Merge tag 'rds-odp-for-5.5' into rdma.git for-next

From https://git.kernel.org/pub/scm/linux/kernel/git/leon/linux-rdma

Leon Romanovsky says:

====================
Use ODP MRs for kernel ULPs

The following series extends MR creation routines to allow creation of
user MRs through kernel ULPs as a proxy. The immediate use case is to
allow RDS to work over FS-DAX, which requires ODP (on-demand-paging)
MRs to be created and such MRs were not possible to create prior this
series.

The first part of this patchset extends RDMA to have special verb
ib_reg_user_mr(). The common use case that uses this function is a
userspace application that allocates memory for HCA access but the
responsibility to register the memory at the HCA is on an kernel ULP.
This ULP acts as an agent for the userspace application.

The second part provides advise MR functionality for ULPs. This is
integral part of ODP flows and used to trigger pagefaults in advance
to prepare memory before running working set.

The third part is actual user of those in-kernel APIs.
====================

* tag 'rds-odp-for-5.5':
  net/rds: Use prefetch for On-Demand-Paging MR
  net/rds: Handle ODP mr registration/unregistration
  net/rds: Detect need of On-Demand-Paging memory registration
  RDMA/mlx5: Fix handling of IOVA != user_va in ODP paths
  IB/mlx5: Mask out unsupported ODP capabilities for kernel QPs
  RDMA/mlx5: Don't fake udata for kernel path
  IB/mlx5: Add ODP WQE handlers for kernel QPs
  IB/core: Add interface to advise_mr for kernel users
  IB/core: Introduce ib_reg_user_mr
  IB: Allow calls to ib_umem_get from kernel ULPs

Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

6 files changed, 68 insertions, 16 deletions

diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index defae23a0169..97830e46d1a0 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -138,6 +138,7 @@ STATIC_OBJDIR	:= $(OUTPUT)staticobjs/
 BPF_IN_SHARED	:= $(SHARED_OBJDIR)libbpf-in.o
 BPF_IN_STATIC	:= $(STATIC_OBJDIR)libbpf-in.o
 VERSION_SCRIPT	:= libbpf.map
+BPF_HELPER_DEFS	:= $(OUTPUT)bpf_helper_defs.h
 
 LIB_TARGET	:= $(addprefix $(OUTPUT),$(LIB_TARGET))
 LIB_FILE	:= $(addprefix $(OUTPUT),$(LIB_FILE))
@@ -159,7 +160,7 @@ all: fixdep
 
 all_cmd: $(CMD_TARGETS) check
 
-$(BPF_IN_SHARED): force elfdep bpfdep bpf_helper_defs.h
+$(BPF_IN_SHARED): force elfdep bpfdep $(BPF_HELPER_DEFS)
 	@(test -f ../../include/uapi/linux/bpf.h -a -f ../../../include/uapi/linux/bpf.h && ( \
 	(diff -B ../../include/uapi/linux/bpf.h ../../../include/uapi/linux/bpf.h >/dev/null) || \
 	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf.h' differs from latest version at 'include/uapi/linux/bpf.h'" >&2 )) || true
@@ -177,12 +178,12 @@ $(BPF_IN_SHARED): force elfdep bpfdep bpf_helper_defs.h
 	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_xdp.h' differs from latest version at 'include/uapi/linux/if_xdp.h'" >&2 )) || true
 	$(Q)$(MAKE) $(build)=libbpf OUTPUT=$(SHARED_OBJDIR) CFLAGS="$(CFLAGS) $(SHLIB_FLAGS)"
 
-$(BPF_IN_STATIC): force elfdep bpfdep bpf_helper_defs.h
+$(BPF_IN_STATIC): force elfdep bpfdep $(BPF_HELPER_DEFS)
 	$(Q)$(MAKE) $(build)=libbpf OUTPUT=$(STATIC_OBJDIR)
 
-bpf_helper_defs.h: $(srctree)/tools/include/uapi/linux/bpf.h
+$(BPF_HELPER_DEFS): $(srctree)/tools/include/uapi/linux/bpf.h
 	$(Q)$(srctree)/scripts/bpf_helpers_doc.py --header 		\
-		--file $(srctree)/tools/include/uapi/linux/bpf.h > bpf_helper_defs.h
+		--file $(srctree)/tools/include/uapi/linux/bpf.h > $(BPF_HELPER_DEFS)
 
 $(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION)
 
@@ -243,7 +244,7 @@ install_lib: all_cmd
 		$(call do_install_mkdir,$(libdir_SQ)); \
 		cp -fpR $(LIB_FILE) $(DESTDIR)$(libdir_SQ)
 
-install_headers: bpf_helper_defs.h
+install_headers: $(BPF_HELPER_DEFS)
 	$(call QUIET_INSTALL, headers) \
 		$(call do_install,bpf.h,$(prefix)/include/bpf,644); \
 		$(call do_install,libbpf.h,$(prefix)/include/bpf,644); \
@@ -251,7 +252,7 @@ install_headers: bpf_helper_defs.h
 		$(call do_install,libbpf_util.h,$(prefix)/include/bpf,644); \
 		$(call do_install,xsk.h,$(prefix)/include/bpf,644); \
 		$(call do_install,bpf_helpers.h,$(prefix)/include/bpf,644); \
-		$(call do_install,bpf_helper_defs.h,$(prefix)/include/bpf,644); \
+		$(call do_install,$(BPF_HELPER_DEFS),$(prefix)/include/bpf,644); \
 		$(call do_install,bpf_tracing.h,$(prefix)/include/bpf,644); \
 		$(call do_install,bpf_endian.h,$(prefix)/include/bpf,644); \
 		$(call do_install,bpf_core_read.h,$(prefix)/include/bpf,644);
@@ -271,7 +272,7 @@ config-clean:
 clean:
 	$(call QUIET_CLEAN, libbpf) $(RM) -rf $(CMD_TARGETS) \
 		*.o *~ *.a *.so *.so.$(LIBBPF_MAJOR_VERSION) .*.d .*.cmd \
-		*.pc LIBBPF-CFLAGS bpf_helper_defs.h \
+		*.pc LIBBPF-CFLAGS $(BPF_HELPER_DEFS) \
 		$(SHARED_OBJDIR) $(STATIC_OBJDIR)
 	$(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf
 
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 419652458da4..1ff0a9f49c01 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -40,3 +40,4 @@ xdping
 test_cpp
 /no_alu32
 /bpf_gcc
+bpf_helper_defs.h
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index e0fe01d9ec33..e2fd6f8d579c 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -120,9 +120,9 @@ force:
 $(BPFOBJ): force
 	$(MAKE) -C $(BPFDIR) OUTPUT=$(OUTPUT)/
 
-BPF_HELPERS := $(BPFDIR)/bpf_helper_defs.h $(wildcard $(BPFDIR)/bpf_*.h)
-$(BPFDIR)/bpf_helper_defs.h:
-	$(MAKE) -C $(BPFDIR) OUTPUT=$(OUTPUT)/ bpf_helper_defs.h
+BPF_HELPERS := $(OUTPUT)/bpf_helper_defs.h $(wildcard $(BPFDIR)/bpf_*.h)
+$(OUTPUT)/bpf_helper_defs.h:
+	$(MAKE) -C $(BPFDIR) OUTPUT=$(OUTPUT)/ $(OUTPUT)/bpf_helper_defs.h
 
 # Get Clang's default includes on this system, as opposed to those seen by
 # '-target bpf'. This fixes "missing" files on some architectures/distros,
diff --git a/tools/testing/selftests/net/forwarding/loopback.sh b/tools/testing/selftests/net/forwarding/loopback.sh
index 6e4626ae71b0..8f4057310b5b 100755
--- a/tools/testing/selftests/net/forwarding/loopback.sh
+++ b/tools/testing/selftests/net/forwarding/loopback.sh
@@ -1,6 +1,9 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
 ALL_TESTS="loopback_test"
 NUM_NETIFS=2
 source tc_common.sh
@@ -72,6 +75,11 @@ setup_prepare()
 
 	h1_create
 	h2_create
+
+	if ethtool -k $h1 | grep loopback | grep -q fixed; then
+		log_test "SKIP: dev $h1 does not support loopback feature"
+		exit $ksft_skip
+	fi
 }
 
 cleanup()
diff --git a/tools/testing/selftests/netfilter/nft_flowtable.sh b/tools/testing/selftests/netfilter/nft_flowtable.sh
index 16571ac1dab4..d3e0809ab368 100755
--- a/tools/testing/selftests/netfilter/nft_flowtable.sh
+++ b/tools/testing/selftests/netfilter/nft_flowtable.sh
@@ -226,17 +226,19 @@ check_transfer()
 	return 0
 }
 
-test_tcp_forwarding()
+test_tcp_forwarding_ip()
 {
 	local nsa=$1
 	local nsb=$2
+	local dstip=$3
+	local dstport=$4
 	local lret=0
 
 	ip netns exec $nsb nc -w 5 -l -p 12345 < "$ns2in" > "$ns2out" &
 	lpid=$!
 
 	sleep 1
-	ip netns exec $nsa nc -w 4 10.0.2.99 12345 < "$ns1in" > "$ns1out" &
+	ip netns exec $nsa nc -w 4 "$dstip" "$dstport" < "$ns1in" > "$ns1out" &
 	cpid=$!
 
 	sleep 3
@@ -258,6 +260,28 @@ test_tcp_forwarding()
 	return $lret
 }
 
+test_tcp_forwarding()
+{
+	test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345
+
+	return $?
+}
+
+test_tcp_forwarding_nat()
+{
+	local lret
+
+	test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345
+	lret=$?
+
+	if [ $lret -eq 0 ] ; then
+		test_tcp_forwarding_ip "$1" "$2" 10.6.6.6 1666
+		lret=$?
+	fi
+
+	return $lret
+}
+
 make_file "$ns1in" "ns1"
 make_file "$ns2in" "ns2"
 
@@ -283,14 +307,19 @@ ip -net ns2 route add 192.168.10.1 via 10.0.2.1
 # Same, but with NAT enabled.
 ip netns exec nsr1 nft -f - <<EOF
 table ip nat {
+   chain prerouting {
+      type nat hook prerouting priority 0; policy accept;
+      meta iif "veth0" ip daddr 10.6.6.6 tcp dport 1666 counter dnat ip to 10.0.2.99:12345
+   }
+
    chain postrouting {
       type nat hook postrouting priority 0; policy accept;
-      meta oifname "veth1" masquerade
+      meta oifname "veth1" counter masquerade
    }
 }
 EOF
 
-test_tcp_forwarding ns1 ns2
+test_tcp_forwarding_nat ns1 ns2
 
 if [ $? -eq 0 ] ;then
 	echo "PASS: flow offloaded for ns1/ns2 with NAT"
@@ -313,7 +342,7 @@ fi
 ip netns exec ns1 sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null
 ip netns exec ns2 sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null
 
-test_tcp_forwarding ns1 ns2
+test_tcp_forwarding_nat ns1 ns2
 if [ $? -eq 0 ] ;then
 	echo "PASS: flow offloaded for ns1/ns2 with NAT and pmtu discovery"
 else
diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index 6944b898bb53..ee1b727ede04 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -3158,7 +3158,18 @@ TEST(user_notification_basic)
 	EXPECT_GT(poll(&pollfd, 1, -1), 0);
 	EXPECT_EQ(pollfd.revents, POLLIN);
 
-	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);
+	/* Test that we can't pass garbage to the kernel. */
+	memset(&req, 0, sizeof(req));
+	req.pid = -1;
+	errno = 0;
+	ret = ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EINVAL, errno);
+
+	if (ret) {
+		req.pid = 0;
+		EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);
+	}
 
 	pollfd.fd = listener;
 	pollfd.events = POLLIN | POLLOUT;
@@ -3278,6 +3289,7 @@ TEST(user_notification_signal)
 
 	close(sk_pair[1]);
 
+	memset(&req, 0, sizeof(req));
 	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);
 
 	EXPECT_EQ(kill(pid, SIGUSR1), 0);
@@ -3296,6 +3308,7 @@ TEST(user_notification_signal)
 	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), -1);
 	EXPECT_EQ(errno, ENOENT);
 
+	memset(&req, 0, sizeof(req));
 	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);
 
 	resp.id = req.id;