[Pkg-ofed-commits] [libibverbs] 01/05: New upstream version 1.2.1
Ana Beatriz Guerrero López
ana at moszumanska.debian.org
Tue Sep 6 20:58:58 UTC 2016
This is an automated email from the git hooks/post-receive script.
ana pushed a commit to branch master
in repository libibverbs.
commit 18daf561bfea86fc183d0bc67a83fc218c4a43f5
Author: Ana Beatriz Guerrero Lopez <ana at debian.org>
Date: Tue Sep 6 22:34:45 2016 +0200
New upstream version 1.2.1
---
Makefile.am | 14 +-
Makefile.in | 14 +-
aclocal.m4 | 211 +++++++++++++++---------
configure | 20 +--
configure.ac | 2 +-
examples/asyncwatch.c | 54 ++++++-
examples/devinfo.c | 106 ++++++++++++
examples/pingpong.c | 10 --
examples/pingpong.h | 1 -
examples/rc_pingpong.c | 278 ++++++++++++++++++++++++--------
examples/xsrq_pingpong.c | 72 +++++++--
include/infiniband/arch.h | 15 +-
include/infiniband/driver.h | 29 ++++
include/infiniband/kern-abi.h | 123 ++++++++++++--
include/infiniband/verbs.h | 367 ++++++++++++++++++++++++++++++++++++++++--
libibverbs.spec | 9 +-
libibverbs.spec.in | 5 +-
man/ibv_alloc_mw.3 | 54 +++++++
man/ibv_asyncwatch.1 | 14 ++
man/ibv_bind_mw.3 | 92 +++++++++++
man/ibv_create_cq_ex.3 | 149 +++++++++++++++++
man/ibv_create_flow.3 | 174 ++++++++++++++++++++
man/ibv_inc_rkey.3 | 32 ++++
man/ibv_post_send.3 | 51 +++++-
man/ibv_query_device_ex.3 | 7 +-
man/ibv_query_rt_values_ex.3 | 50 ++++++
man/ibv_rereg_mr.3 | 76 +++++++++
man/ibv_xsrq_pingpong.1 | 71 ++++++++
src/cmd.c | 340 +++++++++++++++++++++++++++++++-------
src/device.c | 49 ++++++
src/ibverbs.h | 5 +
src/libibverbs.map | 6 +
src/memory.c | 8 +-
src/verbs.c | 62 +++++++
34 files changed, 2277 insertions(+), 293 deletions(-)
diff --git a/Makefile.am b/Makefile.am
index 5a58599..5349314 100644
--- a/Makefile.am
+++ b/Makefile.am
@@ -53,7 +53,7 @@ man_MANS = man/ibv_asyncwatch.1 man/ibv_devices.1 man/ibv_devinfo.1 \
man/ibv_create_ah.3 man/ibv_create_ah_from_wc.3 \
man/ibv_create_comp_channel.3 man/ibv_create_cq.3 \
man/ibv_create_qp.3 man/ibv_create_srq.3 man/ibv_event_type_str.3 \
- man/ibv_fork_init.3 man/ibv_get_async_event.3 \
+ man/ibv_fork_init.3 man/ibv_get_async_event.3 man/ibv_create_flow.3 \
man/ibv_get_cq_event.3 man/ibv_get_device_guid.3 \
man/ibv_get_device_list.3 man/ibv_get_device_name.3 \
man/ibv_modify_qp.3 man/ibv_modify_srq.3 man/ibv_open_device.3 \
@@ -63,8 +63,10 @@ man_MANS = man/ibv_asyncwatch.1 man/ibv_devices.1 man/ibv_devinfo.1 \
man/ibv_query_srq.3 man/ibv_rate_to_mult.3 man/ibv_reg_mr.3 \
man/ibv_req_notify_cq.3 man/ibv_resize_cq.3 man/ibv_rate_to_mbps.3 \
man/ibv_create_qp_ex.3 man/ibv_create_srq_ex.3 man/ibv_open_xrcd.3 \
- man/ibv_get_srq_num.3 man/ibv_open_qp.3 \
- man/ibv_query_device_ex.3
+ man/ibv_get_srq_num.3 man/ibv_open_qp.3 man/ibv_query_device_ex.3 \
+ man/ibv_alloc_mw.3 man/ibv_bind_mw.3 man/ibv_inc_rkey.3 \
+ man/ibv_rereg_mr.3 man/ibv_create_cq_ex.3 \
+ man/ibv_query_rt_values_ex.3 man/ibv_xsrq_pingpong.1
DEBIAN = debian/changelog debian/compat debian/control debian/copyright \
debian/ibverbs-utils.install debian/libibverbs1.install \
@@ -100,6 +102,8 @@ install-data-hook:
$(RM) ibv_port_state_str.3 && \
$(RM) mbps_to_ibv_rate.3 && \
$(RM) ibv_close_xrcd.3 && \
+ $(RM) ibv_dealloc_mw.3 && \
+ $(RM) ibv_destroy_flow.3 && \
$(LN_S) ibv_get_async_event.3 ibv_ack_async_event.3 && \
$(LN_S) ibv_get_cq_event.3 ibv_ack_cq_events.3 && \
$(LN_S) ibv_open_device.3 ibv_close_device.3 && \
@@ -117,4 +121,6 @@ install-data-hook:
$(LN_S) ibv_event_type_str.3 ibv_node_type_str.3 && \
$(LN_S) ibv_event_type_str.3 ibv_port_state_str.3 && \
$(LN_S) ibv_rate_to_mbps.3 mbps_to_ibv_rate.3 && \
- $(LN_S) ibv_open_xrcd.3 ibv_close_xrcd.3
+ $(LN_S) ibv_open_xrcd.3 ibv_close_xrcd.3 && \
+ $(LN_S) ibv_alloc_mw.3 ibv_dealloc_mw.3 && \
+ $(LN_S) ibv_create_flow.3 ibv_destroy_flow.3
diff --git a/Makefile.in b/Makefile.in
index 21c28b9..8b19cbd 100644
--- a/Makefile.in
+++ b/Makefile.in
@@ -492,7 +492,7 @@ man_MANS = man/ibv_asyncwatch.1 man/ibv_devices.1 man/ibv_devinfo.1 \
man/ibv_create_ah.3 man/ibv_create_ah_from_wc.3 \
man/ibv_create_comp_channel.3 man/ibv_create_cq.3 \
man/ibv_create_qp.3 man/ibv_create_srq.3 man/ibv_event_type_str.3 \
- man/ibv_fork_init.3 man/ibv_get_async_event.3 \
+ man/ibv_fork_init.3 man/ibv_get_async_event.3 man/ibv_create_flow.3 \
man/ibv_get_cq_event.3 man/ibv_get_device_guid.3 \
man/ibv_get_device_list.3 man/ibv_get_device_name.3 \
man/ibv_modify_qp.3 man/ibv_modify_srq.3 man/ibv_open_device.3 \
@@ -502,8 +502,10 @@ man_MANS = man/ibv_asyncwatch.1 man/ibv_devices.1 man/ibv_devinfo.1 \
man/ibv_query_srq.3 man/ibv_rate_to_mult.3 man/ibv_reg_mr.3 \
man/ibv_req_notify_cq.3 man/ibv_resize_cq.3 man/ibv_rate_to_mbps.3 \
man/ibv_create_qp_ex.3 man/ibv_create_srq_ex.3 man/ibv_open_xrcd.3 \
- man/ibv_get_srq_num.3 man/ibv_open_qp.3 \
- man/ibv_query_device_ex.3
+ man/ibv_get_srq_num.3 man/ibv_open_qp.3 man/ibv_query_device_ex.3 \
+ man/ibv_alloc_mw.3 man/ibv_bind_mw.3 man/ibv_inc_rkey.3 \
+ man/ibv_rereg_mr.3 man/ibv_create_cq_ex.3 \
+ man/ibv_query_rt_values_ex.3 man/ibv_xsrq_pingpong.1
DEBIAN = debian/changelog debian/compat debian/control debian/copyright \
debian/ibverbs-utils.install debian/libibverbs1.install \
@@ -1379,6 +1381,8 @@ install-data-hook:
$(RM) ibv_port_state_str.3 && \
$(RM) mbps_to_ibv_rate.3 && \
$(RM) ibv_close_xrcd.3 && \
+ $(RM) ibv_dealloc_mw.3 && \
+ $(RM) ibv_destroy_flow.3 && \
$(LN_S) ibv_get_async_event.3 ibv_ack_async_event.3 && \
$(LN_S) ibv_get_cq_event.3 ibv_ack_cq_events.3 && \
$(LN_S) ibv_open_device.3 ibv_close_device.3 && \
@@ -1396,7 +1400,9 @@ install-data-hook:
$(LN_S) ibv_event_type_str.3 ibv_node_type_str.3 && \
$(LN_S) ibv_event_type_str.3 ibv_port_state_str.3 && \
$(LN_S) ibv_rate_to_mbps.3 mbps_to_ibv_rate.3 && \
- $(LN_S) ibv_open_xrcd.3 ibv_close_xrcd.3
+ $(LN_S) ibv_open_xrcd.3 ibv_close_xrcd.3 && \
+ $(LN_S) ibv_alloc_mw.3 ibv_dealloc_mw.3 && \
+ $(LN_S) ibv_create_flow.3 ibv_destroy_flow.3
# Tell versions [3.59,3.63) of GNU make to not export all variables.
# Otherwise a system limit (for SysV at least) may be exceeded.
diff --git a/aclocal.m4 b/aclocal.m4
index ca50e82..53098a5 100644
--- a/aclocal.m4
+++ b/aclocal.m4
@@ -20,32 +20,63 @@ You have another version of autoconf. It may work, but is not guaranteed to.
If you have problems, you may need to regenerate the build system entirely.
To do so, use the procedure documented by the package, typically 'autoreconf'.])])
-# pkg.m4 - Macros to locate and utilise pkg-config. -*- Autoconf -*-
-# serial 1 (pkg-config-0.24)
-#
-# Copyright © 2004 Scott James Remnant <scott at netsplit.com>.
-#
-# 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, write to the Free Software
-# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
-#
-# As a special exception to the GNU General Public License, if you
-# distribute this file as part of a program that contains a
-# configuration script generated by Autoconf, you may include it under
-# the same distribution terms that you use for the rest of that program.
-
-# PKG_PROG_PKG_CONFIG([MIN-VERSION])
-# ----------------------------------
+dnl pkg.m4 - Macros to locate and utilise pkg-config. -*- Autoconf -*-
+dnl serial 11 (pkg-config-0.29)
+dnl
+dnl Copyright © 2004 Scott James Remnant <scott at netsplit.com>.
+dnl Copyright © 2012-2015 Dan Nicholson <dbn.lists at gmail.com>
+dnl
+dnl This program is free software; you can redistribute it and/or modify
+dnl it under the terms of the GNU General Public License as published by
+dnl the Free Software Foundation; either version 2 of the License, or
+dnl (at your option) any later version.
+dnl
+dnl This program is distributed in the hope that it will be useful, but
+dnl WITHOUT ANY WARRANTY; without even the implied warranty of
+dnl MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+dnl General Public License for more details.
+dnl
+dnl You should have received a copy of the GNU General Public License
+dnl along with this program; if not, write to the Free Software
+dnl Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
+dnl 02111-1307, USA.
+dnl
+dnl As a special exception to the GNU General Public License, if you
+dnl distribute this file as part of a program that contains a
+dnl configuration script generated by Autoconf, you may include it under
+dnl the same distribution terms that you use for the rest of that
+dnl program.
+
+dnl PKG_PREREQ(MIN-VERSION)
+dnl -----------------------
+dnl Since: 0.29
+dnl
+dnl Verify that the version of the pkg-config macros are at least
+dnl MIN-VERSION. Unlike PKG_PROG_PKG_CONFIG, which checks the user's
+dnl installed version of pkg-config, this checks the developer's version
+dnl of pkg.m4 when generating configure.
+dnl
+dnl To ensure that this macro is defined, also add:
+dnl m4_ifndef([PKG_PREREQ],
+dnl [m4_fatal([must install pkg-config 0.29 or later before running autoconf/autogen])])
+dnl
+dnl See the "Since" comment for each macro you use to see what version
+dnl of the macros you require.
+m4_defun([PKG_PREREQ],
+[m4_define([PKG_MACROS_VERSION], [0.29])
+m4_if(m4_version_compare(PKG_MACROS_VERSION, [$1]), -1,
+ [m4_fatal([pkg.m4 version $1 or higher is required but ]PKG_MACROS_VERSION[ found])])
+])dnl PKG_PREREQ
+
+dnl PKG_PROG_PKG_CONFIG([MIN-VERSION])
+dnl ----------------------------------
+dnl Since: 0.16
+dnl
+dnl Search for the pkg-config tool and set the PKG_CONFIG variable to
+dnl first found in the path. Checks that the version of pkg-config found
+dnl is at least MIN-VERSION. If MIN-VERSION is not specified, 0.9.0 is
+dnl used since that's the first version where most current features of
+dnl pkg-config existed.
AC_DEFUN([PKG_PROG_PKG_CONFIG],
[m4_pattern_forbid([^_?PKG_[A-Z_]+$])
m4_pattern_allow([^PKG_CONFIG(_(PATH|LIBDIR|SYSROOT_DIR|ALLOW_SYSTEM_(CFLAGS|LIBS)))?$])
@@ -67,18 +98,19 @@ if test -n "$PKG_CONFIG"; then
PKG_CONFIG=""
fi
fi[]dnl
-])# PKG_PROG_PKG_CONFIG
+])dnl PKG_PROG_PKG_CONFIG
-# PKG_CHECK_EXISTS(MODULES, [ACTION-IF-FOUND], [ACTION-IF-NOT-FOUND])
-#
-# Check to see whether a particular set of modules exists. Similar
-# to PKG_CHECK_MODULES(), but does not set variables or print errors.
-#
-# Please remember that m4 expands AC_REQUIRE([PKG_PROG_PKG_CONFIG])
-# only at the first occurence in configure.ac, so if the first place
-# it's called might be skipped (such as if it is within an "if", you
-# have to call PKG_CHECK_EXISTS manually
-# --------------------------------------------------------------
+dnl PKG_CHECK_EXISTS(MODULES, [ACTION-IF-FOUND], [ACTION-IF-NOT-FOUND])
+dnl -------------------------------------------------------------------
+dnl Since: 0.18
+dnl
+dnl Check to see whether a particular set of modules exists. Similar to
+dnl PKG_CHECK_MODULES(), but does not set variables or print errors.
+dnl
+dnl Please remember that m4 expands AC_REQUIRE([PKG_PROG_PKG_CONFIG])
+dnl only at the first occurence in configure.ac, so if the first place
+dnl it's called might be skipped (such as if it is within an "if", you
+dnl have to call PKG_CHECK_EXISTS manually
AC_DEFUN([PKG_CHECK_EXISTS],
[AC_REQUIRE([PKG_PROG_PKG_CONFIG])dnl
if test -n "$PKG_CONFIG" && \
@@ -88,8 +120,10 @@ m4_ifvaln([$3], [else
$3])dnl
fi])
-# _PKG_CONFIG([VARIABLE], [COMMAND], [MODULES])
-# ---------------------------------------------
+dnl _PKG_CONFIG([VARIABLE], [COMMAND], [MODULES])
+dnl ---------------------------------------------
+dnl Internal wrapper calling pkg-config via PKG_CONFIG and setting
+dnl pkg_failed based on the result.
m4_define([_PKG_CONFIG],
[if test -n "$$1"; then
pkg_cv_[]$1="$$1"
@@ -101,10 +135,11 @@ m4_define([_PKG_CONFIG],
else
pkg_failed=untried
fi[]dnl
-])# _PKG_CONFIG
+])dnl _PKG_CONFIG
-# _PKG_SHORT_ERRORS_SUPPORTED
-# -----------------------------
+dnl _PKG_SHORT_ERRORS_SUPPORTED
+dnl ---------------------------
+dnl Internal check to see if pkg-config supports short errors.
AC_DEFUN([_PKG_SHORT_ERRORS_SUPPORTED],
[AC_REQUIRE([PKG_PROG_PKG_CONFIG])
if $PKG_CONFIG --atleast-pkgconfig-version 0.20; then
@@ -112,19 +147,17 @@ if $PKG_CONFIG --atleast-pkgconfig-version 0.20; then
else
_pkg_short_errors_supported=no
fi[]dnl
-])# _PKG_SHORT_ERRORS_SUPPORTED
+])dnl _PKG_SHORT_ERRORS_SUPPORTED
-# PKG_CHECK_MODULES(VARIABLE-PREFIX, MODULES, [ACTION-IF-FOUND],
-# [ACTION-IF-NOT-FOUND])
-#
-#
-# Note that if there is a possibility the first call to
-# PKG_CHECK_MODULES might not happen, you should be sure to include an
-# explicit call to PKG_PROG_PKG_CONFIG in your configure.ac
-#
-#
-# --------------------------------------------------------------
+dnl PKG_CHECK_MODULES(VARIABLE-PREFIX, MODULES, [ACTION-IF-FOUND],
+dnl [ACTION-IF-NOT-FOUND])
+dnl --------------------------------------------------------------
+dnl Since: 0.4.0
+dnl
+dnl Note that if there is a possibility the first call to
+dnl PKG_CHECK_MODULES might not happen, you should be sure to include an
+dnl explicit call to PKG_PROG_PKG_CONFIG in your configure.ac
AC_DEFUN([PKG_CHECK_MODULES],
[AC_REQUIRE([PKG_PROG_PKG_CONFIG])dnl
AC_ARG_VAR([$1][_CFLAGS], [C compiler flags for $1, overriding pkg-config])dnl
@@ -178,16 +211,40 @@ else
AC_MSG_RESULT([yes])
$3
fi[]dnl
-])# PKG_CHECK_MODULES
+])dnl PKG_CHECK_MODULES
+
+
+dnl PKG_CHECK_MODULES_STATIC(VARIABLE-PREFIX, MODULES, [ACTION-IF-FOUND],
+dnl [ACTION-IF-NOT-FOUND])
+dnl ---------------------------------------------------------------------
+dnl Since: 0.29
+dnl
+dnl Checks for existence of MODULES and gathers its build flags with
+dnl static libraries enabled. Sets VARIABLE-PREFIX_CFLAGS from --cflags
+dnl and VARIABLE-PREFIX_LIBS from --libs.
+dnl
+dnl Note that if there is a possibility the first call to
+dnl PKG_CHECK_MODULES_STATIC might not happen, you should be sure to
+dnl include an explicit call to PKG_PROG_PKG_CONFIG in your
+dnl configure.ac.
+AC_DEFUN([PKG_CHECK_MODULES_STATIC],
+[AC_REQUIRE([PKG_PROG_PKG_CONFIG])dnl
+_save_PKG_CONFIG=$PKG_CONFIG
+PKG_CONFIG="$PKG_CONFIG --static"
+PKG_CHECK_MODULES($@)
+PKG_CONFIG=$_save_PKG_CONFIG[]dnl
+])dnl PKG_CHECK_MODULES_STATIC
-# PKG_INSTALLDIR(DIRECTORY)
-# -------------------------
-# Substitutes the variable pkgconfigdir as the location where a module
-# should install pkg-config .pc files. By default the directory is
-# $libdir/pkgconfig, but the default can be changed by passing
-# DIRECTORY. The user can override through the --with-pkgconfigdir
-# parameter.
+dnl PKG_INSTALLDIR([DIRECTORY])
+dnl -------------------------
+dnl Since: 0.27
+dnl
+dnl Substitutes the variable pkgconfigdir as the location where a module
+dnl should install pkg-config .pc files. By default the directory is
+dnl $libdir/pkgconfig, but the default can be changed by passing
+dnl DIRECTORY. The user can override through the --with-pkgconfigdir
+dnl parameter.
AC_DEFUN([PKG_INSTALLDIR],
[m4_pushdef([pkg_default], [m4_default([$1], ['${libdir}/pkgconfig'])])
m4_pushdef([pkg_description],
@@ -198,16 +255,18 @@ AC_ARG_WITH([pkgconfigdir],
AC_SUBST([pkgconfigdir], [$with_pkgconfigdir])
m4_popdef([pkg_default])
m4_popdef([pkg_description])
-]) dnl PKG_INSTALLDIR
+])dnl PKG_INSTALLDIR
-# PKG_NOARCH_INSTALLDIR(DIRECTORY)
-# -------------------------
-# Substitutes the variable noarch_pkgconfigdir as the location where a
-# module should install arch-independent pkg-config .pc files. By
-# default the directory is $datadir/pkgconfig, but the default can be
-# changed by passing DIRECTORY. The user can override through the
-# --with-noarch-pkgconfigdir parameter.
+dnl PKG_NOARCH_INSTALLDIR([DIRECTORY])
+dnl --------------------------------
+dnl Since: 0.27
+dnl
+dnl Substitutes the variable noarch_pkgconfigdir as the location where a
+dnl module should install arch-independent pkg-config .pc files. By
+dnl default the directory is $datadir/pkgconfig, but the default can be
+dnl changed by passing DIRECTORY. The user can override through the
+dnl --with-noarch-pkgconfigdir parameter.
AC_DEFUN([PKG_NOARCH_INSTALLDIR],
[m4_pushdef([pkg_default], [m4_default([$1], ['${datadir}/pkgconfig'])])
m4_pushdef([pkg_description],
@@ -218,13 +277,15 @@ AC_ARG_WITH([noarch-pkgconfigdir],
AC_SUBST([noarch_pkgconfigdir], [$with_noarch_pkgconfigdir])
m4_popdef([pkg_default])
m4_popdef([pkg_description])
-]) dnl PKG_NOARCH_INSTALLDIR
+])dnl PKG_NOARCH_INSTALLDIR
-# PKG_CHECK_VAR(VARIABLE, MODULE, CONFIG-VARIABLE,
-# [ACTION-IF-FOUND], [ACTION-IF-NOT-FOUND])
-# -------------------------------------------
-# Retrieves the value of the pkg-config variable for the given module.
+dnl PKG_CHECK_VAR(VARIABLE, MODULE, CONFIG-VARIABLE,
+dnl [ACTION-IF-FOUND], [ACTION-IF-NOT-FOUND])
+dnl -------------------------------------------
+dnl Since: 0.28
+dnl
+dnl Retrieves the value of the pkg-config variable for the given module.
AC_DEFUN([PKG_CHECK_VAR],
[AC_REQUIRE([PKG_PROG_PKG_CONFIG])dnl
AC_ARG_VAR([$1], [value of $3 for $2, overriding pkg-config])dnl
@@ -233,7 +294,7 @@ _PKG_CONFIG([$1], [variable="][$3]["], [$2])
AS_VAR_COPY([$1], [pkg_cv_][$1])
AS_VAR_IF([$1], [""], [$5], [$4])dnl
-])# PKG_CHECK_VAR
+])dnl PKG_CHECK_VAR
# Copyright (C) 2002-2014 Free Software Foundation, Inc.
#
diff --git a/configure b/configure
index a5a9cf2..270f485 100755
--- a/configure
+++ b/configure
@@ -1,6 +1,6 @@
#! /bin/sh
# Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.69 for libibverbs 1.2.0.
+# Generated by GNU Autoconf 2.69 for libibverbs 1.2.1.
#
# Report bugs to <linux-rdma at vger.kernel.org>.
#
@@ -590,8 +590,8 @@ MAKEFLAGS=
# Identity of this package.
PACKAGE_NAME='libibverbs'
PACKAGE_TARNAME='libibverbs'
-PACKAGE_VERSION='1.2.0'
-PACKAGE_STRING='libibverbs 1.2.0'
+PACKAGE_VERSION='1.2.1'
+PACKAGE_STRING='libibverbs 1.2.1'
PACKAGE_BUGREPORT='linux-rdma at vger.kernel.org'
PACKAGE_URL=''
@@ -1334,7 +1334,7 @@ if test "$ac_init_help" = "long"; then
# Omit some internal or obsolete options to make the list less imposing.
# This message is too long to be a string in the A/UX 3.1 sh.
cat <<_ACEOF
-\`configure' configures libibverbs 1.2.0 to adapt to many kinds of systems.
+\`configure' configures libibverbs 1.2.1 to adapt to many kinds of systems.
Usage: $0 [OPTION]... [VAR=VALUE]...
@@ -1404,7 +1404,7 @@ fi
if test -n "$ac_init_help"; then
case $ac_init_help in
- short | recursive ) echo "Configuration of libibverbs 1.2.0:";;
+ short | recursive ) echo "Configuration of libibverbs 1.2.1:";;
esac
cat <<\_ACEOF
@@ -1530,7 +1530,7 @@ fi
test -n "$ac_init_help" && exit $ac_status
if $ac_init_version; then
cat <<\_ACEOF
-libibverbs configure 1.2.0
+libibverbs configure 1.2.1
generated by GNU Autoconf 2.69
Copyright (C) 2012 Free Software Foundation, Inc.
@@ -1945,7 +1945,7 @@ cat >config.log <<_ACEOF
This file contains any messages produced by compilers while
running configure, to aid debugging if configure makes a mistake.
-It was created by libibverbs $as_me 1.2.0, which was
+It was created by libibverbs $as_me 1.2.1, which was
generated by GNU Autoconf 2.69. Invocation command line was
$ $0 $@
@@ -2812,7 +2812,7 @@ fi
# Define the identity of the package.
PACKAGE='libibverbs'
- VERSION='1.2.0'
+ VERSION='1.2.1'
cat >>confdefs.h <<_ACEOF
@@ -13564,7 +13564,7 @@ cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1
# report actual input values of CONFIG_FILES etc. instead of their
# values after options handling.
ac_log="
-This file was extended by libibverbs $as_me 1.2.0, which was
+This file was extended by libibverbs $as_me 1.2.1, which was
generated by GNU Autoconf 2.69. Invocation command line was
CONFIG_FILES = $CONFIG_FILES
@@ -13630,7 +13630,7 @@ _ACEOF
cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1
ac_cs_config="`$as_echo "$ac_configure_args" | sed 's/^ //; s/[\\""\`\$]/\\\\&/g'`"
ac_cs_version="\\
-libibverbs config.status 1.2.0
+libibverbs config.status 1.2.1
configured by $0, generated by GNU Autoconf 2.69,
with options \\"\$ac_cs_config\\"
diff --git a/configure.ac b/configure.ac
index 987725f..90c33df 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1,7 +1,7 @@
dnl Process this file with autoconf to produce a configure script.
AC_PREREQ([2.67])
-AC_INIT([libibverbs],[1.2.0],[linux-rdma at vger.kernel.org])
+AC_INIT([libibverbs],[1.2.1],[linux-rdma at vger.kernel.org])
AC_CONFIG_SRCDIR([src/ibverbs.h])
AC_CONFIG_AUX_DIR(config)
AC_CONFIG_MACRO_DIR(config)
diff --git a/examples/asyncwatch.c b/examples/asyncwatch.c
index da7ebd4..a77c1c8 100644
--- a/examples/asyncwatch.c
+++ b/examples/asyncwatch.c
@@ -37,6 +37,8 @@
#include <stdio.h>
#include <endian.h>
#include <byteswap.h>
+#include <getopt.h>
+#include <string.h>
#include <infiniband/verbs.h>
@@ -76,35 +78,77 @@ static const char *event_name_str(enum ibv_event_type event_type)
}
}
+static void usage(const char *argv0)
+{
+ printf("Usage:\n");
+ printf(" %s start an asyncwatch process\n", argv0);
+ printf("\n");
+ printf("Options:\n");
+ printf(" -d, --ib-dev=<dev> use IB device <dev> (default first device found)\n");
+ printf(" -h, --help print a help text and exit\n");
+}
+
int main(int argc, char *argv[])
{
struct ibv_device **dev_list;
struct ibv_context *context;
struct ibv_async_event event;
+ char *ib_devname = NULL;
+ int i = 0;
/* Force line-buffering in case stdout is redirected */
setvbuf(stdout, NULL, _IOLBF, 0);
+ while (1) {
+ int ret = 1;
+ int c;
+ static struct option long_options[] = {
+ { .name = "ib-dev", .has_arg = 1, .val = 'd' },
+ { .name = "help", .has_arg = 0, .val = 'h' },
+ { 0 }
+ };
+
+ c = getopt_long(argc, argv, "d:h", long_options, NULL);
+ if (c == -1)
+ break;
+ switch (c) {
+ case 'd':
+ ib_devname = strdupa(optarg);
+ break;
+ case 'h':
+ ret = 0;
+ default:
+ usage(argv[0]);
+ return ret;
+ }
+ }
dev_list = ibv_get_device_list(NULL);
if (!dev_list) {
perror("Failed to get IB devices list");
return 1;
}
+ if (ib_devname) {
+ for (; dev_list[i]; ++i) {
+ if (!strcmp(ibv_get_device_name(dev_list[i]), ib_devname))
+ break;
+ }
+ }
- if (!*dev_list) {
- fprintf(stderr, "No IB devices found\n");
+ if (!dev_list[i]) {
+ fprintf(stderr, "IB device %s not found\n",
+ ib_devname ? ib_devname : "");
return 1;
}
- context = ibv_open_device(*dev_list);
+ context = ibv_open_device(dev_list[i]);
if (!context) {
fprintf(stderr, "Couldn't get context for %s\n",
- ibv_get_device_name(*dev_list));
+ ibv_get_device_name(dev_list[i]));
return 1;
}
printf("%s: async event FD %d\n",
- ibv_get_device_name(*dev_list), context->async_fd);
+ ibv_get_device_name(dev_list[i]), context->async_fd);
while (1) {
if (ibv_get_async_event(context, &event))
diff --git a/examples/devinfo.c b/examples/devinfo.c
index a8de982..915ebb3 100644
--- a/examples/devinfo.c
+++ b/examples/devinfo.c
@@ -205,6 +205,86 @@ static const char *link_layer_str(uint8_t link_layer)
}
}
+static void print_device_cap_flags(uint32_t dev_cap_flags)
+{
+ uint32_t unknown_flags = ~(IBV_DEVICE_RESIZE_MAX_WR |
+ IBV_DEVICE_BAD_PKEY_CNTR |
+ IBV_DEVICE_BAD_QKEY_CNTR |
+ IBV_DEVICE_RAW_MULTI |
+ IBV_DEVICE_AUTO_PATH_MIG |
+ IBV_DEVICE_CHANGE_PHY_PORT |
+ IBV_DEVICE_UD_AV_PORT_ENFORCE |
+ IBV_DEVICE_CURR_QP_STATE_MOD |
+ IBV_DEVICE_SHUTDOWN_PORT |
+ IBV_DEVICE_INIT_TYPE |
+ IBV_DEVICE_PORT_ACTIVE_EVENT |
+ IBV_DEVICE_SYS_IMAGE_GUID |
+ IBV_DEVICE_RC_RNR_NAK_GEN |
+ IBV_DEVICE_SRQ_RESIZE |
+ IBV_DEVICE_N_NOTIFY_CQ |
+ IBV_DEVICE_MEM_WINDOW |
+ IBV_DEVICE_UD_IP_CSUM |
+ IBV_DEVICE_XRC |
+ IBV_DEVICE_MEM_MGT_EXTENSIONS |
+ IBV_DEVICE_MEM_WINDOW_TYPE_2A |
+ IBV_DEVICE_MEM_WINDOW_TYPE_2B |
+ IBV_DEVICE_RC_IP_CSUM |
+ IBV_DEVICE_RAW_IP_CSUM |
+ IBV_DEVICE_MANAGED_FLOW_STEERING);
+
+ if (dev_cap_flags & IBV_DEVICE_RESIZE_MAX_WR)
+ printf("\t\t\t\t\tRESIZE_MAX_WR\n");
+ if (dev_cap_flags & IBV_DEVICE_BAD_PKEY_CNTR)
+ printf("\t\t\t\t\tBAD_PKEY_CNTR\n");
+ if (dev_cap_flags & IBV_DEVICE_BAD_QKEY_CNTR)
+ printf("\t\t\t\t\tBAD_QKEY_CNTR\n");
+ if (dev_cap_flags & IBV_DEVICE_RAW_MULTI)
+ printf("\t\t\t\t\tRAW_MULTI\n");
+ if (dev_cap_flags & IBV_DEVICE_AUTO_PATH_MIG)
+ printf("\t\t\t\t\tAUTO_PATH_MIG\n");
+ if (dev_cap_flags & IBV_DEVICE_CHANGE_PHY_PORT)
+ printf("\t\t\t\t\tCHANGE_PHY_PORT\n");
+ if (dev_cap_flags & IBV_DEVICE_UD_AV_PORT_ENFORCE)
+ printf("\t\t\t\t\tUD_AV_PORT_ENFORCE\n");
+ if (dev_cap_flags & IBV_DEVICE_CURR_QP_STATE_MOD)
+ printf("\t\t\t\t\tCURR_QP_STATE_MOD\n");
+ if (dev_cap_flags & IBV_DEVICE_SHUTDOWN_PORT)
+ printf("\t\t\t\t\tSHUTDOWN_PORT\n");
+ if (dev_cap_flags & IBV_DEVICE_INIT_TYPE)
+ printf("\t\t\t\t\tINIT_TYPE\n");
+ if (dev_cap_flags & IBV_DEVICE_PORT_ACTIVE_EVENT)
+ printf("\t\t\t\t\tPORT_ACTIVE_EVENT\n");
+ if (dev_cap_flags & IBV_DEVICE_SYS_IMAGE_GUID)
+ printf("\t\t\t\t\tSYS_IMAGE_GUID\n");
+ if (dev_cap_flags & IBV_DEVICE_RC_RNR_NAK_GEN)
+ printf("\t\t\t\t\tRC_RNR_NAK_GEN\n");
+ if (dev_cap_flags & IBV_DEVICE_SRQ_RESIZE)
+ printf("\t\t\t\t\tSRQ_RESIZE\n");
+ if (dev_cap_flags & IBV_DEVICE_N_NOTIFY_CQ)
+ printf("\t\t\t\t\tN_NOTIFY_CQ\n");
+ if (dev_cap_flags & IBV_DEVICE_MEM_WINDOW)
+ printf("\t\t\t\t\tMEM_WINDOW\n");
+ if (dev_cap_flags & IBV_DEVICE_UD_IP_CSUM)
+ printf("\t\t\t\t\tUD_IP_CSUM\n");
+ if (dev_cap_flags & IBV_DEVICE_XRC)
+ printf("\t\t\t\t\tXRC\n");
+ if (dev_cap_flags & IBV_DEVICE_MEM_MGT_EXTENSIONS)
+ printf("\t\t\t\t\tMEM_MGT_EXTENSIONS\n");
+ if (dev_cap_flags & IBV_DEVICE_MEM_WINDOW_TYPE_2A)
+ printf("\t\t\t\t\tMEM_WINDOW_TYPE_2A\n");
+ if (dev_cap_flags & IBV_DEVICE_MEM_WINDOW_TYPE_2B)
+ printf("\t\t\t\t\tMEM_WINDOW_TYPE_2B\n");
+ if (dev_cap_flags & IBV_DEVICE_RC_IP_CSUM)
+ printf("\t\t\t\t\tRC_IP_CSUM\n");
+ if (dev_cap_flags & IBV_DEVICE_RAW_IP_CSUM)
+ printf("\t\t\t\t\tRAW_IP_CSUM\n");
+ if (dev_cap_flags & IBV_DEVICE_MANAGED_FLOW_STEERING)
+ printf("\t\t\t\t\tMANAGED_FLOW_STEERING\n");
+ if (dev_cap_flags & unknown_flags)
+ printf("\t\t\t\t\tUnknown flags: 0x%" PRIX32 "\n",
+ dev_cap_flags & unknown_flags);
+}
+
void print_odp_trans_caps(uint32_t trans)
{
uint32_t unknown_transport_caps = ~(IBV_ODP_SUPPORT_SEND |
@@ -253,6 +333,18 @@ void print_odp_caps(const struct ibv_odp_caps *caps)
print_odp_trans_caps(caps->per_transport_caps.ud_odp_caps);
}
+static void print_device_cap_flags_ex(uint64_t device_cap_flags_ex)
+{
+ uint64_t ex_flags = device_cap_flags_ex & 0xffffffff00000000;
+ uint64_t unknown_flags = ~(IBV_DEVICE_RAW_SCATTER_FCS);
+
+ if (ex_flags & IBV_DEVICE_RAW_SCATTER_FCS)
+ printf("\t\t\t\t\tRAW_SCATTER_FCS\n");
+ if (ex_flags & unknown_flags)
+ printf("\t\t\t\t\tUnknown flags: 0x%" PRIX64 "\n",
+ ex_flags & unknown_flags);
+}
+
static int print_hca_cap(struct ibv_device *ib_dev, uint8_t ib_port)
{
struct ibv_context *ctx;
@@ -304,6 +396,7 @@ static int print_hca_cap(struct ibv_device *ib_dev, uint8_t ib_port)
printf("\tmax_qp:\t\t\t\t%d\n", device_attr.orig_attr.max_qp);
printf("\tmax_qp_wr:\t\t\t%d\n", device_attr.orig_attr.max_qp_wr);
printf("\tdevice_cap_flags:\t\t0x%08x\n", device_attr.orig_attr.device_cap_flags);
+ print_device_cap_flags(device_attr.orig_attr.device_cap_flags);
printf("\tmax_sge:\t\t\t%d\n", device_attr.orig_attr.max_sge);
printf("\tmax_sge_rd:\t\t\t%d\n", device_attr.orig_attr.max_sge_rd);
printf("\tmax_cq:\t\t\t\t%d\n", device_attr.orig_attr.max_cq);
@@ -339,6 +432,19 @@ static int print_hca_cap(struct ibv_device *ib_dev, uint8_t ib_port)
printf("\tlocal_ca_ack_delay:\t\t%d\n", device_attr.orig_attr.local_ca_ack_delay);
print_odp_caps(&device_attr.odp_caps);
+ if (device_attr.completion_timestamp_mask)
+ printf("\tcompletion timestamp_mask:\t\t\t0x%016lx\n",
+ device_attr.completion_timestamp_mask);
+ else
+ printf("\tcompletion_timestamp_mask not supported\n");
+
+ if (device_attr.hca_core_clock)
+ printf("\thca_core_clock:\t\t\t%lukHZ\n", device_attr.hca_core_clock);
+ else
+ printf("\tcore clock not supported\n");
+
+ printf("\tdevice_cap_flags_ex:\t\t0x%" PRIX64 "\n", device_attr.device_cap_flags_ex);
+ print_device_cap_flags_ex(device_attr.device_cap_flags_ex);
}
for (port = 1; port <= device_attr.orig_attr.phys_port_cnt; ++port) {
diff --git a/examples/pingpong.c b/examples/pingpong.c
index 90732ef..2fe4a04 100644
--- a/examples/pingpong.c
+++ b/examples/pingpong.c
@@ -48,16 +48,6 @@ enum ibv_mtu pp_mtu_to_enum(int mtu)
}
}
-uint16_t pp_get_local_lid(struct ibv_context *context, int port)
-{
- struct ibv_port_attr attr;
-
- if (ibv_query_port(context, port, &attr))
- return 0;
-
- return attr.lid;
-}
-
int pp_get_port_info(struct ibv_context *context, int port,
struct ibv_port_attr *attr)
{
diff --git a/examples/pingpong.h b/examples/pingpong.h
index 9cdc03e..8dc5dd0 100644
--- a/examples/pingpong.h
+++ b/examples/pingpong.h
@@ -36,7 +36,6 @@
#include <infiniband/verbs.h>
enum ibv_mtu pp_mtu_to_enum(int mtu);
-uint16_t pp_get_local_lid(struct ibv_context *context, int port);
int pp_get_port_info(struct ibv_context *context, int port,
struct ibv_port_attr *attr);
void wire_gid_to_gid(const char *wgid, union ibv_gid *gid);
diff --git a/examples/rc_pingpong.c b/examples/rc_pingpong.c
index 90a8320..8d58357 100644
--- a/examples/rc_pingpong.c
+++ b/examples/rc_pingpong.c
@@ -49,6 +49,14 @@
#include "pingpong.h"
+#ifndef max
+#define max(x, y) (((x) > (y)) ? (x) : (y))
+#endif
+
+#ifndef min
+#define min(x, y) (((x) < (y)) ? (x) : (y))
+#endif
+
enum {
PINGPONG_RECV_WRID = 1,
PINGPONG_SEND_WRID = 2,
@@ -56,13 +64,17 @@ enum {
static int page_size;
static int use_odp;
+static int use_ts;
struct pingpong_context {
struct ibv_context *context;
struct ibv_comp_channel *channel;
struct ibv_pd *pd;
struct ibv_mr *mr;
- struct ibv_cq *cq;
+ union {
+ struct ibv_cq *cq;
+ struct ibv_cq_ex *cq_ex;
+ } cq_s;
struct ibv_qp *qp;
void *buf;
int size;
@@ -70,8 +82,15 @@ struct pingpong_context {
int rx_depth;
int pending;
struct ibv_port_attr portinfo;
+ uint64_t completion_timestamp_mask;
};
+struct ibv_cq *pp_cq(struct pingpong_context *ctx)
+{
+ return use_ts ? ibv_cq_ex_to_cq(ctx->cq_s.cq_ex) :
+ ctx->cq_s.cq;
+}
+
struct pingpong_dest {
int lid;
int qpn;
@@ -357,7 +376,7 @@ static struct pingpong_context *pp_init_ctx(struct ibv_device *ib_dev, int size,
goto clean_comp_channel;
}
- if (use_odp) {
+ if (use_odp || use_ts) {
const uint32_t rc_caps_mask = IBV_ODP_SUPPORT_SEND |
IBV_ODP_SUPPORT_RECV;
struct ibv_device_attr_ex attrx;
@@ -367,12 +386,22 @@ static struct pingpong_context *pp_init_ctx(struct ibv_device *ib_dev, int size,
goto clean_comp_channel;
}
- if (!(attrx.odp_caps.general_caps & IBV_ODP_SUPPORT) ||
- (attrx.odp_caps.per_transport_caps.rc_odp_caps & rc_caps_mask) != rc_caps_mask) {
- fprintf(stderr, "The device isn't ODP capable or does not support RC send and receive with ODP\n");
- goto clean_comp_channel;
+ if (use_odp) {
+ if (!(attrx.odp_caps.general_caps & IBV_ODP_SUPPORT) ||
+ (attrx.odp_caps.per_transport_caps.rc_odp_caps & rc_caps_mask) != rc_caps_mask) {
+ fprintf(stderr, "The device isn't ODP capable or does not support RC send and receive with ODP\n");
+ goto clean_comp_channel;
+ }
+ access_flags |= IBV_ACCESS_ON_DEMAND;
+ }
+
+ if (use_ts) {
+ if (!attrx.completion_timestamp_mask) {
+ fprintf(stderr, "The device isn't completion timestamp capable\n");
+ goto clean_comp_channel;
+ }
+ ctx->completion_timestamp_mask = attrx.completion_timestamp_mask;
}
- access_flags |= IBV_ACCESS_ON_DEMAND;
}
ctx->mr = ibv_reg_mr(ctx->pd, ctx->buf, size, access_flags);
@@ -381,9 +410,22 @@ static struct pingpong_context *pp_init_ctx(struct ibv_device *ib_dev, int size,
goto clean_pd;
}
- ctx->cq = ibv_create_cq(ctx->context, rx_depth + 1, NULL,
- ctx->channel, 0);
- if (!ctx->cq) {
+ if (use_ts) {
+ struct ibv_cq_init_attr_ex attr_ex = {
+ .cqe = rx_depth + 1,
+ .cq_context = NULL,
+ .channel = ctx->channel,
+ .comp_vector = 0,
+ .wc_flags = IBV_WC_EX_WITH_COMPLETION_TIMESTAMP
+ };
+
+ ctx->cq_s.cq_ex = ibv_create_cq_ex(ctx->context, &attr_ex);
+ } else {
+ ctx->cq_s.cq = ibv_create_cq(ctx->context, rx_depth + 1, NULL,
+ ctx->channel, 0);
+ }
+
+ if (!pp_cq(ctx)) {
fprintf(stderr, "Couldn't create CQ\n");
goto clean_mr;
}
@@ -391,8 +433,8 @@ static struct pingpong_context *pp_init_ctx(struct ibv_device *ib_dev, int size,
{
struct ibv_qp_attr attr;
struct ibv_qp_init_attr init_attr = {
- .send_cq = ctx->cq,
- .recv_cq = ctx->cq,
+ .send_cq = pp_cq(ctx),
+ .recv_cq = pp_cq(ctx),
.cap = {
.max_send_wr = 1,
.max_recv_wr = rx_depth,
@@ -438,7 +480,7 @@ clean_qp:
ibv_destroy_qp(ctx->qp);
clean_cq:
- ibv_destroy_cq(ctx->cq);
+ ibv_destroy_cq(pp_cq(ctx));
clean_mr:
ibv_dereg_mr(ctx->mr);
@@ -469,7 +511,7 @@ int pp_close_ctx(struct pingpong_context *ctx)
return 1;
}
- if (ibv_destroy_cq(ctx->cq)) {
+ if (ibv_destroy_cq(pp_cq(ctx))) {
fprintf(stderr, "Couldn't destroy CQ\n");
return 1;
}
@@ -543,6 +585,89 @@ static int pp_post_send(struct pingpong_context *ctx)
return ibv_post_send(ctx->qp, &wr, &bad_wr);
}
+struct ts_params {
+ unsigned int comp_recv_max_time_delta;
+ unsigned int comp_recv_min_time_delta;
+ uint64_t comp_recv_total_time_delta;
+ uint64_t comp_recv_prev_time;
+ int last_comp_with_ts;
+ unsigned int comp_with_time_iters;
+};
+
+static inline int parse_single_wc(struct pingpong_context *ctx, int *scnt,
+ int *rcnt, int *routs, int iters,
+ uint64_t wr_id, enum ibv_wc_status status,
+ uint64_t completion_timestamp,
+ struct ts_params *ts)
+{
+ if (status != IBV_WC_SUCCESS) {
+ fprintf(stderr, "Failed status %s (%d) for wr_id %d\n",
+ ibv_wc_status_str(status),
+ status, (int)wr_id);
+ return 1;
+ }
+
+ switch ((int)wr_id) {
+ case PINGPONG_SEND_WRID:
+ ++(*scnt);
+ break;
+
+ case PINGPONG_RECV_WRID:
+ if (--(*routs) <= 1) {
+ *routs += pp_post_recv(ctx, ctx->rx_depth - *routs);
+ if (*routs < ctx->rx_depth) {
+ fprintf(stderr,
+ "Couldn't post receive (%d)\n",
+ *routs);
+ return 1;
+ }
+ }
+
+ ++(*rcnt);
+ if (use_ts) {
+ if (ts->last_comp_with_ts) {
+ uint64_t delta;
+
+ /* checking whether the clock was wrapped around */
+ if (completion_timestamp >= ts->comp_recv_prev_time)
+ delta = completion_timestamp - ts->comp_recv_prev_time;
+ else
+ delta = ctx->completion_timestamp_mask - ts->comp_recv_prev_time +
+ completion_timestamp + 1;
+
+ ts->comp_recv_max_time_delta = max(ts->comp_recv_max_time_delta, delta);
+ ts->comp_recv_min_time_delta = min(ts->comp_recv_min_time_delta, delta);
+ ts->comp_recv_total_time_delta += delta;
+ ts->comp_with_time_iters++;
+ }
+
+ ts->comp_recv_prev_time = completion_timestamp;
+ ts->last_comp_with_ts = 1;
+ } else {
+ ts->last_comp_with_ts = 0;
+ }
+
+ break;
+
+ default:
+ fprintf(stderr, "Completion for unknown wr_id %d\n",
+ (int)wr_id);
+ return 1;
+ }
+
+ ctx->pending &= ~(int)wr_id;
+ if (*scnt < iters && !ctx->pending) {
+ if (pp_post_send(ctx)) {
+ fprintf(stderr, "Couldn't post send\n");
+ return 1;
+ }
+ ctx->pending = PINGPONG_RECV_WRID |
+ PINGPONG_SEND_WRID;
+ }
+
+ return 0;
+}
+
static void usage(const char *argv0)
{
printf("Usage:\n");
@@ -561,6 +686,7 @@ static void usage(const char *argv0)
printf(" -e, --events sleep on CQ events (default poll)\n");
printf(" -g, --gid-idx=<gid index> local port gid index\n");
printf(" -o, --odp use on demand paging\n");
+ printf(" -t, --ts get CQE with timestamp\n");
}
int main(int argc, char *argv[])
@@ -586,6 +712,7 @@ int main(int argc, char *argv[])
int sl = 0;
int gidx = -1;
char gid[33];
+ struct ts_params ts;
srand48(getpid() * time(NULL));
@@ -604,11 +731,12 @@ int main(int argc, char *argv[])
{ .name = "events", .has_arg = 0, .val = 'e' },
{ .name = "gid-idx", .has_arg = 1, .val = 'g' },
{ .name = "odp", .has_arg = 0, .val = 'o' },
+ { .name = "ts", .has_arg = 0, .val = 't' },
{ 0 }
};
- c = getopt_long(argc, argv, "p:d:i:s:m:r:n:l:eg:o",
- long_options, NULL);
+ c = getopt_long(argc, argv, "p:d:i:s:m:r:n:l:eg:ot",
+ long_options, NULL);
if (c == -1)
break;
@@ -669,6 +797,9 @@ int main(int argc, char *argv[])
case 'o':
use_odp = 1;
break;
+ case 't':
+ use_ts = 1;
+ break;
default:
usage(argv[0]);
@@ -683,6 +814,15 @@ int main(int argc, char *argv[])
return 1;
}
+ if (use_ts) {
+ ts.comp_recv_max_time_delta = 0;
+ ts.comp_recv_min_time_delta = 0xffffffff;
+ ts.comp_recv_total_time_delta = 0;
+ ts.comp_recv_prev_time = 0;
+ ts.last_comp_with_ts = 0;
+ ts.comp_with_time_iters = 0;
+ }
+
page_size = sysconf(_SC_PAGESIZE);
dev_list = ibv_get_device_list(NULL);
@@ -720,7 +860,7 @@ int main(int argc, char *argv[])
}
if (use_event)
- if (ibv_req_notify_cq(ctx->cq, 0)) {
+ if (ibv_req_notify_cq(pp_cq(ctx), 0)) {
fprintf(stderr, "Couldn't request CQ notification\n");
return 1;
}
@@ -788,6 +928,8 @@ int main(int argc, char *argv[])
rcnt = scnt = 0;
while (rcnt < iters || scnt < iters) {
+ int ret;
+
if (use_event) {
struct ibv_cq *ev_cq;
void *ev_ctx;
@@ -799,72 +941,73 @@ int main(int argc, char *argv[])
++num_cq_events;
- if (ev_cq != ctx->cq) {
+ if (ev_cq != pp_cq(ctx)) {
fprintf(stderr, "CQ event for unknown CQ %p\n", ev_cq);
return 1;
}
- if (ibv_req_notify_cq(ctx->cq, 0)) {
+ if (ibv_req_notify_cq(pp_cq(ctx), 0)) {
fprintf(stderr, "Couldn't request CQ notification\n");
return 1;
}
}
- {
- struct ibv_wc wc[2];
+ if (use_ts) {
+ struct ibv_poll_cq_attr attr = {};
+
+ do {
+ ret = ibv_start_poll(ctx->cq_s.cq_ex, &attr);
+ } while (!use_event && ret == ENOENT);
+
+ if (ret) {
+ fprintf(stderr, "poll CQ failed %d\n", ret);
+ return ret;
+ }
+ ret = parse_single_wc(ctx, &scnt, &rcnt, &routs,
+ iters,
+ ctx->cq_s.cq_ex->wr_id,
+ ctx->cq_s.cq_ex->status,
+ ibv_wc_read_completion_ts(ctx->cq_s.cq_ex),
+ &ts);
+ if (ret) {
+ ibv_end_poll(ctx->cq_s.cq_ex);
+ return ret;
+ }
+ ret = ibv_next_poll(ctx->cq_s.cq_ex);
+ if (!ret)
+ ret = parse_single_wc(ctx, &scnt, &rcnt, &routs,
+ iters,
+ ctx->cq_s.cq_ex->wr_id,
+ ctx->cq_s.cq_ex->status,
+ ibv_wc_read_completion_ts(ctx->cq_s.cq_ex),
+ &ts);
+ ibv_end_poll(ctx->cq_s.cq_ex);
+ if (ret && ret != ENOENT) {
+ fprintf(stderr, "poll CQ failed %d\n", ret);
+ return ret;
+ }
+ } else {
int ne, i;
+ struct ibv_wc wc[2];
do {
- ne = ibv_poll_cq(ctx->cq, 2, wc);
+ ne = ibv_poll_cq(pp_cq(ctx), 2, wc);
if (ne < 0) {
fprintf(stderr, "poll CQ failed %d\n", ne);
return 1;
}
-
} while (!use_event && ne < 1);
for (i = 0; i < ne; ++i) {
- if (wc[i].status != IBV_WC_SUCCESS) {
- fprintf(stderr, "Failed status %s (%d) for wr_id %d\n",
- ibv_wc_status_str(wc[i].status),
- wc[i].status, (int) wc[i].wr_id);
+ ret = parse_single_wc(ctx, &scnt, &rcnt, &routs,
+ iters,
+ wc[i].wr_id,
+ wc[i].status,
+ 0, &ts);
+ if (ret) {
+ fprintf(stderr, "parse WC failed %d\n", ne);
return 1;
}
-
- switch ((int) wc[i].wr_id) {
- case PINGPONG_SEND_WRID:
- ++scnt;
- break;
-
- case PINGPONG_RECV_WRID:
- if (--routs <= 1) {
- routs += pp_post_recv(ctx, ctx->rx_depth - routs);
- if (routs < ctx->rx_depth) {
- fprintf(stderr,
- "Couldn't post receive (%d)\n",
- routs);
- return 1;
- }
- }
-
- ++rcnt;
- break;
-
- default:
- fprintf(stderr, "Completion for unknown wr_id %d\n",
- (int) wc[i].wr_id);
- return 1;
- }
-
- ctx->pending &= ~(int) wc[i].wr_id;
- if (scnt < iters && !ctx->pending) {
- if (pp_post_send(ctx)) {
- fprintf(stderr, "Couldn't post send\n");
- return 1;
- }
- ctx->pending = PINGPONG_RECV_WRID |
- PINGPONG_SEND_WRID;
- }
}
}
}
@@ -883,9 +1026,18 @@ int main(int argc, char *argv[])
bytes, usec / 1000000., bytes * 8. / usec);
printf("%d iters in %.2f seconds = %.2f usec/iter\n",
iters, usec / 1000000., usec / iters);
+
+ if (use_ts && ts.comp_with_time_iters) {
+ printf("Max receive completion clock cycles = %u\n",
+ ts.comp_recv_max_time_delta);
+ printf("Min receive completion clock cycles = %u\n",
+ ts.comp_recv_min_time_delta);
+ printf("Average receive completion clock cycles = %f\n",
+ (double)ts.comp_recv_total_time_delta / ts.comp_with_time_iters);
+ }
}
- ibv_ack_cq_events(ctx->cq, num_cq_events);
+ ibv_ack_cq_events(pp_cq(ctx), num_cq_events);
if (pp_close_ctx(ctx))
return 1;
diff --git a/examples/xsrq_pingpong.c b/examples/xsrq_pingpong.c
index 74205ec..70c5760 100644
--- a/examples/xsrq_pingpong.c
+++ b/examples/xsrq_pingpong.c
@@ -52,17 +52,18 @@
#include "pingpong.h"
-#define MSG_FORMAT "%04x:%06x:%06x:%06x:%04x"
-#define MSG_SIZE 31
-#define MSG_SSCAN "%x:%x:%x:%x:%x"
+#define MSG_FORMAT "%04x:%06x:%06x:%06x:%06x:%32s"
+#define MSG_SIZE 66
+#define MSG_SSCAN "%x:%x:%x:%x:%x:%s"
#define ADDR_FORMAT \
- "%8s: LID %04x, QPN RECV %06x SEND %06x, PSN %06x, SRQN %04x\n"
+ "%8s: LID %04x, QPN RECV %06x SEND %06x, PSN %06x, SRQN %06x, GID %s\n"
#define TERMINATION_FORMAT "%s"
#define TERMINATION_MSG_SIZE 4
#define TERMINATION_MSG "END"
static int page_size;
struct pingpong_dest {
+ union ibv_gid gid;
int lid;
int recv_qpn;
int send_qpn;
@@ -95,6 +96,7 @@ struct pingpong_context {
int num_clients;
int num_tests;
int use_event;
+ int gidx;
};
struct pingpong_context ctx;
@@ -201,6 +203,7 @@ static int pp_init_ctx(char *ib_devname)
{
struct ibv_srq_init_attr_ex attr;
struct ibv_xrcd_init_attr xrcd_attr;
+ struct ibv_port_attr port_attr;
ctx.recv_qp = calloc(ctx.num_clients, sizeof *ctx.recv_qp);
ctx.send_qp = calloc(ctx.num_clients, sizeof *ctx.send_qp);
@@ -213,9 +216,14 @@ static int pp_init_ctx(char *ib_devname)
return 1;
}
- ctx.lid = pp_get_local_lid(ctx.context, ctx.ib_port);
- if (ctx.lid < 0) {
- fprintf(stderr, "Failed to get SLID\n");
+ if (pp_get_port_info(ctx.context, ctx.ib_port, &port_attr)) {
+ fprintf(stderr, "Failed to get port info\n");
+ return 1;
+ }
+
+ ctx.lid = port_attr.lid;
+ if (port_attr.link_layer != IBV_LINK_LAYER_ETHERNET && !ctx.lid) {
+ fprintf(stderr, "Couldn't get local LID\n");
return 1;
}
@@ -378,7 +386,20 @@ static int pp_server_termination()
static int send_local_dest(int sockfd, int index)
{
char msg[MSG_SIZE];
+ char gid[33];
uint32_t srq_num;
+ union ibv_gid local_gid;
+
+ if (ctx.gidx >= 0) {
+ if (ibv_query_gid(ctx.context, ctx.ib_port, ctx.gidx,
+ &local_gid)) {
+ fprintf(stderr, "can't read sgid of index %d\n",
+ ctx.gidx);
+ return -1;
+ }
+ } else {
+ memset(&local_gid, 0, sizeof(local_gid));
+ }
ctx.rem_dest[index].recv_psn = lrand48() & 0xffffff;
if (ibv_get_srq_num(ctx.srq, &srq_num)) {
@@ -386,13 +407,15 @@ static int send_local_dest(int sockfd, int index)
return -1;
}
+ inet_ntop(AF_INET6, &local_gid, gid, sizeof(gid));
printf(ADDR_FORMAT, "local", ctx.lid, ctx.recv_qp[index]->qp_num,
ctx.send_qp[index]->qp_num, ctx.rem_dest[index].recv_psn,
- srq_num);
+ srq_num, gid);
+ gid_to_wire_gid(&local_gid, gid);
sprintf(msg, MSG_FORMAT, ctx.lid, ctx.recv_qp[index]->qp_num,
ctx.send_qp[index]->qp_num, ctx.rem_dest[index].recv_psn,
- srq_num);
+ srq_num, gid);
if (write(sockfd, msg, MSG_SIZE) != MSG_SIZE) {
fprintf(stderr, "Couldn't send local address\n");
@@ -406,6 +429,7 @@ static int recv_remote_dest(int sockfd, int index)
{
struct pingpong_dest *rem_dest;
char msg[MSG_SIZE];
+ char gid[33];
int n = 0, r;
while (n < MSG_SIZE) {
@@ -422,15 +446,27 @@ static int recv_remote_dest(int sockfd, int index)
rem_dest = &ctx.rem_dest[index];
sscanf(msg, MSG_SSCAN, &rem_dest->lid, &rem_dest->recv_qpn,
- &rem_dest->send_qpn, &rem_dest->send_psn, &rem_dest->srqn);
+ &rem_dest->send_qpn, &rem_dest->send_psn, &rem_dest->srqn, gid);
+ wire_gid_to_gid(gid, &rem_dest->gid);
+ inet_ntop(AF_INET6, &rem_dest->gid, gid, sizeof(gid));
printf(ADDR_FORMAT, "remote", rem_dest->lid, rem_dest->recv_qpn,
- rem_dest->send_qpn, rem_dest->send_psn, rem_dest->srqn);
+ rem_dest->send_qpn, rem_dest->send_psn, rem_dest->srqn,
+ gid);
rem_dest->sockfd = sockfd;
return 0;
}
+static void set_ah_attr(struct ibv_ah_attr *attr, struct pingpong_context *ctx,
+ int index)
+{
+ attr->is_global = 1;
+ attr->grh.hop_limit = 5;
+ attr->grh.dgid = ctx->rem_dest[index].gid;
+ attr->grh.sgid_index = ctx->gidx;
+}
+
static int connect_qps(int index)
{
struct ibv_qp_attr attr;
@@ -445,6 +481,9 @@ static int connect_qps(int index)
attr.ah_attr.sl = ctx.sl;
attr.ah_attr.port_num = ctx.ib_port;
+ if (ctx.rem_dest[index].gid.global.interface_id)
+ set_ah_attr(&attr.ah_attr, &ctx, index);
+
if (ibv_modify_qp(ctx.recv_qp[index], &attr,
IBV_QP_STATE | IBV_QP_AV | IBV_QP_PATH_MTU |
IBV_QP_DEST_QPN | IBV_QP_RQ_PSN |
@@ -473,6 +512,9 @@ static int connect_qps(int index)
attr.ah_attr.sl = ctx.sl;
attr.ah_attr.port_num = ctx.ib_port;
+ if (ctx.rem_dest[index].gid.global.interface_id)
+ set_ah_attr(&attr.ah_attr, &ctx, index);
+
if (ibv_modify_qp(ctx.send_qp[index], &attr,
IBV_QP_STATE | IBV_QP_AV | IBV_QP_PATH_MTU |
IBV_QP_DEST_QPN | IBV_QP_RQ_PSN)) {
@@ -787,6 +829,7 @@ static void init(void)
ctx.num_tests = 5;
ctx.mtu = IBV_MTU_2048;
ctx.sl = 0;
+ ctx.gidx = -1;
}
static void usage(const char *argv0)
@@ -805,6 +848,7 @@ static void usage(const char *argv0)
printf(" -n, --num_tests=<n> number of tests per client (default 5)\n");
printf(" -l, --sl=<sl> service level value\n");
printf(" -e, --events sleep on CQ events (default poll)\n");
+ printf(" -g, --gid-idx=<gid index> local port gid index\n");
}
int main(int argc, char *argv[])
@@ -830,10 +874,11 @@ int main(int argc, char *argv[])
{ .name = "num_tests", .has_arg = 1, .val = 'n' },
{ .name = "sl", .has_arg = 1, .val = 'l' },
{ .name = "events", .has_arg = 0, .val = 'e' },
+ { .name = "gid-idx", .has_arg = 1, .val = 'g' },
{ 0 }
};
- c = getopt_long(argc, argv, "p:d:i:s:m:c:n:l:e", long_options,
+ c = getopt_long(argc, argv, "p:d:i:s:m:c:n:l:eg:", long_options,
NULL);
if (c == -1)
break;
@@ -875,6 +920,9 @@ int main(int argc, char *argv[])
case 'l':
ctx.sl = strtol(optarg, NULL, 0);
break;
+ case 'g':
+ ctx.gidx = strtol(optarg, NULL, 0);
+ break;
case 'e':
ctx.use_event = 1;
break;
diff --git a/include/infiniband/arch.h b/include/infiniband/arch.h
index bc1738a..e35ecf0 100644
--- a/include/infiniband/arch.h
+++ b/include/infiniband/arch.h
@@ -122,15 +122,18 @@ static inline uint64_t ntohll(uint64_t x) { return x; }
#define wmb() mb() /* for s390x */
#define wc_wmb() wmb() /* for s390x */
-#else
-
-#warning No architecture specific defines found. Using generic implementation.
+#elif defined(__aarch64__)
-#define mb() asm volatile("" ::: "memory")
-#define rmb() mb()
-#define wmb() mb()
+/* Perhaps dmb would be sufficient? Let us be conservative for now. */
+#define mb() { asm volatile("dsb sy" ::: "memory"); }
+#define rmb() { asm volatile("dsb ld" ::: "memory"); }
+#define wmb() { asm volatile("dsb st" ::: "memory"); }
#define wc_wmb() wmb()
+#else
+
+#error No architecture specific memory barrier defines found!
+
#endif
#endif /* INFINIBAND_ARCH_H */
diff --git a/include/infiniband/driver.h b/include/infiniband/driver.h
index 8227df0..65fa44f 100644
--- a/include/infiniband/driver.h
+++ b/include/infiniband/driver.h
@@ -138,12 +138,32 @@ int ibv_cmd_reg_mr(struct ibv_pd *pd, void *addr, size_t length,
struct ibv_mr *mr, struct ibv_reg_mr *cmd,
size_t cmd_size,
struct ibv_reg_mr_resp *resp, size_t resp_size);
+int ibv_cmd_rereg_mr(struct ibv_mr *mr, uint32_t flags, void *addr,
+ size_t length, uint64_t hca_va, int access,
+ struct ibv_pd *pd, struct ibv_rereg_mr *cmd,
+ size_t cmd_sz, struct ibv_rereg_mr_resp *resp,
+ size_t resp_sz);
int ibv_cmd_dereg_mr(struct ibv_mr *mr);
+int ibv_cmd_alloc_mw(struct ibv_pd *pd, enum ibv_mw_type type,
+ struct ibv_mw *mw, struct ibv_alloc_mw *cmd,
+ size_t cmd_size,
+ struct ibv_alloc_mw_resp *resp, size_t resp_size);
+int ibv_cmd_dealloc_mw(struct ibv_mw *mw,
+ struct ibv_dealloc_mw *cmd, size_t cmd_size);
int ibv_cmd_create_cq(struct ibv_context *context, int cqe,
struct ibv_comp_channel *channel,
int comp_vector, struct ibv_cq *cq,
struct ibv_create_cq *cmd, size_t cmd_size,
struct ibv_create_cq_resp *resp, size_t resp_size);
+int ibv_cmd_create_cq_ex(struct ibv_context *context,
+ struct ibv_cq_init_attr_ex *cq_attr,
+ struct ibv_cq_ex *cq,
+ struct ibv_create_cq_ex *cmd,
+ size_t cmd_core_size,
+ size_t cmd_size,
+ struct ibv_create_cq_resp_ex *resp,
+ size_t resp_core_size,
+ size_t resp_size);
int ibv_cmd_poll_cq(struct ibv_cq *cq, int ne, struct ibv_wc *wc);
int ibv_cmd_req_notify_cq(struct ibv_cq *cq, int solicited_only);
#define IBV_CMD_RESIZE_CQ_HAS_RESP_PARAMS
@@ -179,6 +199,15 @@ int ibv_cmd_create_qp_ex(struct ibv_context *context,
struct ibv_qp_init_attr_ex *attr_ex,
struct ibv_create_qp *cmd, size_t cmd_size,
struct ibv_create_qp_resp *resp, size_t resp_size);
+int ibv_cmd_create_qp_ex2(struct ibv_context *context,
+ struct verbs_qp *qp, int vqp_sz,
+ struct ibv_qp_init_attr_ex *qp_attr,
+ struct ibv_create_qp_ex *cmd,
+ size_t cmd_core_size,
+ size_t cmd_size,
+ struct ibv_create_qp_resp_ex *resp,
+ size_t resp_core_size,
+ size_t resp_size);
int ibv_cmd_open_qp(struct ibv_context *context,
struct verbs_qp *qp, int vqp_sz,
struct ibv_qp_open_attr *attr,
diff --git a/include/infiniband/kern-abi.h b/include/infiniband/kern-abi.h
index 800c5ab..f70fa44 100644
--- a/include/infiniband/kern-abi.h
+++ b/include/infiniband/kern-abi.h
@@ -110,6 +110,10 @@ enum {
enum {
IB_USER_VERBS_CMD_QUERY_DEVICE_EX = IB_USER_VERBS_CMD_EXTENDED_MASK |
IB_USER_VERBS_CMD_QUERY_DEVICE,
+ IB_USER_VERBS_CMD_CREATE_QP_EX = IB_USER_VERBS_CMD_EXTENDED_MASK |
+ IB_USER_VERBS_CMD_CREATE_QP,
+ IB_USER_VERBS_CMD_CREATE_CQ_EX = IB_USER_VERBS_CMD_EXTENDED_MASK |
+ IB_USER_VERBS_CMD_CREATE_CQ,
IB_USER_VERBS_CMD_CREATE_FLOW = IB_USER_VERBS_CMD_EXTENDED_MASK +
IB_USER_VERBS_CMD_THRESHOLD,
IB_USER_VERBS_CMD_DESTROY_FLOW
@@ -267,6 +271,9 @@ struct ibv_query_device_resp_ex {
__u32 comp_mask;
__u32 response_length;
struct ibv_odp_caps_resp odp_caps;
+ __u64 timestamp_mask;
+ __u64 hca_core_clock;
+ __u64 device_cap_flags_ex;
};
struct ibv_query_port {
@@ -362,6 +369,26 @@ struct ibv_reg_mr_resp {
__u32 rkey;
};
+struct ibv_rereg_mr {
+ __u32 command;
+ __u16 in_words;
+ __u16 out_words;
+ __u64 response;
+ __u32 mr_handle;
+ __u32 flags;
+ __u64 start;
+ __u64 length;
+ __u64 hca_va;
+ __u32 pd_handle;
+ __u32 access_flags;
+ __u64 driver_data[0];
+};
+
+struct ibv_rereg_mr_resp {
+ __u32 lkey;
+ __u32 rkey;
+};
+
struct ibv_dereg_mr {
__u32 command;
__u16 in_words;
@@ -369,6 +396,29 @@ struct ibv_dereg_mr {
__u32 mr_handle;
};
+struct ibv_alloc_mw {
+ __u32 command;
+ __u16 in_words;
+ __u16 out_words;
+ __u64 response;
+ __u32 pd_handle;
+ __u8 mw_type;
+ __u8 reserved[3];
+};
+
+struct ibv_alloc_mw_resp {
+ __u32 mw_handle;
+ __u32 rkey;
+};
+
+struct ibv_dealloc_mw {
+ __u32 command;
+ __u16 in_words;
+ __u16 out_words;
+ __u32 mw_handle;
+ __u32 reserved;
+};
+
struct ibv_create_comp_channel {
__u32 command;
__u16 in_words;
@@ -398,6 +448,27 @@ struct ibv_create_cq_resp {
__u32 cqe;
};
+enum ibv_create_cq_ex_kernel_flags {
+ IBV_CREATE_CQ_EX_KERNEL_FLAG_COMPLETION_TIMESTAMP = 1 << 0,
+};
+
+struct ibv_create_cq_ex {
+ struct ex_hdr hdr;
+ __u64 user_handle;
+ __u32 cqe;
+ __u32 comp_vector;
+ __s32 comp_channel;
+ __u32 comp_mask;
+ __u32 flags;
+ __u32 reserved;
+};
+
+struct ibv_create_cq_resp_ex {
+ struct ibv_create_cq_resp base;
+ __u32 comp_mask;
+ __u32 response_length;
+};
+
struct ibv_kern_wc {
__u64 wr_id;
__u32 status;
@@ -527,28 +598,35 @@ struct ibv_kern_qp_attr {
__u8 reserved[5];
};
+#define IBV_CREATE_QP_COMMON \
+ __u64 user_handle; \
+ __u32 pd_handle; \
+ __u32 send_cq_handle; \
+ __u32 recv_cq_handle; \
+ __u32 srq_handle; \
+ __u32 max_send_wr; \
+ __u32 max_recv_wr; \
+ __u32 max_send_sge; \
+ __u32 max_recv_sge; \
+ __u32 max_inline_data; \
+ __u8 sq_sig_all; \
+ __u8 qp_type; \
+ __u8 is_srq; \
+ __u8 reserved
+
struct ibv_create_qp {
__u32 command;
__u16 in_words;
__u16 out_words;
__u64 response;
- __u64 user_handle;
- __u32 pd_handle;
- __u32 send_cq_handle;
- __u32 recv_cq_handle;
- __u32 srq_handle;
- __u32 max_send_wr;
- __u32 max_recv_wr;
- __u32 max_send_sge;
- __u32 max_recv_sge;
- __u32 max_inline_data;
- __u8 sq_sig_all;
- __u8 qp_type;
- __u8 is_srq;
- __u8 reserved;
+ IBV_CREATE_QP_COMMON;
__u64 driver_data[0];
};
+struct ibv_create_qp_common {
+ IBV_CREATE_QP_COMMON;
+};
+
struct ibv_open_qp {
__u32 command;
__u16 in_words;
@@ -574,6 +652,19 @@ struct ibv_create_qp_resp {
__u32 reserved;
};
+struct ibv_create_qp_ex {
+ struct ex_hdr hdr;
+ struct ibv_create_qp_common base;
+ __u32 comp_mask;
+ __u32 create_flags;
+};
+
+struct ibv_create_qp_resp_ex {
+ struct ibv_create_qp_resp base;
+ __u32 comp_mask;
+ __u32 response_length;
+};
+
struct ibv_qp_dest {
__u8 dgid[16];
__u32 flow_label;
@@ -1031,7 +1122,9 @@ enum {
IB_USER_VERBS_CMD_OPEN_QP_V2 = -1,
IB_USER_VERBS_CMD_CREATE_FLOW_V2 = -1,
IB_USER_VERBS_CMD_DESTROY_FLOW_V2 = -1,
- IB_USER_VERBS_CMD_QUERY_DEVICE_EX_V2 = -1
+ IB_USER_VERBS_CMD_QUERY_DEVICE_EX_V2 = -1,
+ IB_USER_VERBS_CMD_CREATE_QP_EX_V2 = -1,
+ IB_USER_VERBS_CMD_CREATE_CQ_EX_V2 = -1,
};
struct ibv_modify_srq_v3 {
diff --git a/include/infiniband/verbs.h b/include/infiniband/verbs.h
index ae22768..ccf1d51 100644
--- a/include/infiniband/verbs.h
+++ b/include/infiniband/verbs.h
@@ -116,13 +116,23 @@ enum ibv_device_cap_flags {
IBV_DEVICE_RC_RNR_NAK_GEN = 1 << 12,
IBV_DEVICE_SRQ_RESIZE = 1 << 13,
IBV_DEVICE_N_NOTIFY_CQ = 1 << 14,
+ IBV_DEVICE_MEM_WINDOW = 1 << 17,
IBV_DEVICE_UD_IP_CSUM = 1 << 18,
IBV_DEVICE_XRC = 1 << 20,
+ IBV_DEVICE_MEM_MGT_EXTENSIONS = 1 << 21,
+ IBV_DEVICE_MEM_WINDOW_TYPE_2A = 1 << 23,
+ IBV_DEVICE_MEM_WINDOW_TYPE_2B = 1 << 24,
IBV_DEVICE_RC_IP_CSUM = 1 << 25,
IBV_DEVICE_RAW_IP_CSUM = 1 << 26,
IBV_DEVICE_MANAGED_FLOW_STEERING = 1 << 29
};
+/*
+ * Can't extended above ibv_device_cap_flags enum as in some systems/compilers
+ * enum range is limited to 4 bytes.
+ */
+#define IBV_DEVICE_RAW_SCATTER_FCS (1ULL << 34)
+
enum ibv_atomic_cap {
IBV_ATOMIC_NONE,
IBV_ATOMIC_HCA,
@@ -203,6 +213,9 @@ struct ibv_device_attr_ex {
struct ibv_device_attr orig_attr;
uint32_t comp_mask;
struct ibv_odp_caps odp_caps;
+ uint64_t completion_timestamp_mask;
+ uint64_t hca_core_clock;
+ uint64_t device_cap_flags_ex;
};
enum ibv_mtu {
@@ -343,6 +356,7 @@ enum ibv_wc_opcode {
IBV_WC_COMP_SWAP,
IBV_WC_FETCH_ADD,
IBV_WC_BIND_MW,
+ IBV_WC_LOCAL_INV,
/*
* Set value of IBV_WC_RECV so consumers can test if a completion is a
* receive by testing (opcode & IBV_WC_RECV).
@@ -355,10 +369,37 @@ enum {
IBV_WC_IP_CSUM_OK_SHIFT = 2
};
+enum ibv_create_cq_wc_flags {
+ IBV_WC_EX_WITH_BYTE_LEN = 1 << 0,
+ IBV_WC_EX_WITH_IMM = 1 << 1,
+ IBV_WC_EX_WITH_QP_NUM = 1 << 2,
+ IBV_WC_EX_WITH_SRC_QP = 1 << 3,
+ IBV_WC_EX_WITH_SLID = 1 << 4,
+ IBV_WC_EX_WITH_SL = 1 << 5,
+ IBV_WC_EX_WITH_DLID_PATH_BITS = 1 << 6,
+ IBV_WC_EX_WITH_COMPLETION_TIMESTAMP = 1 << 7,
+};
+
+enum {
+ IBV_WC_STANDARD_FLAGS = IBV_WC_EX_WITH_BYTE_LEN |
+ IBV_WC_EX_WITH_IMM |
+ IBV_WC_EX_WITH_QP_NUM |
+ IBV_WC_EX_WITH_SRC_QP |
+ IBV_WC_EX_WITH_SLID |
+ IBV_WC_EX_WITH_SL |
+ IBV_WC_EX_WITH_DLID_PATH_BITS
+};
+
+enum {
+ IBV_CREATE_CQ_SUP_WC_FLAGS = IBV_WC_STANDARD_FLAGS |
+ IBV_WC_EX_WITH_COMPLETION_TIMESTAMP
+};
+
enum ibv_wc_flags {
IBV_WC_GRH = 1 << 0,
IBV_WC_WITH_IMM = 1 << 1,
- IBV_WC_IP_CSUM_OK = 1 << IBV_WC_IP_CSUM_OK_SHIFT
+ IBV_WC_IP_CSUM_OK = 1 << IBV_WC_IP_CSUM_OK_SHIFT,
+ IBV_WC_WITH_INV = 1 << 3
};
struct ibv_wc {
@@ -367,7 +408,10 @@ struct ibv_wc {
enum ibv_wc_opcode opcode;
uint32_t vendor_err;
uint32_t byte_len;
- uint32_t imm_data; /* in network byte order */
+ /* When (wc_flags & IBV_WC_WITH_IMM): Immediate data in network byte order.
+ * When (wc_flags & IBV_WC_WITH_INV): Stores the invalidated rkey.
+ */
+ uint32_t imm_data;
uint32_t qp_num;
uint32_t src_qp;
int wc_flags;
@@ -383,9 +427,17 @@ enum ibv_access_flags {
IBV_ACCESS_REMOTE_READ = (1<<2),
IBV_ACCESS_REMOTE_ATOMIC = (1<<3),
IBV_ACCESS_MW_BIND = (1<<4),
+ IBV_ACCESS_ZERO_BASED = (1<<5),
IBV_ACCESS_ON_DEMAND = (1<<6),
};
+struct ibv_mw_bind_info {
+ struct ibv_mr *mr;
+ uint64_t addr;
+ uint64_t length;
+ int mw_access_flags; /* use ibv_access_flags */
+};
+
struct ibv_pd {
struct ibv_context *context;
uint32_t handle;
@@ -411,7 +463,8 @@ enum ibv_rereg_mr_flags {
IBV_REREG_MR_CHANGE_TRANSLATION = (1 << 0),
IBV_REREG_MR_CHANGE_PD = (1 << 1),
IBV_REREG_MR_CHANGE_ACCESS = (1 << 2),
- IBV_REREG_MR_KEEP_VALID = (1 << 3)
+ IBV_REREG_MR_KEEP_VALID = (1 << 3),
+ IBV_REREG_MR_FLAGS_SUPPORTED = ((IBV_REREG_MR_KEEP_VALID << 1) - 1)
};
struct ibv_mr {
@@ -433,6 +486,8 @@ struct ibv_mw {
struct ibv_context *context;
struct ibv_pd *pd;
uint32_t rkey;
+ uint32_t handle;
+ enum ibv_mw_type type;
};
struct ibv_global_route {
@@ -580,7 +635,13 @@ struct ibv_qp_init_attr {
enum ibv_qp_init_attr_mask {
IBV_QP_INIT_ATTR_PD = 1 << 0,
IBV_QP_INIT_ATTR_XRCD = 1 << 1,
- IBV_QP_INIT_ATTR_RESERVED = 1 << 2
+ IBV_QP_INIT_ATTR_CREATE_FLAGS = 1 << 2,
+ IBV_QP_INIT_ATTR_RESERVED = 1 << 3
+};
+
+enum ibv_qp_create_flags {
+ IBV_QP_CREATE_BLOCK_SELF_MCAST_LB = 1 << 1,
+ IBV_QP_CREATE_SCATTER_FCS = 1 << 8,
};
struct ibv_qp_init_attr_ex {
@@ -595,6 +656,8 @@ struct ibv_qp_init_attr_ex {
uint32_t comp_mask;
struct ibv_pd *pd;
struct ibv_xrcd *xrcd;
+ uint32_t create_flags;
+
};
enum ibv_qp_open_attr_mask {
@@ -689,7 +752,10 @@ enum ibv_wr_opcode {
IBV_WR_SEND_WITH_IMM,
IBV_WR_RDMA_READ,
IBV_WR_ATOMIC_CMP_AND_SWP,
- IBV_WR_ATOMIC_FETCH_AND_ADD
+ IBV_WR_ATOMIC_FETCH_AND_ADD,
+ IBV_WR_LOCAL_INV,
+ IBV_WR_BIND_MW,
+ IBV_WR_SEND_WITH_INV,
};
enum ibv_send_flags {
@@ -736,6 +802,12 @@ struct ibv_send_wr {
uint32_t remote_srqn;
} xrc;
} qp_type;
+ struct {
+ struct ibv_mw *mw;
+ uint32_t rkey;
+ struct ibv_mw_bind_info bind_info;
+ } bind_mw;
+
};
struct ibv_recv_wr {
@@ -747,11 +819,8 @@ struct ibv_recv_wr {
struct ibv_mw_bind {
uint64_t wr_id;
- struct ibv_mr *mr;
- void *addr;
- size_t length;
int send_flags;
- int mw_access_flags;
+ struct ibv_mw_bind_info bind_info;
};
struct ibv_srq {
@@ -801,6 +870,118 @@ struct ibv_cq {
uint32_t async_events_completed;
};
+struct ibv_poll_cq_attr {
+ uint32_t comp_mask;
+};
+
+struct ibv_cq_ex {
+ struct ibv_context *context;
+ struct ibv_comp_channel *channel;
+ void *cq_context;
+ uint32_t handle;
+ int cqe;
+
+ pthread_mutex_t mutex;
+ pthread_cond_t cond;
+ uint32_t comp_events_completed;
+ uint32_t async_events_completed;
+
+ uint32_t comp_mask;
+ enum ibv_wc_status status;
+ uint64_t wr_id;
+ int (*start_poll)(struct ibv_cq_ex *current,
+ struct ibv_poll_cq_attr *attr);
+ int (*next_poll)(struct ibv_cq_ex *current);
+ void (*end_poll)(struct ibv_cq_ex *current);
+ enum ibv_wc_opcode (*read_opcode)(struct ibv_cq_ex *current);
+ uint32_t (*read_vendor_err)(struct ibv_cq_ex *current);
+ uint32_t (*read_byte_len)(struct ibv_cq_ex *current);
+ uint32_t (*read_imm_data)(struct ibv_cq_ex *current);
+ uint32_t (*read_qp_num)(struct ibv_cq_ex *current);
+ uint32_t (*read_src_qp)(struct ibv_cq_ex *current);
+ int (*read_wc_flags)(struct ibv_cq_ex *current);
+ uint32_t (*read_slid)(struct ibv_cq_ex *current);
+ uint8_t (*read_sl)(struct ibv_cq_ex *current);
+ uint8_t (*read_dlid_path_bits)(struct ibv_cq_ex *current);
+ uint64_t (*read_completion_ts)(struct ibv_cq_ex *current);
+};
+
+static inline struct ibv_cq *ibv_cq_ex_to_cq(struct ibv_cq_ex *cq)
+{
+ return (struct ibv_cq *)cq;
+}
+
+static inline int ibv_start_poll(struct ibv_cq_ex *cq,
+ struct ibv_poll_cq_attr *attr)
+{
+ return cq->start_poll(cq, attr);
+}
+
+static inline int ibv_next_poll(struct ibv_cq_ex *cq)
+{
+ return cq->next_poll(cq);
+}
+
+static inline void ibv_end_poll(struct ibv_cq_ex *cq)
+{
+ cq->end_poll(cq);
+}
+
+static inline enum ibv_wc_opcode ibv_wc_read_opcode(struct ibv_cq_ex *cq)
+{
+ return cq->read_opcode(cq);
+}
+
+static inline uint32_t ibv_wc_read_vendor_err(struct ibv_cq_ex *cq)
+{
+ return cq->read_vendor_err(cq);
+}
+
+static inline uint32_t ibv_wc_read_byte_len(struct ibv_cq_ex *cq)
+{
+ return cq->read_byte_len(cq);
+}
+
+static inline uint32_t ibv_wc_read_imm_data(struct ibv_cq_ex *cq)
+{
+ return cq->read_imm_data(cq);
+}
+
+static inline uint32_t ibv_wc_read_qp_num(struct ibv_cq_ex *cq)
+{
+ return cq->read_qp_num(cq);
+}
+
+static inline uint32_t ibv_wc_read_src_qp(struct ibv_cq_ex *cq)
+{
+ return cq->read_src_qp(cq);
+}
+
+static inline int ibv_wc_read_wc_flags(struct ibv_cq_ex *cq)
+{
+ return cq->read_wc_flags(cq);
+}
+
+static inline uint32_t ibv_wc_read_slid(struct ibv_cq_ex *cq)
+{
+ return cq->read_slid(cq);
+}
+
+static inline uint8_t ibv_wc_read_sl(struct ibv_cq_ex *cq)
+{
+ return cq->read_sl(cq);
+}
+
+static inline uint8_t ibv_wc_read_dlid_path_bits(struct ibv_cq_ex *cq)
+{
+ return cq->read_dlid_path_bits(cq);
+}
+
+static inline uint64_t ibv_wc_read_completion_ts(struct ibv_cq_ex *cq)
+{
+ return cq->read_completion_ts(cq);
+}
+
struct ibv_ah {
struct ibv_context *context;
struct ibv_pd *pd;
@@ -808,7 +989,8 @@ struct ibv_ah {
};
enum ibv_flow_flags {
- IBV_FLOW_ATTR_FLAGS_ALLOW_LOOP_BACK = 1,
+ IBV_FLOW_ATTR_FLAGS_ALLOW_LOOP_BACK = 1 << 0,
+ IBV_FLOW_ATTR_FLAGS_DONT_TRAP = 1 << 1,
};
enum ibv_flow_attr_type {
@@ -951,7 +1133,7 @@ struct ibv_context_ops {
int (*dealloc_pd)(struct ibv_pd *pd);
struct ibv_mr * (*reg_mr)(struct ibv_pd *pd, void *addr, size_t length,
int access);
- struct ibv_mr * (*rereg_mr)(struct ibv_mr *mr,
+ int (*rereg_mr)(struct ibv_mr *mr,
int flags,
struct ibv_pd *pd, void *addr,
size_t length,
@@ -1010,6 +1192,51 @@ struct ibv_context {
void *abi_compat;
};
+enum ibv_cq_init_attr_mask {
+ IBV_CQ_INIT_ATTR_MASK_FLAGS = 1 << 0,
+ IBV_CQ_INIT_ATTR_MASK_RESERVED = 1 << 1
+};
+
+enum ibv_create_cq_attr_flags {
+ IBV_CREATE_CQ_ATTR_SINGLE_THREADED = 1 << 0,
+ IBV_CREATE_CQ_ATTR_RESERVED = 1 << 1,
+};
+
+struct ibv_cq_init_attr_ex {
+ /* Minimum number of entries required for CQ */
+ uint32_t cqe;
+ /* Consumer-supplied context returned for completion events */
+ void *cq_context;
+ /* Completion channel where completion events will be queued.
+ * May be NULL if completion events will not be used.
+ */
+ struct ibv_comp_channel *channel;
+ /* Completion vector used to signal completion events.
+ * Must be < context->num_comp_vectors.
+ */
+ uint32_t comp_vector;
+ /* Or'ed bit of enum ibv_create_cq_wc_flags. */
+ uint64_t wc_flags;
+ /* compatibility mask (extended verb). Or'd flags of
+ * enum ibv_cq_init_attr_mask
+ */
+ uint32_t comp_mask;
+ /* create cq attr flags - one or more flags from
+ * enum ibv_create_cq_attr_flags
+ */
+ uint32_t flags;
+};
+
+enum ibv_values_mask {
+ IBV_VALUES_MASK_RAW_CLOCK = 1 << 0,
+ IBV_VALUES_MASK_RESERVED = 1 << 1
+};
+
+struct ibv_values_ex {
+ uint32_t comp_mask;
+ struct timespec raw_clock;
+};
+
enum verbs_context_mask {
VERBS_CONTEXT_XRCD = 1 << 0,
VERBS_CONTEXT_SRQ = 1 << 1,
@@ -1021,6 +1248,11 @@ enum verbs_context_mask {
struct verbs_context {
/* "grows up" - new fields go here */
+ int (*query_rt_values)(struct ibv_context *context,
+ struct ibv_values_ex *values);
+ struct ibv_cq_ex *(*create_cq_ex)(struct ibv_context *context,
+ struct ibv_cq_init_attr_ex *init_attr);
+ struct verbs_ex_private *priv;
int (*query_device_ex)(struct ibv_context *context,
const struct ibv_query_device_ex_input *input,
struct ibv_device_attr_ex *attr,
@@ -1227,12 +1459,80 @@ static inline int ibv_close_xrcd(struct ibv_xrcd *xrcd)
struct ibv_mr *ibv_reg_mr(struct ibv_pd *pd, void *addr,
size_t length, int access);
+
+enum ibv_rereg_mr_err_code {
+ /* Old MR is valid, invalid input */
+ IBV_REREG_MR_ERR_INPUT = -1,
+ /* Old MR is valid, failed via dont fork on new address range */
+ IBV_REREG_MR_ERR_DONT_FORK_NEW = -2,
+ /* New MR is valid, failed via do fork on old address range */
+ IBV_REREG_MR_ERR_DO_FORK_OLD = -3,
+ /* MR shouldn't be used, command error */
+ IBV_REREG_MR_ERR_CMD = -4,
+ /* MR shouldn't be used, command error, invalid fork state on new address range */
+ IBV_REREG_MR_ERR_CMD_AND_DO_FORK_NEW = -5,
+};
+
+/**
+ * ibv_rereg_mr - Re-Register a memory region
+ */
+int ibv_rereg_mr(struct ibv_mr *mr, int flags,
+ struct ibv_pd *pd, void *addr,
+ size_t length, int access);
/**
* ibv_dereg_mr - Deregister a memory region
*/
int ibv_dereg_mr(struct ibv_mr *mr);
/**
+ * ibv_alloc_mw - Allocate a memory window
+ */
+static inline struct ibv_mw *ibv_alloc_mw(struct ibv_pd *pd,
+ enum ibv_mw_type type)
+{
+ struct ibv_mw *mw;
+
+ if (!pd->context->ops.alloc_mw) {
+ errno = ENOSYS;
+ return NULL;
+ }
+
+ mw = pd->context->ops.alloc_mw(pd, type);
+ return mw;
+}
+
+/**
+ * ibv_dealloc_mw - Free a memory window
+ */
+static inline int ibv_dealloc_mw(struct ibv_mw *mw)
+{
+ return mw->context->ops.dealloc_mw(mw);
+}
+
+/**
+ * ibv_inc_rkey - Increase the 8 lsb in the given rkey
+ */
+static inline uint32_t ibv_inc_rkey(uint32_t rkey)
+{
+ const uint32_t mask = 0x000000ff;
+ uint8_t newtag = (uint8_t)((rkey + 1) & mask);
+
+ return (rkey & ~mask) | newtag;
+}
+
+/**
+ * ibv_bind_mw - Bind a memory window to a region
+ */
+static inline int ibv_bind_mw(struct ibv_qp *qp, struct ibv_mw *mw,
+ struct ibv_mw_bind *mw_bind)
+{
+ if (mw->type != IBV_MW_TYPE_1)
+ return EINVAL;
+
+ return mw->context->ops.bind_mw(qp, mw, mw_bind);
+}
+
+/**
* ibv_create_comp_channel - Create a completion event channel
*/
struct ibv_comp_channel *ibv_create_comp_channel(struct ibv_context *context);
@@ -1258,6 +1558,30 @@ struct ibv_cq *ibv_create_cq(struct ibv_context *context, int cqe,
int comp_vector);
/**
+ * ibv_create_cq_ex - Create a completion queue
+ * @context - Context CQ will be attached to
+ * @cq_attr - Attributes to create the CQ with
+ */
+static inline
+struct ibv_cq_ex *ibv_create_cq_ex(struct ibv_context *context,
+ struct ibv_cq_init_attr_ex *cq_attr)
+{
+ struct verbs_context *vctx = verbs_get_ctx_op(context, create_cq_ex);
+
+ if (!vctx) {
+ errno = ENOSYS;
+ return NULL;
+ }
+
+ if (cq_attr->comp_mask & ~(IBV_CQ_INIT_ATTR_MASK_RESERVED - 1)) {
+ errno = EINVAL;
+ return NULL;
+ }
+
+ return vctx->create_cq_ex(context, cq_attr);
+}
+
+/**
* ibv_resize_cq - Modifies the capacity of the CQ.
* @cq: The CQ to resize.
* @cqe: The minimum size of the CQ.
@@ -1445,6 +1769,27 @@ ibv_create_qp_ex(struct ibv_context *context, struct ibv_qp_init_attr_ex *qp_ini
}
/**
+ * ibv_query_rt_values_ex - Get current real time @values of a device.
+ * @values - in/out - defines the attributes we need to query/queried.
+ * (Or's bits of enum ibv_values_mask on values->comp_mask field)
+ */
+static inline int
+ibv_query_rt_values_ex(struct ibv_context *context,
+ struct ibv_values_ex *values)
+{
+ struct verbs_context *vctx;
+
+ vctx = verbs_get_ctx_op(context, query_rt_values);
+ if (!vctx)
+ return ENOSYS;
+
+ if (values->comp_mask & ~(IBV_VALUES_MASK_RESERVED - 1))
+ return EINVAL;
+
+ return vctx->query_rt_values(context, values);
+}
+
+/**
* ibv_query_device_ex - Get extended device properties
*/
static inline int
diff --git a/libibverbs.spec b/libibverbs.spec
index b555c71..387c3f1 100644
--- a/libibverbs.spec
+++ b/libibverbs.spec
@@ -1,12 +1,12 @@
Name: libibverbs
-Version: 1.2.0
+Version: 1.2.1
Release: 1%{?dist}
Summary: A library for direct userspace use of RDMA (InfiniBand/iWARP) hardware
Group: System Environment/Libraries
License: GPLv2 or BSD
Url: http://openfabrics.org/
-Source: http://openfabrics.org/downloads/verbs/libibverbs-1.2.0.tar.gz
+Source: http://openfabrics.org/downloads/verbs/libibverbs-1.2.1.tar.gz
BuildRoot: %(mktemp -ud %{_tmppath}/%{name}-%{version}-%{release}-XXXXXX)
Requires(post): /sbin/ldconfig
Requires(postun): /sbin/ldconfig
@@ -46,7 +46,7 @@ Useful libibverbs1 example programs such as ibv_devinfo, which
displays information about RDMA devices.
%prep
-%setup -q -n %{name}-1.2.0
+%setup -q -n %{name}-1.2.1
%build
%configure
@@ -85,6 +85,9 @@ rm -rf $RPM_BUILD_ROOT
%{_mandir}/man1/*
%changelog
+* Tue Jul 19 2016 Doug Ledford <dledford at redhat.com> - 1.2.1-1
+- New upstream release
+
* Fri Feb 26 2016 Doug Ledford <dledford at redhat.com> - 1.2.0-1
- New upstream release
diff --git a/libibverbs.spec.in b/libibverbs.spec.in
index d3200bd..040948e 100644
--- a/libibverbs.spec.in
+++ b/libibverbs.spec.in
@@ -85,7 +85,10 @@ rm -rf $RPM_BUILD_ROOT
%{_mandir}/man1/*
%changelog
-* Fri Feb 26 2016 Doug Ledford <dledford at redhat.com> - @VERSION at -1
+* Tue Jul 19 2016 Doug Ledford <dledford at redhat.com> - @VERSION at -1
+- New upstream release
+
+* Fri Feb 26 2016 Doug Ledford <dledford at redhat.com> - 1.2.0-1
- New upstream release
* Tue May 5 2014 Roland Dreier <roland at digitalvampire.org> - 1.1.8-1
diff --git a/man/ibv_alloc_mw.3 b/man/ibv_alloc_mw.3
new file mode 100644
index 0000000..366cefb
--- /dev/null
+++ b/man/ibv_alloc_mw.3
@@ -0,0 +1,54 @@
+.\" -*- nroff -*-
+.\"
+.TH IBV_ALLOC_MW 3 2016-02-02 libibverbs "Libibverbs Programmer's Manual"
+.SH "NAME"
+ibv_alloc_mw, ibv_dealloc_mw \- allocate or deallocate a memory window (MW)
+.SH "SYNOPSIS"
+.nf
+.B #include <infiniband/verbs.h>
+.sp
+.BI "struct ibv_mw *ibv_alloc_mw(struct ibv_pd " "*pd" ,
+.BI " enum ibv_mw_type " "type");
+.sp
+.BI "int ibv_dealloc_mw(struct ibv_mw " "*mw" );
+.fi
+.SH "DESCRIPTION"
+.B ibv_alloc_mw()
+allocates a memory window (MW) associated with the protection domain
+.I pd\fR.
+The MW's type (1 or 2A/2B) is
+.I type\fR.
+.PP
+The MW is created not bound. For it to be useful, the MW must be bound, through either ibv_bind_mw (type 1) or a special WR (type 2).
+Once bound, the memory window allows RDMA (remote) access to a subset of the MR to which it was bound,
+until invalidated by: ibv_bind_mw verb with zero length for type 1,
+IBV_WR_LOCAL_INV/IBV_WR_SEND_WITH_INV WR opcode for type 2, deallocation.
+.PP
+.B ibv_dealloc_mw()
+Unbinds in case was previously bound and deallocates the MW
+.I mw\fR.
+.SH "RETURN VALUE"
+.B ibv_alloc_mw()
+returns a pointer to the allocated MW, or NULL if the request fails.
+The remote key (\fBR_Key\fR)
+field
+.B rkey
+is used by remote processes to perform Atomic and RDMA operations. This key will be changed during bind operations. The remote process places this
+.B rkey
+as the rkey field of struct ibv_send_wr passed to the ibv_post_send function.
+.PP
+.B ibv_dealloc_mw()
+returns 0 on success, or the value of errno on failure (which indicates the failure reason).
+.SH "NOTES"
+.B ibv_dereg_mr()
+fails if any memory window is still bound to this MR.
+.SH "SEE ALSO"
+.BR ibv_alloc_pd (3),
+.BR ibv_post_send (3),
+.BR ibv_bind_mw (3),
+.BR ibv_reg_mr (3),
+.SH "AUTHORS"
+.TP
+Majd Dibbiny <majd at mellanox.com>
+.TP
+Yishai Hadas <yishaih at mellanox.com>
diff --git a/man/ibv_asyncwatch.1 b/man/ibv_asyncwatch.1
index ece25f8..09f9f65 100644
--- a/man/ibv_asyncwatch.1
+++ b/man/ibv_asyncwatch.1
@@ -5,12 +5,26 @@ ibv_asyncwatch \- display asynchronous events
.SH SYNOPSIS
.B ibv_asyncwatch
+[\-d device] [-h]
.SH DESCRIPTION
.PP
Display asynchronous events forwarded to userspace for an RDMA device.
+.SH OPTIONS
+
+.PP
+.TP
+\fB\-d\fR, \fB\-\-ib\-dev\fR=\fIDEVICE\fR
+use IB device \fIDEVICE\fR (default first device found)
+.TP
+\fB\-h\fR, \fB\-\-help\fR=\fIDEVICE\fR
+Print a help text and exit.
+
.SH AUTHORS
.TP
Roland Dreier
.RI < rolandd at cisco.com >
+.TP
+Eran Ben Elisha
+.RI < eranbe at mellanox.com >
diff --git a/man/ibv_bind_mw.3 b/man/ibv_bind_mw.3
new file mode 100644
index 0000000..2943cbc
--- /dev/null
+++ b/man/ibv_bind_mw.3
@@ -0,0 +1,92 @@
+.\" -*- nroff -*-
+.\"
+.TH IBV_BIND_MW 3 2016-02-02 libibverbs "Libibverbs Programmer's Manual"
+.SH "NAME"
+ibv_bind_mw \- post a request to bind a type 1 memory window to a memory region
+.SH "SYNOPSIS"
+.nf
+.B #include <infiniband/verbs.h>
+.sp
+.BI "int ibv_bind_mw(struct ibv_qp " "*qp" ", struct ibv_mw " "*mw" ",
+.BI " struct ibv_mw_bind " "*mw_bind" ");
+.fi
+.SH "DESCRIPTION"
+.B ibv_bind_mw()
+posts to the queue pair
+.I qp
+a request to bind the memory window
+.I mw
+according to the details in
+.I mw_bind\fR.
+.PP
+The argument
+.I mw_bind
+is an ibv_mw_bind struct, as defined in <infiniband/verbs.h>.
+.PP
+.nf
+struct ibv_mw_bind {
+.in +8
+uint64_t wr_id; /* User defined WR ID */
+int send_flags; /* Use ibv_send_flags */
+struct ibv_mw_bind_info bind_info; /* MW bind information */
+.in -8
+}
+.fi
+.PP
+.nf
+struct ibv_mw_bind_info {
+.in +8
+struct ibv_mr *mr; /* The MR to bind the MW to */
+uint64_t addr; /* The address the MW should start at */
+uint64_t length; /* The length (in bytes) the MW should span */
+int mw_access_flags; /* Access flags to the MW. Use ibv_access_flags */
+.in -8
+};
+.fi
+.PP
+The QP Transport Service Type must be either UC, RC or XRC_SEND for bind operations.
+.PP
+The attribute send_flags describes the properties of the \s-1WR\s0. It is either 0 or the bitwise \s-1OR\s0 of one or more of the following flags:
+.PP
+.TP
+.B IBV_SEND_FENCE \fR Set the fence indicator.
+.TP
+.B IBV_SEND_SIGNALED \fR Set the completion notification indicator. Relevant only if QP was created with sq_sig_all=0
+.PP
+The mw_access_flags define the allowed access to the MW after the bind
+completes successfully. It is either 0 or the bitwise \s-1OR\s0 of one
+or more of the following flags:
+.TP
+.B IBV_ACCESS_REMOTE_WRITE \fR Enable Remote Write Access. Requires local write access to the MR.
+.TP
+.B IBV_ACCESS_REMOTE_READ\fR Enable Remote Read Access
+.TP
+.B IBV_ACCESS_REMOTE_ATOMIC\fR Enable Remote Atomic Operation Access (if supported). Requires local write access to the MR.
+.TP
+.B IBV_ACCESS_ZERO_BASED\fR If set, the address set on the 'remote_addr' field on the WR will be an offset from the MW's start address.
+.SH "RETURN VALUE"
+.B ibv_bind_mw()
+returns 0 on success, or the value of errno on failure (which
+indicates the failure reason). In case of a success, the R_key of the
+memory window after the bind is returned in the mw_bind->mw->rkey field.
+.SH "NOTES"
+The bind does not complete when the function return - it is merely
+posted to the QP. The user should keep a copy of the old R_key, and
+fix the mw structure if the subsequent CQE for the bind operation
+indicates a failure. The user may safely send the R_key using a send
+request on the same QP, (based on QP ordering rules: a send after a bind
+request on the same QP are always ordered), but must not transfer it to the
+remote in any other manner before reading a successful CQE.
+.PP
+Note that for type 2 MW, one should directly post bind WR to the QP,
+using ibv_post_send.
+.SH "SEE ALSO"
+.BR ibv_alloc_mw (3),
+.BR ibv_post_send (3),
+.BR ibv_poll_cq (3)
+.BR ibv_reg_mr (3),
+.SH "AUTHORS"
+.TP
+Majd Dibbiny <majd at mellanox.com>
+.TP
+Yishai Hadas <yishaih at mellanox.com>
diff --git a/man/ibv_create_cq_ex.3 b/man/ibv_create_cq_ex.3
new file mode 100644
index 0000000..ecaeb0a
--- /dev/null
+++ b/man/ibv_create_cq_ex.3
@@ -0,0 +1,149 @@
+.\" -*- nroff -*-
+.\"
+.TH IBV_CREATE_CQ_EX 3 2016-05-08 libibverbs "Libibverbs Programmer's Manual"
+.SH "NAME"
+ibv_create_cq_ex \- create a completion queue (CQ)
+.SH "SYNOPSIS"
+.nf
+.B #include <infiniband/verbs.h>
+.sp
+.BI "struct ibv_cq_ex *ibv_create_cq_ex(struct ibv_context " "*context" ",
+.BI " struct ibv_create_cq_attr_ex " "*cq_attr" );
+.fi
+.SH "DESCRIPTION"
+.B ibv_create_cq_ex()
+creates a completion queue (CQ) for RDMA device context
+.I context\fR.
+The argument
+.I cq_attr
+is a pointer to struct ibv_create_cq_attr_ex as defined in <infiniband/verbs.h>.
+.PP
+.nf
+struct ibv_create_cq_attr_ex {
+.in +8
+int cqe; /* Minimum number of entries required for CQ */
+void *cq_context; /* Consumer-supplied context returned for completion events */
+struct ibv_comp_channel *channel; /* Completion channel where completion events will be queued. May be NULL if completion events will not be used. */
+int comp_vector; /* Completion vector used to signal completion events. Must be >= 0 and < context->num_comp_vectors. */
+uint64_t wc_flags; /* The wc_flags that should be returned in ibv_poll_cq_ex. Or'ed bit of enum ibv_wc_flags_ex. */
+uint32_t comp_mask; /* compatibility mask (extended verb). */
+.in -8
+};
+
+enum ibv_wc_flags_ex {
+ IBV_WC_EX_WITH_BYTE_LEN = 1 << 0, /* Require byte len in WC */
+ IBV_WC_EX_WITH_IMM = 1 << 1, /* Require immediate in WC */
+ IBV_WC_EX_WITH_QP_NUM = 1 << 2, /* Require QP number in WC */
+ IBV_WC_EX_WITH_SRC_QP = 1 << 3, /* Require source QP in WC */
+ IBV_WC_EX_WITH_SLID = 1 << 4, /* Require slid in WC */
+ IBV_WC_EX_WITH_SL = 1 << 5, /* Require sl in WC */
+ IBV_WC_EX_WITH_DLID_PATH_BITS = 1 << 6, /* Require dlid path bits in WC */
+ IBV_WC_EX_WITH_COMPLETION_TIMESTAMP = 1 << 7, /* Require completion timestamp in WC /*
+};
+
+enum ibv_cq_init_attr_mask {
+ IBV_CQ_INIT_ATTR_MASK_FLAGS = 1 << 0,
+};
+
+enum ibv_create_cq_attr_flags {
+ IBV_CREATE_CQ_ATTR_SINGLE_THREADED = 1 << 0, /* This CQ is used from a single threaded, thus no locking is required */
+};
+
+.SH "Polling an extended CQ"
+In order to poll an extended CQ efficiently, a user could use the following functions.
+
+.TP
+.B Completion iterator functions
+
+.BI "int ibv_start_poll(struct ibv_cq_ex " "*cq" ", struct ibv_poll_cq_attr " "*attr")
+.br
+Start polling a batch of work completions.
+.I attr
+is given in order to make this function
+easily extensible in the future. This function either returns 0 on success or an error code
+otherwise. When no completions are available on the CQ, ENOENT is returned, but the CQ remains
+in a valid state. On success, querying the completion's attribute could be done using the query
+functions described below. If an error code is given, end_poll shouldn't be called.
+
+.BI "int ibv_next_poll(struct ibv_cq_ex " "*cq")
+.br
+This function is called in order to get the next work completion. It has to be called after
+.I start_poll
+and before
+.I end_poll
+are called. This function either returns 0 on success or an error code
+otherwise. When no completions are available on the CQ, ENOENT is returned, but the CQ remains
+in a valid state. On success, querying the completion's attribute could be done using the query
+functions described below. If an error code is given, end_poll should still be called,
+indicating this is the end of the polled batch.
+
+.BI "void ibv_end_poll(struct ibv_cq_ex " "*cq")
+.br
+This function indicates the end of polling batch of work completions. After calling this function, the user should start a new batch
+by calling
+.I start_poll.
+
+.TP
+.B Polling fields in the completion
+Below members and functions are used in order to poll the current completion. The current completion is the completion which the iterator points to (start_poll and next_poll advances this iterator). Only fields that the user requested via wc_flags in ibv_create_cq_ex could be queried. In addition, some fields are only valid in certain opcodes and status codes.
+
+.BI "uint64_t wr_id - Can be accessed directly from struct ibv_cq_ex".
+
+.BI "enum ibv_wc_status - Can be accessed directly from struct ibv_cq_ex".
+
+.BI "enum ibv_wc_opcode ibv_wc_read_opcode(struct ibv_cq_ex " "*cq"); \c
+ Get the opcode from the current completion.
+
+.BI "uint32_t ibv_wc_read_vendor_err(struct ibv_cq_ex " "*cq"); \c
+ Get the vendor error from the current completion.
+
+.BI "uint32_t ibv_wc_read_byte_len(struct ibv_cq_ex " "*cq"); \c
+ Get the vendor error from the current completion.
+
+.BI "uint32_t ibv_wc_read_imm_data(struct ibv_cq_ex " "*cq"); \c
+ Get the immediate data field from the current completion.
+
+.BI "uint32_t ibv_wc_read_qp_num(struct ibv_cq_ex " "*cq"); \c
+ Get the QP number field from the current completion.
+
+.BI "uint32_t ibv_wc_read_src_qp(struct ibv_cq_ex " "*cq"); \c
+ Get the source QP number field from the current completion.
+
+.BI "int ibv_wc_read_wc_flags(struct ibv_cq_ex " "*cq"); \c
+ Get the QP flags field from the current completion.
+
+.BI "uint16_t ibv_wc_read_pkey_index(struct ibv_cq_ex " "*cq"); \c
+ Get the pkey index field from the current completion.
+
+.BI "uint32_t ibv_wc_read_slid(struct ibv_cq_ex " "*cq"); \c
+ Get the slid field from the current completion.
+
+.BI "uint8_t ibv_wc_read_sl(struct ibv_cq_ex " "*cq"); \c
+ Get the sl field from the current completion.
+
+.BI "uint8_t ibv_wc_read_dlid_path_bits(struct ibv_cq_ex " "*cq"); \c
+ Get the dlid_path_bits field from the current completion.
+
+.BI "uint64_t ibv_wc_read_completion_ts(struct ibv_cq_ex " "*cq"); \c
+ Get the completion timestamp from the current completion.
+
+.SH "RETURN VALUE"
+.B ibv_create_cq_ex()
+returns a pointer to the CQ, or NULL if the request fails.
+.SH "NOTES"
+.B ibv_create_cq_ex()
+may create a CQ with size greater than or equal to the requested
+size. Check the cqe attribute in the returned CQ for the actual size.
+.PP
+CQ should be destroyed with ibv_destroy_cq.
+.PP
+.SH "SEE ALSO"
+.BR ibv_create_cq (3),
+.BR ibv_destroy_cq (3),
+.BR ibv_resize_cq (3),
+.BR ibv_req_notify_cq (3),
+.BR ibv_ack_cq_events (3),
+.BR ibv_create_qp (3)
+.SH "AUTHORS"
+.TP
+Matan Barak <matanb at mellanox.com>
diff --git a/man/ibv_create_flow.3 b/man/ibv_create_flow.3
new file mode 100644
index 0000000..df6ddd3
--- /dev/null
+++ b/man/ibv_create_flow.3
@@ -0,0 +1,174 @@
+.TH IBV_CREATE_FLOW 3 2016-03-15 libibverbs "Libibverbs Programmer's Manual"
+.SH "NAME"
+ibv_create_flow, ibv_destroy_flow \- create or destroy flow steering rules
+.SH "SYNOPSIS"
+.nf
+.B #include <infiniband/verbs.h>
+.sp
+.BI "struct ibv_flow *ibv_create_flow(struct ibv_qp " "*qp" ,
+.BI " struct ibv_flow_attr " "*flow_attr");
+.BI "int ibv_destroy_flow(struct ibv_flow " "*flow_id");
+.sp
+.fi
+.SH "DESCRIPTION"
+.SS ibv_create_flow()
+allows a user application QP
+.I qp
+to be attached into a specified flow
+.I flow
+which is defined in
+.I <infiniband/verbs.h>
+.PP
+.nf
+struct ibv_flow_attr {
+.in +8
+uint32_t comp_mask; /* Future extendibility */
+enum ibv_flow_attr_type type; /* Rule type - see below */
+uint16_t size; /* Size of command */
+uint16_t priority; /* Rule priority - see below */
+uint8_t num_of_specs; /* Number of ibv_flow_spec_xxx */
+uint8_t port; /* The uplink port number */
+uint32_t flags; /* Extra flags for rule - see below */
+/* Following are the optional layers according to user request
+ * struct ibv_flow_spec_xxx
+ * struct ibv_flow_spec_yyy
+ */
+.in -8
+};
+.sp
+.nf
+enum ibv_flow_attr_type {
+.in +8
+IBV_FLOW_ATTR_NORMAL = 0x0, /* Steering according to rule specifications */
+IBV_FLOW_ATTR_ALL_DEFAULT = 0x1, /* Default unicast and multicast rule - receive all Eth traffic which isn't steered to any QP */
+IBV_FLOW_ATTR_MC_DEFAULT = 0x2, /* Default multicast rule - receive all Eth multicast traffic which isn't steered to any QP */
+.in -8
+};
+.sp
+.nf
+enum ibv_flow_flags {
+.in +8
+IBV_FLOW_ATTR_FLAGS_ALLOW_LOOP_BACK = 1 << 0, /* Apply the rules on packets that were sent from the attached QP through loopback */
+IBV_FLOW_ATTR_FLAGS_DONT_TRAP = 1 << 1, /* Rule doesn't trap received packets, allowing them to match lower prioritized rules */
+.in -8
+};
+.fi
+.PP
+Each spec struct holds the relevant network layer parameters for matching. To enforce the match, the user sets a mask for each parameter.
+.br
+If the bit is set in the mask, the corresponding bit in the value should be matched.
+.br
+Note that most vendors support either full mask (all "1"s) or zero mask (all "0"s).
+.br
+.B Network parameters in the relevant network structs should be given in network order (big endian).
+
+.SS Flow domains and priority
+Flow steering defines the concept of domain and priority. Each domain represents an application that can attach a flow.
+Domains are prioritized. A higher priority domain will always supersede a lower priority domain when their flow specifications overlap.
+.br
+.B IB verbs have the higher priority domain.
+.br
+In addition to the domain, there is priority within each of the domains.
+A lower priority numeric value (higher priority) takes precedence over matching rules with higher numeric priority value (lower priority).
+It is important to note that the priority value of a flow spec is used not only to establish the precedence of conflicting flow matches
+but also as a way to abstract the order on which flow specs are tested for matches. Flows with higher priorities will be tested before flows with lower priorities.
+.PP
+.SS ibv_destroy_flow()
+destroys the flow
+.I flow_id\fR.
+.SH "RETURN VALUE"
+.B ibv_create_flow()
+returns a pointer to the flow, or NULL if the request fails. In case of an error, errno is updated.
+.PP
+.B ibv_destroy_flow()
+returns 0 on success, or the value of errno on failure (which indicates the failure reason).
+.SH "ERRORS"
+.SS EINVAL
+.B ibv_create_flow()
+flow specification, QP or priority are invalid
+.PP
+.B ibv_destroy_flow()
+flow_id is invalid
+.SS ENOMEM
+Couldn't create/destroy flow, not enough memory
+.SS ENXIO
+Device managed flow steering isn't currently supported
+.SS EPERM
+No permissions to add the flow steering rule
+.SH "NOTES"
+These verbs are available only for devices supporting
+.br
+IBV_DEVICE_MANAGED_FLOW_STEERING and only for QPs of Transport Service Type
+.BR IBV_QPT_UD
+or
+.BR IBV_QPT_RAW_PACKET
+.PP
+.SH EXAMPLE
+.br
+Below flow_attr defines a rule in priority 0 to match a destination
+mac address and a source ipv4 address. For that, L2 and L3 specs are used.
+.br
+If there is a hit on this rule, means the
+received packet has destination mac: 66:11:22:33:44:55 and source ip: 0x0B86C806,
+the packet is steered to its attached qp.
+.sp
+.nf
+struct raw_eth_flow_attr {
+.in +8
+struct ibv_flow_attr attr;
+struct ibv_flow_spec_eth spec_eth;
+struct ibv_flow_spec_ipv4 spec_ipv4;
+.in -8
+} __attribute__((packed));
+.sp
+.nf
+struct raw_eth_flow_attr flow_attr = {
+.in +8
+ .attr = {
+ .comp_mask = 0,
+ .type = IBV_FLOW_ATTR_NORMAL,
+ .size = sizeof(flow_attr),
+ .priority = 0,
+ .num_of_specs = 2,
+ .port = 1,
+ .flags = 0,
+ },
+ .spec_eth = {
+ .type = IBV_FLOW_SPEC_ETH,
+ .size = sizeof(struct ibv_flow_spec_eth),
+ .val = {
+ .dst_mac = {0x66, 0x11, 0x22, 0x33, 0x44, 0x55},
+ .src_mac = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00},
+ .ether_type = 0,
+ .vlan_tag = 0,
+ },
+ .mask = {
+ .dst_mac = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF},
+ .src_mac = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF},
+ .ether_type = 0,
+ .vlan_tag = 0,
+ }
+ },
+ .spec_ipv4 = {
+ .type = IBV_FLOW_SPEC_IPV4,
+ .size = sizeof(struct ibv_flow_spec_ipv4),
+ .val = {
+ .src_ip = 0x0B86C806,
+ .dst_ip = 0,
+ },
+ .mask = {
+ .src_ip = 0xFFFFFFFF,
+ .dst_ip = 0,
+ }
+ }
+.in -8
+};
+.sp
+.nf
+.SH "AUTHORS"
+.TP
+Hadar Hen Zion <hadarh at mellanox.com>
+.TP
+Matan Barak <matanb at mellanox.com>
+.TP
+Yishai Hadas <yishaih at mellanox.com>
diff --git a/man/ibv_inc_rkey.3 b/man/ibv_inc_rkey.3
new file mode 100644
index 0000000..930368b
--- /dev/null
+++ b/man/ibv_inc_rkey.3
@@ -0,0 +1,32 @@
+.\" -*- nroff -*-
+.\"
+.TH IBV_INC_RKEY 3 2015-01-29 libibverbs "Libibverbs Programmer's Manual"
+.SH "NAME"
+.nf
+ibv_inc_rkey \- creates a new rkey from the given one
+.SH "SYNOPSIS"
+.nf
+.B #include <infiniband/verbs.h>
+.sp
+.BI "uint32_t ibv_inc_rkey(uint32_t " "rkey" ");
+.fi
+.SH "DESCRIPTION"
+.B ibv_inc_rkey()
+Increases the 8 LSB of
+.I rkey
+and returns the new value.
+.PP
+.SH "RETURN VALUE"
+.B ibv_inc_rkey()
+returns the new rkey.
+.SH "NOTES"
+.PP
+The verb generates a new rkey that is different from the previous one on its tag part
+but has the same index (bits 0xffffff00).
+A use case for this verb can be to create a new rkey from a Memory window's rkey
+when binding it to a Memory region.
+.SH "AUTHORS"
+.TP
+Majd Dibbiny <majd at mellanox.com>
+.TP
+Yishai Hadas <yishaih at mellanox.com>
diff --git a/man/ibv_post_send.3 b/man/ibv_post_send.3
index eeea078..f918afb 100644
--- a/man/ibv_post_send.3
+++ b/man/ibv_post_send.3
@@ -60,8 +60,36 @@ uint32_t remote_qkey; /* Q_Key number of the destination QP */
} ud;
.in -8
} wr;
+union {
+.in +8
+struct {
+.in +8
+uint32_t remote_srqn; /* Number of the remote SRQ */
+.in -8
+} xrc;
+.in -8
+} qp_type;
+struct {
+.in +8
+struct ibv_mw *mw; /* Memory window (MW) of type 2 to bind */
+uint32_t rkey; /* The desired new rkey of the MW */
+struct ibv_mw_bind_info bind_info; /* MW additional bind information */
+.in -8
+} bind_mw;
.in -8
};
+.fi
+.sp
+.nf
+struct ibv_mw_bind_info {
+.in +8
+struct ibv_mr *mr; /* The Memory region (MR) to bind the MW to */
+uint64_t addr; /* The address the MW should start at */
+uint64_t length; /* The length (in bytes) the MW should span */
+int mw_access_flags; /* Access flags to the MW. Use ibv_access_flags */
+.in -8
+};
+.fi
.sp
.nf
struct ibv_sge {
@@ -76,15 +104,18 @@ uint32_t lkey; /* Key of the local Memory Regio
Each QP Transport Service Type supports a specific set of opcodes, as shown in the following table:
.PP
.nf
-OPCODE | IBV_QPT_UD | IBV_QPT_UC | IBV_QPT_RC
+OPCODE | IBV_QPT_UD | IBV_QPT_UC | IBV_QPT_RC | IBV_QPT_XRC_SEND
\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-+\-\-\-\-\-\-\-\-\-\-\-\-+\-\-\-\-\-\-\-\-\-\-\-\-+\-\-\-\-\-\-\-\-\-\-\-
-IBV_WR_SEND | X | X | X
-IBV_WR_SEND_WITH_IMM | X | X | X
-IBV_WR_RDMA_WRITE | | X | X
-IBV_WR_RDMA_WRITE_WITH_IMM | | X | X
-IBV_WR_RDMA_READ | | | X
-IBV_WR_ATOMIC_CMP_AND_SWP | | | X
-IBV_WR_ATOMIC_FETCH_AND_ADD | | | X
+IBV_WR_SEND | X | X | X | X
+IBV_WR_SEND_WITH_IMM | X | X | X | X
+IBV_WR_RDMA_WRITE | | X | X | X
+IBV_WR_RDMA_WRITE_WITH_IMM | | X | X | X
+IBV_WR_RDMA_READ | | | X | X
+IBV_WR_ATOMIC_CMP_AND_SWP | | | X | X
+IBV_WR_ATOMIC_FETCH_AND_ADD | | | X | X
+IBV_WR_LOCAL_INV | | X | X | X
+IBV_WR_BIND_MW | | X | X | X
+IBV_WR_SEND_WITH_INV | | X | X | X
.fi
.PP
The attribute send_flags describes the properties of the \s-1WR\s0. It is either 0 or the bitwise \s-1OR\s0 of one or more of the following flags:
@@ -125,3 +156,7 @@ after the call returns.
.SH "AUTHORS"
.TP
Dotan Barak <dotanba at gmail.com>
+.TP
+Majd Dibbiny <majd at mellanox.com>
+.TP
+Yishai Hadas <yishaih at mellanox.com>
diff --git a/man/ibv_query_device_ex.3 b/man/ibv_query_device_ex.3
index 1f483d2..5097be0 100644
--- a/man/ibv_query_device_ex.3
+++ b/man/ibv_query_device_ex.3
@@ -22,8 +22,11 @@ is a pointer to an ibv_device_attr_ex struct, as defined in <infiniband/verbs.h>
struct ibv_device_attr_ex {
.in +8
struct ibv_device_attr orig_attr;
-uint32_t comp_mask; /* Compatibility mask that defines which of the following variables are valid */
-struct ibv_odp_caps odp_caps; /* On-Demand Paging capabilities */
+uint32_t comp_mask; /* Compatibility mask that defines which of the following variables are valid */
+struct ibv_odp_caps odp_caps; /* On-Demand Paging capabilities */
+uint64_t completion_timestamp_mask; /* Completion timestamp mask (0 = unsupported) */
+uint64_t hca_core_clock; /* The frequency (in kHZ) of the HCA (0 = unsupported) */
+uint64_t device_cap_flags_ex; /* Extended device capability flags */
.in -8
};
diff --git a/man/ibv_query_rt_values_ex.3 b/man/ibv_query_rt_values_ex.3
new file mode 100644
index 0000000..fcc460c
--- /dev/null
+++ b/man/ibv_query_rt_values_ex.3
@@ -0,0 +1,50 @@
+.\" -*- nroff -*-
+.\"
+.TH IBV_QUERY_RT_VALUES_EX 3 2016-2-20 libibverbs "Libibverbs Programmer's Manual"
+.SH "NAME"
+ibv_query_rt_values_ex \- query an RDMA device for some real time values
+.SH "SYNOPSIS"
+.nf
+.B #include <infiniband/verbs.h>
+.sp
+.BI "int ibv_query_rt_values_ex(struct ibv_context " "*context",
+.BI " struct ibv_values_ex " "*values" );
+.fi
+.SH "DESCRIPTION"
+.B ibv_query_rt_values_ex()
+returns certain real time values of a device
+.I context\fR.
+The argument
+.I attr
+is a pointer to an ibv_device_attr_ex struct, as defined in <infiniband/verbs.h>.
+.PP
+.nf
+struct ibv_values_ex {
+.in +8
+uint32_t comp_mask; /* Compatibility mask that defines the query/queried fields [in/out] */
+struct timespec raw_clock; /* HW raw clock */
+.in -8
+};
+
+enum ibv_values_mask {
+ IBV_VALUES_MASK_RAW_CLOCK = 1 << 0, /* HW raw clock */
+};
+
+.fi
+.SH "RETURN VALUE"
+.B ibv_query_rt_values_ex()
+returns 0 on success, or the value of errno on failure (which indicates the failure reason).
+.SH "NOTES"
+This extension verb only calls the provider, the provider has to query this value somehow and mark
+the queried values in the comp_mask field.
+.SH "SEE ALSO"
+.BR ibv_query_device (3),
+.BR ibv_open_device (3),
+.BR ibv_query_port (3),
+.BR ibv_query_pkey (3),
+.BR ibv_query_gid (3)
+.SH "AUTHORS"
+.TP
+Matan Barak <matanb at mellanox.com>
+.TP
+Yishai Hadas <yishaih at mellanox.com>
diff --git a/man/ibv_rereg_mr.3 b/man/ibv_rereg_mr.3
new file mode 100644
index 0000000..a678437
--- /dev/null
+++ b/man/ibv_rereg_mr.3
@@ -0,0 +1,76 @@
+.\" -*- nroff -*-
+.\"
+.TH IBV_REREG_MR 3 2016-03-13 libibverbs "Libibverbs Programmer's Manual"
+.SH "NAME"
+ibv_rereg_mr \- re-register a memory region (MR)
+.SH "SYNOPSIS"
+.nf
+.B #include <infiniband/verbs.h>
+.sp
+.BI "int ibv_rereg_mr(struct ibv_mr " "*mr" ", int " " flags" ,
+.BI " struct ibv_pd * " "pd" ", void " " *addr",
+.BI " size_t " " length" ", int " " access");
+.fi
+.fi
+.SH "DESCRIPTION"
+.B ibv_rereg_mr()
+Modifies the attributes of an existing memory region (MR)
+.I mr\fR.
+Conceptually, this call performs the functions deregister memory region
+followed by register memory region. Where possible,
+resources are reused instead of deallocated and reallocated.
+.PP
+.I flags\fR
+is a bit-mask used to indicate which of the following properties of the memory region are being modified. Flags should be a combination (bit field) of:
+.PP
+.TP
+.B IBV_REREG_MR_CHANGE_TRANSLATION \fR Change translation (location and length)
+.TP
+.B IBV_REREG_MR_CHANGE_PD \fR Change protection domain
+.TP
+.B IBV_REREG_MR_CHANGE_ACCESS \fR Change access flags
+.PP
+When
+.B IBV_REREG_MR_CHANGE_PD
+is used,
+.I pd\fR
+represents the new PD this MR should be registered to.
+.br
+When
+.B IBV_REREG_MR_CHANGE_TRANSLATION
+is used,
+.I addr\fR.
+represents the virtual address (user-space pointer) of the new MR, while
+.I length\fR
+represents its length.
+.PP
+The access and other flags are represented in the field
+.I access\fR.
+This field describes the desired memory protection attributes; it is either 0 or the bitwise OR of one or more of ibv_access_flags.
+.TP
+.SH "RETURN VALUE"
+.B ibv_rereg_mr()
+returns 0 on success, otherwise an error has occurred,
+.I enum ibv_rereg_mr_err_code\fR
+represents the error as of below.
+.br
+IBV_REREG_MR_ERR_INPUT - Old MR is valid, an input error was detected by libibverbs.
+.br
+IBV_REREG_MR_ERR_DONT_FORK_NEW - Old MR is valid, failed via dont fork on new address range.
+.br
+IBV_REREG_MR_ERR_DO_FORK_OLD - New MR is valid, failed via do fork on old address range.
+.br
+IBV_REREG_MR_ERR_CMD - MR shouldn't be used, command error.
+.br
+IBV_REREG_MR_ERR_CMD_AND_DO_FORK_NEW - MR shouldn't be used, command error, invalid fork state on new address range.
+
+.SH "NOTES"
+Even on a failure, the user still needs to call ibv_dereg_mr on this MR.
+.SH "SEE ALSO"
+.BR ibv_reg_mr (3),
+.BR ibv_dereg_mr (3),
+.SH "AUTHORS"
+.TP
+Matan Barak <matanb at mellanox.com>
+.TP
+Yishai Hadas <yishaih at mellanox.com>
diff --git a/man/ibv_xsrq_pingpong.1 b/man/ibv_xsrq_pingpong.1
new file mode 100644
index 0000000..db4a988
--- /dev/null
+++ b/man/ibv_xsrq_pingpong.1
@@ -0,0 +1,71 @@
+.TH IBV_XSRQ_PINGPONG 1 "May 24, 2016" "libibverbs" "USER COMMANDS"
+
+.SH NAME
+ibv_xsrq_pingpong \- simple InfiniBand shared receive queue test
+
+.SH SYNOPSIS
+.B ibv_xsrq_pingpong
+[\-p port] [\-d device] [\-i ib port] [\-s size] [\-m mtu] [\-c clients]
+[\-n num_tests] [\-l sl] [\-e] \fBHOSTNAME\fR
+
+.B ibv_xsrq_pingpong
+[\-p port] [\-d device] [\-i ib port] [\-s size] [\-m mtu] [\-c clients]
+[\-n num_tests] [\-l sl] [\-e]
+
+.SH DESCRIPTION
+.PP
+Run a simple ping-pong test over InfiniBand via the extended reliable
+connected (XRC) transport service, using a shared receive queue (SRQ).
+
+.SH OPTIONS
+
+.PP
+.TP
+\fB\-p\fR, \fB\-\-port\fR=\fIPORT\fR
+use TCP port \fIPORT\fR for initial synchronization (default 18515)
+.TP
+\fB\-d\fR, \fB\-\-ib\-dev\fR=\fIDEVICE\fR
+use IB device \fIDEVICE\fR (default first device found)
+.TP
+\fB\-i\fR, \fB\-\-ib\-port\fR=\fIPORT\fR
+use IB port \fIPORT\fR (default port 1)
+.TP
+\fB\-s\fR, \fB\-\-size\fR=\fISIZE\fR
+ping-pong messages of size \fISIZE\fR (default 4096)
+.TP
+\fB\-m\fR, \fB\-\-mtu\fR=\fIMTU\fR
+use path mtu of size \fIMTU\fR (default 2048)
+.TP
+\fB\-c\fR, \fB\-\-clients\fR=\fICLIENTS\fR
+number of clients \fICLIENTS\fR (on server only, default 1)
+.TP
+\fB\-n\fR, \fB\-\-num\-tests\fR=\fINUM_TESTS\fR
+perform \fINUM_TESTS\fR tests per client (default 5)
+.TP
+\fB\-l\fR, \fB\-\-sl\fR=\fISL\fR
+use \fISL\fR as the service level value (default 0)
+.TP
+\fB\-e\fR, \fB\-\-events\fR
+sleep while waiting for work completion events (default is to poll for
+completions)
+
+.SH SEE ALSO
+.BR ibv_rc_pingpong (1),
+.BR ibv_uc_pingpong (1),
+.BR ibv_ud_pingpong (1)
+.BR ibv_srq_pingpong (1)
+
+.SH AUTHORS
+.TP
+Roland Dreier
+.RI < roland at purestorage.com >
+.TP
+Jarod Wilson
+.RI < jarod at redhat.com >
+
+.SH BUGS
+The network synchronization between client and server instances is
+weak, and does not prevent incompatible options from being used on the
+two instances. The method used for retrieving work completions is not
+strictly correct, and race conditions may cause failures on some
+systems.
diff --git a/src/cmd.c b/src/cmd.c
index e1914e9..cb9e34c 100644
--- a/src/cmd.c
+++ b/src/cmd.c
@@ -189,6 +189,37 @@ int ibv_cmd_query_device_ex(struct ibv_context *context,
}
}
+ if (attr_size >= offsetof(struct ibv_device_attr_ex,
+ completion_timestamp_mask) +
+ sizeof(attr->completion_timestamp_mask)) {
+ if (resp->response_length >=
+ offsetof(struct ibv_query_device_resp_ex, timestamp_mask) +
+ sizeof(resp->timestamp_mask))
+ attr->completion_timestamp_mask = resp->timestamp_mask;
+ else
+ attr->completion_timestamp_mask = 0;
+ }
+
+ if (attr_size >= offsetof(struct ibv_device_attr_ex, hca_core_clock) +
+ sizeof(attr->hca_core_clock)) {
+ if (resp->response_length >=
+ offsetof(struct ibv_query_device_resp_ex, hca_core_clock) +
+ sizeof(resp->hca_core_clock))
+ attr->hca_core_clock = resp->hca_core_clock;
+ else
+ attr->hca_core_clock = 0;
+ }
+
+ if (attr_size >= offsetof(struct ibv_device_attr_ex, device_cap_flags_ex) +
+ sizeof(attr->device_cap_flags_ex)) {
+ if (resp->response_length >=
+ offsetof(struct ibv_query_device_resp_ex, device_cap_flags_ex) +
+ sizeof(resp->device_cap_flags_ex))
+ attr->device_cap_flags_ex = resp->device_cap_flags_ex;
+ else
+ attr->device_cap_flags_ex = 0;
+ }
+
return 0;
}
@@ -334,6 +365,35 @@ int ibv_cmd_reg_mr(struct ibv_pd *pd, void *addr, size_t length,
return 0;
}
+int ibv_cmd_rereg_mr(struct ibv_mr *mr, uint32_t flags, void *addr,
+ size_t length, uint64_t hca_va, int access,
+ struct ibv_pd *pd, struct ibv_rereg_mr *cmd,
+ size_t cmd_sz, struct ibv_rereg_mr_resp *resp,
+ size_t resp_sz)
+{
+ IBV_INIT_CMD_RESP(cmd, cmd_sz, REREG_MR, resp, resp_sz);
+
+ cmd->mr_handle = mr->handle;
+ cmd->flags = flags;
+ cmd->start = (uintptr_t)addr;
+ cmd->length = length;
+ cmd->hca_va = hca_va;
+ cmd->pd_handle = (flags & IBV_REREG_MR_CHANGE_PD) ? pd->handle : 0;
+ cmd->access_flags = access;
+
+ if (write(mr->context->cmd_fd, cmd, cmd_sz) != cmd_sz)
+ return errno;
+
+ (void)VALGRIND_MAKE_MEM_DEFINED(resp, resp_sz);
+
+ mr->lkey = resp->lkey;
+ mr->rkey = resp->rkey;
+ if (flags & IBV_REREG_MR_CHANGE_PD)
+ mr->context = pd->context;
+
+ return 0;
+}
+
int ibv_cmd_dereg_mr(struct ibv_mr *mr)
{
struct ibv_dereg_mr cmd;
@@ -347,6 +407,43 @@ int ibv_cmd_dereg_mr(struct ibv_mr *mr)
return 0;
}
+int ibv_cmd_alloc_mw(struct ibv_pd *pd, enum ibv_mw_type type,
+ struct ibv_mw *mw, struct ibv_alloc_mw *cmd,
+ size_t cmd_size,
+ struct ibv_alloc_mw_resp *resp, size_t resp_size)
+{
+ IBV_INIT_CMD_RESP(cmd, cmd_size, ALLOC_MW, resp, resp_size);
+ cmd->pd_handle = pd->handle;
+ cmd->mw_type = type;
+ memset(cmd->reserved, 0, sizeof(cmd->reserved));
+
+ if (write(pd->context->cmd_fd, cmd, cmd_size) != cmd_size)
+ return errno;
+
+ (void) VALGRIND_MAKE_MEM_DEFINED(resp, resp_size);
+
+ mw->context = pd->context;
+ mw->pd = pd;
+ mw->rkey = resp->rkey;
+ mw->handle = resp->mw_handle;
+ mw->type = type;
+
+ return 0;
+}
+
+int ibv_cmd_dealloc_mw(struct ibv_mw *mw,
+ struct ibv_dealloc_mw *cmd, size_t cmd_size)
+{
+ IBV_INIT_CMD(cmd, cmd_size, DEALLOC_MW);
+ cmd->mw_handle = mw->handle;
+ cmd->reserved = 0;
+
+ if (write(mw->context->cmd_fd, cmd, cmd_size) != cmd_size)
+ return errno;
+
+ return 0;
+}
+
int ibv_cmd_create_cq(struct ibv_context *context, int cqe,
struct ibv_comp_channel *channel,
int comp_vector, struct ibv_cq *cq,
@@ -372,6 +469,54 @@ int ibv_cmd_create_cq(struct ibv_context *context, int cqe,
return 0;
}
+int ibv_cmd_create_cq_ex(struct ibv_context *context,
+ struct ibv_cq_init_attr_ex *cq_attr,
+ struct ibv_cq_ex *cq,
+ struct ibv_create_cq_ex *cmd,
+ size_t cmd_core_size,
+ size_t cmd_size,
+ struct ibv_create_cq_resp_ex *resp,
+ size_t resp_core_size,
+ size_t resp_size)
+{
+ int err;
+
+ memset(cmd, 0, cmd_core_size);
+ IBV_INIT_CMD_RESP_EX_V(cmd, cmd_core_size, cmd_size, CREATE_CQ_EX, resp,
+ resp_core_size, resp_size);
+
+ if (cq_attr->comp_mask & ~(IBV_CQ_INIT_ATTR_MASK_RESERVED - 1))
+ return EINVAL;
+
+ cmd->user_handle = (uintptr_t)cq;
+ cmd->cqe = cq_attr->cqe;
+ cmd->comp_vector = cq_attr->comp_vector;
+ cmd->comp_channel = cq_attr->channel ? cq_attr->channel->fd : -1;
+ cmd->comp_mask = 0;
+
+ if (cmd_core_size >= offsetof(struct ibv_create_cq_ex, flags) +
+ sizeof(cmd->flags)) {
+ if ((cq_attr->comp_mask & IBV_CQ_INIT_ATTR_MASK_FLAGS) &&
+ (cq_attr->flags & ~(IBV_CREATE_CQ_ATTR_RESERVED - 1)))
+ return EOPNOTSUPP;
+
+ if (cq_attr->wc_flags & IBV_WC_EX_WITH_COMPLETION_TIMESTAMP)
+ cmd->flags |= IBV_CREATE_CQ_EX_KERNEL_FLAG_COMPLETION_TIMESTAMP;
+ }
+
+ err = write(context->cmd_fd, cmd, cmd_size);
+ if (err != cmd_size)
+ return errno;
+
+ (void)VALGRIND_MAKE_MEM_DEFINED(resp, resp_size);
+
+ cq->handle = resp->base.cq_handle;
+ cq->cqe = resp->base.cqe;
+ cq->context = context;
+
+ return 0;
+}
+
int ibv_cmd_poll_cq(struct ibv_cq *ibcq, int ne, struct ibv_wc *wc)
{
struct ibv_poll_cq cmd;
@@ -677,6 +822,136 @@ int ibv_cmd_destroy_srq(struct ibv_srq *srq)
return 0;
}
+static int create_qp_ex_common(struct verbs_qp *qp,
+ struct ibv_qp_init_attr_ex *qp_attr,
+ struct verbs_xrcd *vxrcd,
+ struct ibv_create_qp_common *cmd)
+{
+ cmd->user_handle = (uintptr_t)qp;
+
+ if (qp_attr->comp_mask & IBV_QP_INIT_ATTR_XRCD) {
+ vxrcd = container_of(qp_attr->xrcd, struct verbs_xrcd, xrcd);
+ cmd->pd_handle = vxrcd->handle;
+ } else {
+ if (!(qp_attr->comp_mask & IBV_QP_INIT_ATTR_PD))
+ return EINVAL;
+
+ cmd->pd_handle = qp_attr->pd->handle;
+ cmd->send_cq_handle = qp_attr->send_cq->handle;
+
+ if (qp_attr->qp_type != IBV_QPT_XRC_SEND) {
+ cmd->recv_cq_handle = qp_attr->recv_cq->handle;
+ cmd->srq_handle = qp_attr->srq ? qp_attr->srq->handle :
+ 0;
+ }
+ }
+
+ cmd->max_send_wr = qp_attr->cap.max_send_wr;
+ cmd->max_recv_wr = qp_attr->cap.max_recv_wr;
+ cmd->max_send_sge = qp_attr->cap.max_send_sge;
+ cmd->max_recv_sge = qp_attr->cap.max_recv_sge;
+ cmd->max_inline_data = qp_attr->cap.max_inline_data;
+ cmd->sq_sig_all = qp_attr->sq_sig_all;
+ cmd->qp_type = qp_attr->qp_type;
+ cmd->is_srq = !!qp_attr->srq;
+ cmd->reserved = 0;
+
+ return 0;
+}
+
+static void create_qp_handle_resp_common(struct ibv_context *context,
+ struct verbs_qp *qp,
+ struct ibv_qp_init_attr_ex *qp_attr,
+ struct ibv_create_qp_resp *resp,
+ struct verbs_xrcd *vxrcd,
+ int vqp_sz)
+{
+ if (abi_ver > 3) {
+ qp_attr->cap.max_recv_sge = resp->max_recv_sge;
+ qp_attr->cap.max_send_sge = resp->max_send_sge;
+ qp_attr->cap.max_recv_wr = resp->max_recv_wr;
+ qp_attr->cap.max_send_wr = resp->max_send_wr;
+ qp_attr->cap.max_inline_data = resp->max_inline_data;
+ }
+
+ qp->qp.handle = resp->qp_handle;
+ qp->qp.qp_num = resp->qpn;
+ qp->qp.context = context;
+ qp->qp.qp_context = qp_attr->qp_context;
+ qp->qp.pd = qp_attr->pd;
+ qp->qp.send_cq = qp_attr->send_cq;
+ qp->qp.recv_cq = qp_attr->recv_cq;
+ qp->qp.srq = qp_attr->srq;
+ qp->qp.qp_type = qp_attr->qp_type;
+ qp->qp.state = IBV_QPS_RESET;
+ qp->qp.events_completed = 0;
+ pthread_mutex_init(&qp->qp.mutex, NULL);
+ pthread_cond_init(&qp->qp.cond, NULL);
+
+ qp->comp_mask = 0;
+ if (vext_field_avail(struct verbs_qp, xrcd, vqp_sz) &&
+ (qp_attr->comp_mask & IBV_QP_INIT_ATTR_XRCD)) {
+ qp->comp_mask |= VERBS_QP_XRCD;
+ qp->xrcd = vxrcd;
+ }
+}
+
+enum {
+ CREATE_QP_EX2_SUP_CREATE_FLAGS = IBV_QP_CREATE_BLOCK_SELF_MCAST_LB |
+ IBV_QP_CREATE_SCATTER_FCS,
+};
+
+int ibv_cmd_create_qp_ex2(struct ibv_context *context,
+ struct verbs_qp *qp, int vqp_sz,
+ struct ibv_qp_init_attr_ex *qp_attr,
+ struct ibv_create_qp_ex *cmd,
+ size_t cmd_core_size,
+ size_t cmd_size,
+ struct ibv_create_qp_resp_ex *resp,
+ size_t resp_core_size,
+ size_t resp_size)
+{
+ struct verbs_xrcd *vxrcd = NULL;
+ int err;
+
+ if (qp_attr->comp_mask >= IBV_QP_INIT_ATTR_RESERVED)
+ return EINVAL;
+
+ if (resp_core_size <
+ offsetof(struct ibv_create_qp_resp_ex, response_length) +
+ sizeof(resp->response_length))
+ return EINVAL;
+
+ memset(cmd, 0, cmd_core_size);
+
+ IBV_INIT_CMD_RESP_EX_V(cmd, cmd_core_size, cmd_size, CREATE_QP_EX, resp,
+ resp_core_size, resp_size);
+
+ err = create_qp_ex_common(qp, qp_attr, vxrcd, &cmd->base);
+ if (err)
+ return err;
+
+ if (qp_attr->comp_mask & IBV_QP_INIT_ATTR_CREATE_FLAGS) {
+ if (qp_attr->create_flags & ~CREATE_QP_EX2_SUP_CREATE_FLAGS)
+ return EINVAL;
+ if (cmd_core_size < offsetof(struct ibv_create_qp_ex, create_flags) +
+ sizeof(qp_attr->create_flags))
+ return EINVAL;
+ cmd->create_flags = qp_attr->create_flags;
+ }
+
+ err = write(context->cmd_fd, cmd, cmd_size);
+ if (err != cmd_size)
+ return errno;
+
+ (void)VALGRIND_MAKE_MEM_DEFINED(resp, resp_size);
+
+ create_qp_handle_resp_common(context, qp, qp_attr, &resp->base, vxrcd,
+ vqp_sz);
+
+ return 0;
+}
+
int ibv_cmd_create_qp_ex(struct ibv_context *context,
struct verbs_qp *qp, int vqp_sz,
struct ibv_qp_init_attr_ex *attr_ex,
@@ -684,52 +959,22 @@ int ibv_cmd_create_qp_ex(struct ibv_context *context,
struct ibv_create_qp_resp *resp, size_t resp_size)
{
struct verbs_xrcd *vxrcd = NULL;
+ int err;
IBV_INIT_CMD_RESP(cmd, cmd_size, CREATE_QP, resp, resp_size);
- if (attr_ex->comp_mask >= IBV_QP_INIT_ATTR_RESERVED)
+ if (attr_ex->comp_mask > (IBV_QP_INIT_ATTR_XRCD | IBV_QP_INIT_ATTR_PD))
return ENOSYS;
- cmd->user_handle = (uintptr_t) qp;
-
- if (attr_ex->comp_mask & IBV_QP_INIT_ATTR_XRCD) {
- vxrcd = container_of(attr_ex->xrcd, struct verbs_xrcd, xrcd);
- cmd->pd_handle = vxrcd->handle;
- } else {
- if (!(attr_ex->comp_mask & IBV_QP_INIT_ATTR_PD))
- return EINVAL;
-
- cmd->pd_handle = attr_ex->pd->handle;
- cmd->send_cq_handle = attr_ex->send_cq->handle;
-
- if (attr_ex->qp_type != IBV_QPT_XRC_SEND) {
- cmd->recv_cq_handle = attr_ex->recv_cq->handle;
- cmd->srq_handle = attr_ex->srq ? attr_ex->srq->handle : 0;
- }
- }
-
- cmd->max_send_wr = attr_ex->cap.max_send_wr;
- cmd->max_recv_wr = attr_ex->cap.max_recv_wr;
- cmd->max_send_sge = attr_ex->cap.max_send_sge;
- cmd->max_recv_sge = attr_ex->cap.max_recv_sge;
- cmd->max_inline_data = attr_ex->cap.max_inline_data;
- cmd->sq_sig_all = attr_ex->sq_sig_all;
- cmd->qp_type = attr_ex->qp_type;
- cmd->is_srq = !!attr_ex->srq;
- cmd->reserved = 0;
+ err = create_qp_ex_common(qp, attr_ex, vxrcd,
+ (struct ibv_create_qp_common *)&cmd->user_handle);
+ if (err)
+ return err;
if (write(context->cmd_fd, cmd, cmd_size) != cmd_size)
return errno;
- (void) VALGRIND_MAKE_MEM_DEFINED(resp, resp_size);
-
- if (abi_ver > 3) {
- attr_ex->cap.max_recv_sge = resp->max_recv_sge;
- attr_ex->cap.max_send_sge = resp->max_send_sge;
- attr_ex->cap.max_recv_wr = resp->max_recv_wr;
- attr_ex->cap.max_send_wr = resp->max_send_wr;
- attr_ex->cap.max_inline_data = resp->max_inline_data;
- }
+ (void)VALGRIND_MAKE_MEM_DEFINED(resp, resp_size);
if (abi_ver == 4) {
struct ibv_create_qp_resp_v4 *resp_v4 =
@@ -747,26 +992,7 @@ int ibv_cmd_create_qp_ex(struct ibv_context *context,
resp_size - sizeof *resp);
}
- qp->qp.handle = resp->qp_handle;
- qp->qp.qp_num = resp->qpn;
- qp->qp.context = context;
- qp->qp.qp_context = attr_ex->qp_context;
- qp->qp.pd = attr_ex->pd;
- qp->qp.send_cq = attr_ex->send_cq;
- qp->qp.recv_cq = attr_ex->recv_cq;
- qp->qp.srq = attr_ex->srq;
- qp->qp.qp_type = attr_ex->qp_type;
- qp->qp.state = IBV_QPS_RESET;
- qp->qp.events_completed = 0;
- pthread_mutex_init(&qp->qp.mutex, NULL);
- pthread_cond_init(&qp->qp.cond, NULL);
-
- qp->comp_mask = 0;
- if (vext_field_avail(struct verbs_qp, xrcd, vqp_sz) &&
- (attr_ex->comp_mask & IBV_QP_INIT_ATTR_XRCD)) {
- qp->comp_mask |= VERBS_QP_XRCD;
- qp->xrcd = vxrcd;
- }
+ create_qp_handle_resp_common(context, qp, attr_ex, resp, vxrcd, vqp_sz);
return 0;
}
diff --git a/src/device.c b/src/device.c
index f2b889c..e520295 100644
--- a/src/device.c
+++ b/src/device.c
@@ -122,6 +122,38 @@ uint64_t __ibv_get_device_guid(struct ibv_device *device)
}
default_symver(__ibv_get_device_guid, ibv_get_device_guid);
+struct ibv_cq_ex *__lib_ibv_create_cq_ex(struct ibv_context *context,
+ struct ibv_cq_init_attr_ex *cq_attr)
+{
+ struct verbs_context *vctx = verbs_get_ctx(context);
+ struct ibv_cq_ex *cq;
+
+ if (cq_attr->wc_flags & ~IBV_CREATE_CQ_SUP_WC_FLAGS) {
+ errno = EOPNOTSUPP;
+ return NULL;
+ }
+
+ pthread_mutex_lock(&context->mutex);
+
+ cq = vctx->priv->create_cq_ex(context, cq_attr);
+
+ if (cq) {
+ cq->context = context;
+ cq->channel = cq_attr->channel;
+ if (cq->channel)
+ ++cq->channel->refcnt;
+ cq->cq_context = cq_attr->cq_context;
+ cq->comp_events_completed = 0;
+ cq->async_events_completed = 0;
+ pthread_mutex_init(&cq->mutex, NULL);
+ pthread_cond_init(&cq->cond, NULL);
+ }
+
+ pthread_mutex_unlock(&context->mutex);
+
+ return cq;
+}
+
struct ibv_context *__ibv_open_device(struct ibv_device *device)
{
struct verbs_device *verbs_device = verbs_get_device(device);
@@ -148,6 +180,8 @@ struct ibv_context *__ibv_open_device(struct ibv_device *device)
if (!context)
goto err;
} else {
+ struct verbs_ex_private *priv;
+
/* Library now allocates the context */
context_ex = calloc(1, sizeof(*context_ex) +
verbs_device->size_of_context);
@@ -156,6 +190,14 @@ struct ibv_context *__ibv_open_device(struct ibv_device *device)
goto err;
}
+ priv = calloc(1, sizeof(*priv));
+ if (!priv) {
+ errno = ENOMEM;
+ free(context_ex);
+ goto err;
+ }
+
+ context_ex->priv = priv;
context_ex->context.abi_compat = __VERBS_ABI_IS_EXTENDED;
context_ex->sz = sizeof(*context_ex);
@@ -177,6 +219,11 @@ struct ibv_context *__ibv_open_device(struct ibv_device *device)
*/
context_ex->ABI_placeholder1 = (void (*)(void)) context_ex->ibv_create_flow;
context_ex->ABI_placeholder2 = (void (*)(void)) context_ex->ibv_destroy_flow;
+
+ if (context_ex->create_cq_ex) {
+ priv->create_cq_ex = context_ex->create_cq_ex;
+ context_ex->create_cq_ex = __lib_ibv_create_cq_ex;
+ }
}
context->device = device;
@@ -186,6 +233,7 @@ struct ibv_context *__ibv_open_device(struct ibv_device *device)
return context;
verbs_err:
+ free(context_ex->priv);
free(context_ex);
err:
close(cmd_fd);
@@ -204,6 +252,7 @@ int __ibv_close_device(struct ibv_context *context)
if (context_ex) {
struct verbs_device *verbs_device = verbs_get_device(context->device);
verbs_device->uninit_context(verbs_device, context);
+ free(context_ex->priv);
free(context_ex);
} else {
context->device->ops.free_context(context);
diff --git a/src/ibverbs.h b/src/ibverbs.h
index ff206f9..062a490 100644
--- a/src/ibverbs.h
+++ b/src/ibverbs.h
@@ -81,6 +81,11 @@ extern HIDDEN int abi_ver;
HIDDEN int ibverbs_init(struct ibv_device ***list);
+struct verbs_ex_private {
+ struct ibv_cq_ex *(*create_cq_ex)(struct ibv_context *context,
+ struct ibv_cq_init_attr_ex *init_attr);
+};
+
#define IBV_INIT_CMD(cmd, size, opcode) \
do { \
if (abi_ver > 2) \
diff --git a/src/libibverbs.map b/src/libibverbs.map
index 3b40a0f..5134bd9 100644
--- a/src/libibverbs.map
+++ b/src/libibverbs.map
@@ -47,6 +47,7 @@ IBVERBS_1.0 {
ibv_cmd_reg_mr;
ibv_cmd_dereg_mr;
ibv_cmd_create_cq;
+ ibv_cmd_create_cq_ex;
ibv_cmd_poll_cq;
ibv_cmd_req_notify_cq;
ibv_cmd_resize_cq;
@@ -102,6 +103,9 @@ IBVERBS_1.1 {
ibv_event_type_str;
ibv_wc_status_str;
+ ibv_cmd_alloc_mw;
+ ibv_cmd_dealloc_mw;
+
ibv_rate_to_mbps;
mbps_to_ibv_rate;
@@ -111,6 +115,8 @@ IBVERBS_1.1 {
ibv_cmd_close_xrcd;
ibv_cmd_create_srq_ex;
ibv_cmd_create_qp_ex;
+ ibv_cmd_create_qp_ex2;
ibv_cmd_open_qp;
+ ibv_cmd_rereg_mr;
} IBVERBS_1.0;
diff --git a/src/memory.c b/src/memory.c
index e9d1eec..89509c6 100644
--- a/src/memory.c
+++ b/src/memory.c
@@ -140,6 +140,9 @@ int ibv_fork_init(void)
int ret;
unsigned long size;
+ if (getenv("RDMAV_HUGEPAGES_SAFE"))
+ huge_page_enabled = 1;
+
if (mm_root)
return 0;
@@ -153,11 +156,6 @@ int ibv_fork_init(void)
if (posix_memalign(&tmp, page_size, page_size))
return ENOMEM;
- if (getenv("RDMAV_HUGEPAGES_SAFE"))
- huge_page_enabled = 1;
- else
- huge_page_enabled = 0;
-
if (huge_page_enabled) {
size = get_page_size(tmp);
tmp_aligned = (void *) ((uintptr_t) tmp & ~(size - 1));
diff --git a/src/verbs.c b/src/verbs.c
index ada3515..68888c3 100644
--- a/src/verbs.c
+++ b/src/verbs.c
@@ -228,6 +228,68 @@ struct ibv_mr *__ibv_reg_mr(struct ibv_pd *pd, void *addr,
}
default_symver(__ibv_reg_mr, ibv_reg_mr);
+int __ibv_rereg_mr(struct ibv_mr *mr, int flags,
+ struct ibv_pd *pd, void *addr,
+ size_t length, int access)
+{
+ int dofork_onfail = 0;
+ int err;
+ void *old_addr;
+ size_t old_len;
+
+ if (flags & ~IBV_REREG_MR_FLAGS_SUPPORTED) {
+ errno = EINVAL;
+ return IBV_REREG_MR_ERR_INPUT;
+ }
+
+ if ((flags & IBV_REREG_MR_CHANGE_TRANSLATION) &&
+ (!length || !addr)) {
+ errno = EINVAL;
+ return IBV_REREG_MR_ERR_INPUT;
+ }
+
+ if (access && !(flags & IBV_REREG_MR_CHANGE_ACCESS)) {
+ errno = EINVAL;
+ return IBV_REREG_MR_ERR_INPUT;
+ }
+
+ if (!mr->context->ops.rereg_mr) {
+ errno = ENOSYS;
+ return IBV_REREG_MR_ERR_INPUT;
+ }
+
+ if (flags & IBV_REREG_MR_CHANGE_TRANSLATION) {
+ err = ibv_dontfork_range(addr, length);
+ if (err)
+ return IBV_REREG_MR_ERR_DONT_FORK_NEW;
+ dofork_onfail = 1;
+ }
+
+ old_addr = mr->addr;
+ old_len = mr->length;
+ err = mr->context->ops.rereg_mr(mr, flags, pd, addr, length, access);
+ if (!err) {
+ if (flags & IBV_REREG_MR_CHANGE_PD)
+ mr->pd = pd;
+ if (flags & IBV_REREG_MR_CHANGE_TRANSLATION) {
+ mr->addr = addr;
+ mr->length = length;
+ err = ibv_dofork_range(old_addr, old_len);
+ if (err)
+ return IBV_REREG_MR_ERR_DO_FORK_OLD;
+ }
+ } else {
+ err = IBV_REREG_MR_ERR_CMD;
+ if (dofork_onfail) {
+ if (ibv_dofork_range(addr, length))
+ err = IBV_REREG_MR_ERR_CMD_AND_DO_FORK_NEW;
+ }
+ }
+
+ return err;
+}
+default_symver(__ibv_rereg_mr, ibv_rereg_mr);
+
int __ibv_dereg_mr(struct ibv_mr *mr)
{
int ret;
--
Alioth's /usr/local/bin/git-commit-notice on /srv/git.debian.org/git/pkg-ofed/libibverbs.git
More information about the Pkg-ofed-commits
mailing list