, unsigned int src_index) "%s: @0x%" PRIx64 "/%" PRIu64 " host:@%p src_index: %u" -rdma_registration_handle_register(int requests) "%d requests" -rdma_registration_handle_register_loop(int req, int index, uint64_t addr, uint64_t chunks) "Registration request (%d): index %d, current_addr %" PRIu64 " chunks: %" PRIu64 -rdma_registration_handle_register_rkey(int rkey) "0x%x" -rdma_registration_handle_unregister(int requests) "%d requests" -rdma_registration_handle_unregister_loop(int count, int index, uint64_t chunk) "Unregistration request (%d): index %d, chunk %" PRIu64 -rdma_registration_handle_unregister_success(uint64_t chunk) "%" PRIu64 -rdma_registration_handle_wait(void) "" -rdma_registration_start(uint64_t flags) "%" PRIu64 -rdma_registration_stop(uint64_t flags) "%" PRIu64 -rdma_registration_stop_ram(void) "" -rdma_start_incoming_migration(void) "" -rdma_start_incoming_migration_after_dest_init(void) "" -rdma_start_incoming_migration_after_rdma_listen(void) "" -rdma_start_outgoing_migration_after_rdma_connect(void) "" -rdma_start_outgoing_migration_after_rdma_source_init(void) "" - # postcopy-ram.c postcopy_discard_send_finish(const char *ramblock, int nwords, int ncmds) "%s mask words sent=%d in %d commands" postcopy_discard_send_range(const char *ramblock, unsigned long start, unsigned long length) "%s:%lx/%lx" diff --git a/qapi/meson.build b/qapi/meson.build index 375d564277..c92af6e063 100644 --- a/qapi/meson.build +++ b/qapi/meson.build @@ -62,7 +62,6 @@ if have_system 'cryptodev', 'qdev', 'pci', - 'rdma', 'rocker', 'tpm', ] diff --git a/qemu-options.hx b/qemu-options.hx index 7fd1713fa8..4f390c33ef 100644 --- a/qemu-options.hx +++ b/qemu-options.hx @@ -4759,7 +4759,6 @@ ERST DEF("incoming", HAS_ARG, QEMU_OPTION_incoming, \ "-incoming tcp:[host]:port[,to=maxport][,ipv4=on|off][,ipv6=on|off]\n" \ - "-incoming rdma:host:port[,ipv4=on|off][,ipv6=on|off]\n" \ "-incoming unix:socketpath\n" \ " prepare for incoming migration, listen on\n" \ " specified protocol and socket address\n" \ @@ -4773,8 +4772,6 @@ DEF("incoming", HAS_ARG, QEMU_OPTION_incoming, \ QEMU_ARCH_ALL) SRST ``-incoming tcp:[host]:port[,to=maxport][,ipv4=on|off][,ipv6=on|off]`` - \ -``-incoming rdma:host:port[,ipv4=on|off][,ipv6=on|off]`` Prepare for incoming migration, listen on a given tcp port. ``-incoming unix:socketpath`` @@ -5113,9 +5110,6 @@ SRST allows a co-operating external process to access the QEMU memory region. - The ``share`` is also required for pvrdma devices due to - limitations in the RDMA API provided by Linux. - Setting share=on might affect the ability to configure NUMA bindings for the memory backend under some circumstances, see Documentation/vm/numa\_memory\_policy.txt on the Linux kernel diff --git a/scripts/ci/org.centos/stream/8/x86_64/configure b/scripts/ci/org.centos/stream/8/x86_64/configure index 76781f17f4..868db665f6 100755 --- a/scripts/ci/org.centos/stream/8/x86_64/configure +++ b/scripts/ci/org.centos/stream/8/x86_64/configure @@ -99,7 +99,6 @@ --disable-opengl \ --disable-parallels \ --disable-pie \ ---disable-pvrdma \ --disable-qcow1 \ --disable-qed \ --disable-qom-cast-debug \ diff --git a/scripts/ci/setup/build-environment.yml b/scripts/ci/setup/build-environment.yml index f344d1a850..8a6098215b 100644 --- a/scripts/ci/setup/build-environment.yml +++ b/scripts/ci/setup/build-environment.yml @@ -81,8 +81,6 @@ - libglusterfs-dev - libgnutls28-dev - libgtk-3-dev - - libibumad-dev - - libibverbs-dev - libiscsi-dev - libjemalloc-dev - libjpeg-turbo8-dev diff --git a/scripts/coverity-scan/run-coverity-scan b/scripts/coverity-scan/run-coverity-scan index 43cf770f5e..3dd14c3cc4 100755 --- a/scripts/coverity-scan/run-coverity-scan +++ b/scripts/coverity-scan/run-coverity-scan @@ -426,7 +426,7 @@ echo "Configuring..." --enable-libusb --enable-usb-redir \ --enable-libiscsi --enable-libnfs --enable-seccomp \ --enable-tpm --enable-libssh --enable-lzo --enable-snappy --enable-bzip2 \ - --enable-numa --enable-rdma --enable-smartcard --enable-virglrenderer \ + --enable-numa --enable-smartcard --enable-virglrenderer \ --enable-mpath --enable-glusterfs \ --enable-virtfs --enable-zstd diff --git a/scripts/meson-buildoptions.sh b/scripts/meson-buildoptions.sh index 680fa3f581..52c34598ba 100644 --- a/scripts/meson-buildoptions.sh +++ b/scripts/meson-buildoptions.sh @@ -163,12 +163,10 @@ meson_options_help() { printf "%s\n" ' pixman pixman support' printf "%s\n" ' plugins TCG plugins via shared library loading' printf "%s\n" ' png PNG support with libpng' - printf "%s\n" ' pvrdma Enable PVRDMA support' printf "%s\n" ' qcow1 qcow1 image format support' printf "%s\n" ' qed qed image format support' printf "%s\n" ' qga-vss build QGA VSS support (broken with MinGW)' printf "%s\n" ' rbd Ceph block device driver' - printf "%s\n" ' rdma Enable RDMA-based migration' printf "%s\n" ' replication replication support' printf "%s\n" ' rutabaga-gfx rutabaga_gfx support' printf "%s\n" ' sdl SDL user interface' @@ -428,8 +426,6 @@ _meson_option_parse() { --enable-png) printf "%s" -Dpng=enabled ;; --disable-png) printf "%s" -Dpng=disabled ;; --prefix=*) quote_sh "-Dprefix=$2" ;; - --enable-pvrdma) printf "%s" -Dpvrdma=enabled ;; - --disable-pvrdma) printf "%s" -Dpvrdma=disabled ;; --enable-qcow1) printf "%s" -Dqcow1=enabled ;; --disable-qcow1) printf "%s" -Dqcow1=disabled ;; --enable-qed) printf "%s" -Dqed=enabled ;; @@ -445,8 +441,6 @@ _meson_option_parse() { --disable-qom-cast-debug) printf "%s" -Dqom_cast_debug=false ;; --enable-rbd) printf "%s" -Drbd=enabled ;; --disable-rbd) printf "%s" -Drbd=disabled ;; - --enable-rdma) printf "%s" -Drdma=enabled ;; - --disable-rdma) printf "%s" -Drdma=disabled ;; --enable-relocatable) printf "%s" -Drelocatable=true ;; --disable-relocatable) printf "%s" -Drelocatable=false ;; --enable-replication) printf "%s" -Dreplication=enabled ;; diff --git a/scripts/update-linux-headers.sh b/scripts/update-linux-headers.sh index a0006eec6f..73c292bbac 100755 --- a/scripts/update-linux-headers.sh +++ b/scripts/update-linux-headers.sh @@ -55,7 +55,6 @@ cp_portable() { -e 'linux/if_ether' \ -e 'input-event-codes' \ -e 'sys/' \ - -e 'pvrdma_verbs' \ -e 'drm.h' \ -e 'limits' \ -e 'linux/const' \ @@ -226,32 +225,6 @@ mkdir -p "$output/include/standard-headers/drm" cp_portable "$tmpdir/include/drm/drm_fourcc.h" \ "$output/include/standard-headers/drm" -rm -rf "$output/include/standard-headers/drivers/infiniband/hw/vmw_pvrdma" -mkdir -p "$output/include/standard-headers/drivers/infiniband/hw/vmw_pvrdma" - -# Remove the unused functions from pvrdma_verbs.h avoiding the unnecessary -# import of several infiniband/networking/other headers -tmp_pvrdma_verbs="$tmpdir/pvrdma_verbs.h" -# Parse the entire file instead of single lines to match -# function declarations expanding over multiple lines -# and strip the declarations starting with pvrdma prefix. -sed -e '1h;2,$H;$!d;g' -e 's/[^};]*pvrdma[^(| ]*([^)]*);//g' \ - "$linux/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h" > \ - "$tmp_pvrdma_verbs"; - -for i in "$linux/drivers/infiniband/hw/vmw_pvrdma/pvrdma_dev_api.h" \ - "$tmp_pvrdma_verbs"; do \ - cp_portable "$i" \ - "$output/include/standard-headers/drivers/infiniband/hw/vmw_pvrdma/" -done - -rm -rf "$output/include/standard-headers/rdma/" -mkdir -p "$output/include/standard-headers/rdma/" -for i in "$tmpdir/include/rdma/vmw_pvrdma-abi.h"; do - cp_portable "$i" \ - "$output/include/standard-headers/rdma/" -done - cat <<EOF >$output/include/standard-headers/linux/types.h /* For QEMU all types are already defined via osdep.h, so this * header does not need to do anything. diff --git a/tests/lcitool/projects/qemu.yml b/tests/lcitool/projects/qemu.yml index 149b15de57..0190bde8b1 100644 --- a/tests/lcitool/projects/qemu.yml +++ b/tests/lcitool/projects/qemu.yml @@ -48,8 +48,6 @@ packages: - libfdt - libffi - libgcrypt - - libibumad - - libibverbs - libiscsi - libjemalloc - libjpeg diff --git a/tests/migration/guestperf/engine.py b/tests/migration/guestperf/engine.py index 608d7270f6..a704419082 100644 --- a/tests/migration/guestperf/engine.py +++ b/tests/migration/guestperf/engine.py @@ -41,7 +41,7 @@ def __init__(self, binary, dst_host, kernel, initrd, transport="tcp", self._dst_host = dst_host # Hostname of target host self._kernel = kernel # Path to kernel image self._initrd = initrd # Path to stress initrd - self._transport = transport # 'unix' or 'tcp' or 'rdma' + self._transport = transport # 'unix' or 'tcp' self._sleep = sleep self._verbose = verbose self._debug = debug @@ -427,8 +427,6 @@ def run(self, hardware, scenario, result_dir=os.getcwd()): if self._transport == "tcp": uri = "tcp:%s:9000" % self._dst_host - elif self._transport == "rdma": - uri = "rdma:%s:9000" % self._dst_host elif self._transport == "unix": if self._dst_host != "localhost": raise Exception("Running use unix migration transport for non-local host") -- 2.41.0

6 7

Entering freeze for libvirt-10.2.0
by Jiri Denemark 28 Mar '24

28 Mar '24

I have just tagged v10.2.0-rc1 in the repository and pushed signed tarballs to https://download.libvirt.org/ Please give the release candidate some testing and in case you find a serious issue which should have a fix in the upcoming release, feel free to reply to this thread to make sure the issue is more visible. If you have not done so yet, please update NEWS.rst to document any significant change you made since the last release. Thanks, Jirka

1 1

[RFC 00/15] block job API
by Vladimir Sementsov-Ogievskiy 28 Mar '24

28 Mar '24

Hi all! The series aims to reach feature parity between job-* and block-job-* APIs and finally deprecate block-job-* APIs. 01: new type-based unions for QAPI 02-07: rework block-job-change and add similar job-change command 08: support set-speed in new API (as an option to job-change) 09: support soft-cancelling ready mirror job in new API (as an option to job-complete) 10-14: prepare query-jobs to substitute query-block-jobs 15: finally, deprecate old APIs RFC: the series are untested. I plan to move tests to using new APIs instead of deprecated ones in v2. Vladimir Sementsov-Ogievskiy (15): scripts/qapi: support type-based unions qapi: rename BlockJobChangeOptions to JobChangeOptions blockjob: block_job_change_locked(): check job type qapi: block-job-change: make copy-mode parameter optional qapi: JobChangeOptions: make type member optional and deprecated blockjob: move change action implementation to job from block-job qapi: add job-change qapi: job-change: support speed parameter qapi: job-complete: introduce no-block-replace option for mirror qapi: query-jobs: add information specific for job type job-qmp: job_query_single_locked: add assertion on job ret qapi: rename BlockDeviceIoStatus to IoStatus qapi: move IoStatus to common.json qapi: query-job: add block-job specific information qapi/block-core: derpecate block-job- APIs block/backup.c | 14 ++ block/block-backend.c | 14 +- block/commit.c | 16 ++- block/mirror.c | 98 +++++++++----- block/monitor/block-hmp-cmds.c | 4 +- block/stream.c | 14 ++ blockdev.c | 4 +- blockjob.c | 39 +++--- docs/about/deprecated.rst | 75 +++++++++++ include/block/blockjob.h | 26 ++-- include/block/blockjob_int.h | 7 - include/qemu/job.h | 25 +++- include/sysemu/block-backend-global-state.h | 2 +- job-qmp.c | 55 +++++++- job.c | 35 ++++- qapi/block-core.json | 136 +++++++++++++++----- qapi/common.json | 16 +++ qapi/job.json | 69 +++++++++- scripts/qapi/introspect.py | 5 +- scripts/qapi/schema.py | 50 ++++--- scripts/qapi/types.py | 3 +- scripts/qapi/visit.py | 43 ++++++- stubs/meson.build | 1 + stubs/qapi-jobchangeoptions-mapper.c | 13 ++ tests/unit/test-bdrv-drain.c | 2 +- tests/unit/test-block-iothread.c | 2 +- tests/unit/test-blockjob.c | 2 +- 27 files changed, 616 insertions(+), 154 deletions(-) create mode 100644 stubs/qapi-jobchangeoptions-mapper.c -- 2.34.1

2 21

[libvirt PATCH] NEWS: Update
by Ján Tomko 27 Mar '24

27 Mar '24

Update NEWS with new news. Signed-off-by: Ján Tomko <jtomko(a)redhat.com> --- NEWS.rst | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/NEWS.rst b/NEWS.rst index ef9e312698..ce83ee629f 100644 --- a/NEWS.rst +++ b/NEWS.rst @@ -36,6 +36,13 @@ v10.2.0 (unreleased) use the upcoming QEMU 9.0.0 release together with the development version of edk2. + * qemu: Introduce virDomainGraphicsReload API + + Reloading the graphics display is now supported for QEMU guests using + VNC. This is useful to make QEMU reload the TLS certificats without + restarting the guest. Available via the `virDomainGraphicsReload` API + and the `domdisplay-reload` virsh command. + * **Improvements** * **Bug fixes** @@ -52,6 +59,20 @@ v10.2.0 (unreleased) releases to 10.2.0 works as well, but the other direction remains broken unless the fix is backported. + * qemu: set correct SELinux label for unprivileged virtiofsd + + Now, it's possible to use virtiofsd-based `<filesystem>` shares even + if the guest is confined using SELinux. + + * qemu: fix a crash on unprivileged virtiofsd hotplug + + Hotplugging virtiofsd-based filesystems works now. + + * virt-admin: Fix segfault when libvirtd dies + + Now, `virt-admin` no longer crashes when `libvirtd` unexpectedly closes + the connection. + v10.1.0 (2024-03-01) ==================== -- 2.44.0

2 1

[PATCH-for-9.1] target/nios2: Remove machines and system emulation
by Philippe Mathieu-Daudé 27 Mar '24

27 Mar '24

Remove the Nios II machines and the system emulation code (deprecated since v8.2 in commit 9997771bc1 "target/nios2: Deprecate the Nios II architecture"). Cc: Marek Vasut <marex(a)denx.de> Signed-off-by: Philippe Mathieu-Daudé <philmd(a)linaro.org> --- MAINTAINERS | 4 - docs/about/deprecated.rst | 5 - docs/about/emulation.rst | 3 - docs/about/removed-features.rst | 5 + docs/system/replay.rst | 2 +- configs/devices/nios2-softmmu/default.mak | 6 - configs/targets/nios2-softmmu.mak | 2 - qapi/machine.json | 2 +- hw/nios2/boot.h | 10 - include/hw/intc/nios2_vic.h | 66 ---- include/sysemu/arch_init.h | 1 - target/nios2/cpu-param.h | 6 +- target/nios2/cpu.h | 42 --- target/nios2/helper.h | 9 - target/nios2/mmu.h | 52 --- hw/intc/nios2_vic.c | 313 ------------------ hw/nios2/10m50_devboard.c | 181 ----------- hw/nios2/boot.c | 234 -------------- hw/nios2/generic_nommu.c | 101 ------ target/nios2/cpu.c | 160 +--------- target/nios2/helper.c | 371 ---------------------- target/nios2/mmu.c | 216 ------------- target/nios2/monitor.c | 35 -- target/nios2/nios2-semi.c | 230 -------------- target/nios2/op_helper.c | 45 --- target/nios2/translate.c | 254 +-------------- tests/qtest/machine-none-test.c | 1 - .gitlab-ci.d/buildtest.yml | 4 +- .gitlab-ci.d/crossbuilds.yml | 2 +- hw/Kconfig | 1 - hw/intc/Kconfig | 3 - hw/intc/meson.build | 1 - hw/meson.build | 1 - hw/nios2/Kconfig | 13 - hw/nios2/meson.build | 6 - qemu-options.hx | 8 +- scripts/coverity-scan/COMPONENTS.md | 2 +- target/nios2/meson.build | 9 - tests/avocado/boot_linux_console.py | 8 - tests/avocado/replay_kernel.py | 11 - tests/tcg/nios2/Makefile.softmmu-target | 32 -- tests/tcg/nios2/test-shadow-1.S | 40 --- 42 files changed, 24 insertions(+), 2473 deletions(-) delete mode 100644 configs/devices/nios2-softmmu/default.mak delete mode 100644 configs/targets/nios2-softmmu.mak delete mode 100644 hw/nios2/boot.h delete mode 100644 include/hw/intc/nios2_vic.h delete mode 100644 target/nios2/mmu.h delete mode 100644 hw/intc/nios2_vic.c delete mode 100644 hw/nios2/10m50_devboard.c delete mode 100644 hw/nios2/boot.c delete mode 100644 hw/nios2/generic_nommu.c delete mode 100644 target/nios2/helper.c delete mode 100644 target/nios2/mmu.c delete mode 100644 target/nios2/monitor.c delete mode 100644 target/nios2/nios2-semi.c delete mode 100644 hw/nios2/Kconfig delete mode 100644 hw/nios2/meson.build delete mode 100644 tests/tcg/nios2/Makefile.softmmu-target delete mode 100644 tests/tcg/nios2/test-shadow-1.S diff --git a/MAINTAINERS b/MAINTAINERS index a07af6b9d4..3b48fcf8d7 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -296,11 +296,7 @@ R: Chris Wulff <crwulff(a)gmail.com> R: Marek Vasut <marex(a)denx.de> S: Orphan F: target/nios2/ -F: hw/nios2/ -F: hw/intc/nios2_vic.c F: disas/nios2.c -F: include/hw/intc/nios2_vic.h -F: configs/devices/nios2-softmmu/default.mak F: tests/docker/dockerfiles/debian-nios2-cross.d/build-toolchain.sh F: tests/tcg/nios2/ diff --git a/docs/about/deprecated.rst b/docs/about/deprecated.rst index 7b548519b5..0b709dfc72 100644 --- a/docs/about/deprecated.rst +++ b/docs/about/deprecated.rst @@ -226,11 +226,6 @@ These old machine types are quite neglected nowadays and thus might have various pitfalls with regards to live migration. Use a newer machine type instead. -Nios II ``10m50-ghrd`` and ``nios2-generic-nommu`` machines (since 8.2) -''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''' - -The Nios II architecture is orphan. - ``shix`` (since 9.0) '''''''''''''''''''' diff --git a/docs/about/emulation.rst b/docs/about/emulation.rst index a2eefe3f3f..a7c185bbfb 100644 --- a/docs/about/emulation.rst +++ b/docs/about/emulation.rst @@ -180,9 +180,6 @@ for that architecture. * - MIPS - System - Unified Hosting Interface (MD01069) - * - Nios II - - System - - https://sourceware.org/git/gitweb.cgi?p=newlib-cygwin.git;a=blob;f=libgloss… * - RISC-V - System and User-mode - https://github.com/riscv/riscv-semihosting-spec/blob/main/riscv-semihosting… diff --git a/docs/about/removed-features.rst b/docs/about/removed-features.rst index f9cf874f7b..43a9bfa29f 100644 --- a/docs/about/removed-features.rst +++ b/docs/about/removed-features.rst @@ -841,6 +841,11 @@ ppc ``taihu`` machine (removed in 7.2) This machine was removed because it was partially emulated and 405 machines are very similar. Use the ``ref405ep`` machine instead. +Nios II ``10m50-ghrd`` and ``nios2-generic-nommu`` machines (removed 9.1) +''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''' + +The Nios II architecture is orphan. + linux-user mode CPUs -------------------- diff --git a/docs/system/replay.rst b/docs/system/replay.rst index ca7c17c63d..28e5772a2b 100644 --- a/docs/system/replay.rst +++ b/docs/system/replay.rst @@ -24,7 +24,7 @@ Deterministic replay has the following features: * Writes execution log into the file for later replaying for multiple times on different machines. * Supports i386, x86_64, ARM, AArch64, Risc-V, MIPS, MIPS64, S390X, Alpha, - PowerPC, PowerPC64, M68000, Microblaze, OpenRISC, Nios II, SPARC, + PowerPC, PowerPC64, M68000, Microblaze, OpenRISC, SPARC, and Xtensa hardware platforms. * Performs deterministic replay of all operations with keyboard and mouse input devices, serial ports, and network. diff --git a/configs/devices/nios2-softmmu/default.mak b/configs/devices/nios2-softmmu/default.mak deleted file mode 100644 index e130d024e6..0000000000 --- a/configs/devices/nios2-softmmu/default.mak +++ /dev/null @@ -1,6 +0,0 @@ -# Default configuration for nios2-softmmu - -# Boards: -# -CONFIG_NIOS2_10M50=y -CONFIG_NIOS2_GENERIC_NOMMU=y diff --git a/configs/targets/nios2-softmmu.mak b/configs/targets/nios2-softmmu.mak deleted file mode 100644 index c99ae3777e..0000000000 --- a/configs/targets/nios2-softmmu.mak +++ /dev/null @@ -1,2 +0,0 @@ -TARGET_ARCH=nios2 -TARGET_NEED_FDT=y diff --git a/qapi/machine.json b/qapi/machine.json index e8b60641f2..6ab713a4c4 100644 --- a/qapi/machine.json +++ b/qapi/machine.json @@ -33,7 +33,7 @@ { 'enum' : 'SysEmuTarget', 'data' : [ 'aarch64', 'alpha', 'arm', 'avr', 'cris', 'hppa', 'i386', 'loongarch64', 'm68k', 'microblaze', 'microblazeel', 'mips', 'mips64', - 'mips64el', 'mipsel', 'nios2', 'or1k', 'ppc', + 'mips64el', 'mipsel', 'or1k', 'ppc', 'ppc64', 'riscv32', 'riscv64', 'rx', 's390x', 'sh4', 'sh4eb', 'sparc', 'sparc64', 'tricore', 'x86_64', 'xtensa', 'xtensaeb' ] } diff --git a/hw/nios2/boot.h b/hw/nios2/boot.h deleted file mode 100644 index 59b9fbfc62..0000000000 --- a/hw/nios2/boot.h +++ /dev/null @@ -1,10 +0,0 @@ -#ifndef NIOS2_BOOT_H -#define NIOS2_BOOT_H - -#include "cpu.h" - -void nios2_load_kernel(Nios2CPU *cpu, hwaddr ddr_base, uint32_t ramsize, - const char *initrd_filename, const char *dtb_filename, - void (*machine_cpu_reset)(Nios2CPU *)); - -#endif /* NIOS2_BOOT_H */ diff --git a/include/hw/intc/nios2_vic.h b/include/hw/intc/nios2_vic.h deleted file mode 100644 index 5c975a2ac4..0000000000 --- a/include/hw/intc/nios2_vic.h +++ /dev/null @@ -1,66 +0,0 @@ -/* - * Vectored Interrupt Controller for nios2 processor - * - * Copyright (c) 2022 Neuroblade - * - * Interface: - * QOM property "cpu": link to the Nios2 CPU (must be set) - * Unnamed GPIO inputs 0..NIOS2_VIC_MAX_IRQ-1: input IRQ lines - * IRQ should be connected to nios2 IRQ0. - * - * Reference: "Embedded Peripherals IP User Guide - * for Intel® Quartus® Prime Design Suite: 21.4" - * Chapter 38 "Vectored Interrupt Controller Core" - * See: https://www.intel.com/content/www/us/en/docs/programmable/683130/21-4/vecto… - * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to deal - * in the Software without restriction, including without limitation the rights - * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell - * copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, - * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN - * THE SOFTWARE. - */ - -#ifndef HW_INTC_NIOS2_VIC_H -#define HW_INTC_NIOS2_VIC_H - -#include "hw/sysbus.h" - -#define TYPE_NIOS2_VIC "nios2-vic" -OBJECT_DECLARE_SIMPLE_TYPE(Nios2VIC, NIOS2_VIC) - -#define NIOS2_VIC_MAX_IRQ 32 - -struct Nios2VIC { - /*< private >*/ - SysBusDevice parent_obj; - - /*< public >*/ - qemu_irq output_int; - - /* properties */ - CPUState *cpu; - MemoryRegion csr; - - uint32_t int_config[NIOS2_VIC_MAX_IRQ]; - uint32_t vic_config; - uint32_t int_raw_status; - uint32_t int_enable; - uint32_t sw_int; - uint32_t vic_status; - uint32_t vec_tbl_base; - uint32_t vec_tbl_addr; -}; - -#endif /* HW_INTC_NIOS2_VIC_H */ diff --git a/include/sysemu/arch_init.h b/include/sysemu/arch_init.h index 8850cb1a14..8d041aa84e 100644 --- a/include/sysemu/arch_init.h +++ b/include/sysemu/arch_init.h @@ -18,7 +18,6 @@ enum { QEMU_ARCH_XTENSA = (1 << 12), QEMU_ARCH_OPENRISC = (1 << 13), QEMU_ARCH_TRICORE = (1 << 16), - QEMU_ARCH_NIOS2 = (1 << 17), QEMU_ARCH_HPPA = (1 << 18), QEMU_ARCH_RISCV = (1 << 19), QEMU_ARCH_RX = (1 << 20), diff --git a/target/nios2/cpu-param.h b/target/nios2/cpu-param.h index 767bba4b7b..9fe9a97a6c 100644 --- a/target/nios2/cpu-param.h +++ b/target/nios2/cpu-param.h @@ -11,10 +11,6 @@ #define TARGET_LONG_BITS 32 #define TARGET_PAGE_BITS 12 #define TARGET_PHYS_ADDR_SPACE_BITS 32 -#ifdef CONFIG_USER_ONLY -# define TARGET_VIRT_ADDR_SPACE_BITS 31 -#else -# define TARGET_VIRT_ADDR_SPACE_BITS 32 -#endif +#define TARGET_VIRT_ADDR_SPACE_BITS 31 #endif diff --git a/target/nios2/cpu.h b/target/nios2/cpu.h index 4164a3432e..2969b116d5 100644 --- a/target/nios2/cpu.h +++ b/target/nios2/cpu.h @@ -26,9 +26,6 @@ #include "hw/registerfields.h" typedef struct CPUArchState CPUNios2State; -#if !defined(CONFIG_USER_ONLY) -#include "mmu.h" -#endif /** * Nios2CPUClass: @@ -179,19 +176,10 @@ FIELD(CR_TLBMISC, EE, 24, 1) #define EXCP_MPUD 17 struct CPUArchState { -#ifdef CONFIG_USER_ONLY uint32_t regs[NUM_GP_REGS]; -#else - uint32_t shadow_regs[NUM_REG_SETS][NUM_GP_REGS]; - /* Pointer into shadow_regs for the current register set. */ - uint32_t *regs; -#endif uint32_t ctrl[NUM_CR_REGS]; uint32_t pc; -#if !defined(CONFIG_USER_ONLY) - Nios2MMU mmu; -#endif int error_code; }; @@ -212,17 +200,9 @@ struct ArchCPU { CPUNios2State env; bool diverr_present; - bool mmu_present; - bool eic_present; - - uint32_t pid_num_bits; - uint32_t tlb_num_ways; - uint32_t tlb_num_entries; /* Addresses that are hard-coded in the FPGA build settings */ uint32_t reset_addr; - uint32_t exception_addr; - uint32_t fast_tlb_miss_addr; /* Bits within each control register which are reserved or readonly. */ ControlRegState cr_state[NUM_CR_REGS]; @@ -240,26 +220,11 @@ static inline bool nios2_cr_reserved(const ControlRegState *s) return (s->writable | s->readonly) == 0; } -static inline void nios2_update_crs(CPUNios2State *env) -{ -#ifndef CONFIG_USER_ONLY - unsigned crs = FIELD_EX32(env->ctrl[CR_STATUS], CR_STATUS, CRS); - env->regs = env->shadow_regs[crs]; -#endif -} - void nios2_tcg_init(void); -void nios2_cpu_do_interrupt(CPUState *cs); -void dump_mmu(CPUNios2State *env); void nios2_cpu_dump_state(CPUState *cpu, FILE *f, int flags); -G_NORETURN void nios2_cpu_do_unaligned_access(CPUState *cpu, vaddr addr, - MMUAccessType access_type, int mmu_idx, - uintptr_t retaddr); G_NORETURN void nios2_cpu_loop_exit_advance(CPUNios2State *env, uintptr_t retaddr); -void do_nios2_semihosting(CPUNios2State *env); - #define CPU_RESOLVING_TYPE TYPE_NIOS2_CPU #define cpu_gen_code cpu_nios2_gen_code @@ -270,13 +235,6 @@ void do_nios2_semihosting(CPUNios2State *env); #define MMU_SUPERVISOR_IDX 0 #define MMU_USER_IDX 1 -#ifndef CONFIG_USER_ONLY -hwaddr nios2_cpu_get_phys_page_debug(CPUState *cpu, vaddr addr); -bool nios2_cpu_tlb_fill(CPUState *cs, vaddr address, int size, - MMUAccessType access_type, int mmu_idx, - bool probe, uintptr_t retaddr); -#endif - typedef CPUNios2State CPUArchState; typedef Nios2CPU ArchCPU; diff --git a/target/nios2/helper.h b/target/nios2/helper.h index 1648d76ade..a4513ec669 100644 --- a/target/nios2/helper.h +++ b/target/nios2/helper.h @@ -21,12 +21,3 @@ DEF_HELPER_FLAGS_2(raise_exception, TCG_CALL_NO_WG, noreturn, env, i32) DEF_HELPER_FLAGS_3(divs, TCG_CALL_NO_WG, s32, env, s32, s32) DEF_HELPER_FLAGS_3(divu, TCG_CALL_NO_WG, i32, env, i32, i32) - -#if !defined(CONFIG_USER_ONLY) -DEF_HELPER_3(eret, noreturn, env, i32, i32) -DEF_HELPER_FLAGS_2(rdprs, TCG_CALL_NO_WG, i32, env, i32) -DEF_HELPER_3(wrprs, void, env, i32, i32) -DEF_HELPER_2(mmu_write_tlbacc, void, env, i32) -DEF_HELPER_2(mmu_write_tlbmisc, void, env, i32) -DEF_HELPER_2(mmu_write_pteaddr, void, env, i32) -#endif diff --git a/target/nios2/mmu.h b/target/nios2/mmu.h deleted file mode 100644 index 5b085900fb..0000000000 --- a/target/nios2/mmu.h +++ /dev/null @@ -1,52 +0,0 @@ -/* - * Altera Nios II MMU emulation for qemu. - * - * Copyright (C) 2012 Chris Wulff <crwulff(a)gmail.com> - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see - * <http://www.gnu.org/licenses/lgpl-2.1.html> - */ - -#ifndef NIOS2_MMU_H -#define NIOS2_MMU_H - -#include "cpu.h" - -typedef struct Nios2TLBEntry { - target_ulong tag; - target_ulong data; -} Nios2TLBEntry; - -typedef struct Nios2MMU { - int tlb_entry_mask; - uint32_t pteaddr_wr; - uint32_t tlbacc_wr; - uint32_t tlbmisc_wr; - Nios2TLBEntry *tlb; -} Nios2MMU; - -typedef struct Nios2MMULookup { - target_ulong vaddr; - target_ulong paddr; - int prot; -} Nios2MMULookup; - -void mmu_flip_um(CPUNios2State *env, unsigned int um); -unsigned int mmu_translate(CPUNios2State *env, - Nios2MMULookup *lu, - target_ulong vaddr, int rw, int mmu_idx); -void mmu_write(CPUNios2State *env, uint32_t rn, uint32_t v); -void mmu_init(CPUNios2State *env); - -#endif /* NIOS2_MMU_H */ diff --git a/hw/intc/nios2_vic.c b/hw/intc/nios2_vic.c deleted file mode 100644 index 7e2d9d6327..0000000000 --- a/hw/intc/nios2_vic.c +++ /dev/null @@ -1,313 +0,0 @@ -/* - * Vectored Interrupt Controller for nios2 processor - * - * Copyright (c) 2022 Neuroblade - * - * Interface: - * QOM property "cpu": link to the Nios2 CPU (must be set) - * Unnamed GPIO inputs 0..NIOS2_VIC_MAX_IRQ-1: input IRQ lines - * IRQ should be connected to nios2 IRQ0. - * - * Reference: "Embedded Peripherals IP User Guide - * for Intel® Quartus® Prime Design Suite: 21.4" - * Chapter 38 "Vectored Interrupt Controller Core" - * See: https://www.intel.com/content/www/us/en/docs/programmable/683130/21-4/vecto… - * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to deal - * in the Software without restriction, including without limitation the rights - * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell - * copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, - * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN - * THE SOFTWARE. - */ - -#include "qemu/osdep.h" - -#include "hw/irq.h" -#include "hw/qdev-properties.h" -#include "hw/sysbus.h" -#include "migration/vmstate.h" -#include "qapi/error.h" -#include "qemu/bitops.h" -#include "qemu/log.h" -#include "qom/object.h" -#include "hw/intc/nios2_vic.h" -#include "cpu.h" - - -enum { - INT_CONFIG0 = 0, - INT_CONFIG31 = 31, - INT_ENABLE = 32, - INT_ENABLE_SET = 33, - INT_ENABLE_CLR = 34, - INT_PENDING = 35, - INT_RAW_STATUS = 36, - SW_INTERRUPT = 37, - SW_INTERRUPT_SET = 38, - SW_INTERRUPT_CLR = 39, - VIC_CONFIG = 40, - VIC_STATUS = 41, - VEC_TBL_BASE = 42, - VEC_TBL_ADDR = 43, - CSR_COUNT /* Last! */ -}; - -/* Requested interrupt level (INT_CONFIG[0:5]) */ -static inline uint32_t vic_int_config_ril(const Nios2VIC *vic, int irq_num) -{ - return extract32(vic->int_config[irq_num], 0, 6); -} - -/* Requested NMI (INT_CONFIG[6]) */ -static inline uint32_t vic_int_config_rnmi(const Nios2VIC *vic, int irq_num) -{ - return extract32(vic->int_config[irq_num], 6, 1); -} - -/* Requested register set (INT_CONFIG[7:12]) */ -static inline uint32_t vic_int_config_rrs(const Nios2VIC *vic, int irq_num) -{ - return extract32(vic->int_config[irq_num], 7, 6); -} - -static inline uint32_t vic_config_vec_size(const Nios2VIC *vic) -{ - return 1 << (2 + extract32(vic->vic_config, 0, 3)); -} - -static inline uint32_t vic_int_pending(const Nios2VIC *vic) -{ - return (vic->int_raw_status | vic->sw_int) & vic->int_enable; -} - -static void vic_update_irq(Nios2VIC *vic) -{ - Nios2CPU *cpu = NIOS2_CPU(vic->cpu); - uint32_t pending = vic_int_pending(vic); - int irq = -1; - int max_ril = 0; - /* Note that if RIL is 0 for an interrupt it is effectively disabled */ - - vic->vec_tbl_addr = 0; - vic->vic_status = 0; - - if (pending == 0) { - qemu_irq_lower(vic->output_int); - return; - } - - for (int i = 0; i < NIOS2_VIC_MAX_IRQ; i++) { - if (pending & BIT(i)) { - int ril = vic_int_config_ril(vic, i); - if (ril > max_ril) { - irq = i; - max_ril = ril; - } - } - } - - if (irq < 0) { - qemu_irq_lower(vic->output_int); - return; - } - - vic->vec_tbl_addr = irq * vic_config_vec_size(vic) + vic->vec_tbl_base; - vic->vic_status = irq | BIT(31); - - /* - * In hardware, the interface between the VIC and the CPU is via the - * External Interrupt Controller interface, where the interrupt controller - * presents the CPU with a packet of data containing: - * - Requested Handler Address (RHA): 32 bits - * - Requested Register Set (RRS) : 6 bits - * - Requested Interrupt Level (RIL) : 6 bits - * - Requested NMI flag (RNMI) : 1 bit - * In our emulation, we implement this by writing the data directly to - * fields in the CPU object and then raising the IRQ line to tell - * the CPU that we've done so. - */ - - cpu->rha = vic->vec_tbl_addr; - cpu->ril = max_ril; - cpu->rrs = vic_int_config_rrs(vic, irq); - cpu->rnmi = vic_int_config_rnmi(vic, irq); - - qemu_irq_raise(vic->output_int); -} - -static void vic_set_irq(void *opaque, int irq_num, int level) -{ - Nios2VIC *vic = opaque; - - vic->int_raw_status = deposit32(vic->int_raw_status, irq_num, 1, !!level); - vic_update_irq(vic); -} - -static void nios2_vic_reset(DeviceState *dev) -{ - Nios2VIC *vic = NIOS2_VIC(dev); - - memset(&vic->int_config, 0, sizeof(vic->int_config)); - vic->vic_config = 0; - vic->int_raw_status = 0; - vic->int_enable = 0; - vic->sw_int = 0; - vic->vic_status = 0; - vic->vec_tbl_base = 0; - vic->vec_tbl_addr = 0; -} - -static uint64_t nios2_vic_csr_read(void *opaque, hwaddr offset, unsigned size) -{ - Nios2VIC *vic = opaque; - int index = offset / 4; - - switch (index) { - case INT_CONFIG0 ... INT_CONFIG31: - return vic->int_config[index - INT_CONFIG0]; - case INT_ENABLE: - return vic->int_enable; - case INT_PENDING: - return vic_int_pending(vic); - case INT_RAW_STATUS: - return vic->int_raw_status; - case SW_INTERRUPT: - return vic->sw_int; - case VIC_CONFIG: - return vic->vic_config; - case VIC_STATUS: - return vic->vic_status; - case VEC_TBL_BASE: - return vic->vec_tbl_base; - case VEC_TBL_ADDR: - return vic->vec_tbl_addr; - default: - return 0; - } -} - -static void nios2_vic_csr_write(void *opaque, hwaddr offset, uint64_t value, - unsigned size) -{ - Nios2VIC *vic = opaque; - int index = offset / 4; - - switch (index) { - case INT_CONFIG0 ... INT_CONFIG31: - vic->int_config[index - INT_CONFIG0] = value; - break; - case INT_ENABLE: - vic->int_enable = value; - break; - case INT_ENABLE_SET: - vic->int_enable |= value; - break; - case INT_ENABLE_CLR: - vic->int_enable &= ~value; - break; - case SW_INTERRUPT: - vic->sw_int = value; - break; - case SW_INTERRUPT_SET: - vic->sw_int |= value; - break; - case SW_INTERRUPT_CLR: - vic->sw_int &= ~value; - break; - case VIC_CONFIG: - vic->vic_config = value; - break; - case VEC_TBL_BASE: - vic->vec_tbl_base = value; - break; - default: - qemu_log_mask(LOG_GUEST_ERROR, - "nios2-vic: write to invalid CSR address %#" - HWADDR_PRIx "\n", offset); - } - - vic_update_irq(vic); -} - -static const MemoryRegionOps nios2_vic_csr_ops = { - .read = nios2_vic_csr_read, - .write = nios2_vic_csr_write, - .endianness = DEVICE_LITTLE_ENDIAN, - .valid = { .min_access_size = 4, .max_access_size = 4 } -}; - -static void nios2_vic_realize(DeviceState *dev, Error **errp) -{ - Nios2VIC *vic = NIOS2_VIC(dev); - - if (!vic->cpu) { - /* This is a programming error in the code using this device */ - error_setg(errp, "nios2-vic 'cpu' link property was not set"); - return; - } - - sysbus_init_irq(SYS_BUS_DEVICE(dev), &vic->output_int); - qdev_init_gpio_in(dev, vic_set_irq, NIOS2_VIC_MAX_IRQ); - - memory_region_init_io(&vic->csr, OBJECT(dev), &nios2_vic_csr_ops, vic, - "nios2.vic.csr", CSR_COUNT * sizeof(uint32_t)); - sysbus_init_mmio(SYS_BUS_DEVICE(dev), &vic->csr); -} - -static Property nios2_vic_properties[] = { - DEFINE_PROP_LINK("cpu", Nios2VIC, cpu, TYPE_CPU, CPUState *), - DEFINE_PROP_END_OF_LIST() -}; - -static const VMStateDescription nios2_vic_vmstate = { - .name = "nios2-vic", - .version_id = 1, - .minimum_version_id = 1, - .fields = (const VMStateField[]){ - VMSTATE_UINT32_ARRAY(int_config, Nios2VIC, 32), - VMSTATE_UINT32(vic_config, Nios2VIC), - VMSTATE_UINT32(int_raw_status, Nios2VIC), - VMSTATE_UINT32(int_enable, Nios2VIC), - VMSTATE_UINT32(sw_int, Nios2VIC), - VMSTATE_UINT32(vic_status, Nios2VIC), - VMSTATE_UINT32(vec_tbl_base, Nios2VIC), - VMSTATE_UINT32(vec_tbl_addr, Nios2VIC), - VMSTATE_END_OF_LIST() - }, -}; - -static void nios2_vic_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - dc->reset = nios2_vic_reset; - dc->realize = nios2_vic_realize; - dc->vmsd = &nios2_vic_vmstate; - device_class_set_props(dc, nios2_vic_properties); -} - -static const TypeInfo nios2_vic_info = { - .name = TYPE_NIOS2_VIC, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(Nios2VIC), - .class_init = nios2_vic_class_init, -}; - -static void nios2_vic_register_types(void) -{ - type_register_static(&nios2_vic_info); -} - -type_init(nios2_vic_register_types); diff --git a/hw/nios2/10m50_devboard.c b/hw/nios2/10m50_devboard.c deleted file mode 100644 index 6cb32f777b..0000000000 --- a/hw/nios2/10m50_devboard.c +++ /dev/null @@ -1,181 +0,0 @@ -/* - * Altera 10M50 Nios2 GHRD - * - * Copyright (c) 2016 Marek Vasut <marek.vasut(a)gmail.com> - * - * Based on LabX device code - * - * Copyright (c) 2012 Chris Wulff <crwulff(a)gmail.com> - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see - * <http://www.gnu.org/licenses/lgpl-2.1.html> - */ - -#include "qemu/osdep.h" -#include "qapi/error.h" - -#include "hw/sysbus.h" -#include "hw/char/serial.h" -#include "hw/intc/nios2_vic.h" -#include "hw/qdev-properties.h" -#include "sysemu/sysemu.h" -#include "hw/boards.h" -#include "exec/memory.h" -#include "exec/address-spaces.h" -#include "qemu/config-file.h" - -#include "boot.h" - -struct Nios2MachineState { - MachineState parent_obj; - - MemoryRegion phys_tcm; - MemoryRegion phys_tcm_alias; - MemoryRegion phys_ram; - MemoryRegion phys_ram_alias; - - bool vic; -}; - -#define TYPE_NIOS2_MACHINE MACHINE_TYPE_NAME("10m50-ghrd") -OBJECT_DECLARE_TYPE(Nios2MachineState, MachineClass, NIOS2_MACHINE) - -#define BINARY_DEVICE_TREE_FILE "10m50-devboard.dtb" - -static void nios2_10m50_ghrd_init(MachineState *machine) -{ - Nios2MachineState *nms = NIOS2_MACHINE(machine); - Nios2CPU *cpu; - DeviceState *dev; - MemoryRegion *address_space_mem = get_system_memory(); - ram_addr_t tcm_base = 0x0; - ram_addr_t tcm_size = 0x1000; /* 1 kiB, but QEMU limit is 4 kiB */ - ram_addr_t ram_base = 0x08000000; - ram_addr_t ram_size = 0x08000000; - qemu_irq irq[32]; - int i; - - /* Physical TCM (tb_ram_1k) with alias at 0xc0000000 */ - memory_region_init_ram(&nms->phys_tcm, NULL, "nios2.tcm", tcm_size, - &error_abort); - memory_region_init_alias(&nms->phys_tcm_alias, NULL, "nios2.tcm.alias", - &nms->phys_tcm, 0, tcm_size); - memory_region_add_subregion(address_space_mem, tcm_base, &nms->phys_tcm); - memory_region_add_subregion(address_space_mem, 0xc0000000 + tcm_base, - &nms->phys_tcm_alias); - - /* Physical DRAM with alias at 0xc0000000 */ - memory_region_init_ram(&nms->phys_ram, NULL, "nios2.ram", ram_size, - &error_abort); - memory_region_init_alias(&nms->phys_ram_alias, NULL, "nios2.ram.alias", - &nms->phys_ram, 0, ram_size); - memory_region_add_subregion(address_space_mem, ram_base, &nms->phys_ram); - memory_region_add_subregion(address_space_mem, 0xc0000000 + ram_base, - &nms->phys_ram_alias); - - /* Create CPU. We need to set eic_present between init and realize. */ - cpu = NIOS2_CPU(object_new(TYPE_NIOS2_CPU)); - - /* Enable the External Interrupt Controller within the CPU. */ - cpu->eic_present = nms->vic; - - /* Configure new exception vectors. */ - cpu->reset_addr = 0xd4000000; - cpu->exception_addr = 0xc8000120; - cpu->fast_tlb_miss_addr = 0xc0000100; - - qdev_realize_and_unref(DEVICE(cpu), NULL, &error_fatal); - - if (nms->vic) { - dev = qdev_new(TYPE_NIOS2_VIC); - MemoryRegion *dev_mr; - qemu_irq cpu_irq; - - object_property_set_link(OBJECT(dev), "cpu", OBJECT(cpu), &error_fatal); - sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); - - cpu_irq = qdev_get_gpio_in_named(DEVICE(cpu), "EIC", 0); - sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, cpu_irq); - for (i = 0; i < 32; i++) { - irq[i] = qdev_get_gpio_in(dev, i); - } - - dev_mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(dev), 0); - memory_region_add_subregion(address_space_mem, 0x18002000, dev_mr); - } else { - for (i = 0; i < 32; i++) { - irq[i] = qdev_get_gpio_in_named(DEVICE(cpu), "IRQ", i); - } - } - - /* Register: Altera 16550 UART */ - serial_mm_init(address_space_mem, 0xf8001600, 2, irq[1], 115200, - serial_hd(0), DEVICE_NATIVE_ENDIAN); - - /* Register: Timer sys_clk_timer */ - dev = qdev_new("ALTR.timer"); - qdev_prop_set_uint32(dev, "clock-frequency", 75 * 1000000); - sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); - sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, 0xf8001440); - sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, irq[0]); - - /* Register: Timer sys_clk_timer_1 */ - dev = qdev_new("ALTR.timer"); - qdev_prop_set_uint32(dev, "clock-frequency", 75 * 1000000); - sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); - sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, 0xe0000880); - sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, irq[5]); - - nios2_load_kernel(cpu, ram_base, ram_size, machine->initrd_filename, - BINARY_DEVICE_TREE_FILE, NULL); -} - -static bool get_vic(Object *obj, Error **errp) -{ - Nios2MachineState *nms = NIOS2_MACHINE(obj); - return nms->vic; -} - -static void set_vic(Object *obj, bool value, Error **errp) -{ - Nios2MachineState *nms = NIOS2_MACHINE(obj); - nms->vic = value; -} - -static void nios2_10m50_ghrd_class_init(ObjectClass *oc, void *data) -{ - MachineClass *mc = MACHINE_CLASS(oc); - - mc->desc = "Altera 10M50 GHRD Nios II design"; - mc->init = nios2_10m50_ghrd_init; - mc->is_default = true; - mc->deprecation_reason = "Nios II architecture is deprecated"; - - object_class_property_add_bool(oc, "vic", get_vic, set_vic); - object_class_property_set_description(oc, "vic", - "Set on/off to enable/disable the Vectored Interrupt Controller"); -} - -static const TypeInfo nios2_10m50_ghrd_type_info = { - .name = TYPE_NIOS2_MACHINE, - .parent = TYPE_MACHINE, - .instance_size = sizeof(Nios2MachineState), - .class_init = nios2_10m50_ghrd_class_init, -}; - -static void nios2_10m50_ghrd_type_init(void) -{ - type_register_static(&nios2_10m50_ghrd_type_info); -} -type_init(nios2_10m50_ghrd_type_init); diff --git a/hw/nios2/boot.c b/hw/nios2/boot.c deleted file mode 100644 index cd75803fc2..0000000000 --- a/hw/nios2/boot.c +++ /dev/null @@ -1,234 +0,0 @@ -/* - * Nios2 kernel loader - * - * Copyright (c) 2016 Marek Vasut <marek.vasut(a)gmail.com> - * - * Based on microblaze kernel loader - * - * Copyright (c) 2012 Peter Crosthwaite <peter.crosthwaite(a)petalogix.com> - * Copyright (c) 2012 PetaLogix - * Copyright (c) 2009 Edgar E. Iglesias. - * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to deal - * in the Software without restriction, including without limitation the rights - * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell - * copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, - * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN - * THE SOFTWARE. - */ - -#include "qemu/osdep.h" -#include "qemu/units.h" -#include "qemu/datadir.h" -#include "qemu/option.h" -#include "qemu/config-file.h" -#include "qemu/error-report.h" -#include "qemu/guest-random.h" -#include "sysemu/device_tree.h" -#include "sysemu/reset.h" -#include "hw/boards.h" -#include "hw/loader.h" -#include "elf.h" - -#include "boot.h" - -#include <libfdt.h> - -#define NIOS2_MAGIC 0x534f494e - -static struct nios2_boot_info { - void (*machine_cpu_reset)(Nios2CPU *); - uint32_t bootstrap_pc; - uint32_t cmdline; - uint32_t initrd_start; - uint32_t initrd_end; - uint32_t fdt; -} boot_info; - -static void main_cpu_reset(void *opaque) -{ - Nios2CPU *cpu = opaque; - CPUState *cs = CPU(cpu); - CPUNios2State *env = &cpu->env; - - cpu_reset(CPU(cpu)); - - env->regs[R_ARG0] = NIOS2_MAGIC; - env->regs[R_ARG1] = boot_info.initrd_start; - env->regs[R_ARG2] = boot_info.fdt; - env->regs[R_ARG3] = boot_info.cmdline; - - cpu_set_pc(cs, boot_info.bootstrap_pc); - if (boot_info.machine_cpu_reset) { - boot_info.machine_cpu_reset(cpu); - } -} - -static uint64_t translate_kernel_address(void *opaque, uint64_t addr) -{ - return addr - 0xc0000000LL; -} - -static int nios2_load_dtb(struct nios2_boot_info bi, const uint32_t ramsize, - const char *kernel_cmdline, const char *dtb_filename) -{ - MachineState *machine = MACHINE(qdev_get_machine()); - int fdt_size; - void *fdt = NULL; - int r; - uint8_t rng_seed[32]; - - if (dtb_filename) { - fdt = load_device_tree(dtb_filename, &fdt_size); - } - if (!fdt) { - return 0; - } - - qemu_guest_getrandom_nofail(rng_seed, sizeof(rng_seed)); - qemu_fdt_setprop(fdt, "/chosen", "rng-seed", rng_seed, sizeof(rng_seed)); - - if (kernel_cmdline) { - r = qemu_fdt_setprop_string(fdt, "/chosen", "bootargs", - kernel_cmdline); - if (r < 0) { - fprintf(stderr, "couldn't set /chosen/bootargs\n"); - } - } - - if (bi.initrd_start) { - qemu_fdt_setprop_cell(fdt, "/chosen", "linux,initrd-start", - translate_kernel_address(NULL, bi.initrd_start)); - - qemu_fdt_setprop_cell(fdt, "/chosen", "linux,initrd-end", - translate_kernel_address(NULL, bi.initrd_end)); - } - - cpu_physical_memory_write(bi.fdt, fdt, fdt_size); - - /* Set machine->fdt for 'dumpdtb' QMP/HMP command */ - machine->fdt = fdt; - - return fdt_size; -} - -void nios2_load_kernel(Nios2CPU *cpu, hwaddr ddr_base, - uint32_t ramsize, - const char *initrd_filename, - const char *dtb_filename, - void (*machine_cpu_reset)(Nios2CPU *)) -{ - const char *kernel_filename; - const char *kernel_cmdline; - const char *dtb_arg; - char *filename = NULL; - - kernel_filename = current_machine->kernel_filename; - kernel_cmdline = current_machine->kernel_cmdline; - dtb_arg = current_machine->dtb; - /* default to pcbios dtb as passed by machine_init */ - if (!dtb_arg) { - filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, dtb_filename); - } - - boot_info.machine_cpu_reset = machine_cpu_reset; - qemu_register_reset(main_cpu_reset, cpu); - - if (kernel_filename) { - int kernel_size, fdt_size; - uint64_t entry, high; - - /* Boots a kernel elf binary. */ - kernel_size = load_elf(kernel_filename, NULL, NULL, NULL, - &entry, NULL, &high, NULL, - TARGET_BIG_ENDIAN, EM_ALTERA_NIOS2, 0, 0); - if ((uint32_t)entry == 0xc0000000) { - /* - * The Nios II processor reference guide documents that the - * kernel is placed at virtual memory address 0xc0000000, - * and we've got something that points there. Reload it - * and adjust the entry to get the address in physical RAM. - */ - kernel_size = load_elf(kernel_filename, NULL, - translate_kernel_address, NULL, - &entry, NULL, NULL, NULL, - TARGET_BIG_ENDIAN, EM_ALTERA_NIOS2, 0, 0); - boot_info.bootstrap_pc = ddr_base + 0xc0000000 + - (entry & 0x07ffffff); - } else { - /* Use the entry point in the ELF image. */ - boot_info.bootstrap_pc = (uint32_t)entry; - } - - /* If it wasn't an ELF image, try an u-boot image. */ - if (kernel_size < 0) { - hwaddr uentry, loadaddr = LOAD_UIMAGE_LOADADDR_INVALID; - - kernel_size = load_uimage(kernel_filename, &uentry, &loadaddr, 0, - NULL, NULL); - boot_info.bootstrap_pc = uentry; - high = loadaddr + kernel_size; - } - - /* Not an ELF image nor an u-boot image, try a RAW image. */ - if (kernel_size < 0) { - kernel_size = load_image_targphys(kernel_filename, ddr_base, - ramsize); - boot_info.bootstrap_pc = ddr_base; - high = ddr_base + kernel_size; - } - - high = ROUND_UP(high, 1 * MiB); - - /* If initrd is available, it goes after the kernel, aligned to 1M. */ - if (initrd_filename) { - int initrd_size; - uint32_t initrd_offset; - - boot_info.initrd_start = high; - initrd_offset = boot_info.initrd_start - ddr_base; - - initrd_size = load_ramdisk(initrd_filename, - boot_info.initrd_start, - ramsize - initrd_offset); - if (initrd_size < 0) { - initrd_size = load_image_targphys(initrd_filename, - boot_info.initrd_start, - ramsize - initrd_offset); - } - if (initrd_size < 0) { - error_report("could not load initrd '%s'", - initrd_filename); - exit(EXIT_FAILURE); - } - high += initrd_size; - } - high = ROUND_UP(high, 4); - boot_info.initrd_end = high; - - /* Device tree must be placed right after initrd (if available) */ - boot_info.fdt = high; - fdt_size = nios2_load_dtb(boot_info, ramsize, kernel_cmdline, - /* Preference a -dtb argument */ - dtb_arg ? dtb_arg : filename); - high += fdt_size; - - /* Kernel command is at the end, 4k aligned. */ - boot_info.cmdline = ROUND_UP(high, 4 * KiB); - if (kernel_cmdline && strlen(kernel_cmdline)) { - pstrcpy_targphys("cmdline", boot_info.cmdline, 256, kernel_cmdline); - } - } - g_free(filename); -} diff --git a/hw/nios2/generic_nommu.c b/hw/nios2/generic_nommu.c deleted file mode 100644 index defa16953f..0000000000 --- a/hw/nios2/generic_nommu.c +++ /dev/null @@ -1,101 +0,0 @@ -/* - * Generic simulator target with no MMU or devices. This emulation is - * compatible with the libgloss qemu-hosted.ld linker script for using - * QEMU as an instruction set simulator. - * - * Copyright (c) 2018-2019 Mentor Graphics - * - * Copyright (c) 2016 Marek Vasut <marek.vasut(a)gmail.com> - * - * Based on LabX device code - * - * Copyright (c) 2012 Chris Wulff <crwulff(a)gmail.com> - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see - * <http://www.gnu.org/licenses/lgpl-2.1.html> - */ - -#include "qemu/osdep.h" -#include "qapi/error.h" - -#include "hw/char/serial.h" -#include "hw/boards.h" -#include "exec/memory.h" -#include "exec/address-spaces.h" -#include "qemu/config-file.h" - -#include "boot.h" - -#define BINARY_DEVICE_TREE_FILE "generic-nommu.dtb" - -static void nios2_generic_nommu_init(MachineState *machine) -{ - Nios2CPU *cpu; - MemoryRegion *address_space_mem = get_system_memory(); - MemoryRegion *phys_tcm = g_new(MemoryRegion, 1); - MemoryRegion *phys_tcm_alias = g_new(MemoryRegion, 1); - MemoryRegion *phys_ram = g_new(MemoryRegion, 1); - MemoryRegion *phys_ram_alias = g_new(MemoryRegion, 1); - ram_addr_t tcm_base = 0x0; - ram_addr_t tcm_size = 0x1000; /* 1 kiB, but QEMU limit is 4 kiB */ - ram_addr_t ram_base = 0x10000000; - ram_addr_t ram_size = 0x08000000; - - /* Physical TCM (tb_ram_1k) with alias at 0xc0000000 */ - memory_region_init_ram(phys_tcm, NULL, "nios2.tcm", tcm_size, - &error_abort); - memory_region_init_alias(phys_tcm_alias, NULL, "nios2.tcm.alias", - phys_tcm, 0, tcm_size); - memory_region_add_subregion(address_space_mem, tcm_base, phys_tcm); - memory_region_add_subregion(address_space_mem, 0xc0000000 + tcm_base, - phys_tcm_alias); - - /* Physical DRAM with alias at 0xc0000000 */ - memory_region_init_ram(phys_ram, NULL, "nios2.ram", ram_size, - &error_abort); - memory_region_init_alias(phys_ram_alias, NULL, "nios2.ram.alias", - phys_ram, 0, ram_size); - memory_region_add_subregion(address_space_mem, ram_base, phys_ram); - memory_region_add_subregion(address_space_mem, 0xc0000000 + ram_base, - phys_ram_alias); - - cpu = NIOS2_CPU(cpu_create(TYPE_NIOS2_CPU)); - - /* Remove MMU */ - cpu->mmu_present = false; - - /* Reset vector is the first 32 bytes of RAM. */ - cpu->reset_addr = ram_base; - - /* The interrupt vector comes right after reset. */ - cpu->exception_addr = ram_base + 0x20; - - /* - * The linker script does have a TLB miss memory region declared, - * but this should never be used with no MMU. - */ - cpu->fast_tlb_miss_addr = 0x7fff400; - - nios2_load_kernel(cpu, ram_base, ram_size, machine->initrd_filename, - BINARY_DEVICE_TREE_FILE, NULL); -} - -static void nios2_generic_nommu_machine_init(struct MachineClass *mc) -{ - mc->desc = "Generic NOMMU Nios II design"; - mc->init = nios2_generic_nommu_init; - mc->deprecation_reason = "Nios II architecture is deprecated"; -} - -DEFINE_MACHINE("nios2-generic-nommu", nios2_generic_nommu_machine_init); diff --git a/target/nios2/cpu.c b/target/nios2/cpu.c index 679aff5730..621f32f4a7 100644 --- a/target/nios2/cpu.c +++ b/target/nios2/cpu.c @@ -68,53 +68,9 @@ static void nios2_cpu_reset_hold(Object *obj) memset(env->ctrl, 0, sizeof(env->ctrl)); env->pc = cpu->reset_addr; -#if defined(CONFIG_USER_ONLY) /* Start in user mode with interrupts enabled. */ env->ctrl[CR_STATUS] = CR_STATUS_RSIE | CR_STATUS_U | CR_STATUS_PIE; memset(env->regs, 0, sizeof(env->regs)); -#else - env->ctrl[CR_STATUS] = CR_STATUS_RSIE; - nios2_update_crs(env); - memset(env->shadow_regs, 0, sizeof(env->shadow_regs)); -#endif -} - -#ifndef CONFIG_USER_ONLY -static void eic_set_irq(void *opaque, int irq, int level) -{ - Nios2CPU *cpu = opaque; - CPUState *cs = CPU(cpu); - - if (level) { - cpu_interrupt(cs, CPU_INTERRUPT_HARD); - } else { - cpu_reset_interrupt(cs, CPU_INTERRUPT_HARD); - } -} - -static void iic_set_irq(void *opaque, int irq, int level) -{ - Nios2CPU *cpu = opaque; - CPUNios2State *env = &cpu->env; - CPUState *cs = CPU(cpu); - - env->ctrl[CR_IPENDING] = deposit32(env->ctrl[CR_IPENDING], irq, 1, !!level); - - if (env->ctrl[CR_IPENDING]) { - cpu_interrupt(cs, CPU_INTERRUPT_HARD); - } else { - cpu_reset_interrupt(cs, CPU_INTERRUPT_HARD); - } -} -#endif - -static void nios2_cpu_initfn(Object *obj) -{ -#if !defined(CONFIG_USER_ONLY) - Nios2CPU *cpu = NIOS2_CPU(obj); - - mmu_init(&cpu->env); -#endif } static ObjectClass *nios2_cpu_class_by_name(const char *cpu_model) @@ -146,37 +102,9 @@ static void realize_cr_status(CPUState *cs) RO_REG(CR_EXCEPTION); WR_REG(CR_BADADDR); - if (cpu->eic_present) { - WR_FIELD(CR_STATUS, RSIE); - RO_FIELD(CR_STATUS, NMI); - WR_FIELD(CR_STATUS, PRS); - RO_FIELD(CR_STATUS, CRS); - WR_FIELD(CR_STATUS, IL); - WR_FIELD(CR_STATUS, IH); - } else { - RO_FIELD(CR_STATUS, RSIE); - WR_REG(CR_IENABLE); - RO_REG(CR_IPENDING); - } - - if (cpu->mmu_present) { - WR_FIELD(CR_STATUS, U); - WR_FIELD(CR_STATUS, EH); - - WR_FIELD(CR_PTEADDR, VPN); - WR_FIELD(CR_PTEADDR, PTBASE); - - RO_FIELD(CR_TLBMISC, D); - RO_FIELD(CR_TLBMISC, PERM); - RO_FIELD(CR_TLBMISC, BAD); - RO_FIELD(CR_TLBMISC, DBL); - WR_FIELD(CR_TLBMISC, PID); - WR_FIELD(CR_TLBMISC, WE); - WR_FIELD(CR_TLBMISC, RD); - WR_FIELD(CR_TLBMISC, WAY); - - WR_REG(CR_TLBACC); - } + RO_FIELD(CR_STATUS, RSIE); + WR_REG(CR_IENABLE); + RO_REG(CR_IPENDING); /* * TODO: ECC (config, eccinj) and MPU (config, mpubase, mpuacc) are @@ -209,65 +137,9 @@ static void nios2_cpu_realizefn(DeviceState *dev, Error **errp) /* We have reserved storage for cpuid; might as well use it. */ cpu->env.ctrl[CR_CPUID] = cs->cpu_index; -#ifndef CONFIG_USER_ONLY - if (cpu->eic_present) { - qdev_init_gpio_in_named(DEVICE(cpu), eic_set_irq, "EIC", 1); - } else { - qdev_init_gpio_in_named(DEVICE(cpu), iic_set_irq, "IRQ", 32); - } -#endif - ncc->parent_realize(dev, errp); } -#ifndef CONFIG_USER_ONLY -static bool eic_take_interrupt(Nios2CPU *cpu) -{ - CPUNios2State *env = &cpu->env; - const uint32_t status = env->ctrl[CR_STATUS]; - - if (cpu->rnmi) { - return !(status & CR_STATUS_NMI); - } - if (!(status & CR_STATUS_PIE)) { - return false; - } - if (cpu->ril <= FIELD_EX32(status, CR_STATUS, IL)) { - return false; - } - if (cpu->rrs != FIELD_EX32(status, CR_STATUS, CRS)) { - return true; - } - return status & CR_STATUS_RSIE; -} - -static bool iic_take_interrupt(Nios2CPU *cpu) -{ - CPUNios2State *env = &cpu->env; - - if (!(env->ctrl[CR_STATUS] & CR_STATUS_PIE)) { - return false; - } - return env->ctrl[CR_IPENDING] & env->ctrl[CR_IENABLE]; -} - -static bool nios2_cpu_exec_interrupt(CPUState *cs, int interrupt_request) -{ - Nios2CPU *cpu = NIOS2_CPU(cs); - - if (interrupt_request & CPU_INTERRUPT_HARD) { - if (cpu->eic_present - ? eic_take_interrupt(cpu) - : iic_take_interrupt(cpu)) { - cs->exception_index = EXCP_IRQ; - nios2_cpu_do_interrupt(cs); - return true; - } - } - return false; -} -#endif /* !CONFIG_USER_ONLY */ - static void nios2_cpu_disas_set_info(CPUState *cpu, disassemble_info *info) { /* NOTE: NiosII R2 is not supported yet. */ @@ -331,36 +203,14 @@ static int nios2_cpu_gdb_write_register(CPUState *cs, uint8_t *mem_buf, int n) static Property nios2_properties[] = { DEFINE_PROP_BOOL("diverr_present", Nios2CPU, diverr_present, true), - DEFINE_PROP_BOOL("mmu_present", Nios2CPU, mmu_present, true), - /* ALTR,pid-num-bits */ - DEFINE_PROP_UINT32("mmu_pid_num_bits", Nios2CPU, pid_num_bits, 8), - /* ALTR,tlb-num-ways */ - DEFINE_PROP_UINT32("mmu_tlb_num_ways", Nios2CPU, tlb_num_ways, 16), - /* ALTR,tlb-num-entries */ - DEFINE_PROP_UINT32("mmu_pid_num_entries", Nios2CPU, tlb_num_entries, 256), DEFINE_PROP_END_OF_LIST(), }; -#ifndef CONFIG_USER_ONLY -#include "hw/core/sysemu-cpu-ops.h" - -static const struct SysemuCPUOps nios2_sysemu_ops = { - .get_phys_page_debug = nios2_cpu_get_phys_page_debug, -}; -#endif - #include "hw/core/tcg-cpu-ops.h" static const TCGCPUOps nios2_tcg_ops = { .initialize = nios2_tcg_init, .restore_state_to_opc = nios2_restore_state_to_opc, - -#ifndef CONFIG_USER_ONLY - .tlb_fill = nios2_cpu_tlb_fill, - .cpu_exec_interrupt = nios2_cpu_exec_interrupt, - .do_interrupt = nios2_cpu_do_interrupt, - .do_unaligned_access = nios2_cpu_do_unaligned_access, -#endif /* !CONFIG_USER_ONLY */ }; static void nios2_cpu_class_init(ObjectClass *oc, void *data) @@ -383,9 +233,6 @@ static void nios2_cpu_class_init(ObjectClass *oc, void *data) cc->set_pc = nios2_cpu_set_pc; cc->get_pc = nios2_cpu_get_pc; cc->disas_set_info = nios2_cpu_disas_set_info; -#ifndef CONFIG_USER_ONLY - cc->sysemu_ops = &nios2_sysemu_ops; -#endif cc->gdb_read_register = nios2_cpu_gdb_read_register; cc->gdb_write_register = nios2_cpu_gdb_write_register; cc->gdb_num_core_regs = 49; @@ -397,7 +244,6 @@ static const TypeInfo nios2_cpu_type_info = { .parent = TYPE_CPU, .instance_size = sizeof(Nios2CPU), .instance_align = __alignof(Nios2CPU), - .instance_init = nios2_cpu_initfn, .class_size = sizeof(Nios2CPUClass), .class_init = nios2_cpu_class_init, }; diff --git a/target/nios2/helper.c b/target/nios2/helper.c deleted file mode 100644 index ac57121afc..0000000000 --- a/target/nios2/helper.c +++ /dev/null @@ -1,371 +0,0 @@ -/* - * Altera Nios II helper routines. - * - * Copyright (c) 2012 Chris Wulff <crwulff(a)gmail.com> - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see - * <http://www.gnu.org/licenses/lgpl-2.1.html> - */ - -#include "qemu/osdep.h" - -#include "cpu.h" -#include "qemu/host-utils.h" -#include "exec/exec-all.h" -#include "exec/cpu_ldst.h" -#include "exec/log.h" -#include "exec/helper-proto.h" -#include "semihosting/semihost.h" - - -static void do_exception(Nios2CPU *cpu, uint32_t exception_addr, - uint32_t tlbmisc_set, bool is_break) -{ - CPUNios2State *env = &cpu->env; - CPUState *cs = CPU(cpu); - uint32_t old_status = env->ctrl[CR_STATUS]; - uint32_t new_status = old_status; - - /* With shadow regs, exceptions are always taken into CRS 0. */ - new_status &= ~R_CR_STATUS_CRS_MASK; - env->regs = env->shadow_regs[0]; - - if ((old_status & CR_STATUS_EH) == 0) { - int r_ea = R_EA, cr_es = CR_ESTATUS; - - if (is_break) { - r_ea = R_BA; - cr_es = CR_BSTATUS; - } - env->ctrl[cr_es] = old_status; - env->regs[r_ea] = env->pc; - - if (cpu->mmu_present) { - new_status |= CR_STATUS_EH; - - /* - * There are 4 bits that are always written. - * Explicitly clear them, to be set via the argument. - */ - env->ctrl[CR_TLBMISC] &= ~(CR_TLBMISC_D | - CR_TLBMISC_PERM | - CR_TLBMISC_BAD | - CR_TLBMISC_DBL); - env->ctrl[CR_TLBMISC] |= tlbmisc_set; - } - - /* - * With shadow regs, and EH == 0, PRS is set from CRS. - * At least, so says Table 3-9, and some other text, - * though Table 3-38 says otherwise. - */ - new_status = FIELD_DP32(new_status, CR_STATUS, PRS, - FIELD_EX32(old_status, CR_STATUS, CRS)); - } - - new_status &= ~(CR_STATUS_PIE | CR_STATUS_U); - - env->ctrl[CR_STATUS] = new_status; - if (!is_break) { - env->ctrl[CR_EXCEPTION] = FIELD_DP32(0, CR_EXCEPTION, CAUSE, - cs->exception_index); - } - env->pc = exception_addr; -} - -static void do_iic_irq(Nios2CPU *cpu) -{ - do_exception(cpu, cpu->exception_addr, 0, false); -} - -static void do_eic_irq(Nios2CPU *cpu) -{ - CPUNios2State *env = &cpu->env; - uint32_t old_status = env->ctrl[CR_STATUS]; - uint32_t new_status = old_status; - uint32_t old_rs = FIELD_EX32(old_status, CR_STATUS, CRS); - uint32_t new_rs = cpu->rrs; - - new_status = FIELD_DP32(new_status, CR_STATUS, CRS, new_rs); - new_status = FIELD_DP32(new_status, CR_STATUS, IL, cpu->ril); - new_status = FIELD_DP32(new_status, CR_STATUS, NMI, cpu->rnmi); - new_status &= ~(CR_STATUS_RSIE | CR_STATUS_U); - new_status |= CR_STATUS_IH; - - if (!(new_status & CR_STATUS_EH)) { - new_status = FIELD_DP32(new_status, CR_STATUS, PRS, old_rs); - if (new_rs == 0) { - env->ctrl[CR_ESTATUS] = old_status; - } else { - if (new_rs != old_rs) { - old_status |= CR_STATUS_SRS; - } - env->shadow_regs[new_rs][R_SSTATUS] = old_status; - } - env->shadow_regs[new_rs][R_EA] = env->pc; - } - - env->ctrl[CR_STATUS] = new_status; - nios2_update_crs(env); - - env->pc = cpu->rha; -} - -void nios2_cpu_do_interrupt(CPUState *cs) -{ - Nios2CPU *cpu = NIOS2_CPU(cs); - CPUNios2State *env = &cpu->env; - uint32_t tlbmisc_set = 0; - - if (qemu_loglevel_mask(CPU_LOG_INT)) { - const char *name = NULL; - - switch (cs->exception_index) { - case EXCP_IRQ: - name = "interrupt"; - break; - case EXCP_TLB_X: - case EXCP_TLB_D: - if (env->ctrl[CR_STATUS] & CR_STATUS_EH) { - name = "TLB MISS (double)"; - } else { - name = "TLB MISS (fast)"; - } - break; - case EXCP_PERM_R: - case EXCP_PERM_W: - case EXCP_PERM_X: - name = "TLB PERM"; - break; - case EXCP_SUPERA_X: - case EXCP_SUPERA_D: - name = "SUPERVISOR (address)"; - break; - case EXCP_SUPERI: - name = "SUPERVISOR (insn)"; - break; - case EXCP_ILLEGAL: - name = "ILLEGAL insn"; - break; - case EXCP_UNALIGN: - name = "Misaligned (data)"; - break; - case EXCP_UNALIGND: - name = "Misaligned (destination)"; - break; - case EXCP_DIV: - name = "DIV error"; - break; - case EXCP_TRAP: - name = "TRAP insn"; - break; - case EXCP_BREAK: - name = "BREAK insn"; - break; - case EXCP_SEMIHOST: - name = "SEMIHOST insn"; - break; - } - if (name) { - qemu_log("%s at pc=0x%08x\n", name, env->pc); - } else { - qemu_log("Unknown exception %d at pc=0x%08x\n", - cs->exception_index, env->pc); - } - } - - switch (cs->exception_index) { - case EXCP_IRQ: - /* Note that PC is advanced for interrupts as well. */ - env->pc += 4; - if (cpu->eic_present) { - do_eic_irq(cpu); - } else { - do_iic_irq(cpu); - } - break; - - case EXCP_TLB_D: - tlbmisc_set = CR_TLBMISC_D; - /* fall through */ - case EXCP_TLB_X: - if (env->ctrl[CR_STATUS] & CR_STATUS_EH) { - tlbmisc_set |= CR_TLBMISC_DBL; - /* - * Normally, we don't write to tlbmisc unless !EH, - * so do it manually for the double-tlb miss exception. - */ - env->ctrl[CR_TLBMISC] &= ~(CR_TLBMISC_D | - CR_TLBMISC_PERM | - CR_TLBMISC_BAD); - env->ctrl[CR_TLBMISC] |= tlbmisc_set; - do_exception(cpu, cpu->exception_addr, 0, false); - } else { - tlbmisc_set |= CR_TLBMISC_WE; - do_exception(cpu, cpu->fast_tlb_miss_addr, tlbmisc_set, false); - } - break; - - case EXCP_PERM_R: - case EXCP_PERM_W: - tlbmisc_set = CR_TLBMISC_D; - /* fall through */ - case EXCP_PERM_X: - tlbmisc_set |= CR_TLBMISC_PERM; - if (!(env->ctrl[CR_STATUS] & CR_STATUS_EH)) { - tlbmisc_set |= CR_TLBMISC_WE; - } - do_exception(cpu, cpu->exception_addr, tlbmisc_set, false); - break; - - case EXCP_SUPERA_D: - case EXCP_UNALIGN: - tlbmisc_set = CR_TLBMISC_D; - /* fall through */ - case EXCP_SUPERA_X: - case EXCP_UNALIGND: - tlbmisc_set |= CR_TLBMISC_BAD; - do_exception(cpu, cpu->exception_addr, tlbmisc_set, false); - break; - - case EXCP_SUPERI: - case EXCP_ILLEGAL: - case EXCP_DIV: - case EXCP_TRAP: - do_exception(cpu, cpu->exception_addr, 0, false); - break; - - case EXCP_BREAK: - do_exception(cpu, cpu->exception_addr, 0, true); - break; - - case EXCP_SEMIHOST: - do_nios2_semihosting(env); - break; - - default: - cpu_abort(cs, "unhandled exception type=%d\n", cs->exception_index); - } -} - -hwaddr nios2_cpu_get_phys_page_debug(CPUState *cs, vaddr addr) -{ - Nios2CPU *cpu = NIOS2_CPU(cs); - CPUNios2State *env = &cpu->env; - target_ulong vaddr, paddr = 0; - Nios2MMULookup lu; - unsigned int hit; - - if (cpu->mmu_present && (addr < 0xC0000000)) { - hit = mmu_translate(env, &lu, addr, 0, 0); - if (hit) { - vaddr = addr & TARGET_PAGE_MASK; - paddr = lu.paddr + vaddr - lu.vaddr; - } else { - paddr = -1; - qemu_log("cpu_get_phys_page debug MISS: %#" PRIx64 "\n", addr); - } - } else { - paddr = addr & TARGET_PAGE_MASK; - } - - return paddr; -} - -void nios2_cpu_do_unaligned_access(CPUState *cs, vaddr addr, - MMUAccessType access_type, - int mmu_idx, uintptr_t retaddr) -{ - CPUNios2State *env = cpu_env(cs); - - env->ctrl[CR_BADADDR] = addr; - cs->exception_index = EXCP_UNALIGN; - nios2_cpu_loop_exit_advance(env, retaddr); -} - -bool nios2_cpu_tlb_fill(CPUState *cs, vaddr address, int size, - MMUAccessType access_type, int mmu_idx, - bool probe, uintptr_t retaddr) -{ - Nios2CPU *cpu = NIOS2_CPU(cs); - CPUNios2State *env = &cpu->env; - unsigned int excp; - target_ulong vaddr, paddr; - Nios2MMULookup lu; - unsigned int hit; - - if (!cpu->mmu_present) { - /* No MMU */ - address &= TARGET_PAGE_MASK; - tlb_set_page(cs, address, address, PAGE_BITS, - mmu_idx, TARGET_PAGE_SIZE); - return true; - } - - if (MMU_SUPERVISOR_IDX == mmu_idx) { - if (address >= 0xC0000000) { - /* Kernel physical page - TLB bypassed */ - address &= TARGET_PAGE_MASK; - tlb_set_page(cs, address, address, PAGE_BITS, - mmu_idx, TARGET_PAGE_SIZE); - return true; - } - } else { - if (address >= 0x80000000) { - /* Illegal access from user mode */ - if (probe) { - return false; - } - cs->exception_index = (access_type == MMU_INST_FETCH - ? EXCP_SUPERA_X : EXCP_SUPERA_D); - env->ctrl[CR_BADADDR] = address; - nios2_cpu_loop_exit_advance(env, retaddr); - } - } - - /* Virtual page. */ - hit = mmu_translate(env, &lu, address, access_type, mmu_idx); - if (hit) { - vaddr = address & TARGET_PAGE_MASK; - paddr = lu.paddr + vaddr - lu.vaddr; - - if (((access_type == MMU_DATA_LOAD) && (lu.prot & PAGE_READ)) || - ((access_type == MMU_DATA_STORE) && (lu.prot & PAGE_WRITE)) || - ((access_type == MMU_INST_FETCH) && (lu.prot & PAGE_EXEC))) { - tlb_set_page(cs, vaddr, paddr, lu.prot, - mmu_idx, TARGET_PAGE_SIZE); - return true; - } - - /* Permission violation */ - excp = (access_type == MMU_DATA_LOAD ? EXCP_PERM_R : - access_type == MMU_DATA_STORE ? EXCP_PERM_W : EXCP_PERM_X); - } else { - excp = (access_type == MMU_INST_FETCH ? EXCP_TLB_X: EXCP_TLB_D); - } - - if (probe) { - return false; - } - - env->ctrl[CR_TLBMISC] = FIELD_DP32(env->ctrl[CR_TLBMISC], CR_TLBMISC, D, - access_type != MMU_INST_FETCH); - env->ctrl[CR_PTEADDR] = FIELD_DP32(env->ctrl[CR_PTEADDR], CR_PTEADDR, VPN, - address >> TARGET_PAGE_BITS); - env->mmu.pteaddr_wr = env->ctrl[CR_PTEADDR]; - - cs->exception_index = excp; - env->ctrl[CR_BADADDR] = address; - nios2_cpu_loop_exit_advance(env, retaddr); -} diff --git a/target/nios2/mmu.c b/target/nios2/mmu.c deleted file mode 100644 index d9b690b78e..0000000000 --- a/target/nios2/mmu.c +++ /dev/null @@ -1,216 +0,0 @@ -/* - * Altera Nios II MMU emulation for qemu. - * - * Copyright (C) 2012 Chris Wulff <crwulff(a)gmail.com> - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see - * <http://www.gnu.org/licenses/lgpl-2.1.html> - */ - -#include "qemu/osdep.h" -#include "qemu/qemu-print.h" -#include "cpu.h" -#include "exec/exec-all.h" -#include "mmu.h" -#include "exec/helper-proto.h" -#include "trace/trace-target_nios2.h" - - -/* rw - 0 = read, 1 = write, 2 = fetch. */ -unsigned int mmu_translate(CPUNios2State *env, - Nios2MMULookup *lu, - target_ulong vaddr, int rw, int mmu_idx) -{ - Nios2CPU *cpu = env_archcpu(env); - int pid = FIELD_EX32(env->mmu.tlbmisc_wr, CR_TLBMISC, PID); - int vpn = vaddr >> 12; - int way, n_ways = cpu->tlb_num_ways; - - for (way = 0; way < n_ways; way++) { - uint32_t index = (way * n_ways) + (vpn & env->mmu.tlb_entry_mask); - Nios2TLBEntry *entry = &env->mmu.tlb[index]; - - if (((entry->tag >> 12) != vpn) || - (((entry->tag & (1 << 11)) == 0) && - ((entry->tag & ((1 << cpu->pid_num_bits) - 1)) != pid))) { - trace_nios2_mmu_translate_miss(vaddr, pid, index, entry->tag); - continue; - } - - lu->vaddr = vaddr & TARGET_PAGE_MASK; - lu->paddr = FIELD_EX32(entry->data, CR_TLBACC, PFN) << TARGET_PAGE_BITS; - lu->prot = ((entry->data & CR_TLBACC_R) ? PAGE_READ : 0) | - ((entry->data & CR_TLBACC_W) ? PAGE_WRITE : 0) | - ((entry->data & CR_TLBACC_X) ? PAGE_EXEC : 0); - - trace_nios2_mmu_translate_hit(vaddr, pid, index, lu->paddr, lu->prot); - return 1; - } - return 0; -} - -static void mmu_flush_pid(CPUNios2State *env, uint32_t pid) -{ - CPUState *cs = env_cpu(env); - Nios2CPU *cpu = env_archcpu(env); - int idx; - - for (idx = 0; idx < cpu->tlb_num_entries; idx++) { - Nios2TLBEntry *entry = &env->mmu.tlb[idx]; - - if ((entry->tag & (1 << 10)) && (!(entry->tag & (1 << 11))) && - ((entry->tag & ((1 << cpu->pid_num_bits) - 1)) == pid)) { - uint32_t vaddr = entry->tag & TARGET_PAGE_MASK; - - trace_nios2_mmu_flush_pid_hit(pid, idx, vaddr); - tlb_flush_page(cs, vaddr); - } else { - trace_nios2_mmu_flush_pid_miss(pid, idx, entry->tag); - } - } -} - -void helper_mmu_write_tlbacc(CPUNios2State *env, uint32_t v) -{ - CPUState *cs = env_cpu(env); - Nios2CPU *cpu = env_archcpu(env); - - trace_nios2_mmu_write_tlbacc(FIELD_EX32(v, CR_TLBACC, IG), - (v & CR_TLBACC_C) ? 'C' : '.', - (v & CR_TLBACC_R) ? 'R' : '.', - (v & CR_TLBACC_W) ? 'W' : '.', - (v & CR_TLBACC_X) ? 'X' : '.', - (v & CR_TLBACC_G) ? 'G' : '.', - FIELD_EX32(v, CR_TLBACC, PFN)); - - /* if tlbmisc.WE == 1 then trigger a TLB write on writes to TLBACC */ - if (env->ctrl[CR_TLBMISC] & CR_TLBMISC_WE) { - int way = FIELD_EX32(env->ctrl[CR_TLBMISC], CR_TLBMISC, WAY); - int vpn = FIELD_EX32(env->mmu.pteaddr_wr, CR_PTEADDR, VPN); - int pid = FIELD_EX32(env->mmu.tlbmisc_wr, CR_TLBMISC, PID); - int g = FIELD_EX32(v, CR_TLBACC, G); - int valid = FIELD_EX32(vpn, CR_TLBACC, PFN) < 0xC0000; - Nios2TLBEntry *entry = - &env->mmu.tlb[(way * cpu->tlb_num_ways) + - (vpn & env->mmu.tlb_entry_mask)]; - uint32_t newTag = (vpn << 12) | (g << 11) | (valid << 10) | pid; - uint32_t newData = v & (CR_TLBACC_C | CR_TLBACC_R | CR_TLBACC_W | - CR_TLBACC_X | R_CR_TLBACC_PFN_MASK); - - if ((entry->tag != newTag) || (entry->data != newData)) { - if (entry->tag & (1 << 10)) { - /* Flush existing entry */ - tlb_flush_page(cs, entry->tag & TARGET_PAGE_MASK); - } - entry->tag = newTag; - entry->data = newData; - } - /* Auto-increment tlbmisc.WAY */ - env->ctrl[CR_TLBMISC] = FIELD_DP32(env->ctrl[CR_TLBMISC], - CR_TLBMISC, WAY, - (way + 1) & (cpu->tlb_num_ways - 1)); - } - - /* Writes to TLBACC don't change the read-back value */ - env->mmu.tlbacc_wr = v; -} - -void helper_mmu_write_tlbmisc(CPUNios2State *env, uint32_t v) -{ - Nios2CPU *cpu = env_archcpu(env); - uint32_t new_pid = FIELD_EX32(v, CR_TLBMISC, PID); - uint32_t old_pid = FIELD_EX32(env->mmu.tlbmisc_wr, CR_TLBMISC, PID); - uint32_t way = FIELD_EX32(v, CR_TLBMISC, WAY); - - trace_nios2_mmu_write_tlbmisc(way, - (v & CR_TLBMISC_RD) ? 'R' : '.', - (v & CR_TLBMISC_WE) ? 'W' : '.', - (v & CR_TLBMISC_DBL) ? '2' : '.', - (v & CR_TLBMISC_BAD) ? 'B' : '.', - (v & CR_TLBMISC_PERM) ? 'P' : '.', - (v & CR_TLBMISC_D) ? 'D' : '.', - new_pid); - - if (new_pid != old_pid) { - mmu_flush_pid(env, old_pid); - } - - /* if tlbmisc.RD == 1 then trigger a TLB read on writes to TLBMISC */ - if (v & CR_TLBMISC_RD) { - int vpn = FIELD_EX32(env->mmu.pteaddr_wr, CR_PTEADDR, VPN); - Nios2TLBEntry *entry = - &env->mmu.tlb[(way * cpu->tlb_num_ways) + - (vpn & env->mmu.tlb_entry_mask)]; - - env->ctrl[CR_TLBACC] &= R_CR_TLBACC_IG_MASK; - env->ctrl[CR_TLBACC] |= entry->data; - env->ctrl[CR_TLBACC] |= (entry->tag & (1 << 11)) ? CR_TLBACC_G : 0; - env->ctrl[CR_TLBMISC] = FIELD_DP32(v, CR_TLBMISC, PID, - entry->tag & - ((1 << cpu->pid_num_bits) - 1)); - env->ctrl[CR_PTEADDR] = FIELD_DP32(env->ctrl[CR_PTEADDR], - CR_PTEADDR, VPN, - entry->tag >> TARGET_PAGE_BITS); - } else { - env->ctrl[CR_TLBMISC] = v; - } - - env->mmu.tlbmisc_wr = v; -} - -void helper_mmu_write_pteaddr(CPUNios2State *env, uint32_t v) -{ - trace_nios2_mmu_write_pteaddr(FIELD_EX32(v, CR_PTEADDR, PTBASE), - FIELD_EX32(v, CR_PTEADDR, VPN)); - - /* Writes to PTEADDR don't change the read-back VPN value */ - env->ctrl[CR_PTEADDR] = ((v & ~R_CR_PTEADDR_VPN_MASK) | - (env->ctrl[CR_PTEADDR] & R_CR_PTEADDR_VPN_MASK)); - env->mmu.pteaddr_wr = v; -} - -void mmu_init(CPUNios2State *env) -{ - Nios2CPU *cpu = env_archcpu(env); - Nios2MMU *mmu = &env->mmu; - - mmu->tlb_entry_mask = (cpu->tlb_num_entries / cpu->tlb_num_ways) - 1; - mmu->tlb = g_new0(Nios2TLBEntry, cpu->tlb_num_entries); -} - -void dump_mmu(CPUNios2State *env) -{ - Nios2CPU *cpu = env_archcpu(env); - int i; - - qemu_printf("MMU: ways %d, entries %d, pid bits %d\n", - cpu->tlb_num_ways, cpu->tlb_num_entries, - cpu->pid_num_bits); - - for (i = 0; i < cpu->tlb_num_entries; i++) { - Nios2TLBEntry *entry = &env->mmu.tlb[i]; - qemu_printf("TLB[%d] = %08X %08X %c VPN %05X " - "PID %02X %c PFN %05X %c%c%c%c\n", - i, entry->tag, entry->data, - (entry->tag & (1 << 10)) ? 'V' : '-', - entry->tag >> 12, - entry->tag & ((1 << cpu->pid_num_bits) - 1), - (entry->tag & (1 << 11)) ? 'G' : '-', - FIELD_EX32(entry->data, CR_TLBACC, PFN), - (entry->data & CR_TLBACC_C) ? 'C' : '-', - (entry->data & CR_TLBACC_R) ? 'R' : '-', - (entry->data & CR_TLBACC_W) ? 'W' : '-', - (entry->data & CR_TLBACC_X) ? 'X' : '-'); - } -} diff --git a/target/nios2/monitor.c b/target/nios2/monitor.c deleted file mode 100644 index 0152dec3fa..0000000000 --- a/target/nios2/monitor.c +++ /dev/null @@ -1,35 +0,0 @@ -/* - * QEMU monitor - * - * Copyright (c) 2003-2004 Fabrice Bellard - * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to deal - * in the Software without restriction, including without limitation the rights - * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell - * copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, - * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN - * THE SOFTWARE. - */ -#include "qemu/osdep.h" -#include "cpu.h" -#include "monitor/monitor.h" -#include "monitor/hmp-target.h" -#include "monitor/hmp.h" - -void hmp_info_tlb(Monitor *mon, const QDict *qdict) -{ - CPUArchState *env1 = mon_get_cpu_env(mon); - - dump_mmu(env1); -} diff --git a/target/nios2/nios2-semi.c b/target/nios2/nios2-semi.c deleted file mode 100644 index 420702e293..0000000000 --- a/target/nios2/nios2-semi.c +++ /dev/null @@ -1,230 +0,0 @@ -/* - * Nios II Semihosting syscall interface. - * This code is derived from m68k-semi.c. - * The semihosting protocol implemented here is described in the - * libgloss sources: - * https://sourceware.org/git/gitweb.cgi?p=newlib-cygwin.git;a=blob;f=libgloss… - * - * Copyright (c) 2017-2019 Mentor Graphics - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, see <http://www.gnu.org/licenses/>. - */ - -#include "qemu/osdep.h" -#include "cpu.h" -#include "gdbstub/syscalls.h" -#include "gdbstub/helpers.h" -#include "semihosting/syscalls.h" -#include "semihosting/uaccess.h" -#include "qemu/log.h" - -#define HOSTED_EXIT 0 -#define HOSTED_INIT_SIM 1 -#define HOSTED_OPEN 2 -#define HOSTED_CLOSE 3 -#define HOSTED_READ 4 -#define HOSTED_WRITE 5 -#define HOSTED_LSEEK 6 -#define HOSTED_RENAME 7 -#define HOSTED_UNLINK 8 -#define HOSTED_STAT 9 -#define HOSTED_FSTAT 10 -#define HOSTED_GETTIMEOFDAY 11 -#define HOSTED_ISATTY 12 -#define HOSTED_SYSTEM 13 - -static int host_to_gdb_errno(int err) -{ -#define E(X) case E##X: return GDB_E##X - switch (err) { - E(PERM); - E(NOENT); - E(INTR); - E(BADF); - E(ACCES); - E(FAULT); - E(BUSY); - E(EXIST); - E(NODEV); - E(NOTDIR); - E(ISDIR); - E(INVAL); - E(NFILE); - E(MFILE); - E(FBIG); - E(NOSPC); - E(SPIPE); - E(ROFS); - E(NAMETOOLONG); - default: - return GDB_EUNKNOWN; - } -#undef E -} - -static void nios2_semi_u32_cb(CPUState *cs, uint64_t ret, int err) -{ - CPUNios2State *env = cpu_env(cs); - target_ulong args = env->regs[R_ARG1]; - - if (put_user_u32(ret, args) || - put_user_u32(host_to_gdb_errno(err), args + 4)) { - /* - * The nios2 semihosting ABI does not provide any way to report this - * error to the guest, so the best we can do is log it in qemu. - * It is always a guest error not to pass us a valid argument block. - */ - qemu_log_mask(LOG_GUEST_ERROR, "nios2-semihosting: return value " - "discarded because argument block not writable\n"); - } -} - -static void nios2_semi_u64_cb(CPUState *cs, uint64_t ret, int err) -{ - CPUNios2State *env = cpu_env(cs); - target_ulong args = env->regs[R_ARG1]; - - if (put_user_u32(ret >> 32, args) || - put_user_u32(ret, args + 4) || - put_user_u32(host_to_gdb_errno(err), args + 8)) { - /* No way to report this via nios2 semihosting ABI; just log it */ - qemu_log_mask(LOG_GUEST_ERROR, "nios2-semihosting: return value " - "discarded because argument block not writable\n"); - } -} - -/* - * Read the input value from the argument block; fail the semihosting - * call if the memory read fails. - */ -#define GET_ARG(n) do { \ - if (get_user_ual(arg ## n, args + (n) * 4)) { \ - goto failed; \ - } \ -} while (0) - -#define GET_ARG64(n) do { \ - if (get_user_ual(arg ## n, args + (n) * 4)) { \ - goto failed64; \ - } \ -} while (0) - -void do_nios2_semihosting(CPUNios2State *env) -{ - CPUState *cs = env_cpu(env); - int nr; - uint32_t args; - target_ulong arg0, arg1, arg2, arg3; - - nr = env->regs[R_ARG0]; - args = env->regs[R_ARG1]; - switch (nr) { - case HOSTED_EXIT: - gdb_exit(env->regs[R_ARG1]); - exit(env->regs[R_ARG1]); - - case HOSTED_OPEN: - GET_ARG(0); - GET_ARG(1); - GET_ARG(2); - GET_ARG(3); - semihost_sys_open(cs, nios2_semi_u32_cb, arg0, arg1, arg2, arg3); - break; - - case HOSTED_CLOSE: - GET_ARG(0); - semihost_sys_close(cs, nios2_semi_u32_cb, arg0); - break; - - case HOSTED_READ: - GET_ARG(0); - GET_ARG(1); - GET_ARG(2); - semihost_sys_read(cs, nios2_semi_u32_cb, arg0, arg1, arg2); - break; - - case HOSTED_WRITE: - GET_ARG(0); - GET_ARG(1); - GET_ARG(2); - semihost_sys_write(cs, nios2_semi_u32_cb, arg0, arg1, arg2); - break; - - case HOSTED_LSEEK: - GET_ARG64(0); - GET_ARG64(1); - GET_ARG64(2); - GET_ARG64(3); - semihost_sys_lseek(cs, nios2_semi_u64_cb, arg0, - deposit64(arg2, 32, 32, arg1), arg3); - break; - - case HOSTED_RENAME: - GET_ARG(0); - GET_ARG(1); - GET_ARG(2); - GET_ARG(3); - semihost_sys_rename(cs, nios2_semi_u32_cb, arg0, arg1, arg2, arg3); - break; - - case HOSTED_UNLINK: - GET_ARG(0); - GET_ARG(1); - semihost_sys_remove(cs, nios2_semi_u32_cb, arg0, arg1); - break; - - case HOSTED_STAT: - GET_ARG(0); - GET_ARG(1); - GET_ARG(2); - semihost_sys_stat(cs, nios2_semi_u32_cb, arg0, arg1, arg2); - break; - - case HOSTED_FSTAT: - GET_ARG(0); - GET_ARG(1); - semihost_sys_fstat(cs, nios2_semi_u32_cb, arg0, arg1); - break; - - case HOSTED_GETTIMEOFDAY: - GET_ARG(0); - GET_ARG(1); - semihost_sys_gettimeofday(cs, nios2_semi_u32_cb, arg0, arg1); - break; - - case HOSTED_ISATTY: - GET_ARG(0); - semihost_sys_isatty(cs, nios2_semi_u32_cb, arg0); - break; - - case HOSTED_SYSTEM: - GET_ARG(0); - GET_ARG(1); - semihost_sys_system(cs, nios2_semi_u32_cb, arg0, arg1); - break; - - default: - qemu_log_mask(LOG_GUEST_ERROR, "nios2-semihosting: unsupported " - "semihosting syscall %d\n", nr); - nios2_semi_u32_cb(cs, -1, ENOSYS); - break; - - failed: - nios2_semi_u32_cb(cs, -1, EFAULT); - break; - failed64: - nios2_semi_u64_cb(cs, -1, EFAULT); - break; - } -} diff --git a/target/nios2/op_helper.c b/target/nios2/op_helper.c index 5017457c5e..7baa6dbd41 100644 --- a/target/nios2/op_helper.c +++ b/target/nios2/op_helper.c @@ -72,48 +72,3 @@ uint32_t helper_divu(CPUNios2State *env, uint32_t num, uint32_t den) } return num / den; } - -#ifndef CONFIG_USER_ONLY -void helper_eret(CPUNios2State *env, uint32_t new_status, uint32_t new_pc) -{ - Nios2CPU *cpu = env_archcpu(env); - CPUState *cs = env_cpu(env); - - if (unlikely(new_pc & 3)) { - env->ctrl[CR_BADADDR] = new_pc; - cs->exception_index = EXCP_UNALIGND; - nios2_cpu_loop_exit_advance(env, GETPC()); - } - - /* - * None of estatus, bstatus, or sstatus have constraints on write; - * do not allow reserved fields in status to be set. - * When shadow registers are enabled, eret *does* restore CRS. - * Rather than testing eic_present to decide, mask CRS out of - * the set of readonly fields. - */ - new_status &= cpu->cr_state[CR_STATUS].writable | - (cpu->cr_state[CR_STATUS].readonly & R_CR_STATUS_CRS_MASK); - - env->ctrl[CR_STATUS] = new_status; - env->pc = new_pc; - nios2_update_crs(env); - cpu_loop_exit(cs); -} - -/* - * RDPRS and WRPRS are implemented out of line so that if PRS == CRS, - * all of the tcg global temporaries are synced back to ENV. - */ -uint32_t helper_rdprs(CPUNios2State *env, uint32_t regno) -{ - unsigned prs = FIELD_EX32(env->ctrl[CR_STATUS], CR_STATUS, PRS); - return env->shadow_regs[prs][regno]; -} - -void helper_wrprs(CPUNios2State *env, uint32_t regno, uint32_t val) -{ - unsigned prs = FIELD_EX32(env->ctrl[CR_STATUS], CR_STATUS, PRS); - env->shadow_regs[prs][regno] = val; -} -#endif /* !CONFIG_USER_ONLY */ diff --git a/target/nios2/translate.c b/target/nios2/translate.c index 7ddc6ac1a2..34c3e6fc79 100644 --- a/target/nios2/translate.c +++ b/target/nios2/translate.c @@ -50,6 +50,8 @@ INSTRUCTION_FLG(gen_excp, EXCP_UNIMPL) #define INSTRUCTION_ILLEGAL() \ INSTRUCTION_FLG(gen_excp, EXCP_ILLEGAL) +#define INSTRUCTION_SUPERVISOR() \ + INSTRUCTION_FLG(gen_excp, EXCP_SUPERI) /* Special R-Type instruction opcode */ #define INSN_R_TYPE 0x3A @@ -133,14 +135,10 @@ typedef struct DisasContext { uint32_t tb_flags; TCGv sink; const ControlRegState *cr_state; - bool eic_present; } DisasContext; static TCGv cpu_R[NUM_GP_REGS]; static TCGv cpu_pc; -#ifndef CONFIG_USER_ONLY -static TCGv cpu_crs_R[NUM_GP_REGS]; -#endif typedef struct Nios2Instruction { void (*handler)(DisasContext *dc, uint32_t code, uint32_t flags); @@ -174,11 +172,7 @@ static TCGv load_gpr(DisasContext *dc, unsigned reg) if (FIELD_EX32(dc->tb_flags, TBFLAGS, CRS0)) { return cpu_R[reg]; } -#ifdef CONFIG_USER_ONLY g_assert_not_reached(); -#else - return cpu_crs_R[reg]; -#endif } static TCGv dest_gpr(DisasContext *dc, unsigned reg) @@ -198,11 +192,7 @@ static TCGv dest_gpr(DisasContext *dc, unsigned reg) if (FIELD_EX32(dc->tb_flags, TBFLAGS, CRS0)) { return cpu_R[reg]; } -#ifdef CONFIG_USER_ONLY g_assert_not_reached(); -#else - return cpu_crs_R[reg]; -#endif } static void t_gen_helper_raise_exception(DisasContext *dc, uint32_t index) @@ -301,11 +291,7 @@ static void gen_ldx(DisasContext *dc, uint32_t code, uint32_t flags) TCGv data = dest_gpr(dc, instr.b); tcg_gen_addi_tl(addr, load_gpr(dc, instr.a), instr.imm16.s); -#ifdef CONFIG_USER_ONLY flags |= MO_UNALN; -#else - flags |= MO_ALIGN; -#endif tcg_gen_qemu_ld_tl(data, addr, dc->mem_idx, flags); } @@ -317,11 +303,7 @@ static void gen_stx(DisasContext *dc, uint32_t code, uint32_t flags) TCGv addr = tcg_temp_new(); tcg_gen_addi_tl(addr, load_gpr(dc, instr.a), instr.imm16.s); -#ifdef CONFIG_USER_ONLY flags |= MO_UNALN; -#else - flags |= MO_ALIGN; -#endif tcg_gen_qemu_st_tl(val, addr, dc->mem_idx, flags); } @@ -398,27 +380,6 @@ gen_i_math_logic(andhi, andi, 0, imm_shifted) gen_i_math_logic(orhi , ori, 1, imm_shifted) gen_i_math_logic(xorhi, xori, 1, imm_shifted) -/* rB <- prs.rA + sigma(IMM16) */ -static void rdprs(DisasContext *dc, uint32_t code, uint32_t flags) -{ - if (!dc->eic_present) { - t_gen_helper_raise_exception(dc, EXCP_ILLEGAL); - return; - } - if (!gen_check_supervisor(dc)) { - return; - } - -#ifdef CONFIG_USER_ONLY - g_assert_not_reached(); -#else - I_TYPE(instr, code); - TCGv dest = dest_gpr(dc, instr.b); - gen_helper_rdprs(dest, tcg_env, tcg_constant_i32(instr.a)); - tcg_gen_addi_tl(dest, dest, instr.imm16.s); -#endif -} - /* Prototype only, defined below */ static void handle_r_type_instr(DisasContext *dc, uint32_t code, uint32_t flags); @@ -480,7 +441,7 @@ static const Nios2Instruction i_type_instructions[] = { INSTRUCTION_FLG(gen_stx, MO_TESL), /* stwio */ INSTRUCTION_FLG(gen_bxx, TCG_COND_LTU), /* bltu */ INSTRUCTION_FLG(gen_ldx, MO_TEUL), /* ldwio */ - INSTRUCTION(rdprs), /* rdprs */ + INSTRUCTION_SUPERVISOR(), /* rdprs */ INSTRUCTION_ILLEGAL(), INSTRUCTION_FLG(handle_r_type_instr, 0), /* R-Type */ INSTRUCTION_NOP(), /* flushd */ @@ -493,29 +454,6 @@ static const Nios2Instruction i_type_instructions[] = { /* * R-Type instructions */ -/* - * status <- estatus - * PC <- ea - */ -static void eret(DisasContext *dc, uint32_t code, uint32_t flags) -{ - if (!gen_check_supervisor(dc)) { - return; - } - -#ifdef CONFIG_USER_ONLY - g_assert_not_reached(); -#else - if (FIELD_EX32(dc->tb_flags, TBFLAGS, CRS0)) { - TCGv tmp = tcg_temp_new(); - tcg_gen_ld_tl(tmp, tcg_env, offsetof(CPUNios2State, ctrl[CR_ESTATUS])); - gen_helper_eret(tcg_env, tmp, load_gpr(dc, R_EA)); - } else { - gen_helper_eret(tcg_env, load_gpr(dc, R_SSTATUS), load_gpr(dc, R_EA)); - } - dc->base.is_jmp = DISAS_NORETURN; -#endif -} /* PC <- ra */ static void ret(DisasContext *dc, uint32_t code, uint32_t flags) @@ -533,15 +471,7 @@ static void bret(DisasContext *dc, uint32_t code, uint32_t flags) return; } -#ifdef CONFIG_USER_ONLY g_assert_not_reached(); -#else - TCGv tmp = tcg_temp_new(); - tcg_gen_ld_tl(tmp, tcg_env, offsetof(CPUNios2State, ctrl[CR_BSTATUS])); - gen_helper_eret(tcg_env, tmp, load_gpr(dc, R_BA)); - - dc->base.is_jmp = DISAS_NORETURN; -#endif } /* PC <- rA */ @@ -578,40 +508,7 @@ static void rdctl(DisasContext *dc, uint32_t code, uint32_t flags) return; } -#ifdef CONFIG_USER_ONLY g_assert_not_reached(); -#else - R_TYPE(instr, code); - TCGv t1, t2, dest = dest_gpr(dc, instr.c); - - /* Reserved registers read as zero. */ - if (nios2_cr_reserved(&dc->cr_state[instr.imm5])) { - tcg_gen_movi_tl(dest, 0); - return; - } - - switch (instr.imm5) { - case CR_IPENDING: - /* - * The value of the ipending register is synthetic. - * In hw, this is the AND of a set of hardware irq lines - * with the ienable register. In qemu, we re-use the space - * of CR_IPENDING to store the set of irq lines, and so we - * must perform the AND here, and anywhere else we need the - * guest value of ipending. - */ - t1 = tcg_temp_new(); - t2 = tcg_temp_new(); - tcg_gen_ld_tl(t1, tcg_env, offsetof(CPUNios2State, ctrl[CR_IPENDING])); - tcg_gen_ld_tl(t2, tcg_env, offsetof(CPUNios2State, ctrl[CR_IENABLE])); - tcg_gen_and_tl(dest, t1, t2); - break; - default: - tcg_gen_ld_tl(dest, tcg_env, - offsetof(CPUNios2State, ctrl[instr.imm5])); - break; - } -#endif } /* ctlN <- rA */ @@ -621,90 +518,7 @@ static void wrctl(DisasContext *dc, uint32_t code, uint32_t flags) return; } -#ifdef CONFIG_USER_ONLY g_assert_not_reached(); -#else - R_TYPE(instr, code); - TCGv v = load_gpr(dc, instr.a); - uint32_t ofs = offsetof(CPUNios2State, ctrl[instr.imm5]); - uint32_t wr = dc->cr_state[instr.imm5].writable; - uint32_t ro = dc->cr_state[instr.imm5].readonly; - - /* Skip reserved or readonly registers. */ - if (wr == 0) { - return; - } - - switch (instr.imm5) { - case CR_PTEADDR: - gen_helper_mmu_write_pteaddr(tcg_env, v); - break; - case CR_TLBACC: - gen_helper_mmu_write_tlbacc(tcg_env, v); - break; - case CR_TLBMISC: - gen_helper_mmu_write_tlbmisc(tcg_env, v); - break; - case CR_STATUS: - case CR_IENABLE: - /* If interrupts were enabled using WRCTL, trigger them. */ - dc->base.is_jmp = DISAS_UPDATE; - /* fall through */ - default: - if (wr == -1) { - /* The register is entirely writable. */ - tcg_gen_st_tl(v, tcg_env, ofs); - } else { - /* - * The register is partially read-only or reserved: - * merge the value. - */ - TCGv n = tcg_temp_new(); - - tcg_gen_andi_tl(n, v, wr); - - if (ro != 0) { - TCGv o = tcg_temp_new(); - tcg_gen_ld_tl(o, tcg_env, ofs); - tcg_gen_andi_tl(o, o, ro); - tcg_gen_or_tl(n, n, o); - } - - tcg_gen_st_tl(n, tcg_env, ofs); - } - break; - } -#endif -} - -/* prs.rC <- rA */ -static void wrprs(DisasContext *dc, uint32_t code, uint32_t flags) -{ - if (!dc->eic_present) { - t_gen_helper_raise_exception(dc, EXCP_ILLEGAL); - return; - } - if (!gen_check_supervisor(dc)) { - return; - } - -#ifdef CONFIG_USER_ONLY - g_assert_not_reached(); -#else - R_TYPE(instr, code); - gen_helper_wrprs(tcg_env, tcg_constant_i32(instr.c), - load_gpr(dc, instr.a)); - /* - * The expected write to PRS[r0] is 0, from CRS[r0]. - * If not, and CRS == PRS (which we cannot tell from here), - * we may now have a non-zero value in our current r0. - * By ending the TB, we re-evaluate tb_flags and find out. - */ - if (instr.c == 0 - && (instr.a != 0 || !FIELD_EX32(dc->tb_flags, TBFLAGS, R0_0))) { - dc->base.is_jmp = DISAS_UPDATE; - } -#endif } /* Comparison instructions */ @@ -802,7 +616,6 @@ static void divu(DisasContext *dc, uint32_t code, uint32_t flags) static void trap(DisasContext *dc, uint32_t code, uint32_t flags) { -#ifdef CONFIG_USER_ONLY /* * The imm5 field is not stored anywhere on real hw; the kernel * has to load the insn and extract the field. But we can make @@ -811,28 +624,17 @@ static void trap(DisasContext *dc, uint32_t code, uint32_t flags) R_TYPE(instr, code); tcg_gen_st_i32(tcg_constant_i32(instr.imm5), tcg_env, offsetof(CPUNios2State, error_code)); -#endif t_gen_helper_raise_exception(dc, EXCP_TRAP); } static void gen_break(DisasContext *dc, uint32_t code, uint32_t flags) { -#ifndef CONFIG_USER_ONLY - /* The semihosting instruction is "break 1". */ - bool is_user = FIELD_EX32(dc->tb_flags, TBFLAGS, U); - R_TYPE(instr, code); - if (semihosting_enabled(is_user) && instr.imm5 == 1) { - t_gen_helper_raise_exception(dc, EXCP_SEMIHOST); - return; - } -#endif - t_gen_helper_raise_exception(dc, EXCP_BREAK); } static const Nios2Instruction r_type_instructions[] = { INSTRUCTION_ILLEGAL(), - INSTRUCTION(eret), /* eret */ + INSTRUCTION_SUPERVISOR(), /* eret */ INSTRUCTION(roli), /* roli */ INSTRUCTION(rol), /* rol */ INSTRUCTION_NOP(), /* flushp */ @@ -851,7 +653,7 @@ static const Nios2Instruction r_type_instructions[] = { INSTRUCTION_ILLEGAL(), INSTRUCTION(slli), /* slli */ INSTRUCTION(sll), /* sll */ - INSTRUCTION(wrprs), /* wrprs */ + INSTRUCTION_ILLEGAL(), /* wrprs */ INSTRUCTION_ILLEGAL(), INSTRUCTION(or), /* or */ INSTRUCTION(mulxsu), /* mulxsu */ @@ -927,19 +729,6 @@ static const char * const gr_regnames[NUM_GP_REGS] = { "fp", "ea", "ba", "ra", }; -#ifndef CONFIG_USER_ONLY -static const char * const cr_regnames[NUM_CR_REGS] = { - "status", "estatus", "bstatus", "ienable", - "ipending", "cpuid", "res6", "exception", - "pteaddr", "tlbacc", "tlbmisc", "reserved1", - "badaddr", "config", "mpubase", "mpuacc", - "res16", "res17", "res18", "res19", - "res20", "res21", "res22", "res23", - "res24", "res25", "res26", "res27", - "res28", "res29", "res30", "res31", -}; -#endif - /* generate intermediate code for basic block 'tb'. */ static void nios2_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) { @@ -951,7 +740,6 @@ static void nios2_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) dc->mem_idx = cpu_mmu_index(cs, false); dc->cr_state = cpu->cr_state; dc->tb_flags = dc->base.tb->flags; - dc->eic_present = cpu->eic_present; /* Bound the number of insns to execute to those left on the page. */ page_insns = -(dc->base.pc_first | TARGET_PAGE_MASK) / 4; @@ -1056,44 +844,12 @@ void nios2_cpu_dump_state(CPUState *cs, FILE *f, int flags) } } -#if !defined(CONFIG_USER_ONLY) - int j; - - for (i = j = 0; i < NUM_CR_REGS; i++) { - if (!nios2_cr_reserved(&cpu->cr_state[i])) { - qemu_fprintf(f, "%9s=%8.8x ", cr_regnames[i], env->ctrl[i]); - if (++j % 4 == 0) { - qemu_fprintf(f, "\n"); - } - } - } - if (j % 4 != 0) { - qemu_fprintf(f, "\n"); - } - if (cpu->mmu_present) { - qemu_fprintf(f, " mmu write: VPN=%05X PID %02X TLBACC %08X\n", - env->mmu.pteaddr_wr & R_CR_PTEADDR_VPN_MASK, - FIELD_EX32(env->mmu.tlbmisc_wr, CR_TLBMISC, PID), - env->mmu.tlbacc_wr); - } -#endif qemu_fprintf(f, "\n\n"); } void nios2_tcg_init(void) { -#ifndef CONFIG_USER_ONLY - TCGv_ptr crs = tcg_global_mem_new_ptr(tcg_env, - offsetof(CPUNios2State, regs), "crs"); - - for (int i = 0; i < NUM_GP_REGS; i++) { - cpu_crs_R[i] = tcg_global_mem_new(crs, 4 * i, gr_regnames[i]); - } - -#define offsetof_regs0(N) offsetof(CPUNios2State, shadow_regs[0][N]) -#else #define offsetof_regs0(N) offsetof(CPUNios2State, regs[N]) -#endif for (int i = 0; i < NUM_GP_REGS; i++) { cpu_R[i] = tcg_global_mem_new(tcg_env, offsetof_regs0(i), diff --git a/tests/qtest/machine-none-test.c b/tests/qtest/machine-none-test.c index 31cc0bfb01..05da7bc72d 100644 --- a/tests/qtest/machine-none-test.c +++ b/tests/qtest/machine-none-test.c @@ -38,7 +38,6 @@ static struct arch2cpu cpus_map[] = { { "mipsel", "I7200" }, { "mips64", "20Kc" }, { "mips64el", "I6500" }, - { "nios2", "FIXME" }, { "or1k", "or1200" }, { "ppc", "604" }, { "ppc64", "power8e_v2.1" }, diff --git a/.gitlab-ci.d/buildtest.yml b/.gitlab-ci.d/buildtest.yml index cfdff175c3..5848c73e00 100644 --- a/.gitlab-ci.d/buildtest.yml +++ b/.gitlab-ci.d/buildtest.yml @@ -164,7 +164,7 @@ build-system-centos: CONFIGURE_ARGS: --disable-nettle --enable-gcrypt --enable-vfio-user-server --enable-modules --enable-trace-backends=dtrace --enable-docs TARGETS: ppc64-softmmu or1k-softmmu s390x-softmmu - x86_64-softmmu rx-softmmu sh4-softmmu nios2-softmmu + x86_64-softmmu rx-softmmu sh4-softmmu MAKE_CHECK_ARGS: check-build # Previous QEMU release. Used for cross-version migration tests. @@ -254,7 +254,7 @@ avocado-system-centos: IMAGE: centos8 MAKE_CHECK_ARGS: check-avocado AVOCADO_TAGS: arch:ppc64 arch:or1k arch:s390x arch:x86_64 arch:rx - arch:sh4 arch:nios2 + arch:sh4 build-system-opensuse: extends: diff --git a/.gitlab-ci.d/crossbuilds.yml b/.gitlab-ci.d/crossbuilds.yml index 987ba9694b..47bdb99b5b 100644 --- a/.gitlab-ci.d/crossbuilds.yml +++ b/.gitlab-ci.d/crossbuilds.yml @@ -167,7 +167,7 @@ cross-win64-system: IMAGE: fedora-win64-cross EXTRA_CONFIGURE_OPTS: --enable-fdt=internal --disable-plugins CROSS_SKIP_TARGETS: alpha-softmmu avr-softmmu hppa-softmmu - m68k-softmmu microblazeel-softmmu nios2-softmmu + m68k-softmmu microblazeel-softmmu or1k-softmmu rx-softmmu sh4eb-softmmu sparc64-softmmu tricore-softmmu xtensaeb-softmmu artifacts: diff --git a/hw/Kconfig b/hw/Kconfig index 2c00936c28..ea6a68b1a1 100644 --- a/hw/Kconfig +++ b/hw/Kconfig @@ -57,7 +57,6 @@ source loongarch/Kconfig source m68k/Kconfig source microblaze/Kconfig source mips/Kconfig -source nios2/Kconfig source openrisc/Kconfig source ppc/Kconfig source riscv/Kconfig diff --git a/hw/intc/Kconfig b/hw/intc/Kconfig index 2b5b2d2301..ad59abebaa 100644 --- a/hw/intc/Kconfig +++ b/hw/intc/Kconfig @@ -87,9 +87,6 @@ config GOLDFISH_PIC config M68K_IRQC bool -config NIOS2_VIC - bool - config LOONGARCH_IPI bool diff --git a/hw/intc/meson.build b/hw/intc/meson.build index ed355941d1..58140da5f2 100644 --- a/hw/intc/meson.build +++ b/hw/intc/meson.build @@ -68,7 +68,6 @@ specific_ss.add(when: 'CONFIG_XIVE', if_true: files('xive.c')) specific_ss.add(when: ['CONFIG_KVM', 'CONFIG_XIVE'], if_true: files('spapr_xive_kvm.c')) specific_ss.add(when: 'CONFIG_M68K_IRQC', if_true: files('m68k_irqc.c')) -specific_ss.add(when: 'CONFIG_NIOS2_VIC', if_true: files('nios2_vic.c')) specific_ss.add(when: 'CONFIG_LOONGARCH_IPI', if_true: files('loongarch_ipi.c')) specific_ss.add(when: 'CONFIG_LOONGARCH_PCH_PIC', if_true: files('loongarch_pch_pic.c')) specific_ss.add(when: 'CONFIG_LOONGARCH_PCH_MSI', if_true: files('loongarch_pch_msi.c')) diff --git a/hw/meson.build b/hw/meson.build index 463d702683..fb998aae0f 100644 --- a/hw/meson.build +++ b/hw/meson.build @@ -56,7 +56,6 @@ subdir('loongarch') subdir('m68k') subdir('microblaze') subdir('mips') -subdir('nios2') subdir('openrisc') subdir('ppc') subdir('remote') diff --git a/hw/nios2/Kconfig b/hw/nios2/Kconfig deleted file mode 100644 index 4748ae27b6..0000000000 --- a/hw/nios2/Kconfig +++ /dev/null @@ -1,13 +0,0 @@ -config NIOS2_10M50 - bool - select NIOS2 - select SERIAL - select ALTERA_TIMER - select NIOS2_VIC - -config NIOS2_GENERIC_NOMMU - bool - select NIOS2 - -config NIOS2 - bool diff --git a/hw/nios2/meson.build b/hw/nios2/meson.build deleted file mode 100644 index 22277bd6c5..0000000000 --- a/hw/nios2/meson.build +++ /dev/null @@ -1,6 +0,0 @@ -nios2_ss = ss.source_set() -nios2_ss.add(files('boot.c'), fdt) -nios2_ss.add(when: 'CONFIG_NIOS2_10M50', if_true: files('10m50_devboard.c')) -nios2_ss.add(when: 'CONFIG_NIOS2_GENERIC_NOMMU', if_true: files('generic_nommu.c')) - -hw_arch += {'nios2': nios2_ss} diff --git a/qemu-options.hx b/qemu-options.hx index 7fd1713fa8..9b084d343f 100644 --- a/qemu-options.hx +++ b/qemu-options.hx @@ -4849,10 +4849,10 @@ ERST DEF("semihosting", 0, QEMU_OPTION_semihosting, "-semihosting semihosting mode\n", QEMU_ARCH_ARM | QEMU_ARCH_M68K | QEMU_ARCH_XTENSA | - QEMU_ARCH_MIPS | QEMU_ARCH_NIOS2 | QEMU_ARCH_RISCV) + QEMU_ARCH_MIPS | QEMU_ARCH_RISCV) SRST ``-semihosting`` - Enable :ref:`Semihosting` mode (ARM, M68K, Xtensa, MIPS, Nios II, RISC-V only). + Enable :ref:`Semihosting` mode (ARM, M68K, Xtensa, MIPS, RISC-V only). .. warning:: Note that this allows guest direct access to the host filesystem, so @@ -4865,10 +4865,10 @@ DEF("semihosting-config", HAS_ARG, QEMU_OPTION_semihosting_config, "-semihosting-config [enable=on|off][,target=native|gdb|auto][,chardev=id][,userspace=on|off][,arg=str[,...]]\n" \ " semihosting configuration\n", QEMU_ARCH_ARM | QEMU_ARCH_M68K | QEMU_ARCH_XTENSA | -QEMU_ARCH_MIPS | QEMU_ARCH_NIOS2 | QEMU_ARCH_RISCV) +QEMU_ARCH_MIPS | QEMU_ARCH_RISCV) SRST ``-semihosting-config [enable=on|off][,target=native|gdb|auto][,chardev=id][,userspace=on|off][,arg=str[,...]]`` - Enable and configure :ref:`Semihosting` (ARM, M68K, Xtensa, MIPS, Nios II, RISC-V + Enable and configure :ref:`Semihosting` (ARM, M68K, Xtensa, MIPS, RISC-V only). .. warning:: diff --git a/scripts/coverity-scan/COMPONENTS.md b/scripts/coverity-scan/COMPONENTS.md index 0e62f10aad..cd1ee3d3cf 100644 --- a/scripts/coverity-scan/COMPONENTS.md +++ b/scripts/coverity-scan/COMPONENTS.md @@ -37,7 +37,7 @@ mips ~ (/qemu)?((/include)?/hw/mips/.*|/target/mips/.*) nios2 - ~ (/qemu)?((/include)?/hw/nios2/.*|/target/nios2/.*) + ~ (/qemu)?(/target/nios2/.*) openrisc ~ (/qemu)?((/include)?/hw/openrisc/.*|/target/openrisc/.*) diff --git a/target/nios2/meson.build b/target/nios2/meson.build index 12d8abf0bd..9b89bd4725 100644 --- a/target/nios2/meson.build +++ b/target/nios2/meson.build @@ -5,13 +5,4 @@ nios2_ss.add(files( 'translate.c', )) -nios2_system_ss = ss.source_set() -nios2_system_ss.add(files( - 'helper.c', - 'monitor.c', - 'mmu.c', - 'nios2-semi.c', -)) - target_arch += {'nios2': nios2_ss} -target_system_arch += {'nios2': nios2_system_ss} diff --git a/tests/avocado/boot_linux_console.py b/tests/avocado/boot_linux_console.py index 989b65111c..180ac17326 100644 --- a/tests/avocado/boot_linux_console.py +++ b/tests/avocado/boot_linux_console.py @@ -1426,14 +1426,6 @@ def test_or1k_sim(self): tar_hash = '20334cdaf386108c530ff0badaecc955693027dd' self.do_test_advcal_2018('20', tar_hash, 'vmlinux') - def test_nios2_10m50(self): - """ - :avocado: tags=arch:nios2 - :avocado: tags=machine:10m50-ghrd - """ - tar_hash = 'e4251141726c412ac0407c5a6bceefbbff018918' - self.do_test_advcal_2018('14', tar_hash, 'vmlinux.elf') - def test_ppc64_e500(self): """ :avocado: tags=arch:ppc64 diff --git a/tests/avocado/replay_kernel.py b/tests/avocado/replay_kernel.py index 10d99403a4..2c81412dba 100644 --- a/tests/avocado/replay_kernel.py +++ b/tests/avocado/replay_kernel.py @@ -382,17 +382,6 @@ def test_or1k_sim(self): file_path = self.fetch_asset(tar_url, asset_hash=tar_hash) self.do_test_advcal_2018(file_path, 'vmlinux') - def test_nios2_10m50(self): - """ - :avocado: tags=arch:nios2 - :avocado: tags=machine:10m50-ghrd - """ - tar_hash = 'e4251141726c412ac0407c5a6bceefbbff018918' - tar_url = ('https://qemu-advcal.gitlab.io' - '/qac-best-of-multiarch/download/day14.tar.xz') - file_path = self.fetch_asset(tar_url, asset_hash=tar_hash) - self.do_test_advcal_2018(file_path, 'vmlinux.elf') - def test_ppc_g3beige(self): """ :avocado: tags=arch:ppc diff --git a/tests/tcg/nios2/Makefile.softmmu-target b/tests/tcg/nios2/Makefile.softmmu-target deleted file mode 100644 index bc7fd55060..0000000000 --- a/tests/tcg/nios2/Makefile.softmmu-target +++ /dev/null @@ -1,32 +0,0 @@ -# -# Nios2 system tests -# -# Copyright Linaro Ltd 2022 -# SPDX-License-Identifier: GPL-2.0-or-later -# - -NIOS2_SYSTEM_SRC = $(SRC_PATH)/tests/tcg/nios2 -VPATH += $(NIOS2_SYSTEM_SRC) - -# These objects provide the basic boot code and helper functions for all tests -CRT_OBJS = boot.o intr.o $(MINILIB_OBJS) -LINK_SCRIPT = $(NIOS2_SYSTEM_SRC)/10m50-ghrd.ld - -CFLAGS += -nostdlib -g -O0 $(MINILIB_INC) -LDFLAGS += -Wl,-T$(LINK_SCRIPT) -static -nostdlib $(CRT_OBJS) -lgcc - -%.o: %.S - $(call quiet-command, $(CC) $(CFLAGS) $(EXTRA_CFLAGS) -x assembler-with-cpp -c $< -o $@, AS, $@) - -%.o: %.c - $(call quiet-command, $(CC) $(CFLAGS) $(EXTRA_CFLAGS) -c $< -o $@, CC, $@) - -# Build and link the tests -%: %.o $(LINK_SCRIPT) $(CRT_OBJS) - $(call quiet-command, $(CC) $(CFLAGS) $(EXTRA_CFLAGS) $< -o $@ $(LDFLAGS), LD, $@) - -QEMU_OPTS = -M 10m50-ghrd,vic=on -semihosting-config enable=on,target=native,chardev=output -kernel - -memory: CFLAGS+=-DCHECK_UNALIGNED=0 -TESTS += $(MULTIARCH_TESTS) -TESTS += test-shadow-1 diff --git a/tests/tcg/nios2/test-shadow-1.S b/tests/tcg/nios2/test-shadow-1.S deleted file mode 100644 index 79ef69db12..0000000000 --- a/tests/tcg/nios2/test-shadow-1.S +++ /dev/null @@ -1,40 +0,0 @@ -/* - * Regression test for TCG indirect global lowering. - * - * Copyright Linaro Ltd 2022 - * SPDX-License-Identifier: GPL-2.0-or-later - */ - -#include "semicall.h" - - .text - .set noat - .align 2 - .globl main - .type main, @function - -main: - /* Initialize r0 in shadow register set 1. */ - movhi at, 1 /* PRS=1, CRS=0, RSIE=0, PIE=0 */ - wrctl status, at - wrprs zero, zero - - /* Change current register set to 1. */ - movi at, 1 << 10 /* PRS=0, CRS=1, RSIE=0, PIE=0 */ - wrctl estatus, at - movia ea, 1f - eret - - /* Load address for callr, then end TB. */ -1: movia at, 3f - br 2f - - /* Test case! TCG abort on indirect lowering across brcond. */ -2: callr at - - /* exit(0) */ -3: movi r4, HOSTED_EXIT - movi r5, 0 - semihosting_call - - .size main, . - main -- 2.41.0

2 5

[PATCH for 10.2.0 0/3] Fix spurious error from PCI VPD parsing
by Peter Krempa 27 Mar '24

27 Mar '24

Multiple people complained, let's fix it for the next release. Peter Krempa (3): virpcivpd: Revert error reporting from PCI VPD parser pci: Remove error reporting from PCI VPD parsing NEWS: Mention fix for PCI VPD error reporting NEWS.rst | 11 ++++++++ po/POTFILES | 1 - src/conf/node_device_conf.c | 13 ++++------ src/libvirt_private.syms | 1 - src/util/virpci.c | 35 ++++++-------------------- src/util/virpci.h | 1 - src/util/virpcivpd.c | 50 +++++++++++++++---------------------- 7 files changed, 43 insertions(+), 69 deletions(-) -- 2.44.0

2 5

[PATCH-for-9.0] hw/i386/pc: Deprecate 64-bit CPUs on ISA-only PC machine
by Philippe Mathieu-Daudé 27 Mar '24

27 Mar '24

Per Daniel suggestion [*]: > isapc could arguably be restricted to just 32-bit CPU models, > because we should not need it to support any feature that didn't > exist prior to circa 1995. eg refuse to start with isapc, if 'lm' > is present in the CPU model for example. [*] https://lore.kernel.org/qemu-devel/ZgQkS4RPmSt5Xa08@redhat.com/ Suggested-by: Daniel P. Berrangé <berrange(a)redhat.com> Signed-off-by: Philippe Mathieu-Daudé <philmd(a)linaro.org> --- docs/about/deprecated.rst | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/docs/about/deprecated.rst b/docs/about/deprecated.rst index 7b548519b5..345c35507f 100644 --- a/docs/about/deprecated.rst +++ b/docs/about/deprecated.rst @@ -208,6 +208,13 @@ is no longer packaged in any distro making it harder to run the ``check-tcg`` tests. Unless we can improve the testing situation there is a chance the code will bitrot without anyone noticing. +64-bit (x86_64) CPUs on the ``isapc`` machine (since 9.0) +''''''''''''''''''''''''''''''''''''''''''''''''''''''''' + +The ``isapc`` machine aims to emulate old PC machine without PCI was +generalized, so hardware available around 1995, before 64-bit intel +CPUs were produced. + System emulator machines ------------------------ -- 2.41.0

2 1

[libvirt PATCH 0/2] correctly update metadata when deleting external snapshot
by Pavel Hrdina 27 Mar '24

27 Mar '24

Pavel Hrdina (2): qemu_snapshot: call qemuSnapshotDeleteUpdateDisks only for external snapshots qemu_snapshot: correctly update metadata when deleting external snapshot with multiple branches src/qemu/qemu_snapshot.c | 52 ++++++++++++++++++++++++---------------- 1 file changed, 31 insertions(+), 21 deletions(-) -- 2.43.2

2 4

[PATCH-for-9.1 00/18] hw/i386: Remove deprecated pc-i440fx-2.0 -> 2.3 machines
by Philippe Mathieu-Daudé 27 Mar '24

27 Mar '24

Kill legacy code, because we need to evolve. I ended there via dynamic machine -> ICH9 -> legacy ACPI... Based-on: <20240301185936.95175-1-philmd(a)linaro.org> "hw/i386/pc: Trivial cleanups" Philippe Mathieu-Daudé (18): hw/i386/pc: Remove deprecated pc-i440fx-2.0 machine hw/usb/hcd-xhci: Enumerate xhci_flags setting values hw/usb/hcd-xhci: Remove XHCI_FLAG_FORCE_PCIE_ENDCAP flag hw/usb/hcd-xhci: Remove XHCI_FLAG_SS_FIRST flag hw/i386/acpi: Remove PCMachineClass::legacy_acpi_table_size hw/i386/pc: Remove deprecated pc-i440fx-2.1 machine target/i386/kvm: Remove x86_cpu_change_kvm_default() and 'kvm-cpu.h' hw/i386/pc: Remove PCMachineClass::smbios_uuid_encoded hw/i386/pc: Remove PCMachineClass::enforce_aligned_dimm hw/mem/pc-dimm: Remove legacy_align argument from pc_dimm_pre_plug() hw/mem/memory-device: Remove legacy_align from memory_device_pre_plug() hw/i386/pc: Remove deprecated pc-i440fx-2.2 machine hw/i386/pc: Remove PCMachineClass::resizable_acpi_blob hw/i386/pc: Remove PCMachineClass::rsdp_in_ram hw/i386/acpi: Remove AcpiBuildState::rsdp field hw/i386/pc: Remove deprecated pc-i440fx-2.3 machine target/i386: Remove X86CPU::kvm_no_smi_migration field hw/i386/pc: Replace PCMachineClass::acpi_data_size by PC_ACPI_DATA_SIZE docs/about/deprecated.rst | 7 --- docs/about/removed-features.rst | 2 +- hw/usb/hcd-xhci.h | 4 +- include/hw/i386/pc.h | 22 ------- include/hw/mem/memory-device.h | 2 +- include/hw/mem/pc-dimm.h | 3 +- target/i386/cpu.h | 3 - target/i386/kvm/kvm-cpu.h | 41 ------------ hw/arm/virt.c | 2 +- hw/i386/acpi-build.c | 94 +++------------------------- hw/i386/fw_cfg.c | 2 +- hw/i386/pc.c | 107 +++++--------------------------- hw/i386/pc_piix.c | 101 ------------------------------ hw/loongarch/virt.c | 2 +- hw/mem/memory-device.c | 12 ++-- hw/mem/pc-dimm.c | 6 +- hw/ppc/spapr.c | 2 +- hw/usb/hcd-xhci-nec.c | 4 -- hw/usb/hcd-xhci-pci.c | 4 +- hw/usb/hcd-xhci.c | 42 +++---------- hw/virtio/virtio-md-pci.c | 2 +- target/i386/cpu.c | 2 - target/i386/kvm/kvm-cpu.c | 3 +- target/i386/kvm/kvm.c | 6 -- 24 files changed, 48 insertions(+), 427 deletions(-) delete mode 100644 target/i386/kvm/kvm-cpu.h -- 2.41.0

3 39

[RFC] virsysinfo: Try reading DMI table
by brett.holman＠canonical.com 26 Mar '24

26 Mar '24

This patch intends to add DMI support to libvirt for RISC-V and mips. This change is based on commit ec6ce6363, which added ARM support. This is not tested on the target arches, as I've been unable to find hardware to test this on. src/util/virsysinfo.c | 2 ++ 1 file changed, 2 insertions(+) Cheers, Brett Holman PS: This is my first post on this mailing list. I believe that I've followed the documented steps, but if I've missed anything please let me know.

2 5