Sync from SUSE:SLFO:Main libfabric revision 67e5139e591a93578d7a52a7bbb53b4a

_service

@@ -1,5 +1,5 @@
 <services>
-  <service name="tar_scm" mode="disabled">
+  <service name="tar_scm" mode="manual">
     <param name="scm">git</param>
     <param name="url">https://github.com/ofiwg/libfabric.git</param>
     <param name="package-meta">no</param>
@@ -8,9 +8,9 @@
     <param name="versionformat">@PARENT_TAG@.@TAG_OFFSET@.%h</param>
     <param name="versionrewrite-pattern">v(.*)</param>
     <param name="versionrewrite-replacement">\1</param>
-    <param name="revision">153261eadc7b318d69369cdad2a21f7189f3d8ab</param>
+    <param name="revision">159219639b7fd69d140892120121bbb4d694e295</param>
   </service>
-  <service name="recompress" mode="disabled">
+  <service name="recompress" mode="manual">
     <param name="file">libfabric*.tar</param>
     <param name="compression">bz2</param>
   </service>

fabtests.spec

@@ -1,7 +1,7 @@
 #
 # spec file for package fabtests
 #
-# Copyright (c) 2023 SUSE LLC
+# Copyright (c) 2024 SUSE LLC
 #
 # All modifications and additions to the file contributed by third parties
 # remain the property of their copyright owners, unless otherwise agreed
@@ -16,10 +16,10 @@
 #
 
 
-%define git_ver .0.153261eadc7b
+%define git_ver .0.159219639b7f
 
 Name:           fabtests
-Version:        1.20.0
+Version:        1.22.0
 Release:        0
 Summary:        Test suite for libfabric API
 License:        BSD-2-Clause OR GPL-2.0-only
@@ -38,8 +38,7 @@ BuildRoot:      %{_tmppath}/%{name}-%{version}-build
 Fabtests provides a set of examples that uses libfabric, a fabric software library.
 
 %prep
-%setup -q -n  libfabric-%{version}%{git_ver}
+%autosetup -p1 -n  libfabric-%{version}%{git_ver}
-%patch0 -p1
 
 %build
 cd fabtests

libfabric.changes

@@ -1,3 +1,362 @@
+-------------------------------------------------------------------
+Mon Aug  5 11:20:55 UTC 2024 - Filip Kastl <filip.kastl@suse.com>
+
+- Add -Wno-incompatible-pointer-types to CFLAGS to enable building
+  for 32bit with GCC 14.
+
+-------------------------------------------------------------------
+Sun Aug  4 16:17:16 UTC 2024 - Nicolas Morey <nicolas.morey@suse.com>
+
+- Update to 1.22.0
+  - Coll
+    - Fix Coverity issues
+  - Core
+    - General bug fixes
+    - hmem: change neuron get_dmabuf_fd error code
+    - Fix an error in the error handling path of fi_param_define()
+    - Makefile.am: Add Windows build files to distribution tarball
+    - hmem: disable ZE IPC
+    - Add profile variables for connections and memory allocated
+    - hmem: Fix `cuDeviceCanAccessPeer()` error reporting
+    - man: Update text for `len` parameter
+    - Add page size MR attr field
+    - man: Extend fi_mr_refresh support
+    - man: Improve FI_MR_ALLOCATED documentation
+    - man: Support optional MR desc
+    - man: Improve FI_MR_HMEM documentation
+    - Added ofi_get_realtime interfaces
+    - Add endpoint options for max message size and inject size
+    - Add Windows definition for `EREMOTEIO`
+  - EFA
+    - General improvement and bug fixes
+    - Handle recv cancel for zero copy recv
+    - Avoid iterating EP list in CQ read
+    - Add RDMA core errno for remote unknown peer
+    - Map EFA errnos to Libfabric codes
+    - Improve the zero-copy receive feature
+    - Improve the handshake enforcement procedure
+    - Support unsolicited rdma-write recv
+    - Support FI_MORE for eager send and rdma-write
+    - Improve the EFA_IO_COMP error code and explanation
+    - Improve the unit test for LL128 protocol
+    - Distinguish max RMA size from msg size
+  - Hooks
+    - dmabuf: Fix incompatible pointer warning
+  - OPX
+    - Add missing file needed for fabric direct build to release package
+    - Fix performance issue caused by not setting ACK bit in the single
+      SDMA packet case
+    - TID cache debug improvements
+    - Detection of driver lack of support for TID
+    - Multi-CTS support for TID
+    - Removal of statement that TID is not supported
+    - OPX Tracer improvements
+    - Improvements to OPX shared memory cleanup
+    - H to H performance improvements for build that supports HMEM
+    - Bug fix for a threshold check
+    - Bug fix for FI_SELECTIVE_COMPLETION
+    - CN5000 fixes
+    - Parameterization of various thresholds
+    - Further enhancements to support NVIDIA GPUs, included CUDA-allocated
+      bounce buffers and in-provider support for GDRCopy
+    - Enhancements to enable support for CN5000 hardware
+    - Better checking for TID support
+    - General TID enhancements
+    - Pkey error handling
+    - Send work queue splitting
+    - Support for OPX tracer for profiling purposes
+    - Coverity scan fixes
+    - Fixes and enhancements to logging and debug messages
+    - Intranode RMA read fixes
+    - Fix compile issues
+    - Fix shared memory segment index creation bug
+  - PSM3
+    - Update provider to sync with IEFS 11.7.0.0.110
+    - Improved auto-tuning features for PSM3, including dynamic Credit Flows
+  and detecting the presence of the rv kernel module
+    - Improved PSM3 intra-node performance for large message sizes
+  - SHM
+    - Added support for write() method to submit DSA work
+    - Touch all buffer pages after DSA page fault
+    - Add return and more descriptive error message
+    - Fix coverity about incorrect sign
+    - Fix memory leaks for srx
+    - Fix atomic read
+  - Sockets
+    - Fix Coverity issues
+  - USNIC
+    - Fix a few Coverity issues
+  - Util
+    - Discard outstanding operations in util_srx_close
+    - Enable profile on the size of bufpool allocated.
+    - Add more predefined profile variables.
+    - Fix issue while displaying addresses with fi_info -a <addr_format>
+    - fi_pingpong: Fix out of scope memory leak
+    - Add source address to fi_pingpong
+  - Verbs
+    - Flush CQ for SQ on no SQ credit
+    - Optimize search for device max inline size
+    - Enable profiling
+  - Fabtests
+    - pytest/shm: reduce the msg size in test_unexpected_msg
+    - Fix synapseai fabtests build
+    - Add pytests for EFA zero-copy receive
+    - Add benchmark option for `FI_OPT_MAX_MSG_SIZE`
+    - benchmarks: Add synapseai support
+    - Disable fi_rdm_tagged_peek test for ucx and psm3
+    - Add manual init sync to fi_rdm_multiclient and fi_rdm
+    - Refactor ft_sock_sync to take in a socket
+    - Add fi_rdm_bw test
+    - Skip rma_pingpong write tests
+    - Init rx_buf before sending data
+    - Add rma_pingpong tests to makefile
+    - pytest: use different message sizes for rma pingpong
+    - Fix missing fixture memory_type in test_rma_pingpong_range_no_inject
+    - pytest: account for process startup overhead in client-server tests
+    - pytest: save client process output to a file
+    - Support testing inject with cq data
+    - multinode: update arguments
+    - multi_ep: Fix memory leak
+    - rdm_tagged_peek: Align rx's msg_order with tx's
+    - Add backlog > 0 to listen call
+
+-------------------------------------------------------------------
+Wed Apr  3 11:32:43 UTC 2024 - Nicolas Morey <nicolas.morey@suse.com>
+
+- Enable ucx and new efa provider on 64b architectures.
+- Use a single changes file for libfabric and fabtests.
+- Update to 1.21.0
+  - Core
+    - Various update and fixed in man pages
+    - Fix xpmem memory corruption
+    - Extend FI_PROVIDER_PATH to allow setting preferred DL provider
+    - Add a SECURITY.md file
+    - Document preferred threading model for scalable endpoints
+    - Move FI_PRIORITY to internal flag
+    - Remove FI_PROV_SPECIFIC
+    - Remove unimplemented or unused features
+    - Support cntr byte counting
+    - configure: Do not check for xpmem if disabled
+    - Add FI_PROGRESS_CONTROL_UNIFIED
+    - hmem/cuda: Get multiple attributes at once in cuda_is_addr_valid
+    - configure: Add -pipe by default to CFLAGS
+    - Selectively generate warnings on failed loading of DL providers
+    - hmem: introduce ofi_dev_reg_copy_*_iov ops
+    - Print provider path on fabric creation
+    - Introduce FI_OPT_SHARED_MEMORY_PERMITTED
+    - README.md: Add badge for openssf scorecard
+    - man: Regulate the fi_setopt call sequence.
+    - man: Clarify the usage of FI_RMOTE_CQ_DATA flag
+    - man: Add ucx provider to the fi_provider man page
+    - configure.ac: add extra check for 128 bit atomic support
+    - include/osd: align atomic complex definitions
+    - hmem/synapseai: Refine the error handling and warning
+    - Specify C11 standard for Visual Studio builds
+    - configure: Do not check for xpmem if disabled
+    - man page fixes
+  - EFA
+    - General improvement and bug fixes
+    - Propagate errnos from core functions untouched
+    - Create 1:1 relationship between libfabric CQs and IBV CQs
+    - Do not progress ep inside transmission call when hitting EAGAIN
+    - Remove unnecessary check in rdma write.
+    - Handle rx pkts error without ope
+    - Add a new rx pkt counter
+    - Enable runting for neuron with a different runt size
+    - Distinguish unresponsive receiver errors
+    - Remove unnecessary handshake in send path
+    - Don't fail the whole domain init if cudamalloc failed
+    - Introduce efa specific domain operations
+    - Implement FI_OPT_SHARED_MEMORY_PERMITTED
+    - Do not memset rxe to 0 on init
+    - Reduce # of error cases in happy path
+    - Add FI_EFA_USE_HUGE_PAGE to efa man page.
+    - Don't do handshake for local fi_write
+    - Add pingpong test after exhausting MRs
+    - Introduce utilities to exhaust MRs on EFA device
+    - Test EFA with a 1GiB message
+    - Do not abort on all deprecated env vars
+    - Onboard fi_mr_dmabuf API in mem reg ops.
+    - Try registering cuda memory via dmabuf when checking p2p
+    - Introduce HAVE_EFA_DMABUF_MR macro in configure
+    - Use long CTS protocol if long read and runting read protocols fail
+      because of memory registration limits
+    - Remove unnecessary check in rdma write.
+    - Enable runting for neuron with a different runt size
+    - Handle rx pkts error without ope
+    - Distinguish unresponsive receiver errors
+    - Add `efa_show_help()`
+    - Refactor error code definitions
+    - Remove error message assertions from CQ unit tests
+    - Refactor `efa_strerror()`
+    - Doxyfile: Configure tabs to 8 spaces
+    - Rename Doxyfile
+  - Hooks
+    - dmabuf_peer_mem: initialize fd to supress compiler warning
+  - NETDIR
+    -Removed. The functionality is intergrated into the verbs provider.
+  - OPX
+    - Fix compiler warnings and coverity issues
+    - General improvement and bug fixes
+    - Add GPU support to expected TID
+    - RZV RTS packet exclude empty immediate data
+    - Add more efficient check for cuda-resident user buffer
+    - Improve default HFI selection logic in multi rail environments
+    - Flush dead list opportunistically
+    - Add RISC-V support
+    - Make update HDRQ register frequency configurable at build time
+    - Removed all references to the reliability nack threshold env var
+    - Added missing tuneables, rearraged to match fi_info -e output
+    - Use BAR load/store macros
+    - Check HFI driver version to allow GPU-enabled build/run
+    - Added kernel and driver version check to allow/disallow expected receive TID
+    - Fix max SHM connections to allow up to 16 HFIs
+    - Use FI_HMEM_SYSTEM for Cuda-Managed (Unified) memory
+    - Handle FI_OPT_CUDA_API_PERMITTED
+    - Use contiguous send when only one iov present
+    - Always replay TID packets over SDMA
+    - Add Virtual Lane and Partition pkey (FI_OPX_SL and FI_OPX_PKEY)
+    - Forced AV type to be AV Map when requested AV is unsupported
+    - Reduce size of opx_shm_tx
+    - Add GPU support for RMA Atomic operations
+    - Add GPU support for RMA reads and writes
+    - Add HMEM debug counters
+    - Print debug counters upon receiving SIGUSR1
+    - Fix multi-receive to work with contiguous rzv payload
+    - Initial support for GPU / FI_HMEM
+    - Limit multipacket eager implementation to tagged sends
+    - Read, verify and store some hfi chip attributes
+  - PSM3
+    - Update provider to sync with IEFS 11.6.0.0.231
+    - Fix some conditional build errors
+  - RSTREAM
+    - Removed.
+  - RXM
+    - Add option to auto detect hmem iface of user buffers
+  - SHM
+    - Manually align 8 byte fields in memory region
+    - Close device_fds for connected peers when the EP is closed
+    - Print shm name and error code when failed to open
+    - Mark send as completed when a message is discarded
+    - Don't close dmabuf-fd when a request is done
+    - Revert the smr_region fields adjustment
+    - Fix various coverity issues
+    - Add ep to cq ep list once in cq bind
+    - Add ofi_buf_alloc error handling
+    - Revert the smr_region fields adjustment
+    - Don't close dmabuf-fd when a request is done
+    - Mark send as completed when a message is discarded
+    - Print shm name and error code when failed to open
+    - Close device_fds for connected peers when the EP is closed
+  - SOCKETS
+    - fix compiler warnings and coverity issues
+  - UCX
+    - Fix incorrect enum value in FI_DBG() and FI_WARN()
+  - USNIC
+    - Turn off compiler warnings of possible string truncation
+  - Util
+    - Make ep_list_lock noop for FI_PROGRESS_CONTROL_UNIFIED
+    - Save control progress model to util_domain
+    - Set import monitor state to idle upon close
+    - Add name field to memory monitors
+    - memhooks: Fix a bug when calculating mprotect region
+    - Modify domain_attr based on FI_AV_AUTH_KEY
+  - Verbs
+    - Non-blocking EP creation
+    - Address cm_id resource leak in rdma_reject path
+    - Redirected error handle logic for dmabuf failure in verbs
+    - Added rocr dmabuf support under verbs
+    - Windows: Check error code from GetPrivateData
+    - Add missing lock to protect SRX
+    - Fix compiler warnings about out of boundary access
+  - Fabtests
+    - Fix various coverity issues
+    - General improvement and bug fixes
+    - Add multi_ep test
+    - Serialize the run of fi_cq_test
+    - Utilize `junitparser` module directly
+    - Add progress models to SHM/EFA fabtests
+    - Add option to change progress model
+    - efa/rnr_cq_read_err: poll cq when hitting EAGAIN
+    - Allow testing multi_ep with shared/non-shared cq and av
+    - Print warning for HMEM iface init failure
+    - efa: Add small tx_rx size test
+    - pytest: Make ssh connection error pattern less stringent
+    - Add new exclude file for io_uring tests
+    - Add rma_pingpong benchmark
+    - efa: Make 1G tests run faster
+    - pytests: add command line argument for dmabuf reg
+    - Bump Libfabric API version.
+    - Add option to support dmabuf MR
+    - Add dmabuf ops for cuda.
+    - Replace strtok with strtok_r
+    - Add new exclude file for io_uring tests
+
+-------------------------------------------------------------------
+Mon Mar 25 07:45:03 UTC 2024 - Nicolas Morey <nicolas.morey@suse.com>
+
+- Update to 1.20.1
+  - Core
+    - hmem/ze: Change the library name passed to dlopen
+    - hmem/ze: map device id to physical device
+    - hmem/ze: skip duplicate initialization
+    - hmem/ze: dynamically allocate device resources based on number of devices
+    - hmem/ze: fix hmem_ze_copy_engine variable look up
+    - hmem/ze: Increase ZE_MAX_DEVICES to 32
+    - man: Fix typo in fi_getinfo man page
+    - Fix compiler warning when compiling with ICX
+    - man: Fix fi_rxm.7 and fi_collective.3 man pages
+    - man: Update EFA docs for FI_EFA_INTER_MIN_READ_WRITE_SIZE
+  - EFA
+    - efa_rdm_ep_record_tx_op_submitted() rm peer lookup
+    - Remove peer lookup from efa_rdm_pke_sendv()
+    - Make handshake response use txe
+    - test: Only close SHM if SHM peer is Created
+    - Handshake code allocs txe via efa util
+    - Initialize txe.rma_iov_count to 0
+    - Switch fi_addr to efa_rdm_peer in trigger_handshake
+    - Downgrade EFA Endpoint Creation WARN to INFO
+    - Init srx_ctx before use
+    - Clean up generic_send path
+    - Pass in efa_rdm_ep to efa_rdm_msg_generic_recv()
+    - Make recv path slightly more efficient
+    - re-org rma write to avoid duplicate checks
+    - Add missing sync_memops call to writedata
+    - use peer pointer from txe in read, write and send
+    - Pass in peer pointer to txe
+    - Get rid of noop instruction from empty #define
+    - Remove noop memset
+    - Fix the ibv cq error handling.
+    - Don't do handshake for local read
+    - Fix a typo in configure.m4
+    - Make runt_size aligned
+  - OPX
+    - Initialize cq error data size
+  - RXM
+    - Fix data error with FI_OFI_RXM_USE_RNDV_WRITE=1
+  - SHM
+    - Fix coverity issue about resource leak
+    - Adjust the order of smr_region fields.
+    - Allocate peer device fds dynamically
+  - Util
+    - Fix coverity issue about missing lock
+    - Implement timeout in util_wait_yield_run()
+    - Fix bug in util_cq startup error case
+    - util_mem_hooks: add missing parantheses
+  - Verbs
+    - Windows: Resolve regression in user data retrieval
+  - Fabtests
+    - efa: Close ibv device after use
+    - efa: Get device MR limit from ibv_query_device
+    - efa: Add simple unexpected test to MR exhaustion test
+    - pytest: add a new ssh connection error pattern
+
+-------------------------------------------------------------------
+Thu Feb 29 16:18:32 UTC 2024 - pgajdos@suse.com
+
+- Use %autosetup macro. Allows to eliminate the usage of deprecated
+  %patchN
+
 -------------------------------------------------------------------
 Sun Nov 19 17:27:58 UTC 2023 - Nicolas Morey <nicolas.morey@suse.com>
 

libfabric.spec

@@ -1,7 +1,7 @@
 #
 # spec file for package libfabric
 #
-# Copyright (c) 2023 SUSE LLC
+# Copyright (c) 2024 SUSE LLC
 #
 # All modifications and additions to the file contributed by third parties
 # remain the property of their copyright owners, unless otherwise agreed
@@ -17,10 +17,17 @@
 
 
 #
-%define git_ver .0.153261eadc7b
+%define git_ver .0.159219639b7f
+
+%ifarch aarch64 %power64 x86_64 s390x
+%if 0%{?suse_version} > 1530
+%define with_ucx 1
+%endif
+%define with_efa 1
+%endif
 
 Name:           libfabric
-Version:        1.20.0
+Version:        1.22.0
 Release:        0
 Summary:        User-space RDMA Fabric Interfaces
 License:        BSD-2-Clause OR GPL-2.0-only
@@ -40,6 +47,13 @@ BuildRequires:  libpsm2-devel
 BuildRequires:  fdupes
 BuildRequires:  librdmacm-devel
 BuildRequires:  libtool
+%if 0%{?with_ucx}
+BuildRequires:  libucm-devel
+BuildRequires:  libucp-devel
+ # 1.10 Needed for UCS_MEMORY_TYPE_UNKNOWN
+BuildRequires:  libucs-devel >= 1.10
+BuildRequires:  libuct-devel
+%endif
 BuildRequires:  pkg-config
 %define lib_major 1
 
@@ -65,15 +79,21 @@ libfabric provides a user-space API to access high-performance fabric
 services, such as RDMA. This package contains the development files.
 
 %prep
-%setup -q -n  %{name}-%{version}%{git_ver}
+%autosetup -p1 -n  %{name}-%{version}%{git_ver}
-%patch0 -p1
 
 %build
+export CFLAGS=-Wno-incompatible-pointer-types
 rm -f config/libtool.m4
 autoreconf -fi
 # defaults: with-dlopen and without-valgrind can be over-rode:
 %configure %{?_without_dlopen} %{?_with_valgrind} \
 	--enable-sockets --enable-verbs --enable-usnic \
+%if 0%{?with_efa}
+        --enable-efa \
+%endif
+%if 0%{?with_ucx}
+        --enable-ucx \
+%endif
 %ifarch x86_64
     --enable-psm2 \
     --enable-psm3 \
@@ -129,6 +149,9 @@ rm -f %{buildroot}%{_libdir}/*.la
 %ifarch x86_64
 %{_includedir}/rdma/fi_ext_psm2.h
 %endif
+%if 0%{?with_efa}
+%{_includedir}/rdma/fi_ext_efa.h
+%endif
 %{_mandir}/man3/*
 %{_mandir}/man7/*
 

pre_checkin.sh

@@ -1,9 +1,8 @@
 #!/bin/bash
 # This script has to be run prior to a check-in if changes were done
 # to spec and/or changes
-cp libfabric.changes fabtests.changes
 GIT_VER=$(grep "%define git_ver" libfabric.spec)
 VERSION=$(egrep "^Version:" libfabric.spec)
 sed -i -e 's/^%define git_ver.*$/'"$GIT_VER/"  -e 's/^Version:.*$/'"$VERSION/" fabtests.spec
-osc service localrun format_spec_file
+osc service run format_spec_file