From 33b8aad21ac175eba9577a73eb62b0aa141c241c Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 18 Oct 2021 14:38:13 +0200
Subject: selftests: netfilter: add a vrf+conntrack testcase

Rework the reproducer for the vrf+conntrack regression reported
by Eugene into a selftest and also add a test for ip masquerading
that Lahav fixed recently.

With net or net-next tree, the first test fails and the latter
two pass.

With 09e856d54bda5f28 ("vrf: Reset skb conntrack connection on VRF rcv")
reverted first test passes but the last two fail.

A proper fix needs more work, for time being a revert seems to be
the best choice, snat/masquerade did not work before the fix.

Link: https://lore.kernel.org/netdev/378ca299-4474-7e9a-3d36-2350c8c98995@gmail.com/T/#m95358a31810df7392f541f99d187227bc75c9963
Reported-by: Eugene Crosser <crosser@average.org>
Cc: Lahav Schlesinger <lschlesinger@drivenets.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 tools/testing/selftests/netfilter/Makefile         |   3 +-
 tools/testing/selftests/netfilter/conntrack_vrf.sh | 219 +++++++++++++++++++++
 2 files changed, 221 insertions(+), 1 deletion(-)
 create mode 100755 tools/testing/selftests/netfilter/conntrack_vrf.sh

(limited to 'tools')

diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile
index 8748199ac109..ffca314897c4 100644
--- a/tools/testing/selftests/netfilter/Makefile
+++ b/tools/testing/selftests/netfilter/Makefile
@@ -5,7 +5,8 @@ TEST_PROGS := nft_trans_stress.sh nft_fib.sh nft_nat.sh bridge_brouter.sh \
 	conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh \
 	nft_concat_range.sh nft_conntrack_helper.sh \
 	nft_queue.sh nft_meta.sh nf_nat_edemux.sh \
-	ipip-conntrack-mtu.sh conntrack_tcp_unreplied.sh
+	ipip-conntrack-mtu.sh conntrack_tcp_unreplied.sh \
+	conntrack_vrf.sh
 
 LDLIBS = -lmnl
 TEST_GEN_FILES =  nf-queue
diff --git a/tools/testing/selftests/netfilter/conntrack_vrf.sh b/tools/testing/selftests/netfilter/conntrack_vrf.sh
new file mode 100755
index 000000000000..91f3ef0f1192
--- /dev/null
+++ b/tools/testing/selftests/netfilter/conntrack_vrf.sh
@@ -0,0 +1,219 @@
+#!/bin/sh
+
+# This script demonstrates interaction of conntrack and vrf.
+# The vrf driver calls the netfilter hooks again, with oif/iif
+# pointing at the VRF device.
+#
+# For ingress, this means first iteration has iifname of lower/real
+# device.  In this script, thats veth0.
+# Second iteration is iifname set to vrf device, tvrf in this script.
+#
+# For egress, this is reversed: first iteration has the vrf device,
+# second iteration is done with the lower/real/veth0 device.
+#
+# test_ct_zone_in demonstrates unexpected change of nftables
+# behavior # caused by commit 09e856d54bda5f28 "vrf: Reset skb conntrack
+# connection on VRF rcv"
+#
+# It was possible to assign conntrack zone to a packet (or mark it for
+# `notracking`) in the prerouting chain before conntrack, based on real iif.
+#
+# After the change, the zone assignment is lost and the zone is assigned based
+# on the VRF master interface (in case such a rule exists).
+# assignment is lost. Instead, assignment based on the `iif` matching
+# Thus it is impossible to distinguish packets based on the original
+# interface.
+#
+# test_masquerade_vrf and test_masquerade_veth0 demonstrate the problem
+# that was supposed to be fixed by the commit mentioned above to make sure
+# that any fix to test case 1 won't break masquerade again.
+
+ksft_skip=4
+
+IP0=172.30.30.1
+IP1=172.30.30.2
+PFXL=30
+ret=0
+
+sfx=$(mktemp -u "XXXXXXXX")
+ns0="ns0-$sfx"
+ns1="ns1-$sfx"
+
+cleanup()
+{
+	ip netns pids $ns0 | xargs kill 2>/dev/null
+	ip netns pids $ns1 | xargs kill 2>/dev/null
+
+	ip netns del $ns0 $ns1
+}
+
+nft --version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without nft tool"
+	exit $ksft_skip
+fi
+
+ip -Version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without ip tool"
+	exit $ksft_skip
+fi
+
+ip netns add "$ns0"
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not create net namespace $ns0"
+	exit $ksft_skip
+fi
+ip netns add "$ns1"
+
+trap cleanup EXIT
+
+ip netns exec $ns0 sysctl -q -w net.ipv4.conf.default.rp_filter=0
+ip netns exec $ns0 sysctl -q -w net.ipv4.conf.all.rp_filter=0
+ip netns exec $ns0 sysctl -q -w net.ipv4.conf.all.rp_filter=0
+
+ip link add veth0 netns "$ns0" type veth peer name veth0 netns "$ns1" > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not add veth device"
+	exit $ksft_skip
+fi
+
+ip -net $ns0 li add tvrf type vrf table 9876
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not add vrf device"
+	exit $ksft_skip
+fi
+
+ip -net $ns0 li set lo up
+
+ip -net $ns0 li set veth0 master tvrf
+ip -net $ns0 li set tvrf up
+ip -net $ns0 li set veth0 up
+ip -net $ns1 li set veth0 up
+
+ip -net $ns0 addr add $IP0/$PFXL dev veth0
+ip -net $ns1 addr add $IP1/$PFXL dev veth0
+
+ip netns exec $ns1 iperf3 -s > /dev/null 2>&1&
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not start iperf3"
+	exit $ksft_skip
+fi
+
+# test vrf ingress handling.
+# The incoming connection should be placed in conntrack zone 1,
+# as decided by the first iteration of the ruleset.
+test_ct_zone_in()
+{
+ip netns exec $ns0 nft -f - <<EOF
+table testct {
+	chain rawpre {
+		type filter hook prerouting priority raw;
+
+		iif { veth0, tvrf } counter meta nftrace set 1
+		iif veth0 counter ct zone set 1 counter return
+		iif tvrf counter ct zone set 2 counter return
+		ip protocol icmp counter
+		notrack counter
+	}
+
+	chain rawout {
+		type filter hook output priority raw;
+
+		oif veth0 counter ct zone set 1 counter return
+		oif tvrf counter ct zone set 2 counter return
+		notrack counter
+	}
+}
+EOF
+	ip netns exec $ns1 ping -W 1 -c 1 -I veth0 $IP0 > /dev/null
+
+	# should be in zone 1, not zone 2
+	count=$(ip netns exec $ns0 conntrack -L -s $IP1 -d $IP0 -p icmp --zone 1 2>/dev/null | wc -l)
+	if [ $count -eq 1 ]; then
+		echo "PASS: entry found in conntrack zone 1"
+	else
+		echo "FAIL: entry not found in conntrack zone 1"
+		count=$(ip netns exec $ns0 conntrack -L -s $IP1 -d $IP0 -p icmp --zone 2 2> /dev/null | wc -l)
+		if [ $count -eq 1 ]; then
+			echo "FAIL: entry found in zone 2 instead"
+		else
+			echo "FAIL: entry not in zone 1 or 2, dumping table"
+			ip netns exec $ns0 conntrack -L
+			ip netns exec $ns0 nft list ruleset
+		fi
+	fi
+}
+
+# add masq rule that gets evaluated w. outif set to vrf device.
+# This tests the first iteration of the packet through conntrack,
+# oifname is the vrf device.
+test_masquerade_vrf()
+{
+	ip netns exec $ns0 conntrack -F 2>/dev/null
+
+ip netns exec $ns0 nft -f - <<EOF
+flush ruleset
+table ip nat {
+	chain postrouting {
+		type nat hook postrouting priority 0;
+		# NB: masquerade should always be combined with 'oif(name) bla',
+		# lack of this is intentional here, we want to exercise double-snat.
+		ip saddr 172.30.30.0/30 counter masquerade random
+	}
+}
+EOF
+	ip netns exec $ns0 ip vrf exec tvrf iperf3 -t 1 -c $IP1 >/dev/null
+	if [ $? -ne 0 ]; then
+		echo "FAIL: iperf3 connect failure with masquerade + sport rewrite on vrf device"
+		ret=1
+		return
+	fi
+
+	# must also check that nat table was evaluated on second (lower device) iteration.
+	ip netns exec $ns0 nft list table ip nat |grep -q 'counter packets 2'
+	if [ $? -eq 0 ]; then
+		echo "PASS: iperf3 connect with masquerade + sport rewrite on vrf device"
+	else
+		echo "FAIL: vrf masq rule has unexpected counter value"
+		ret=1
+	fi
+}
+
+# add masq rule that gets evaluated w. outif set to veth device.
+# This tests the 2nd iteration of the packet through conntrack,
+# oifname is the lower device (veth0 in this case).
+test_masquerade_veth()
+{
+	ip netns exec $ns0 conntrack -F 2>/dev/null
+ip netns exec $ns0 nft -f - <<EOF
+flush ruleset
+table ip nat {
+	chain postrouting {
+		type nat hook postrouting priority 0;
+		meta oif veth0 ip saddr 172.30.30.0/30 counter masquerade random
+	}
+}
+EOF
+	ip netns exec $ns0 ip vrf exec tvrf iperf3 -t 1 -c $IP1 > /dev/null
+	if [ $? -ne 0 ]; then
+		echo "FAIL: iperf3 connect failure with masquerade + sport rewrite on veth device"
+		ret=1
+		return
+	fi
+
+	# must also check that nat table was evaluated on second (lower device) iteration.
+	ip netns exec $ns0 nft list table ip nat |grep -q 'counter packets 2'
+	if [ $? -eq 0 ]; then
+		echo "PASS: iperf3 connect with masquerade + sport rewrite on veth device"
+	else
+		echo "FAIL: vrf masq rule has unexpected counter value"
+		ret=1
+	fi
+}
+
+test_ct_zone_in
+test_masquerade_vrf
+test_masquerade_veth
+
+exit $ret
-- 
cgit v1.2.3


From 228c3fa054ad118f78fc60f1a3f05ba29b043608 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 20 Oct 2021 18:25:37 +0200
Subject: selftests: netfilter: extend nfqueue tests to cover vrf device

VRF device calls the output/postrouting hooks so packet should be seeon
with oifname tvrf and once with eth0.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 tools/testing/selftests/netfilter/nft_queue.sh | 54 ++++++++++++++++++++++++++
 1 file changed, 54 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/netfilter/nft_queue.sh b/tools/testing/selftests/netfilter/nft_queue.sh
index 3d202b90b33d..7d27f1f3bc01 100755
--- a/tools/testing/selftests/netfilter/nft_queue.sh
+++ b/tools/testing/selftests/netfilter/nft_queue.sh
@@ -16,6 +16,10 @@ timeout=4
 
 cleanup()
 {
+	ip netns pids ${ns1} | xargs kill 2>/dev/null
+	ip netns pids ${ns2} | xargs kill 2>/dev/null
+	ip netns pids ${nsrouter} | xargs kill 2>/dev/null
+
 	ip netns del ${ns1}
 	ip netns del ${ns2}
 	ip netns del ${nsrouter}
@@ -332,6 +336,55 @@ EOF
 	echo "PASS: tcp via loopback and re-queueing"
 }
 
+test_icmp_vrf() {
+	ip -net $ns1 link add tvrf type vrf table 9876
+	if [ $? -ne 0 ];then
+		echo "SKIP: Could not add vrf device"
+		return
+	fi
+
+	ip -net $ns1 li set eth0 master tvrf
+	ip -net $ns1 li set tvrf up
+
+	ip -net $ns1 route add 10.0.2.0/24 via 10.0.1.1 dev eth0 table 9876
+ip netns exec ${ns1} nft -f /dev/stdin <<EOF
+flush ruleset
+table inet filter {
+	chain output {
+		type filter hook output priority 0; policy accept;
+		meta oifname "tvrf" icmp type echo-request counter queue num 1
+		meta oifname "eth0" icmp type echo-request counter queue num 1
+	}
+	chain post {
+		type filter hook postrouting priority 0; policy accept;
+		meta oifname "tvrf" icmp type echo-request counter queue num 1
+		meta oifname "eth0" icmp type echo-request counter queue num 1
+	}
+}
+EOF
+	ip netns exec ${ns1} ./nf-queue -q 1 -t $timeout &
+	local nfqpid=$!
+
+	sleep 1
+	ip netns exec ${ns1} ip vrf exec tvrf ping -c 1 10.0.2.99 > /dev/null
+
+	for n in output post; do
+		for d in tvrf eth0; do
+			ip netns exec ${ns1} nft list chain inet filter $n | grep -q "oifname \"$d\" icmp type echo-request counter packets 1"
+			if [ $? -ne 0 ] ; then
+				echo "FAIL: chain $n: icmp packet counter mismatch for device $d" 1>&2
+				ip netns exec ${ns1} nft list ruleset
+				ret=1
+				return
+			fi
+		done
+	done
+
+	wait $nfqpid
+	[ $? -eq 0 ] && echo "PASS: icmp+nfqueue via vrf"
+	wait 2>/dev/null
+}
+
 ip netns exec ${nsrouter} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
 ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
 ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
@@ -372,5 +425,6 @@ test_queue 20
 test_tcp_forward
 test_tcp_localhost
 test_tcp_localhost_requeue
+test_icmp_vrf
 
 exit $ret
-- 
cgit v1.2.3


From e1f8bc06e49794ebecc0f276429a7ab9f105ac06 Mon Sep 17 00:00:00 2001
From: Phil Sutter <phil@nwl.cc>
Date: Wed, 3 Nov 2021 19:53:42 +0100
Subject: selftests: nft_nat: Improve port shadow test stability

Setup phase in test_port_shadow() relied upon a race-condition:
Listening nc on port 1405 was started in background before attempting to
create the fake conntrack entry using the same source port. If listening
nc won, fake conntrack entry could not be created causing wrong
behaviour. Reorder nc calls to fix this and introduce a short delay
before testing the setup to wait for listening nc process startup.

Fixes: 465f15a6d1a8f ("selftests: nft_nat: add udp hole punch test case")
Signed-off-by: Phil Sutter <phil@nwl.cc>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 tools/testing/selftests/netfilter/nft_nat.sh | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh
index da1c1e4b6c86..905c033db74d 100755
--- a/tools/testing/selftests/netfilter/nft_nat.sh
+++ b/tools/testing/selftests/netfilter/nft_nat.sh
@@ -759,14 +759,16 @@ test_port_shadow()
 	local result=""
 	local logmsg=""
 
+	# make shadow entry, from client (ns2), going to (ns1), port 41404, sport 1405.
+	echo "fake-entry" | ip netns exec "$ns2" nc -w 1 -p 1405 -u "$daddrc" 41404 > /dev/null
+
 	echo ROUTER | ip netns exec "$ns0" nc -w 5 -u -l -p 1405 >/dev/null 2>&1 &
 	nc_r=$!
 
 	echo CLIENT | ip netns exec "$ns2" nc -w 5 -u -l -p 1405 >/dev/null 2>&1 &
 	nc_c=$!
 
-	# make shadow entry, from client (ns2), going to (ns1), port 41404, sport 1405.
-	echo "fake-entry" | ip netns exec "$ns2" nc -w 1 -p 1405 -u "$daddrc" 41404 > /dev/null
+	sleep 0.3
 
 	# ns1 tries to connect to ns0:1405.  With default settings this should connect
 	# to client, it matches the conntrack entry created above.
-- 
cgit v1.2.3


From 85c0c8b342e89761554eed3f572ee55c0e5c6536 Mon Sep 17 00:00:00 2001
From: Phil Sutter <phil@nwl.cc>
Date: Wed, 3 Nov 2021 19:53:43 +0100
Subject: selftests: nft_nat: Simplify port shadow notrack test

The second rule in prerouting chain was probably a leftover: The router
listens on veth0, so not tracking connections via that interface is
sufficient. Likewise, the rule in output chain can be limited to that
interface as well.

Signed-off-by: Phil Sutter <phil@nwl.cc>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 tools/testing/selftests/netfilter/nft_nat.sh | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh
index 905c033db74d..c62e4e26252c 100755
--- a/tools/testing/selftests/netfilter/nft_nat.sh
+++ b/tools/testing/selftests/netfilter/nft_nat.sh
@@ -818,11 +818,10 @@ table $family raw {
 	chain prerouting {
 		type filter hook prerouting priority -300; policy accept;
 		meta iif veth0 udp dport 1405 notrack
-		udp dport 1405 notrack
 	}
 	chain output {
 		type filter hook output priority -300; policy accept;
-		udp sport 1405 notrack
+		meta oif veth0 udp sport 1405 notrack
 	}
 }
 EOF
-- 
cgit v1.2.3


From 6af2e1237412ca735e3f18f2044902b0c514f2db Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@cloudflare.com>
Date: Thu, 11 Nov 2021 16:14:52 +0000
Subject: selftests/bpf: Check map in map pruning

Ensure that two registers with a map_value loaded from a nested
map are considered equivalent for the purpose of state pruning
and don't cause the verifier to revisit a pruning point.

This uses a rather crude match on the number of insns visited by
the verifier, which might change in the future. I've therefore
tried to keep the code as "unpruneable" as possible by having
the code paths only converge on the second to last instruction.

Should you require to adjust the test in the future, reducing the
number of processed instructions should always be safe. Increasing
them could cause another regression, so proceed with caution.

Suggested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/CACAyw99hVEJFoiBH_ZGyy=+oO-jyydoz6v1DeKPKs2HVsUH28w@mail.gmail.com
Link: https://lore.kernel.org/bpf/20211111161452.86864-1-lmb@cloudflare.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/verifier/map_in_map.c | 34 +++++++++++++++++++++++
 1 file changed, 34 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/verifier/map_in_map.c b/tools/testing/selftests/bpf/verifier/map_in_map.c
index 2798927ee9ff..128a348b762d 100644
--- a/tools/testing/selftests/bpf/verifier/map_in_map.c
+++ b/tools/testing/selftests/bpf/verifier/map_in_map.c
@@ -18,6 +18,40 @@
 	.fixup_map_in_map = { 3 },
 	.result = ACCEPT,
 },
+{
+	"map in map state pruning",
+	.insns = {
+	BPF_ST_MEM(0, BPF_REG_10, -4, 0),
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -4),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_6),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_6),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 11),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_6),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_6),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_in_map = { 4, 14 },
+	.flags = BPF_F_TEST_STATE_FREQ,
+	.result = VERBOSE_ACCEPT,
+	.errstr = "processed 25 insns",
+	.prog_type = BPF_PROG_TYPE_XDP,
+},
 {
 	"invalid inner map pointer",
 	.insns = {
-- 
cgit v1.2.3


From e4ac80ef8198636a23866a59575917550328886f Mon Sep 17 00:00:00 2001
From: Jean-Philippe Brucker <jean-philippe@linaro.org>
Date: Fri, 12 Nov 2021 15:51:30 +0000
Subject: tools/runqslower: Fix cross-build

Commit be79505caf3f ("tools/runqslower: Install libbpf headers when
building") uses the target libbpf to build the host bpftool, which
doesn't work when cross-building:

  make ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu- -C tools/bpf/runqslower O=/tmp/runqslower
  ...
    LINK    /tmp/runqslower/bpftool/bpftool
  /usr/bin/ld: /tmp/runqslower/libbpf/libbpf.a(libbpf-in.o): Relocations in generic ELF (EM: 183)
  /usr/bin/ld: /tmp/runqslower/libbpf/libbpf.a: error adding symbols: file in wrong format
  collect2: error: ld returned 1 exit status

When cross-building, the target architecture differs from the host. The
bpftool used for building runqslower is executed on the host, and thus
must use a different libbpf than that used for runqslower itself.
Remove the LIBBPF_OUTPUT and LIBBPF_DESTDIR parameters, so the bpftool
build makes its own library if necessary.

In the selftests, pass the host bpftool, already a prerequisite for the
runqslower recipe, as BPFTOOL_OUTPUT. The runqslower Makefile will use
the bpftool that's already built for selftests instead of making a new
one.

Fixes: be79505caf3f ("tools/runqslower: Install libbpf headers when building")
Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Quentin Monnet <quentin@isovalent.com>
Link: https://lore.kernel.org/bpf/20211112155128.565680-1-jean-philippe@linaro.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/runqslower/Makefile        | 3 +--
 tools/testing/selftests/bpf/Makefile | 2 +-
 2 files changed, 2 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/runqslower/Makefile b/tools/bpf/runqslower/Makefile
index bbd1150578f7..8791d0e2762b 100644
--- a/tools/bpf/runqslower/Makefile
+++ b/tools/bpf/runqslower/Makefile
@@ -88,5 +88,4 @@ $(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(BPFOBJ_OU
 
 $(DEFAULT_BPFTOOL): $(BPFOBJ) | $(BPFTOOL_OUTPUT)
 	$(Q)$(MAKE) $(submake_extras) -C ../bpftool OUTPUT=$(BPFTOOL_OUTPUT)   \
-		    LIBBPF_OUTPUT=$(BPFOBJ_OUTPUT)			       \
-		    LIBBPF_DESTDIR=$(BPF_DESTDIR) CC=$(HOSTCC) LD=$(HOSTLD)
+		    CC=$(HOSTCC) LD=$(HOSTLD)
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 54b0a41a3775..62fafbeb4672 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -187,7 +187,7 @@ DEFAULT_BPFTOOL := $(HOST_SCRATCH_DIR)/sbin/bpftool
 $(OUTPUT)/runqslower: $(BPFOBJ) | $(DEFAULT_BPFTOOL) $(RUNQSLOWER_OUTPUT)
 	$(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/runqslower	       \
 		    OUTPUT=$(RUNQSLOWER_OUTPUT) VMLINUX_BTF=$(VMLINUX_BTF)     \
-		    BPFTOOL_OUTPUT=$(BUILD_DIR)/bpftool/		       \
+		    BPFTOOL_OUTPUT=$(HOST_BUILD_DIR)/bpftool/		       \
 		    BPFOBJ_OUTPUT=$(BUILD_DIR)/libbpf			       \
 		    BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR) &&	       \
 		    cp $(RUNQSLOWER_OUTPUT)runqslower $@
-- 
cgit v1.2.3


From ba05fd36b8512d6aeefe9c2c5b6a25b726c4bfff Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Sat, 13 Nov 2021 04:50:22 +0530
Subject: libbpf: Perform map fd cleanup for gen_loader in case of error

Alexei reported a fd leak issue in gen loader (when invoked from
bpftool) [0]. When adding ksym support, map fd allocation was moved from
stack to loader map, however I missed closing these fds (relevant when
cleanup label is jumped to on error). For the success case, the
allocated fd is returned in loader ctx, hence this problem is not
noticed.

Make three changes, first MAX_USED_MAPS in MAX_FD_ARRAY_SZ instead of
MAX_USED_PROGS, the braino was not a problem until now for this case as
we didn't try to close map fds (otherwise use of it would have tried
closing 32 additional fds in ksym btf fd range). Then, do a cleanup for
all nr_maps fds in cleanup label code, so that in case of error all
temporary map fds from bpf_gen__map_create are closed.

Then, adjust the cleanup label to only generate code for the required
number of program and map fds.  To trim code for remaining program
fds, lay out prog_fd array in stack in the end, so that we can
directly skip the remaining instances.  Still stack size remains same,
since changing that would require changes in a lot of places
(including adjustment of stack_off macro), so nr_progs_sz variable is
only used to track required number of iterations (and jump over
cleanup size calculated from that), stack offset calculation remains
unaffected.

The difference for test_ksyms_module.o is as follows:
libbpf: //prog cleanup iterations: before = 34, after = 5
libbpf: //maps cleanup iterations: before = 64, after = 2

Also, move allocation of gen->fd_array offset to bpf_gen__init. Since
offset can now be 0, and we already continue even if add_data returns 0
in case of failure, we do not need to distinguish between 0 offset and
failure case 0, as we rely on bpf_gen__finish to check errors. We can
also skip check for gen->fd_array in add_*_fd functions, since
bpf_gen__init will take care of it.

  [0]: https://lore.kernel.org/bpf/CAADnVQJ6jSitKSNKyxOrUzwY2qDRX0sPkJ=VLGHuCLVJ=qOt9g@mail.gmail.com

Fixes: 18f4fccbf314 ("libbpf: Update gen_loader to emit BTF_KIND_FUNC relocations")
Reported-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20211112232022.899074-1-memxor@gmail.com
---
 tools/lib/bpf/bpf_gen_internal.h |  4 ++--
 tools/lib/bpf/gen_loader.c       | 47 +++++++++++++++++++++++++---------------
 tools/lib/bpf/libbpf.c           |  4 ++--
 3 files changed, 34 insertions(+), 21 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/bpf_gen_internal.h b/tools/lib/bpf/bpf_gen_internal.h
index d26e5472fe50..6f3df004479b 100644
--- a/tools/lib/bpf/bpf_gen_internal.h
+++ b/tools/lib/bpf/bpf_gen_internal.h
@@ -45,8 +45,8 @@ struct bpf_gen {
 	int nr_fd_array;
 };
 
-void bpf_gen__init(struct bpf_gen *gen, int log_level);
-int bpf_gen__finish(struct bpf_gen *gen);
+void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps);
+int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps);
 void bpf_gen__free(struct bpf_gen *gen);
 void bpf_gen__load_btf(struct bpf_gen *gen, const void *raw_data, __u32 raw_size);
 void bpf_gen__map_create(struct bpf_gen *gen, struct bpf_create_map_params *map_attr, int map_idx);
diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c
index 502dea53a742..9934851ccde7 100644
--- a/tools/lib/bpf/gen_loader.c
+++ b/tools/lib/bpf/gen_loader.c
@@ -18,7 +18,7 @@
 #define MAX_USED_MAPS	64
 #define MAX_USED_PROGS	32
 #define MAX_KFUNC_DESCS 256
-#define MAX_FD_ARRAY_SZ (MAX_USED_PROGS + MAX_KFUNC_DESCS)
+#define MAX_FD_ARRAY_SZ (MAX_USED_MAPS + MAX_KFUNC_DESCS)
 
 /* The following structure describes the stack layout of the loader program.
  * In addition R6 contains the pointer to context.
@@ -33,8 +33,8 @@
  */
 struct loader_stack {
 	__u32 btf_fd;
-	__u32 prog_fd[MAX_USED_PROGS];
 	__u32 inner_map_fd;
+	__u32 prog_fd[MAX_USED_PROGS];
 };
 
 #define stack_off(field) \
@@ -42,6 +42,11 @@ struct loader_stack {
 
 #define attr_field(attr, field) (attr + offsetof(union bpf_attr, field))
 
+static int blob_fd_array_off(struct bpf_gen *gen, int index)
+{
+	return gen->fd_array + index * sizeof(int);
+}
+
 static int realloc_insn_buf(struct bpf_gen *gen, __u32 size)
 {
 	size_t off = gen->insn_cur - gen->insn_start;
@@ -102,11 +107,15 @@ static void emit2(struct bpf_gen *gen, struct bpf_insn insn1, struct bpf_insn in
 	emit(gen, insn2);
 }
 
-void bpf_gen__init(struct bpf_gen *gen, int log_level)
+static int add_data(struct bpf_gen *gen, const void *data, __u32 size);
+static void emit_sys_close_blob(struct bpf_gen *gen, int blob_off);
+
+void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps)
 {
-	size_t stack_sz = sizeof(struct loader_stack);
+	size_t stack_sz = sizeof(struct loader_stack), nr_progs_sz;
 	int i;
 
+	gen->fd_array = add_data(gen, NULL, MAX_FD_ARRAY_SZ * sizeof(int));
 	gen->log_level = log_level;
 	/* save ctx pointer into R6 */
 	emit(gen, BPF_MOV64_REG(BPF_REG_6, BPF_REG_1));
@@ -118,19 +127,27 @@ void bpf_gen__init(struct bpf_gen *gen, int log_level)
 	emit(gen, BPF_MOV64_IMM(BPF_REG_3, 0));
 	emit(gen, BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel));
 
+	/* amount of stack actually used, only used to calculate iterations, not stack offset */
+	nr_progs_sz = offsetof(struct loader_stack, prog_fd[nr_progs]);
 	/* jump over cleanup code */
 	emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0,
-			      /* size of cleanup code below */
-			      (stack_sz / 4) * 3 + 2));
+			      /* size of cleanup code below (including map fd cleanup) */
+			      (nr_progs_sz / 4) * 3 + 2 +
+			      /* 6 insns for emit_sys_close_blob,
+			       * 6 insns for debug_regs in emit_sys_close_blob
+			       */
+			      nr_maps * (6 + (gen->log_level ? 6 : 0))));
 
 	/* remember the label where all error branches will jump to */
 	gen->cleanup_label = gen->insn_cur - gen->insn_start;
 	/* emit cleanup code: close all temp FDs */
-	for (i = 0; i < stack_sz; i += 4) {
+	for (i = 0; i < nr_progs_sz; i += 4) {
 		emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_10, -stack_sz + i));
 		emit(gen, BPF_JMP_IMM(BPF_JSLE, BPF_REG_1, 0, 1));
 		emit(gen, BPF_EMIT_CALL(BPF_FUNC_sys_close));
 	}
+	for (i = 0; i < nr_maps; i++)
+		emit_sys_close_blob(gen, blob_fd_array_off(gen, i));
 	/* R7 contains the error code from sys_bpf. Copy it into R0 and exit. */
 	emit(gen, BPF_MOV64_REG(BPF_REG_0, BPF_REG_7));
 	emit(gen, BPF_EXIT_INSN());
@@ -160,8 +177,6 @@ static int add_data(struct bpf_gen *gen, const void *data, __u32 size)
  */
 static int add_map_fd(struct bpf_gen *gen)
 {
-	if (!gen->fd_array)
-		gen->fd_array = add_data(gen, NULL, MAX_FD_ARRAY_SZ * sizeof(int));
 	if (gen->nr_maps == MAX_USED_MAPS) {
 		pr_warn("Total maps exceeds %d\n", MAX_USED_MAPS);
 		gen->error = -E2BIG;
@@ -174,8 +189,6 @@ static int add_kfunc_btf_fd(struct bpf_gen *gen)
 {
 	int cur;
 
-	if (!gen->fd_array)
-		gen->fd_array = add_data(gen, NULL, MAX_FD_ARRAY_SZ * sizeof(int));
 	if (gen->nr_fd_array == MAX_KFUNC_DESCS) {
 		cur = add_data(gen, NULL, sizeof(int));
 		return (cur - gen->fd_array) / sizeof(int);
@@ -183,11 +196,6 @@ static int add_kfunc_btf_fd(struct bpf_gen *gen)
 	return MAX_USED_MAPS + gen->nr_fd_array++;
 }
 
-static int blob_fd_array_off(struct bpf_gen *gen, int index)
-{
-	return gen->fd_array + index * sizeof(int);
-}
-
 static int insn_bytes_to_bpf_size(__u32 sz)
 {
 	switch (sz) {
@@ -359,10 +367,15 @@ static void emit_sys_close_blob(struct bpf_gen *gen, int blob_off)
 	__emit_sys_close(gen);
 }
 
-int bpf_gen__finish(struct bpf_gen *gen)
+int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps)
 {
 	int i;
 
+	if (nr_progs != gen->nr_progs || nr_maps != gen->nr_maps) {
+		pr_warn("progs/maps mismatch\n");
+		gen->error = -EFAULT;
+		return gen->error;
+	}
 	emit_sys_close_stack(gen, stack_off(btf_fd));
 	for (i = 0; i < gen->nr_progs; i++)
 		move_stack2ctx(gen,
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index a1bea1953df6..7c74342bb668 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -7258,7 +7258,7 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr)
 	}
 
 	if (obj->gen_loader)
-		bpf_gen__init(obj->gen_loader, attr->log_level);
+		bpf_gen__init(obj->gen_loader, attr->log_level, obj->nr_programs, obj->nr_maps);
 
 	err = bpf_object__probe_loading(obj);
 	err = err ? : bpf_object__load_vmlinux_btf(obj, false);
@@ -7277,7 +7277,7 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr)
 		for (i = 0; i < obj->nr_maps; i++)
 			obj->maps[i].fd = -1;
 		if (!err)
-			err = bpf_gen__finish(obj->gen_loader);
+			err = bpf_gen__finish(obj->gen_loader, obj->nr_programs, obj->nr_maps);
 	}
 
 	/* clean up fd_array */
-- 
cgit v1.2.3


From 0cda7d4bac5fd29dceb13df26083333fa99d6bb4 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 11 Nov 2021 08:29:29 -0800
Subject: selftests: net: switch to socat in the GSO GRE test

Commit a985442fdecb ("selftests: net: properly support IPv6 in GSO GRE test")
is not compatible with:

  Ncat: Version 7.80 ( https://nmap.org/ncat )

(which is distributed with Fedora/Red Hat), tests fail with:

  nc: invalid option -- 'N'

Let's switch to socat which is far more dependable.

Fixes: 025efa0a82df ("selftests: add simple GSO GRE test")
Fixes: a985442fdecb ("selftests: net: properly support IPv6 in GSO GRE test")
Tested-by: Andrea Righi <andrea.righi@canonical.com>
Link: https://lore.kernel.org/r/20211111162929.530470-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/gre_gso.sh | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/gre_gso.sh b/tools/testing/selftests/net/gre_gso.sh
index fdeb44d621eb..3224651db97b 100755
--- a/tools/testing/selftests/net/gre_gso.sh
+++ b/tools/testing/selftests/net/gre_gso.sh
@@ -118,16 +118,18 @@ gre_gst_test_checks()
 	local addr=$2
 	local proto=$3
 
-	$NS_EXEC nc $proto -kl $port >/dev/null &
+	[ "$proto" == 6 ] && addr="[$addr]"
+
+	$NS_EXEC socat - tcp${proto}-listen:$port,reuseaddr,fork >/dev/null &
 	PID=$!
 	while ! $NS_EXEC ss -ltn | grep -q $port; do ((i++)); sleep 0.01; done
 
-	cat $TMPFILE | timeout 1 nc $proto -N $addr $port
+	cat $TMPFILE | timeout 1 socat -u STDIN TCP:$addr:$port
 	log_test $? 0 "$name - copy file w/ TSO"
 
 	ethtool -K veth0 tso off
 
-	cat $TMPFILE | timeout 1 nc $proto -N $addr $port
+	cat $TMPFILE | timeout 1 socat -u STDIN TCP:$addr:$port
 	log_test $? 0 "$name - copy file w/ GSO"
 
 	ethtool -K veth0 tso on
@@ -155,8 +157,8 @@ gre6_gso_test()
 
 	sleep 2
 
-	gre_gst_test_checks GREv6/v4 172.16.2.2
-	gre_gst_test_checks GREv6/v6 2001:db8:1::2 -6
+	gre_gst_test_checks GREv6/v4 172.16.2.2 4
+	gre_gst_test_checks GREv6/v6 2001:db8:1::2 6
 
 	cleanup
 }
@@ -212,8 +214,8 @@ if [ ! -x "$(command -v ip)" ]; then
 	exit $ksft_skip
 fi
 
-if [ ! -x "$(command -v nc)" ]; then
-	echo "SKIP: Could not run test without nc tool"
+if [ ! -x "$(command -v socat)" ]; then
+	echo "SKIP: Could not run test without socat tool"
 	exit $ksft_skip
 fi
 
-- 
cgit v1.2.3


From a2acf0c0e2da29950d0361a3b5ea05e8d0351dfe Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 11 Nov 2021 18:23:30 +0100
Subject: selftests: nft_nat: switch port shadow test cases to socat

There are now at least three distinct flavours of netcat/nc tool:
'original' version, one version ported from openbsd and nmap-ncat.

The script only works with original because it sets SOREUSEPORT option.

Other nc versions return 'port already in use' error and port shadow test fails:

PASS: inet IPv6 redirection for ns2-hMHcaRvx
nc: bind failed: Address already in use
ERROR: portshadow test default: got reply from "ROUTER", not CLIENT as intended

Switch to socat instead.

Reported-by: kernel test robot <oliver.sang@intel.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 tools/testing/selftests/netfilter/nft_nat.sh | 26 +++++++++++++++++++-------
 1 file changed, 19 insertions(+), 7 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh
index c62e4e26252c..d88867d2fed7 100755
--- a/tools/testing/selftests/netfilter/nft_nat.sh
+++ b/tools/testing/selftests/netfilter/nft_nat.sh
@@ -760,20 +760,20 @@ test_port_shadow()
 	local logmsg=""
 
 	# make shadow entry, from client (ns2), going to (ns1), port 41404, sport 1405.
-	echo "fake-entry" | ip netns exec "$ns2" nc -w 1 -p 1405 -u "$daddrc" 41404 > /dev/null
+	echo "fake-entry" | ip netns exec "$ns2" timeout 1 socat -u STDIN UDP:"$daddrc":41404,sourceport=1405
 
-	echo ROUTER | ip netns exec "$ns0" nc -w 5 -u -l -p 1405 >/dev/null 2>&1 &
-	nc_r=$!
+	echo ROUTER | ip netns exec "$ns0" timeout 5 socat -u STDIN UDP4-LISTEN:1405 &
+	sc_r=$!
 
-	echo CLIENT | ip netns exec "$ns2" nc -w 5 -u -l -p 1405 >/dev/null 2>&1 &
-	nc_c=$!
+	echo CLIENT | ip netns exec "$ns2" timeout 5 socat -u STDIN UDP4-LISTEN:1405,reuseport &
+	sc_c=$!
 
 	sleep 0.3
 
 	# ns1 tries to connect to ns0:1405.  With default settings this should connect
 	# to client, it matches the conntrack entry created above.
 
-	result=$(echo "" | ip netns exec "$ns1" nc -w 1 -p 41404 -u "$daddrs" 1405)
+	result=$(echo "data" | ip netns exec "$ns1" timeout 1 socat - UDP:"$daddrs":1405,sourceport=41404)
 
 	if [ "$result" = "$expect" ] ;then
 		echo "PASS: portshadow test $test: got reply from ${expect}${logmsg}"
@@ -782,7 +782,7 @@ test_port_shadow()
 		ret=1
 	fi
 
-	kill $nc_r $nc_c 2>/dev/null
+	kill $sc_r $sc_c 2>/dev/null
 
 	# flush udp entries for next test round, if any
 	ip netns exec "$ns0" conntrack -F >/dev/null 2>&1
@@ -852,6 +852,18 @@ test_port_shadowing()
 {
 	local family="ip"
 
+	conntrack -h >/dev/null 2>&1
+	if [ $? -ne 0 ];then
+		echo "SKIP: Could not run nat port shadowing test without conntrack tool"
+		return
+	fi
+
+	socat -h > /dev/null 2>&1
+	if [ $? -ne 0 ];then
+		echo "SKIP: Could not run nat port shadowing test without socat tool"
+		return
+	fi
+
 	ip netns exec "$ns0" sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
 	ip netns exec "$ns0" sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
 
-- 
cgit v1.2.3


From 92a59d7f381d2caf69385bfa00590028e32eea26 Mon Sep 17 00:00:00 2001
From: Li Zhijian <lizhijian@cn.fujitsu.com>
Date: Mon, 8 Nov 2021 09:28:49 +0800
Subject: selftests: gpio: fix gpio compiling error

The gpio selftests build against the system includes rather than the
headers from the linux tree.  This results in the compile failing if
the system includes are outdated.

Prefer the headers from the linux tree, as per other selftests.

Fixes: 8bc395a6a2e2 ("selftests: gpio: rework and simplify test implementation")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
[Kent: reworded commit comment and added Fixes:]
Signed-off-by: Kent Gibson <warthog618@gmail.com>
Signed-off-by: Bartosz Golaszewski <brgl@bgdev.pl>
---
 tools/testing/selftests/gpio/Makefile | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/gpio/Makefile b/tools/testing/selftests/gpio/Makefile
index 39f2bbe8dd3d..42ea7d2aa844 100644
--- a/tools/testing/selftests/gpio/Makefile
+++ b/tools/testing/selftests/gpio/Makefile
@@ -3,5 +3,6 @@
 TEST_PROGS := gpio-mockup.sh
 TEST_FILES := gpio-mockup-sysfs.sh
 TEST_GEN_PROGS_EXTENDED := gpio-mockup-cdev
+CFLAGS += -I../../../../usr/include
 
 include ../lib.mk
-- 
cgit v1.2.3


From c472d71be0be0f0ca0fbb794dce83bd76623ee2f Mon Sep 17 00:00:00 2001
From: Kent Gibson <warthog618@gmail.com>
Date: Mon, 8 Nov 2021 09:28:50 +0800
Subject: selftests: gpio: fix uninitialised variable warning

When compiled with -Wall gpio-mockup-cdev.c reports an uninitialised
variable warning.  This is a false positive, as the variable is ignored
in the case it is uninitialised, but initialise the variable anyway
to remove the warning.

Signed-off-by: Kent Gibson <warthog618@gmail.com>
Signed-off-by: Bartosz Golaszewski <brgl@bgdev.pl>
---
 tools/testing/selftests/gpio/gpio-mockup-cdev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/gpio/gpio-mockup-cdev.c b/tools/testing/selftests/gpio/gpio-mockup-cdev.c
index e83eac71621a..d1640f44f8ac 100644
--- a/tools/testing/selftests/gpio/gpio-mockup-cdev.c
+++ b/tools/testing/selftests/gpio/gpio-mockup-cdev.c
@@ -117,7 +117,7 @@ int main(int argc, char *argv[])
 {
 	char *chip;
 	int opt, ret, cfd, lfd;
-	unsigned int offset, val, abiv;
+	unsigned int offset, val = 0, abiv;
 	uint32_t flags_v1;
 	uint64_t flags_v2;
 
-- 
cgit v1.2.3


From 4f4d0af7b2d997635b08fabd748673eff1bb12d6 Mon Sep 17 00:00:00 2001
From: Kent Gibson <warthog618@gmail.com>
Date: Mon, 8 Nov 2021 09:28:51 +0800
Subject: selftests: gpio: restore CFLAGS options

All the CFLAGS options were incorrectly removed in the recent rework
of the GPIO selftests.  While some of the flags were specific to the old
implementation the remainder are still relevant.  Restore those options.

Signed-off-by: Kent Gibson <warthog618@gmail.com>
Signed-off-by: Bartosz Golaszewski <brgl@bgdev.pl>
---
 tools/testing/selftests/gpio/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/gpio/Makefile b/tools/testing/selftests/gpio/Makefile
index 42ea7d2aa844..d7b312b44a62 100644
--- a/tools/testing/selftests/gpio/Makefile
+++ b/tools/testing/selftests/gpio/Makefile
@@ -3,6 +3,6 @@
 TEST_PROGS := gpio-mockup.sh
 TEST_FILES := gpio-mockup-sysfs.sh
 TEST_GEN_PROGS_EXTENDED := gpio-mockup-cdev
-CFLAGS += -I../../../../usr/include
+CFLAGS += -O2 -g -Wall -I../../../../usr/include/
 
 include ../lib.mk
-- 
cgit v1.2.3


From e60e6962c503f337531f80e2752423b5bd885443 Mon Sep 17 00:00:00 2001
From: Dmitrii Banshchikov <me@ubique.spb.ru>
Date: Sat, 13 Nov 2021 18:22:27 +0400
Subject: selftests/bpf: Add tests for restricted helpers

This patch adds tests that bpf_ktime_get_coarse_ns(), bpf_timer_* and
bpf_spin_lock()/bpf_spin_unlock() helpers are forbidden in tracing progs
as their use there may result in various locking issues.

Signed-off-by: Dmitrii Banshchikov <me@ubique.spb.ru>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20211113142227.566439-3-me@ubique.spb.ru
---
 .../selftests/bpf/prog_tests/helper_restricted.c   |  33 ++++
 .../selftests/bpf/progs/test_helper_restricted.c   | 123 +++++++++++++
 tools/testing/selftests/bpf/test_verifier.c        |  46 ++++-
 .../selftests/bpf/verifier/helper_restricted.c     | 196 +++++++++++++++++++++
 4 files changed, 397 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/helper_restricted.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_helper_restricted.c
 create mode 100644 tools/testing/selftests/bpf/verifier/helper_restricted.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/helper_restricted.c b/tools/testing/selftests/bpf/prog_tests/helper_restricted.c
new file mode 100644
index 000000000000..e1de5f80c3b2
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/helper_restricted.c
@@ -0,0 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "test_helper_restricted.skel.h"
+
+void test_helper_restricted(void)
+{
+	int prog_i = 0, prog_cnt;
+	int duration = 0;
+
+	do {
+		struct test_helper_restricted *test;
+		int maybeOK;
+
+		test = test_helper_restricted__open();
+		if (!ASSERT_OK_PTR(test, "open"))
+			return;
+
+		prog_cnt = test->skeleton->prog_cnt;
+
+		for (int j = 0; j < prog_cnt; ++j) {
+			struct bpf_program *prog = *test->skeleton->progs[j].prog;
+
+			maybeOK = bpf_program__set_autoload(prog, prog_i == j);
+			ASSERT_OK(maybeOK, "set autoload");
+		}
+
+		maybeOK = test_helper_restricted__load(test);
+		CHECK(!maybeOK, test->skeleton->progs[prog_i].name, "helper isn't restricted");
+
+		test_helper_restricted__destroy(test);
+	} while (++prog_i < prog_cnt);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_helper_restricted.c b/tools/testing/selftests/bpf/progs/test_helper_restricted.c
new file mode 100644
index 000000000000..68d64c365f90
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_helper_restricted.c
@@ -0,0 +1,123 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <time.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+struct timer {
+	struct bpf_timer t;
+};
+
+struct lock {
+	struct bpf_spin_lock l;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, struct timer);
+} timers SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, struct lock);
+} locks SEC(".maps");
+
+static int timer_cb(void *map, int *key, struct timer *timer)
+{
+	return 0;
+}
+
+static void timer_work(void)
+{
+	struct timer *timer;
+	const int key = 0;
+
+	timer  = bpf_map_lookup_elem(&timers, &key);
+	if (timer) {
+		bpf_timer_init(&timer->t, &timers, CLOCK_MONOTONIC);
+		bpf_timer_set_callback(&timer->t, timer_cb);
+		bpf_timer_start(&timer->t, 10E9, 0);
+		bpf_timer_cancel(&timer->t);
+	}
+}
+
+static void spin_lock_work(void)
+{
+	const int key = 0;
+	struct lock *lock;
+
+	lock = bpf_map_lookup_elem(&locks, &key);
+	if (lock) {
+		bpf_spin_lock(&lock->l);
+		bpf_spin_unlock(&lock->l);
+	}
+}
+
+SEC("raw_tp/sys_enter")
+int raw_tp_timer(void *ctx)
+{
+	timer_work();
+
+	return 0;
+}
+
+SEC("tp/syscalls/sys_enter_nanosleep")
+int tp_timer(void *ctx)
+{
+	timer_work();
+
+	return 0;
+}
+
+SEC("kprobe/sys_nanosleep")
+int kprobe_timer(void *ctx)
+{
+	timer_work();
+
+	return 0;
+}
+
+SEC("perf_event")
+int perf_event_timer(void *ctx)
+{
+	timer_work();
+
+	return 0;
+}
+
+SEC("raw_tp/sys_enter")
+int raw_tp_spin_lock(void *ctx)
+{
+	spin_lock_work();
+
+	return 0;
+}
+
+SEC("tp/syscalls/sys_enter_nanosleep")
+int tp_spin_lock(void *ctx)
+{
+	spin_lock_work();
+
+	return 0;
+}
+
+SEC("kprobe/sys_nanosleep")
+int kprobe_spin_lock(void *ctx)
+{
+	spin_lock_work();
+
+	return 0;
+}
+
+SEC("perf_event")
+int perf_event_spin_lock(void *ctx)
+{
+	spin_lock_work();
+
+	return 0;
+}
+
+const char LICENSE[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 25afe423b3f0..465ef3f112c0 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -92,6 +92,7 @@ struct bpf_test {
 	int fixup_map_event_output[MAX_FIXUPS];
 	int fixup_map_reuseport_array[MAX_FIXUPS];
 	int fixup_map_ringbuf[MAX_FIXUPS];
+	int fixup_map_timer[MAX_FIXUPS];
 	/* Expected verifier log output for result REJECT or VERBOSE_ACCEPT.
 	 * Can be a tab-separated sequence of expected strings. An empty string
 	 * means no log verification.
@@ -604,8 +605,15 @@ static int create_cgroup_storage(bool percpu)
  *   int cnt;
  *   struct bpf_spin_lock l;
  * };
+ * struct bpf_timer {
+ *   __u64 :64;
+ *   __u64 :64;
+ * } __attribute__((aligned(8)));
+ * struct timer {
+ *   struct bpf_timer t;
+ * };
  */
-static const char btf_str_sec[] = "\0bpf_spin_lock\0val\0cnt\0l";
+static const char btf_str_sec[] = "\0bpf_spin_lock\0val\0cnt\0l\0bpf_timer\0timer\0t";
 static __u32 btf_raw_types[] = {
 	/* int */
 	BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
@@ -616,6 +624,11 @@ static __u32 btf_raw_types[] = {
 	BTF_TYPE_ENC(15, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8),
 	BTF_MEMBER_ENC(19, 1, 0), /* int cnt; */
 	BTF_MEMBER_ENC(23, 2, 32),/* struct bpf_spin_lock l; */
+	/* struct bpf_timer */                          /* [4] */
+	BTF_TYPE_ENC(25, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 0), 16),
+	/* struct timer */                              /* [5] */
+	BTF_TYPE_ENC(35, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), 16),
+	BTF_MEMBER_ENC(41, 4, 0), /* struct bpf_timer t; */
 };
 
 static int load_btf(void)
@@ -696,6 +709,29 @@ static int create_sk_storage_map(void)
 	return fd;
 }
 
+static int create_map_timer(void)
+{
+	struct bpf_create_map_attr attr = {
+		.name = "test_map",
+		.map_type = BPF_MAP_TYPE_ARRAY,
+		.key_size = 4,
+		.value_size = 16,
+		.max_entries = 1,
+		.btf_key_type_id = 1,
+		.btf_value_type_id = 5,
+	};
+	int fd, btf_fd;
+
+	btf_fd = load_btf();
+	if (btf_fd < 0)
+		return -1;
+	attr.btf_fd = btf_fd;
+	fd = bpf_create_map_xattr(&attr);
+	if (fd < 0)
+		printf("Failed to create map with timer\n");
+	return fd;
+}
+
 static char bpf_vlog[UINT_MAX >> 8];
 
 static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type,
@@ -722,6 +758,7 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type,
 	int *fixup_map_event_output = test->fixup_map_event_output;
 	int *fixup_map_reuseport_array = test->fixup_map_reuseport_array;
 	int *fixup_map_ringbuf = test->fixup_map_ringbuf;
+	int *fixup_map_timer = test->fixup_map_timer;
 
 	if (test->fill_helper) {
 		test->fill_insns = calloc(MAX_TEST_INSNS, sizeof(struct bpf_insn));
@@ -907,6 +944,13 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type,
 			fixup_map_ringbuf++;
 		} while (*fixup_map_ringbuf);
 	}
+	if (*fixup_map_timer) {
+		map_fds[21] = create_map_timer();
+		do {
+			prog[*fixup_map_timer].imm = map_fds[21];
+			fixup_map_timer++;
+		} while (*fixup_map_timer);
+	}
 }
 
 struct libcap {
diff --git a/tools/testing/selftests/bpf/verifier/helper_restricted.c b/tools/testing/selftests/bpf/verifier/helper_restricted.c
new file mode 100644
index 000000000000..a067b7098b97
--- /dev/null
+++ b/tools/testing/selftests/bpf/verifier/helper_restricted.c
@@ -0,0 +1,196 @@
+{
+	"bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_KPROBE",
+	.insns = {
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ktime_get_coarse_ns),
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.errstr = "unknown func bpf_ktime_get_coarse_ns",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_KPROBE,
+},
+{
+	"bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_TRACEPOINT",
+	.insns = {
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ktime_get_coarse_ns),
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.errstr = "unknown func bpf_ktime_get_coarse_ns",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+},
+{
+	"bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_PERF_EVENT",
+	.insns = {
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ktime_get_coarse_ns),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.errstr = "unknown func bpf_ktime_get_coarse_ns",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_PERF_EVENT,
+},
+{
+	"bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_RAW_TRACEPOINT",
+	.insns = {
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ktime_get_coarse_ns),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.errstr = "unknown func bpf_ktime_get_coarse_ns",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT,
+},
+{
+	"bpf_timer_init isn restricted in BPF_PROG_TYPE_KPROBE",
+	.insns = {
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_LD_MAP_FD(BPF_REG_2, 0),
+	BPF_MOV64_IMM(BPF_REG_3, 1),
+	BPF_EMIT_CALL(BPF_FUNC_timer_init),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_timer = { 3, 8 },
+	.errstr = "tracing progs cannot use bpf_timer yet",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_KPROBE,
+},
+{
+	"bpf_timer_init is forbidden in BPF_PROG_TYPE_PERF_EVENT",
+	.insns = {
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_LD_MAP_FD(BPF_REG_2, 0),
+	BPF_MOV64_IMM(BPF_REG_3, 1),
+	BPF_EMIT_CALL(BPF_FUNC_timer_init),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_timer = { 3, 8 },
+	.errstr = "tracing progs cannot use bpf_timer yet",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_PERF_EVENT,
+},
+{
+	"bpf_timer_init is forbidden in BPF_PROG_TYPE_TRACEPOINT",
+	.insns = {
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_LD_MAP_FD(BPF_REG_2, 0),
+	BPF_MOV64_IMM(BPF_REG_3, 1),
+	BPF_EMIT_CALL(BPF_FUNC_timer_init),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_timer = { 3, 8 },
+	.errstr = "tracing progs cannot use bpf_timer yet",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+},
+{
+	"bpf_timer_init is forbidden in BPF_PROG_TYPE_RAW_TRACEPOINT",
+	.insns = {
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_LD_MAP_FD(BPF_REG_2, 0),
+	BPF_MOV64_IMM(BPF_REG_3, 1),
+	BPF_EMIT_CALL(BPF_FUNC_timer_init),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_timer = { 3, 8 },
+	.errstr = "tracing progs cannot use bpf_timer yet",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT,
+},
+{
+	"bpf_spin_lock is forbidden in BPF_PROG_TYPE_KPROBE",
+	.insns = {
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_spin_lock),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_spin_lock = { 3 },
+	.errstr = "tracing progs cannot use bpf_spin_lock yet",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_KPROBE,
+},
+{
+	"bpf_spin_lock is forbidden in BPF_PROG_TYPE_TRACEPOINT",
+	.insns = {
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_spin_lock),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_spin_lock = { 3 },
+	.errstr = "tracing progs cannot use bpf_spin_lock yet",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+},
+{
+	"bpf_spin_lock is forbidden in BPF_PROG_TYPE_PERF_EVENT",
+	.insns = {
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_spin_lock),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_spin_lock = { 3 },
+	.errstr = "tracing progs cannot use bpf_spin_lock yet",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_PERF_EVENT,
+},
+{
+	"bpf_spin_lock is forbidden in BPF_PROG_TYPE_RAW_TRACEPOINT",
+	.insns = {
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_spin_lock),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_spin_lock = { 3 },
+	.errstr = "tracing progs cannot use bpf_spin_lock yet",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT,
+},
-- 
cgit v1.2.3


From 7c4de881f7eba40088241f1c3ff5ca28c4e7fa48 Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw@amazon.co.uk>
Date: Mon, 15 Nov 2021 16:50:22 +0000
Subject: KVM: selftests: Add event channel upcall support to xen_shinfo_test

When I first looked at this, there was no support for guest exception
handling in the KVM selftests. In fact it was merged into 5.10 before
the Xen support got merged in 5.11, and I could have used it from the
start.

Hook it up now, to exercise the Xen upcall delivery. I'm about to make
things a bit more interesting by handling the full 2level event channel
stuff in-kernel on top of the basic vector injection that we already
have, and I'll want to build more tests on top.

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Message-Id: <20211115165030.7422-3-dwmw2@infradead.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 .../testing/selftests/kvm/x86_64/xen_shinfo_test.c | 75 +++++++++++++++++++---
 1 file changed, 66 insertions(+), 9 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
index eda0d2a51224..a0699f00b3d6 100644
--- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
@@ -24,8 +24,12 @@
 
 #define PVTIME_ADDR	(SHINFO_REGION_GPA + PAGE_SIZE)
 #define RUNSTATE_ADDR	(SHINFO_REGION_GPA + PAGE_SIZE + 0x20)
+#define VCPU_INFO_ADDR	(SHINFO_REGION_GPA + 0x40)
 
 #define RUNSTATE_VADDR	(SHINFO_REGION_GVA + PAGE_SIZE + 0x20)
+#define VCPU_INFO_VADDR	(SHINFO_REGION_GVA + 0x40)
+
+#define EVTCHN_VECTOR	0x10
 
 static struct kvm_vm *vm;
 
@@ -56,15 +60,44 @@ struct vcpu_runstate_info {
     uint64_t time[4];
 };
 
+struct arch_vcpu_info {
+    unsigned long cr2;
+    unsigned long pad; /* sizeof(vcpu_info_t) == 64 */
+};
+
+struct vcpu_info {
+        uint8_t evtchn_upcall_pending;
+        uint8_t evtchn_upcall_mask;
+        unsigned long evtchn_pending_sel;
+        struct arch_vcpu_info arch;
+        struct pvclock_vcpu_time_info time;
+}; /* 64 bytes (x86) */
+
 #define RUNSTATE_running  0
 #define RUNSTATE_runnable 1
 #define RUNSTATE_blocked  2
 #define RUNSTATE_offline  3
 
+static void evtchn_handler(struct ex_regs *regs)
+{
+	struct vcpu_info *vi = (void *)VCPU_INFO_VADDR;
+	vi->evtchn_upcall_pending = 0;
+
+	GUEST_SYNC(0x20);
+}
+
 static void guest_code(void)
 {
 	struct vcpu_runstate_info *rs = (void *)RUNSTATE_VADDR;
 
+	__asm__ __volatile__(
+		"sti\n"
+		"nop\n"
+	);
+
+	/* Trigger an interrupt injection */
+	GUEST_SYNC(0);
+
 	/* Test having the host set runstates manually */
 	GUEST_SYNC(RUNSTATE_runnable);
 	GUEST_ASSERT(rs->time[RUNSTATE_runnable] != 0);
@@ -153,7 +186,7 @@ int main(int argc, char *argv[])
 
 	struct kvm_xen_vcpu_attr vi = {
 		.type = KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO,
-		.u.gpa = SHINFO_REGION_GPA + 0x40,
+		.u.gpa = VCPU_INFO_ADDR,
 	};
 	vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &vi);
 
@@ -163,6 +196,16 @@ int main(int argc, char *argv[])
 	};
 	vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &pvclock);
 
+	struct kvm_xen_hvm_attr vec = {
+		.type = KVM_XEN_ATTR_TYPE_UPCALL_VECTOR,
+		.u.vector = EVTCHN_VECTOR,
+	};
+	vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &vec);
+
+	vm_init_descriptor_tables(vm);
+	vcpu_init_descriptor_tables(vm, VCPU_ID);
+	vm_install_exception_handler(vm, EVTCHN_VECTOR, evtchn_handler);
+
 	if (do_runstate_tests) {
 		struct kvm_xen_vcpu_attr st = {
 			.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR,
@@ -171,9 +214,14 @@ int main(int argc, char *argv[])
 		vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &st);
 	}
 
+	struct vcpu_info *vinfo = addr_gpa2hva(vm, VCPU_INFO_VADDR);
+	vinfo->evtchn_upcall_pending = 0;
+
 	struct vcpu_runstate_info *rs = addr_gpa2hva(vm, RUNSTATE_ADDR);
 	rs->state = 0x5a;
 
+	bool evtchn_irq_expected = false;
+
 	for (;;) {
 		volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID);
 		struct ucall uc;
@@ -193,16 +241,21 @@ int main(int argc, char *argv[])
 			struct kvm_xen_vcpu_attr rst;
 			long rundelay;
 
-			/* If no runstate support, bail out early */
-			if (!do_runstate_tests)
-				goto done;
-
-			TEST_ASSERT(rs->state_entry_time == rs->time[0] +
-				    rs->time[1] + rs->time[2] + rs->time[3],
-				    "runstate times don't add up");
+			if (do_runstate_tests)
+				TEST_ASSERT(rs->state_entry_time == rs->time[0] +
+					    rs->time[1] + rs->time[2] + rs->time[3],
+					    "runstate times don't add up");
 
 			switch (uc.args[1]) {
-			case RUNSTATE_running...RUNSTATE_offline:
+			case 0:
+				evtchn_irq_expected = true;
+				vinfo->evtchn_upcall_pending = 1;
+				break;
+
+			case RUNSTATE_runnable...RUNSTATE_offline:
+				TEST_ASSERT(!evtchn_irq_expected, "Event channel IRQ not seen");
+				if (!do_runstate_tests)
+					goto done;
 				rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT;
 				rst.u.runstate.state = uc.args[1];
 				vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &rst);
@@ -236,6 +289,10 @@ int main(int argc, char *argv[])
 					sched_yield();
 				} while (get_run_delay() < rundelay);
 				break;
+			case 0x20:
+				TEST_ASSERT(evtchn_irq_expected, "Unexpected event channel IRQ");
+				evtchn_irq_expected = false;
+				break;
 			}
 			break;
 		}
-- 
cgit v1.2.3


From 531ca3d6d518f520f67a71e270ac733901896d8f Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 11 Nov 2021 00:02:59 +0000
Subject: KVM: selftests: Explicitly state indicies for vm_guest_mode_params
 array

Explicitly state the indices when populating vm_guest_mode_params to
make it marginally easier to visualize what's going on.

No functional change intended.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
[Added indices for new guest modes.]
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20211111000310.1435032-2-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/lib/kvm_util.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 041004c0fda7..b624c24290dd 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -187,15 +187,15 @@ const char *vm_guest_mode_string(uint32_t i)
 }
 
 const struct vm_guest_mode_params vm_guest_mode_params[] = {
-	{ 52, 48,  0x1000, 12 },
-	{ 52, 48, 0x10000, 16 },
-	{ 48, 48,  0x1000, 12 },
-	{ 48, 48, 0x10000, 16 },
-	{ 40, 48,  0x1000, 12 },
-	{ 40, 48, 0x10000, 16 },
-	{  0,  0,  0x1000, 12 },
-	{ 47, 64,  0x1000, 12 },
-	{ 44, 64,  0x1000, 12 },
+	[VM_MODE_P52V48_4K]	= { 52, 48,  0x1000, 12 },
+	[VM_MODE_P52V48_64K]	= { 52, 48, 0x10000, 16 },
+	[VM_MODE_P48V48_4K]	= { 48, 48,  0x1000, 12 },
+	[VM_MODE_P48V48_64K]	= { 48, 48, 0x10000, 16 },
+	[VM_MODE_P40V48_4K]	= { 40, 48,  0x1000, 12 },
+	[VM_MODE_P40V48_64K]	= { 40, 48, 0x10000, 16 },
+	[VM_MODE_PXXV48_4K]	= {  0,  0,  0x1000, 12 },
+	[VM_MODE_P47V64_4K]	= { 47, 64,  0x1000, 12 },
+	[VM_MODE_P44V64_4K]	= { 44, 64,  0x1000, 12 },
 };
 _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES,
 	       "Missing new mode params?");
-- 
cgit v1.2.3


From c071ff41e1502990a0902c7c3fcf72a462e46330 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 11 Nov 2021 00:03:00 +0000
Subject: KVM: selftests: Expose align() helpers to tests

Refactor align() to work with non-pointers and split into separate
helpers for aligning up vs. down. Add align_ptr_up() for use with
pointers. Expose all helpers so that they can be used by tests and/or
other utilities.  The align_down() helper in particular will be used to
ensure gpa alignment for hugepages.

No functional change intended.

[Added sepearate up/down helpers and replaced open-coded alignment
 bit math throughout the KVM selftests.]

Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: David Matlack <dmatlack@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Message-Id: <20211111000310.1435032-3-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/dirty_log_test.c      |  6 +++---
 tools/testing/selftests/kvm/include/test_util.h   | 25 +++++++++++++++++++++++
 tools/testing/selftests/kvm/kvm_page_table_test.c |  2 +-
 tools/testing/selftests/kvm/lib/elf.c             |  3 +--
 tools/testing/selftests/kvm/lib/kvm_util.c        | 13 ++----------
 tools/testing/selftests/kvm/lib/perf_test_util.c  |  4 ++--
 6 files changed, 34 insertions(+), 19 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index 792c60e1b17d..3fcd89e195c7 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -115,7 +115,7 @@ static void guest_code(void)
 			addr = guest_test_virt_mem;
 			addr += (READ_ONCE(random_array[i]) % guest_num_pages)
 				* guest_page_size;
-			addr &= ~(host_page_size - 1);
+			addr = align_down(addr, host_page_size);
 			*(uint64_t *)addr = READ_ONCE(iteration);
 		}
 
@@ -737,14 +737,14 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	if (!p->phys_offset) {
 		guest_test_phys_mem = (vm_get_max_gfn(vm) -
 				       guest_num_pages) * guest_page_size;
-		guest_test_phys_mem &= ~(host_page_size - 1);
+		guest_test_phys_mem = align_down(guest_test_phys_mem, host_page_size);
 	} else {
 		guest_test_phys_mem = p->phys_offset;
 	}
 
 #ifdef __s390x__
 	/* Align to 1M (segment size) */
-	guest_test_phys_mem &= ~((1 << 20) - 1);
+	guest_test_phys_mem = align_down(guest_test_phys_mem, 1 << 20);
 #endif
 
 	pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);
diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index f8fddc84c0d3..78c06310cc0e 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -117,4 +117,29 @@ static inline bool backing_src_is_shared(enum vm_mem_backing_src_type t)
 	return vm_mem_backing_src_alias(t)->flag & MAP_SHARED;
 }
 
+/* Aligns x up to the next multiple of size. Size must be a power of 2. */
+static inline uint64_t align_up(uint64_t x, uint64_t size)
+{
+	uint64_t mask = size - 1;
+
+	TEST_ASSERT(size != 0 && !(size & (size - 1)),
+		    "size not a power of 2: %lu", size);
+	return ((x + mask) & ~mask);
+}
+
+static inline uint64_t align_down(uint64_t x, uint64_t size)
+{
+	uint64_t x_aligned_up = align_up(x, size);
+
+	if (x == x_aligned_up)
+		return x;
+	else
+		return x_aligned_up - size;
+}
+
+static inline void *align_ptr_up(void *x, size_t size)
+{
+	return (void *)align_up((unsigned long)x, size);
+}
+
 #endif /* SELFTEST_KVM_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c
index 36407cb0ec85..3836322add00 100644
--- a/tools/testing/selftests/kvm/kvm_page_table_test.c
+++ b/tools/testing/selftests/kvm/kvm_page_table_test.c
@@ -280,7 +280,7 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg)
 #ifdef __s390x__
 	alignment = max(0x100000, alignment);
 #endif
-	guest_test_phys_mem &= ~(alignment - 1);
+	guest_test_phys_mem = align_down(guest_test_virt_mem, alignment);
 
 	/* Set up the shared data structure test_args */
 	test_args.vm = vm;
diff --git a/tools/testing/selftests/kvm/lib/elf.c b/tools/testing/selftests/kvm/lib/elf.c
index eac44f5d0db0..13e8e3dcf984 100644
--- a/tools/testing/selftests/kvm/lib/elf.c
+++ b/tools/testing/selftests/kvm/lib/elf.c
@@ -157,8 +157,7 @@ void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename)
 			"memsize of 0,\n"
 			"  phdr index: %u p_memsz: 0x%" PRIx64,
 			n1, (uint64_t) phdr.p_memsz);
-		vm_vaddr_t seg_vstart = phdr.p_vaddr;
-		seg_vstart &= ~(vm_vaddr_t)(vm->page_size - 1);
+		vm_vaddr_t seg_vstart = align_down(phdr.p_vaddr, vm->page_size);
 		vm_vaddr_t seg_vend = phdr.p_vaddr + phdr.p_memsz - 1;
 		seg_vend |= vm->page_size - 1;
 		size_t seg_size = seg_vend - seg_vstart + 1;
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index b624c24290dd..63375118d48f 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -22,15 +22,6 @@
 
 static int vcpu_mmap_sz(void);
 
-/* Aligns x up to the next multiple of size. Size must be a power of 2. */
-static void *align(void *x, size_t size)
-{
-	size_t mask = size - 1;
-	TEST_ASSERT(size != 0 && !(size & (size - 1)),
-		    "size not a power of 2: %lu", size);
-	return (void *) (((size_t) x + mask) & ~mask);
-}
-
 /*
  * Open KVM_DEV_PATH if available, otherwise exit the entire program.
  *
@@ -911,7 +902,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 		    region->mmap_start, errno);
 
 	/* Align host address */
-	region->host_mem = align(region->mmap_start, alignment);
+	region->host_mem = align_ptr_up(region->mmap_start, alignment);
 
 	/* As needed perform madvise */
 	if ((src_type == VM_MEM_SRC_ANONYMOUS ||
@@ -954,7 +945,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 			    "mmap of alias failed, errno: %i", errno);
 
 		/* Align host alias address */
-		region->host_alias = align(region->mmap_alias, alignment);
+		region->host_alias = align_ptr_up(region->mmap_alias, alignment);
 	}
 }
 
diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c
index 0ef80dbdc116..6b8d5020dc54 100644
--- a/tools/testing/selftests/kvm/lib/perf_test_util.c
+++ b/tools/testing/selftests/kvm/lib/perf_test_util.c
@@ -92,10 +92,10 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 
 	guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) *
 			      perf_test_args.guest_page_size;
-	guest_test_phys_mem &= ~(perf_test_args.host_page_size - 1);
+	guest_test_phys_mem = align_down(guest_test_phys_mem, perf_test_args.host_page_size);
 #ifdef __s390x__
 	/* Align to 1M (segment size) */
-	guest_test_phys_mem &= ~((1 << 20) - 1);
+	guest_test_phys_mem = align_down(guest_test_phys_mem, 1 << 20);
 #endif
 	pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);
 
-- 
cgit v1.2.3


From f4870ef3e15ab889a689f99a579fe0fe7c53a960 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 11 Nov 2021 00:03:01 +0000
Subject: KVM: selftests: Assert mmap HVA is aligned when using HugeTLB

Manually padding and aligning the mmap region is only needed when using
THP. When using HugeTLB, mmap will always return an address aligned to
the HugeTLB page size. Add a comment to clarify this and assert the mmap
behavior for HugeTLB.

[Removed requirement that HugeTLB mmaps must be padded per Yanan's
 feedback and added assertion that mmap returns aligned addresses
 when using HugeTLB.]

Cc: Ben Gardon <bgardon@google.com>
Cc: Yanan Wang <wangyanan55@huawei.com>
Cc: Andrew Jones <drjones@redhat.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Aaron Lewis <aaronlewis@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20211111000310.1435032-4-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/include/test_util.h |  1 +
 tools/testing/selftests/kvm/lib/kvm_util.c      | 11 +++++++++++
 tools/testing/selftests/kvm/lib/test_util.c     |  5 +++++
 3 files changed, 17 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index 78c06310cc0e..99e0dcdc923f 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -104,6 +104,7 @@ size_t get_trans_hugepagesz(void);
 size_t get_def_hugetlb_pagesz(void);
 const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(uint32_t i);
 size_t get_backing_src_pagesz(uint32_t i);
+bool is_backing_src_hugetlb(uint32_t i);
 void backing_src_help(const char *flag);
 enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name);
 long get_run_delay(void);
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 63375118d48f..07f37456bba0 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -866,6 +866,12 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 	alignment = 1;
 #endif
 
+	/*
+	 * When using THP mmap is not guaranteed to returned a hugepage aligned
+	 * address so we have to pad the mmap. Padding is not needed for HugeTLB
+	 * because mmap will always return an address aligned to the HugeTLB
+	 * page size.
+	 */
 	if (src_type == VM_MEM_SRC_ANONYMOUS_THP)
 		alignment = max(backing_src_pagesz, alignment);
 
@@ -901,6 +907,11 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 		    "test_malloc failed, mmap_start: %p errno: %i",
 		    region->mmap_start, errno);
 
+	TEST_ASSERT(!is_backing_src_hugetlb(src_type) ||
+		    region->mmap_start == align_ptr_up(region->mmap_start, backing_src_pagesz),
+		    "mmap_start %p is not aligned to HugeTLB page size 0x%lx",
+		    region->mmap_start, backing_src_pagesz);
+
 	/* Align host address */
 	region->host_mem = align_ptr_up(region->mmap_start, alignment);
 
diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c
index b72429108993..6d23878bbfe1 100644
--- a/tools/testing/selftests/kvm/lib/test_util.c
+++ b/tools/testing/selftests/kvm/lib/test_util.c
@@ -283,6 +283,11 @@ size_t get_backing_src_pagesz(uint32_t i)
 	}
 }
 
+bool is_backing_src_hugetlb(uint32_t i)
+{
+	return !!(vm_mem_backing_src_alias(i)->flag & MAP_HUGETLB);
+}
+
 static void print_available_backing_src_types(const char *prefix)
 {
 	int i;
-- 
cgit v1.2.3


From 69cdcfa6f321da2cc1dd2e62fa4a9ee256299b18 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 11 Nov 2021 00:03:02 +0000
Subject: KVM: selftests: Require GPA to be aligned when backed by hugepages

Assert that the GPA for a memslot backed by a hugepage is aligned to
the hugepage size and fix perf_test_util accordingly.  Lack of GPA
alignment prevents KVM from backing the guest with hugepages, e.g. x86's
write-protection of hugepages when dirty logging is activated is
otherwise not exercised.

Add a comment explaining that guest_page_size is for non-huge pages to
try and avoid confusion about what it actually tracks.

Cc: Ben Gardon <bgardon@google.com>
Cc: Yanan Wang <wangyanan55@huawei.com>
Cc: Andrew Jones <drjones@redhat.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Aaron Lewis <aaronlewis@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
[Used get_backing_src_pagesz() to determine alignment dynamically.]
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20211111000310.1435032-5-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/lib/kvm_util.c       | 2 ++
 tools/testing/selftests/kvm/lib/perf_test_util.c | 7 ++++++-
 2 files changed, 8 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 07f37456bba0..1f6a01c33dce 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -875,6 +875,8 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 	if (src_type == VM_MEM_SRC_ANONYMOUS_THP)
 		alignment = max(backing_src_pagesz, alignment);
 
+	ASSERT_EQ(guest_paddr, align_up(guest_paddr, backing_src_pagesz));
+
 	/* Add enough memory to align up if necessary */
 	if (alignment > 1)
 		region->mmap_size += alignment;
diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c
index 6b8d5020dc54..a015f267d945 100644
--- a/tools/testing/selftests/kvm/lib/perf_test_util.c
+++ b/tools/testing/selftests/kvm/lib/perf_test_util.c
@@ -55,11 +55,16 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 {
 	struct kvm_vm *vm;
 	uint64_t guest_num_pages;
+	uint64_t backing_src_pagesz = get_backing_src_pagesz(backing_src);
 	int i;
 
 	pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
 
 	perf_test_args.host_page_size = getpagesize();
+	/*
+	 * Snapshot the non-huge page size.  This is used by the guest code to
+	 * access/dirty pages at the logging granularity.
+	 */
 	perf_test_args.guest_page_size = vm_guest_mode_params[mode].page_size;
 
 	guest_num_pages = vm_adjust_num_guest_pages(mode,
@@ -92,7 +97,7 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 
 	guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) *
 			      perf_test_args.guest_page_size;
-	guest_test_phys_mem = align_down(guest_test_phys_mem, perf_test_args.host_page_size);
+	guest_test_phys_mem = align_down(guest_test_phys_mem, backing_src_pagesz);
 #ifdef __s390x__
 	/* Align to 1M (segment size) */
 	guest_test_phys_mem = align_down(guest_test_phys_mem, 1 << 20);
-- 
cgit v1.2.3


From b65e1051e489be4fe783cb14f1cd33235a0f9803 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 11 Nov 2021 00:03:03 +0000
Subject: KVM: selftests: Use shorthand local var to access struct
 perf_tests_args

Use 'pta' as a local pointer to the global perf_tests_args in order to
shorten line lengths and make the code borderline readable.

No functional change intended.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20211111000310.1435032-6-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/lib/perf_test_util.c | 35 +++++++++++++-----------
 1 file changed, 19 insertions(+), 16 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c
index a015f267d945..ccdc950c829e 100644
--- a/tools/testing/selftests/kvm/lib/perf_test_util.c
+++ b/tools/testing/selftests/kvm/lib/perf_test_util.c
@@ -24,7 +24,8 @@ static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM;
  */
 static void guest_code(uint32_t vcpu_id)
 {
-	struct perf_test_vcpu_args *vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
+	struct perf_test_args *pta = &perf_test_args;
+	struct perf_test_vcpu_args *vcpu_args = &pta->vcpu_args[vcpu_id];
 	uint64_t gva;
 	uint64_t pages;
 	int i;
@@ -37,9 +38,9 @@ static void guest_code(uint32_t vcpu_id)
 
 	while (true) {
 		for (i = 0; i < pages; i++) {
-			uint64_t addr = gva + (i * perf_test_args.guest_page_size);
+			uint64_t addr = gva + (i * pta->guest_page_size);
 
-			if (i % perf_test_args.wr_fract == 0)
+			if (i % pta->wr_fract == 0)
 				*(uint64_t *)addr = 0x0123456789ABCDEF;
 			else
 				READ_ONCE(*(uint64_t *)addr);
@@ -53,6 +54,7 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 				   uint64_t vcpu_memory_bytes, int slots,
 				   enum vm_mem_backing_src_type backing_src)
 {
+	struct perf_test_args *pta = &perf_test_args;
 	struct kvm_vm *vm;
 	uint64_t guest_num_pages;
 	uint64_t backing_src_pagesz = get_backing_src_pagesz(backing_src);
@@ -60,29 +62,29 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 
 	pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
 
-	perf_test_args.host_page_size = getpagesize();
+	pta->host_page_size = getpagesize();
 	/*
 	 * Snapshot the non-huge page size.  This is used by the guest code to
 	 * access/dirty pages at the logging granularity.
 	 */
-	perf_test_args.guest_page_size = vm_guest_mode_params[mode].page_size;
+	pta->guest_page_size = vm_guest_mode_params[mode].page_size;
 
 	guest_num_pages = vm_adjust_num_guest_pages(mode,
-				(vcpus * vcpu_memory_bytes) / perf_test_args.guest_page_size);
+				(vcpus * vcpu_memory_bytes) / pta->guest_page_size);
 
-	TEST_ASSERT(vcpu_memory_bytes % perf_test_args.host_page_size == 0,
+	TEST_ASSERT(vcpu_memory_bytes % pta->host_page_size == 0,
 		    "Guest memory size is not host page size aligned.");
-	TEST_ASSERT(vcpu_memory_bytes % perf_test_args.guest_page_size == 0,
+	TEST_ASSERT(vcpu_memory_bytes % pta->guest_page_size == 0,
 		    "Guest memory size is not guest page size aligned.");
 	TEST_ASSERT(guest_num_pages % slots == 0,
 		    "Guest memory cannot be evenly divided into %d slots.",
 		    slots);
 
 	vm = vm_create_with_vcpus(mode, vcpus, DEFAULT_GUEST_PHY_PAGES,
-				  (vcpus * vcpu_memory_bytes) / perf_test_args.guest_page_size,
+				  (vcpus * vcpu_memory_bytes) / pta->guest_page_size,
 				  0, guest_code, NULL);
 
-	perf_test_args.vm = vm;
+	pta->vm = vm;
 
 	/*
 	 * If there should be more memory in the guest test region than there
@@ -96,7 +98,7 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 		    vcpu_memory_bytes);
 
 	guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) *
-			      perf_test_args.guest_page_size;
+			      pta->guest_page_size;
 	guest_test_phys_mem = align_down(guest_test_phys_mem, backing_src_pagesz);
 #ifdef __s390x__
 	/* Align to 1M (segment size) */
@@ -108,7 +110,7 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 	for (i = 0; i < slots; i++) {
 		uint64_t region_pages = guest_num_pages / slots;
 		vm_paddr_t region_start = guest_test_phys_mem +
-			region_pages * perf_test_args.guest_page_size * i;
+			region_pages * pta->guest_page_size * i;
 
 		vm_userspace_mem_region_add(vm, backing_src, region_start,
 					    PERF_TEST_MEM_SLOT_INDEX + i,
@@ -133,25 +135,26 @@ void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus,
 			   uint64_t vcpu_memory_bytes,
 			   bool partition_vcpu_memory_access)
 {
+	struct perf_test_args *pta = &perf_test_args;
 	vm_paddr_t vcpu_gpa;
 	struct perf_test_vcpu_args *vcpu_args;
 	int vcpu_id;
 
 	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
-		vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
+		vcpu_args = &pta->vcpu_args[vcpu_id];
 
 		vcpu_args->vcpu_id = vcpu_id;
 		if (partition_vcpu_memory_access) {
 			vcpu_args->gva = guest_test_virt_mem +
 					 (vcpu_id * vcpu_memory_bytes);
 			vcpu_args->pages = vcpu_memory_bytes /
-					   perf_test_args.guest_page_size;
+					   pta->guest_page_size;
 			vcpu_gpa = guest_test_phys_mem +
 				   (vcpu_id * vcpu_memory_bytes);
 		} else {
 			vcpu_args->gva = guest_test_virt_mem;
 			vcpu_args->pages = (vcpus * vcpu_memory_bytes) /
-					   perf_test_args.guest_page_size;
+					   pta->guest_page_size;
 			vcpu_gpa = guest_test_phys_mem;
 		}
 
@@ -159,6 +162,6 @@ void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus,
 
 		pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n",
 			 vcpu_id, vcpu_gpa, vcpu_gpa +
-			 (vcpu_args->pages * perf_test_args.guest_page_size));
+			 (vcpu_args->pages * pta->guest_page_size));
 	}
 }
-- 
cgit v1.2.3


From 613d61182fffca6b36ea0df1e44927ccf45b1e9b Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 11 Nov 2021 00:03:04 +0000
Subject: KVM: selftests: Capture per-vCPU GPA in perf_test_vcpu_args

Capture the per-vCPU GPA in perf_test_vcpu_args so that tests can get
the GPA without having to calculate the GPA on their own.

No functional change intended.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20211111000310.1435032-7-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/include/perf_test_util.h | 1 +
 tools/testing/selftests/kvm/lib/perf_test_util.c     | 9 ++++-----
 2 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h
index df9f1a3a3ffb..20aec72fe7b8 100644
--- a/tools/testing/selftests/kvm/include/perf_test_util.h
+++ b/tools/testing/selftests/kvm/include/perf_test_util.h
@@ -18,6 +18,7 @@
 #define PERF_TEST_MEM_SLOT_INDEX	1
 
 struct perf_test_vcpu_args {
+	uint64_t gpa;
 	uint64_t gva;
 	uint64_t pages;
 
diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c
index ccdc950c829e..d9c6bcb7964d 100644
--- a/tools/testing/selftests/kvm/lib/perf_test_util.c
+++ b/tools/testing/selftests/kvm/lib/perf_test_util.c
@@ -136,7 +136,6 @@ void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus,
 			   bool partition_vcpu_memory_access)
 {
 	struct perf_test_args *pta = &perf_test_args;
-	vm_paddr_t vcpu_gpa;
 	struct perf_test_vcpu_args *vcpu_args;
 	int vcpu_id;
 
@@ -149,19 +148,19 @@ void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus,
 					 (vcpu_id * vcpu_memory_bytes);
 			vcpu_args->pages = vcpu_memory_bytes /
 					   pta->guest_page_size;
-			vcpu_gpa = guest_test_phys_mem +
-				   (vcpu_id * vcpu_memory_bytes);
+			vcpu_args->gpa = guest_test_phys_mem +
+					 (vcpu_id * vcpu_memory_bytes);
 		} else {
 			vcpu_args->gva = guest_test_virt_mem;
 			vcpu_args->pages = (vcpus * vcpu_memory_bytes) /
 					   pta->guest_page_size;
-			vcpu_gpa = guest_test_phys_mem;
+			vcpu_args->gpa = guest_test_phys_mem;
 		}
 
 		vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
 
 		pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n",
-			 vcpu_id, vcpu_gpa, vcpu_gpa +
+			 vcpu_id, vcpu_args->gpa, vcpu_args->gpa +
 			 (vcpu_args->pages * pta->guest_page_size));
 	}
 }
-- 
cgit v1.2.3


From 92e34c9974f55519bc0c3386221aadf387162ea6 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 11 Nov 2021 00:03:05 +0000
Subject: KVM: selftests: Use perf util's per-vCPU GPA/pages in demand paging
 test

Grab the per-vCPU GPA and number of pages from perf_util in the demand
paging test instead of duplicating perf_util's calculations.

Note, this may or may not result in a functional change.  It's not clear
that the test's calculations are guaranteed to yield the same value as
perf_util, e.g. if guest_percpu_mem_size != vcpu_args->pages.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20211111000310.1435032-8-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/demand_paging_test.c | 21 +++++----------------
 1 file changed, 5 insertions(+), 16 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
index 1510b21e6306..3c729a0a1ab1 100644
--- a/tools/testing/selftests/kvm/demand_paging_test.c
+++ b/tools/testing/selftests/kvm/demand_paging_test.c
@@ -322,26 +322,15 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 		TEST_ASSERT(pipefds, "Unable to allocate memory for pipefd");
 
 		for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
-			vm_paddr_t vcpu_gpa;
+			struct perf_test_vcpu_args *vcpu_args;
 			void *vcpu_hva;
 			void *vcpu_alias;
-			uint64_t vcpu_mem_size;
 
-
-			if (p->partition_vcpu_memory_access) {
-				vcpu_gpa = guest_test_phys_mem +
-					   (vcpu_id * guest_percpu_mem_size);
-				vcpu_mem_size = guest_percpu_mem_size;
-			} else {
-				vcpu_gpa = guest_test_phys_mem;
-				vcpu_mem_size = guest_percpu_mem_size * nr_vcpus;
-			}
-			PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n",
-				       vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_mem_size);
+			vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
 
 			/* Cache the host addresses of the region */
-			vcpu_hva = addr_gpa2hva(vm, vcpu_gpa);
-			vcpu_alias = addr_gpa2alias(vm, vcpu_gpa);
+			vcpu_hva = addr_gpa2hva(vm, vcpu_args->gpa);
+			vcpu_alias = addr_gpa2alias(vm, vcpu_args->gpa);
 
 			/*
 			 * Set up user fault fd to handle demand paging
@@ -355,7 +344,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 					    pipefds[vcpu_id * 2], p->uffd_mode,
 					    p->uffd_delay, &uffd_args[vcpu_id],
 					    vcpu_hva, vcpu_alias,
-					    vcpu_mem_size);
+					    vcpu_args->pages * perf_test_args.guest_page_size);
 		}
 	}
 
-- 
cgit v1.2.3


From b91b637f4a595c5be435e215f78b1a3bd8c252b3 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 11 Nov 2021 00:03:06 +0000
Subject: KVM: selftests: Move per-VM GPA into perf_test_args

Move the per-VM GPA into perf_test_args instead of storing it as a
separate global variable.  It's not obvious that guest_test_phys_mem
holds a GPA, nor that it's connected/coupled with per_vcpu->gpa.

No functional change intended.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20211111000310.1435032-9-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 .../testing/selftests/kvm/include/perf_test_util.h  |  8 +-------
 tools/testing/selftests/kvm/lib/perf_test_util.c    | 21 ++++++++-------------
 .../kvm/memslot_modification_stress_test.c          |  2 +-
 3 files changed, 10 insertions(+), 21 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h
index 20aec72fe7b8..d7cde1ab2a85 100644
--- a/tools/testing/selftests/kvm/include/perf_test_util.h
+++ b/tools/testing/selftests/kvm/include/perf_test_util.h
@@ -29,6 +29,7 @@ struct perf_test_vcpu_args {
 struct perf_test_args {
 	struct kvm_vm *vm;
 	uint64_t host_page_size;
+	uint64_t gpa;
 	uint64_t guest_page_size;
 	int wr_fract;
 
@@ -37,13 +38,6 @@ struct perf_test_args {
 
 extern struct perf_test_args perf_test_args;
 
-/*
- * Guest physical memory offset of the testing memory slot.
- * This will be set to the topmost valid physical address minus
- * the test memory size.
- */
-extern uint64_t guest_test_phys_mem;
-
 struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 				   uint64_t vcpu_memory_bytes, int slots,
 				   enum vm_mem_backing_src_type backing_src);
diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c
index d9c6bcb7964d..0fc2d834c1c7 100644
--- a/tools/testing/selftests/kvm/lib/perf_test_util.c
+++ b/tools/testing/selftests/kvm/lib/perf_test_util.c
@@ -10,8 +10,6 @@
 
 struct perf_test_args perf_test_args;
 
-uint64_t guest_test_phys_mem;
-
 /*
  * Guest virtual memory offset of the testing memory slot.
  * Must not conflict with identity mapped test code.
@@ -97,20 +95,18 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 		    guest_num_pages, vm_get_max_gfn(vm), vcpus,
 		    vcpu_memory_bytes);
 
-	guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) *
-			      pta->guest_page_size;
-	guest_test_phys_mem = align_down(guest_test_phys_mem, backing_src_pagesz);
+	pta->gpa = (vm_get_max_gfn(vm) - guest_num_pages) * pta->guest_page_size;
+	pta->gpa = align_down(pta->gpa, backing_src_pagesz);
 #ifdef __s390x__
 	/* Align to 1M (segment size) */
-	guest_test_phys_mem = align_down(guest_test_phys_mem, 1 << 20);
+	pta->gpa = align_down(pta->gpa, 1 << 20);
 #endif
-	pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);
+	pr_info("guest physical test memory offset: 0x%lx\n", pta->gpa);
 
 	/* Add extra memory slots for testing */
 	for (i = 0; i < slots; i++) {
 		uint64_t region_pages = guest_num_pages / slots;
-		vm_paddr_t region_start = guest_test_phys_mem +
-			region_pages * pta->guest_page_size * i;
+		vm_paddr_t region_start = pta->gpa + region_pages * pta->guest_page_size * i;
 
 		vm_userspace_mem_region_add(vm, backing_src, region_start,
 					    PERF_TEST_MEM_SLOT_INDEX + i,
@@ -118,7 +114,7 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 	}
 
 	/* Do mapping for the demand paging memory slot */
-	virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages);
+	virt_map(vm, guest_test_virt_mem, pta->gpa, guest_num_pages);
 
 	ucall_init(vm, NULL);
 
@@ -148,13 +144,12 @@ void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus,
 					 (vcpu_id * vcpu_memory_bytes);
 			vcpu_args->pages = vcpu_memory_bytes /
 					   pta->guest_page_size;
-			vcpu_args->gpa = guest_test_phys_mem +
-					 (vcpu_id * vcpu_memory_bytes);
+			vcpu_args->gpa = pta->gpa + (vcpu_id * vcpu_memory_bytes);
 		} else {
 			vcpu_args->gva = guest_test_virt_mem;
 			vcpu_args->pages = (vcpus * vcpu_memory_bytes) /
 					   pta->guest_page_size;
-			vcpu_args->gpa = guest_test_phys_mem;
+			vcpu_args->gpa = pta->gpa;
 		}
 
 		vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
index 4cfcafea9f5a..d105180d5e8c 100644
--- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c
+++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
@@ -80,7 +80,7 @@ static void add_remove_memslot(struct kvm_vm *vm, useconds_t delay,
 	 * Add the dummy memslot just below the perf_test_util memslot, which is
 	 * at the top of the guest physical address space.
 	 */
-	gpa = guest_test_phys_mem - pages * vm_get_page_size(vm);
+	gpa = perf_test_args.gpa - pages * vm_get_page_size(vm);
 
 	for (i = 0; i < nr_modifications; i++) {
 		usleep(delay);
-- 
cgit v1.2.3


From a5ac0fd1b90ae811ba51da6a9928633bddefb792 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 11 Nov 2021 00:03:07 +0000
Subject: KVM: selftests: Remove perf_test_args.host_page_size

Remove perf_test_args.host_page_size and instead use getpagesize() so
that it's somewhat obvious that, for tests that care about the host page
size, they care about the system page size, not the hardware page size,
e.g. that the logic is unchanged if hugepages are in play.

No functional change intended.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20211111000310.1435032-10-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/include/perf_test_util.h | 1 -
 tools/testing/selftests/kvm/lib/perf_test_util.c     | 3 +--
 2 files changed, 1 insertion(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h
index d7cde1ab2a85..9348580dc5be 100644
--- a/tools/testing/selftests/kvm/include/perf_test_util.h
+++ b/tools/testing/selftests/kvm/include/perf_test_util.h
@@ -28,7 +28,6 @@ struct perf_test_vcpu_args {
 
 struct perf_test_args {
 	struct kvm_vm *vm;
-	uint64_t host_page_size;
 	uint64_t gpa;
 	uint64_t guest_page_size;
 	int wr_fract;
diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c
index 0fc2d834c1c7..a0aded8cfce3 100644
--- a/tools/testing/selftests/kvm/lib/perf_test_util.c
+++ b/tools/testing/selftests/kvm/lib/perf_test_util.c
@@ -60,7 +60,6 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 
 	pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
 
-	pta->host_page_size = getpagesize();
 	/*
 	 * Snapshot the non-huge page size.  This is used by the guest code to
 	 * access/dirty pages at the logging granularity.
@@ -70,7 +69,7 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 	guest_num_pages = vm_adjust_num_guest_pages(mode,
 				(vcpus * vcpu_memory_bytes) / pta->guest_page_size);
 
-	TEST_ASSERT(vcpu_memory_bytes % pta->host_page_size == 0,
+	TEST_ASSERT(vcpu_memory_bytes % getpagesize() == 0,
 		    "Guest memory size is not host page size aligned.");
 	TEST_ASSERT(vcpu_memory_bytes % pta->guest_page_size == 0,
 		    "Guest memory size is not guest page size aligned.");
-- 
cgit v1.2.3


From f5e8fe2a92e4923b63d1edd6ed53d9856b6515ce Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 11 Nov 2021 00:03:08 +0000
Subject: KVM: selftests: Create VM with adjusted number of guest pages for
 perf tests

Use the already computed guest_num_pages when creating the so called
extra VM pages for a perf test, and add a comment explaining why the
pages are allocated as extra pages.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20211111000310.1435032-11-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/lib/perf_test_util.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c
index a0aded8cfce3..b3154b5b0cfd 100644
--- a/tools/testing/selftests/kvm/lib/perf_test_util.c
+++ b/tools/testing/selftests/kvm/lib/perf_test_util.c
@@ -77,9 +77,13 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 		    "Guest memory cannot be evenly divided into %d slots.",
 		    slots);
 
+	/*
+	 * Pass guest_num_pages to populate the page tables for test memory.
+	 * The memory is also added to memslot 0, but that's a benign side
+	 * effect as KVM allows aliasing HVAs in meslots.
+	 */
 	vm = vm_create_with_vcpus(mode, vcpus, DEFAULT_GUEST_PHY_PAGES,
-				  (vcpus * vcpu_memory_bytes) / pta->guest_page_size,
-				  0, guest_code, NULL);
+				  guest_num_pages, 0, guest_code, NULL);
 
 	pta->vm = vm;
 
-- 
cgit v1.2.3


From cf1d59300ab27af6a2e96b4882fe3d9a72b32b15 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 11 Nov 2021 00:03:09 +0000
Subject: KVM: selftests: Fill per-vCPU struct during "perf_test" VM creation

Fill the per-vCPU args when creating the perf_test VM instead of having
the caller do so.  This helps ensure that any adjustments to the number
of pages (and thus vcpu_memory_bytes) are reflected in the per-VM args.
Automatically filling the per-vCPU args will also allow a future patch
to do the sync to the guest during creation.

Signed-off-by: Sean Christopherson <seanjc@google.com>
[Updated access_tracking_perf_test as well.]
Signed-off-by: David Matlack <dmatlack@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Message-Id: <20211111000310.1435032-12-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 .../selftests/kvm/access_tracking_perf_test.c      |  5 +-
 tools/testing/selftests/kvm/demand_paging_test.c   |  5 +-
 tools/testing/selftests/kvm/dirty_log_perf_test.c  |  6 +-
 .../testing/selftests/kvm/include/perf_test_util.h |  6 +-
 tools/testing/selftests/kvm/lib/perf_test_util.c   | 71 +++++++++++-----------
 .../kvm/memslot_modification_stress_test.c         |  6 +-
 6 files changed, 45 insertions(+), 54 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c
index 5d95113c7b7c..fdef6c906388 100644
--- a/tools/testing/selftests/kvm/access_tracking_perf_test.c
+++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c
@@ -332,10 +332,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	int vcpus = params->vcpus;
 
 	vm = perf_test_create_vm(mode, vcpus, params->vcpu_memory_bytes, 1,
-				 params->backing_src);
-
-	perf_test_setup_vcpus(vm, vcpus, params->vcpu_memory_bytes,
-			      !overlap_memory_access);
+				 params->backing_src, !overlap_memory_access);
 
 	vcpu_threads = create_vcpu_threads(vcpus);
 
diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
index 3c729a0a1ab1..0fee44f5e5ae 100644
--- a/tools/testing/selftests/kvm/demand_paging_test.c
+++ b/tools/testing/selftests/kvm/demand_paging_test.c
@@ -293,7 +293,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	int r;
 
 	vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1,
-				 p->src_type);
+				 p->src_type, p->partition_vcpu_memory_access);
 
 	perf_test_args.wr_fract = 1;
 
@@ -307,9 +307,6 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
 	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
 
-	perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size,
-			      p->partition_vcpu_memory_access);
-
 	if (p->uffd_mode) {
 		uffd_handler_threads =
 			malloc(nr_vcpus * sizeof(*uffd_handler_threads));
diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c
index 7ffab5bd5ce5..62f9cc2a3146 100644
--- a/tools/testing/selftests/kvm/dirty_log_perf_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c
@@ -186,7 +186,8 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	struct timespec clear_dirty_log_total = (struct timespec){0};
 
 	vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size,
-				 p->slots, p->backing_src);
+				 p->slots, p->backing_src,
+				 p->partition_vcpu_memory_access);
 
 	perf_test_args.wr_fract = p->wr_fract;
 
@@ -206,9 +207,6 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
 	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
 
-	perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size,
-			      p->partition_vcpu_memory_access);
-
 	sync_global_to_guest(vm, perf_test_args);
 
 	/* Start the iterations */
diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h
index 9348580dc5be..91804be1cf53 100644
--- a/tools/testing/selftests/kvm/include/perf_test_util.h
+++ b/tools/testing/selftests/kvm/include/perf_test_util.h
@@ -39,10 +39,8 @@ extern struct perf_test_args perf_test_args;
 
 struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 				   uint64_t vcpu_memory_bytes, int slots,
-				   enum vm_mem_backing_src_type backing_src);
+				   enum vm_mem_backing_src_type backing_src,
+				   bool partition_vcpu_memory_access);
 void perf_test_destroy_vm(struct kvm_vm *vm);
-void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus,
-			   uint64_t vcpu_memory_bytes,
-			   bool partition_vcpu_memory_access);
 
 #endif /* SELFTEST_KVM_PERF_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c
index b3154b5b0cfd..13c8bc22f4e1 100644
--- a/tools/testing/selftests/kvm/lib/perf_test_util.c
+++ b/tools/testing/selftests/kvm/lib/perf_test_util.c
@@ -48,9 +48,43 @@ static void guest_code(uint32_t vcpu_id)
 	}
 }
 
+void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus,
+			   uint64_t vcpu_memory_bytes,
+			   bool partition_vcpu_memory_access)
+{
+	struct perf_test_args *pta = &perf_test_args;
+	struct perf_test_vcpu_args *vcpu_args;
+	int vcpu_id;
+
+	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+		vcpu_args = &pta->vcpu_args[vcpu_id];
+
+		vcpu_args->vcpu_id = vcpu_id;
+		if (partition_vcpu_memory_access) {
+			vcpu_args->gva = guest_test_virt_mem +
+					 (vcpu_id * vcpu_memory_bytes);
+			vcpu_args->pages = vcpu_memory_bytes /
+					   pta->guest_page_size;
+			vcpu_args->gpa = pta->gpa + (vcpu_id * vcpu_memory_bytes);
+		} else {
+			vcpu_args->gva = guest_test_virt_mem;
+			vcpu_args->pages = (vcpus * vcpu_memory_bytes) /
+					   pta->guest_page_size;
+			vcpu_args->gpa = pta->gpa;
+		}
+
+		vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
+
+		pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n",
+			 vcpu_id, vcpu_args->gpa, vcpu_args->gpa +
+			 (vcpu_args->pages * pta->guest_page_size));
+	}
+}
+
 struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 				   uint64_t vcpu_memory_bytes, int slots,
-				   enum vm_mem_backing_src_type backing_src)
+				   enum vm_mem_backing_src_type backing_src,
+				   bool partition_vcpu_memory_access)
 {
 	struct perf_test_args *pta = &perf_test_args;
 	struct kvm_vm *vm;
@@ -119,6 +153,8 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 	/* Do mapping for the demand paging memory slot */
 	virt_map(vm, guest_test_virt_mem, pta->gpa, guest_num_pages);
 
+	perf_test_setup_vcpus(vm, vcpus, vcpu_memory_bytes, partition_vcpu_memory_access);
+
 	ucall_init(vm, NULL);
 
 	return vm;
@@ -129,36 +165,3 @@ void perf_test_destroy_vm(struct kvm_vm *vm)
 	ucall_uninit(vm);
 	kvm_vm_free(vm);
 }
-
-void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus,
-			   uint64_t vcpu_memory_bytes,
-			   bool partition_vcpu_memory_access)
-{
-	struct perf_test_args *pta = &perf_test_args;
-	struct perf_test_vcpu_args *vcpu_args;
-	int vcpu_id;
-
-	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
-		vcpu_args = &pta->vcpu_args[vcpu_id];
-
-		vcpu_args->vcpu_id = vcpu_id;
-		if (partition_vcpu_memory_access) {
-			vcpu_args->gva = guest_test_virt_mem +
-					 (vcpu_id * vcpu_memory_bytes);
-			vcpu_args->pages = vcpu_memory_bytes /
-					   pta->guest_page_size;
-			vcpu_args->gpa = pta->gpa + (vcpu_id * vcpu_memory_bytes);
-		} else {
-			vcpu_args->gva = guest_test_virt_mem;
-			vcpu_args->pages = (vcpus * vcpu_memory_bytes) /
-					   pta->guest_page_size;
-			vcpu_args->gpa = pta->gpa;
-		}
-
-		vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
-
-		pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n",
-			 vcpu_id, vcpu_args->gpa, vcpu_args->gpa +
-			 (vcpu_args->pages * pta->guest_page_size));
-	}
-}
diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
index d105180d5e8c..27af0bb8deb7 100644
--- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c
+++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
@@ -105,16 +105,14 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	int vcpu_id;
 
 	vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1,
-				 VM_MEM_SRC_ANONYMOUS);
+				 VM_MEM_SRC_ANONYMOUS,
+				 p->partition_vcpu_memory_access);
 
 	perf_test_args.wr_fract = 1;
 
 	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
 	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
 
-	perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size,
-			      p->partition_vcpu_memory_access);
-
 	/* Export the shared variables to the guest */
 	sync_global_to_guest(vm, perf_test_args);
 
-- 
cgit v1.2.3


From 13bbc70329c8df003e64c4fbea8678f9db0e75d5 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 11 Nov 2021 00:03:10 +0000
Subject: KVM: selftests: Sync perf_test_args to guest during VM creation

Copy perf_test_args to the guest during VM creation instead of relying on
the caller to do so at their leisure.  Ideally, tests wouldn't even be
able to modify perf_test_args, i.e. they would have no motivation to do
the sync, but enforcing that is arguably a net negative for readability.

No functional change intended.

[Set wr_fract=1 by default and add helper to override it since the new
 access_tracking_perf_test needs to set it dynamically.]

Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: David Matlack <dmatlack@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Message-Id: <20211111000310.1435032-13-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/access_tracking_perf_test.c      |  3 +--
 tools/testing/selftests/kvm/demand_paging_test.c             |  5 -----
 tools/testing/selftests/kvm/dirty_log_perf_test.c            |  4 +---
 tools/testing/selftests/kvm/include/perf_test_util.h         |  2 ++
 tools/testing/selftests/kvm/lib/perf_test_util.c             | 12 ++++++++++++
 .../testing/selftests/kvm/memslot_modification_stress_test.c |  5 -----
 6 files changed, 16 insertions(+), 15 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c
index fdef6c906388..5364a2ed7c68 100644
--- a/tools/testing/selftests/kvm/access_tracking_perf_test.c
+++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c
@@ -277,8 +277,7 @@ static void run_iteration(struct kvm_vm *vm, int vcpus, const char *description)
 static void access_memory(struct kvm_vm *vm, int vcpus, enum access_type access,
 			  const char *description)
 {
-	perf_test_args.wr_fract = (access == ACCESS_READ) ? INT_MAX : 1;
-	sync_global_to_guest(vm, perf_test_args);
+	perf_test_set_wr_fract(vm, (access == ACCESS_READ) ? INT_MAX : 1);
 	iteration_work = ITERATION_ACCESS_MEMORY;
 	run_iteration(vm, vcpus, description);
 }
diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
index 0fee44f5e5ae..26f8fd8a57ec 100644
--- a/tools/testing/selftests/kvm/demand_paging_test.c
+++ b/tools/testing/selftests/kvm/demand_paging_test.c
@@ -295,8 +295,6 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1,
 				 p->src_type, p->partition_vcpu_memory_access);
 
-	perf_test_args.wr_fract = 1;
-
 	demand_paging_size = get_backing_src_pagesz(p->src_type);
 
 	guest_data_prototype = malloc(demand_paging_size);
@@ -345,9 +343,6 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 		}
 	}
 
-	/* Export the shared variables to the guest */
-	sync_global_to_guest(vm, perf_test_args);
-
 	pr_info("Finished creating vCPUs and starting uffd threads\n");
 
 	clock_gettime(CLOCK_MONOTONIC, &start);
diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c
index 62f9cc2a3146..583b4d95aa98 100644
--- a/tools/testing/selftests/kvm/dirty_log_perf_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c
@@ -189,7 +189,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 				 p->slots, p->backing_src,
 				 p->partition_vcpu_memory_access);
 
-	perf_test_args.wr_fract = p->wr_fract;
+	perf_test_set_wr_fract(vm, p->wr_fract);
 
 	guest_num_pages = (nr_vcpus * guest_percpu_mem_size) >> vm_get_page_shift(vm);
 	guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
@@ -207,8 +207,6 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
 	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
 
-	sync_global_to_guest(vm, perf_test_args);
-
 	/* Start the iterations */
 	iteration = 0;
 	host_quit = false;
diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h
index 91804be1cf53..74e3622b3a6e 100644
--- a/tools/testing/selftests/kvm/include/perf_test_util.h
+++ b/tools/testing/selftests/kvm/include/perf_test_util.h
@@ -43,4 +43,6 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 				   bool partition_vcpu_memory_access);
 void perf_test_destroy_vm(struct kvm_vm *vm);
 
+void perf_test_set_wr_fract(struct kvm_vm *vm, int wr_fract);
+
 #endif /* SELFTEST_KVM_PERF_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c
index 13c8bc22f4e1..77f9eb5667c9 100644
--- a/tools/testing/selftests/kvm/lib/perf_test_util.c
+++ b/tools/testing/selftests/kvm/lib/perf_test_util.c
@@ -94,6 +94,9 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 
 	pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
 
+	/* By default vCPUs will write to memory. */
+	pta->wr_fract = 1;
+
 	/*
 	 * Snapshot the non-huge page size.  This is used by the guest code to
 	 * access/dirty pages at the logging granularity.
@@ -157,6 +160,9 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 
 	ucall_init(vm, NULL);
 
+	/* Export the shared variables to the guest. */
+	sync_global_to_guest(vm, perf_test_args);
+
 	return vm;
 }
 
@@ -165,3 +171,9 @@ void perf_test_destroy_vm(struct kvm_vm *vm)
 	ucall_uninit(vm);
 	kvm_vm_free(vm);
 }
+
+void perf_test_set_wr_fract(struct kvm_vm *vm, int wr_fract)
+{
+	perf_test_args.wr_fract = wr_fract;
+	sync_global_to_guest(vm, perf_test_args);
+}
diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
index 27af0bb8deb7..df431d0da1ee 100644
--- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c
+++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
@@ -108,14 +108,9 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 				 VM_MEM_SRC_ANONYMOUS,
 				 p->partition_vcpu_memory_access);
 
-	perf_test_args.wr_fract = 1;
-
 	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
 	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
 
-	/* Export the shared variables to the guest */
-	sync_global_to_guest(vm, perf_test_args);
-
 	pr_info("Finished creating vCPUs\n");
 
 	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++)
-- 
cgit v1.2.3


From 36c5ad73d7016f34146cf0821c78f08737bdb5e9 Mon Sep 17 00:00:00 2001
From: David Matlack <dmatlack@google.com>
Date: Thu, 11 Nov 2021 00:12:54 +0000
Subject: KVM: selftests: Start at iteration 0 instead of -1

Start at iteration 0 instead of -1 to avoid having to initialize
vcpu_last_completed_iteration when setting up vCPU threads. This
simplifies the next commit where we move vCPU thread initialization
out to a common helper.

No functional change intended.

Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20211111001257.1446428-2-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/access_tracking_perf_test.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c
index 5364a2ed7c68..7f25a06e19c9 100644
--- a/tools/testing/selftests/kvm/access_tracking_perf_test.c
+++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c
@@ -47,7 +47,7 @@
 #include "guest_modes.h"
 
 /* Global variable used to synchronize all of the vCPU threads. */
-static int iteration = -1;
+static int iteration;
 
 /* Defines what vCPU threads should do during a given iteration. */
 static enum {
@@ -220,7 +220,7 @@ static void *vcpu_thread_main(void *arg)
 	struct perf_test_vcpu_args *vcpu_args = arg;
 	struct kvm_vm *vm = perf_test_args.vm;
 	int vcpu_id = vcpu_args->vcpu_id;
-	int current_iteration = -1;
+	int current_iteration = 0;
 
 	while (spin_wait_for_next_iteration(&current_iteration)) {
 		switch (READ_ONCE(iteration_work)) {
@@ -303,11 +303,9 @@ static pthread_t *create_vcpu_threads(int vcpus)
 	vcpu_threads = malloc(vcpus * sizeof(vcpu_threads[0]));
 	TEST_ASSERT(vcpu_threads, "Failed to allocate vcpu_threads.");
 
-	for (i = 0; i < vcpus; i++) {
-		vcpu_last_completed_iteration[i] = iteration;
+	for (i = 0; i < vcpus; i++)
 		pthread_create(&vcpu_threads[i], NULL, vcpu_thread_main,
 			       &perf_test_args.vcpu_args[i]);
-	}
 
 	return vcpu_threads;
 }
-- 
cgit v1.2.3


From 81bcb26172a8f00840e0ca44277272dcb673887a Mon Sep 17 00:00:00 2001
From: David Matlack <dmatlack@google.com>
Date: Thu, 11 Nov 2021 00:12:55 +0000
Subject: KVM: selftests: Move vCPU thread creation and joining to common
 helpers

Move vCPU thread creation and joining to common helper functions. This
is in preparation for the next commit which ensures that all vCPU
threads are fully created before entering guest mode on any one
vCPU.

No functional change intended.

Signed-off-by: David Matlack <dmatlack@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Message-Id: <20211111001257.1446428-3-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 .../selftests/kvm/access_tracking_perf_test.c      | 40 +++----------------
 tools/testing/selftests/kvm/demand_paging_test.c   | 25 ++----------
 tools/testing/selftests/kvm/dirty_log_perf_test.c  | 19 ++-------
 .../testing/selftests/kvm/include/perf_test_util.h |  5 +++
 tools/testing/selftests/kvm/lib/perf_test_util.c   | 46 ++++++++++++++++++++++
 .../kvm/memslot_modification_stress_test.c         | 22 ++---------
 6 files changed, 67 insertions(+), 90 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c
index 7f25a06e19c9..d8909032317a 100644
--- a/tools/testing/selftests/kvm/access_tracking_perf_test.c
+++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c
@@ -215,9 +215,8 @@ static bool spin_wait_for_next_iteration(int *current_iteration)
 	return true;
 }
 
-static void *vcpu_thread_main(void *arg)
+static void vcpu_thread_main(struct perf_test_vcpu_args *vcpu_args)
 {
-	struct perf_test_vcpu_args *vcpu_args = arg;
 	struct kvm_vm *vm = perf_test_args.vm;
 	int vcpu_id = vcpu_args->vcpu_id;
 	int current_iteration = 0;
@@ -235,8 +234,6 @@ static void *vcpu_thread_main(void *arg)
 
 		vcpu_last_completed_iteration[vcpu_id] = current_iteration;
 	}
-
-	return NULL;
 }
 
 static void spin_wait_for_vcpu(int vcpu_id, int target_iteration)
@@ -295,43 +292,16 @@ static void mark_memory_idle(struct kvm_vm *vm, int vcpus)
 	run_iteration(vm, vcpus, "Mark memory idle");
 }
 
-static pthread_t *create_vcpu_threads(int vcpus)
-{
-	pthread_t *vcpu_threads;
-	int i;
-
-	vcpu_threads = malloc(vcpus * sizeof(vcpu_threads[0]));
-	TEST_ASSERT(vcpu_threads, "Failed to allocate vcpu_threads.");
-
-	for (i = 0; i < vcpus; i++)
-		pthread_create(&vcpu_threads[i], NULL, vcpu_thread_main,
-			       &perf_test_args.vcpu_args[i]);
-
-	return vcpu_threads;
-}
-
-static void terminate_vcpu_threads(pthread_t *vcpu_threads, int vcpus)
-{
-	int i;
-
-	/* Set done to signal the vCPU threads to exit */
-	done = true;
-
-	for (i = 0; i < vcpus; i++)
-		pthread_join(vcpu_threads[i], NULL);
-}
-
 static void run_test(enum vm_guest_mode mode, void *arg)
 {
 	struct test_params *params = arg;
 	struct kvm_vm *vm;
-	pthread_t *vcpu_threads;
 	int vcpus = params->vcpus;
 
 	vm = perf_test_create_vm(mode, vcpus, params->vcpu_memory_bytes, 1,
 				 params->backing_src, !overlap_memory_access);
 
-	vcpu_threads = create_vcpu_threads(vcpus);
+	perf_test_start_vcpu_threads(vcpus, vcpu_thread_main);
 
 	pr_info("\n");
 	access_memory(vm, vcpus, ACCESS_WRITE, "Populating memory");
@@ -346,8 +316,10 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	mark_memory_idle(vm, vcpus);
 	access_memory(vm, vcpus, ACCESS_READ, "Reading from idle memory");
 
-	terminate_vcpu_threads(vcpu_threads, vcpus);
-	free(vcpu_threads);
+	/* Set done to signal the vCPU threads to exit */
+	done = true;
+
+	perf_test_join_vcpu_threads(vcpus);
 	perf_test_destroy_vm(vm);
 }
 
diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
index 26f8fd8a57ec..6a719d065599 100644
--- a/tools/testing/selftests/kvm/demand_paging_test.c
+++ b/tools/testing/selftests/kvm/demand_paging_test.c
@@ -42,10 +42,9 @@ static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE;
 static size_t demand_paging_size;
 static char *guest_data_prototype;
 
-static void *vcpu_worker(void *data)
+static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args)
 {
 	int ret;
-	struct perf_test_vcpu_args *vcpu_args = (struct perf_test_vcpu_args *)data;
 	int vcpu_id = vcpu_args->vcpu_id;
 	struct kvm_vm *vm = perf_test_args.vm;
 	struct kvm_run *run;
@@ -68,8 +67,6 @@ static void *vcpu_worker(void *data)
 	ts_diff = timespec_elapsed(start);
 	PER_VCPU_DEBUG("vCPU %d execution time: %ld.%.9lds\n", vcpu_id,
 		       ts_diff.tv_sec, ts_diff.tv_nsec);
-
-	return NULL;
 }
 
 static int handle_uffd_page_request(int uffd_mode, int uffd, uint64_t addr)
@@ -282,7 +279,6 @@ struct test_params {
 static void run_test(enum vm_guest_mode mode, void *arg)
 {
 	struct test_params *p = arg;
-	pthread_t *vcpu_threads;
 	pthread_t *uffd_handler_threads = NULL;
 	struct uffd_handler_args *uffd_args = NULL;
 	struct timespec start;
@@ -302,9 +298,6 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 		    "Failed to allocate buffer for guest data pattern");
 	memset(guest_data_prototype, 0xAB, demand_paging_size);
 
-	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
-	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
-
 	if (p->uffd_mode) {
 		uffd_handler_threads =
 			malloc(nr_vcpus * sizeof(*uffd_handler_threads));
@@ -346,22 +339,11 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	pr_info("Finished creating vCPUs and starting uffd threads\n");
 
 	clock_gettime(CLOCK_MONOTONIC, &start);
-
-	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
-		pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker,
-			       &perf_test_args.vcpu_args[vcpu_id]);
-	}
-
+	perf_test_start_vcpu_threads(nr_vcpus, vcpu_worker);
 	pr_info("Started all vCPUs\n");
 
-	/* Wait for the vcpu threads to quit */
-	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
-		pthread_join(vcpu_threads[vcpu_id], NULL);
-		PER_VCPU_DEBUG("Joined thread for vCPU %d\n", vcpu_id);
-	}
-
+	perf_test_join_vcpu_threads(nr_vcpus);
 	ts_diff = timespec_elapsed(start);
-
 	pr_info("All vCPU threads joined\n");
 
 	if (p->uffd_mode) {
@@ -385,7 +367,6 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	perf_test_destroy_vm(vm);
 
 	free(guest_data_prototype);
-	free(vcpu_threads);
 	if (p->uffd_mode) {
 		free(uffd_handler_threads);
 		free(uffd_args);
diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c
index 583b4d95aa98..1954b964d1cf 100644
--- a/tools/testing/selftests/kvm/dirty_log_perf_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c
@@ -31,7 +31,7 @@ static bool host_quit;
 static int iteration;
 static int vcpu_last_completed_iteration[KVM_MAX_VCPUS];
 
-static void *vcpu_worker(void *data)
+static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args)
 {
 	int ret;
 	struct kvm_vm *vm = perf_test_args.vm;
@@ -41,7 +41,6 @@ static void *vcpu_worker(void *data)
 	struct timespec ts_diff;
 	struct timespec total = (struct timespec){0};
 	struct timespec avg;
-	struct perf_test_vcpu_args *vcpu_args = (struct perf_test_vcpu_args *)data;
 	int vcpu_id = vcpu_args->vcpu_id;
 
 	run = vcpu_state(vm, vcpu_id);
@@ -83,8 +82,6 @@ static void *vcpu_worker(void *data)
 	pr_debug("\nvCPU %d dirtied 0x%lx pages over %d iterations in %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
 		vcpu_id, pages_count, vcpu_last_completed_iteration[vcpu_id],
 		total.tv_sec, total.tv_nsec, avg.tv_sec, avg.tv_nsec);
-
-	return NULL;
 }
 
 struct test_params {
@@ -170,7 +167,6 @@ static void free_bitmaps(unsigned long *bitmaps[], int slots)
 static void run_test(enum vm_guest_mode mode, void *arg)
 {
 	struct test_params *p = arg;
-	pthread_t *vcpu_threads;
 	struct kvm_vm *vm;
 	unsigned long **bitmaps;
 	uint64_t guest_num_pages;
@@ -204,20 +200,15 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 		vm_enable_cap(vm, &cap);
 	}
 
-	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
-	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
-
 	/* Start the iterations */
 	iteration = 0;
 	host_quit = false;
 
 	clock_gettime(CLOCK_MONOTONIC, &start);
-	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
+	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++)
 		vcpu_last_completed_iteration[vcpu_id] = -1;
 
-		pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker,
-			       &perf_test_args.vcpu_args[vcpu_id]);
-	}
+	perf_test_start_vcpu_threads(nr_vcpus, vcpu_worker);
 
 	/* Allow the vCPUs to populate memory */
 	pr_debug("Starting iteration %d - Populating\n", iteration);
@@ -286,8 +277,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 
 	/* Tell the vcpu thread to quit */
 	host_quit = true;
-	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++)
-		pthread_join(vcpu_threads[vcpu_id], NULL);
+	perf_test_join_vcpu_threads(nr_vcpus);
 
 	avg = timespec_div(get_dirty_log_total, p->iterations);
 	pr_info("Get dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
@@ -302,7 +292,6 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	}
 
 	free_bitmaps(bitmaps, p->slots);
-	free(vcpu_threads);
 	perf_test_destroy_vm(vm);
 }
 
diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h
index 74e3622b3a6e..a86f953d8d36 100644
--- a/tools/testing/selftests/kvm/include/perf_test_util.h
+++ b/tools/testing/selftests/kvm/include/perf_test_util.h
@@ -8,6 +8,8 @@
 #ifndef SELFTEST_KVM_PERF_TEST_UTIL_H
 #define SELFTEST_KVM_PERF_TEST_UTIL_H
 
+#include <pthread.h>
+
 #include "kvm_util.h"
 
 /* Default guest test virtual memory offset */
@@ -45,4 +47,7 @@ void perf_test_destroy_vm(struct kvm_vm *vm);
 
 void perf_test_set_wr_fract(struct kvm_vm *vm, int wr_fract);
 
+void perf_test_start_vcpu_threads(int vcpus, void (*vcpu_fn)(struct perf_test_vcpu_args *));
+void perf_test_join_vcpu_threads(int vcpus);
+
 #endif /* SELFTEST_KVM_PERF_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c
index 77f9eb5667c9..d646477ed16a 100644
--- a/tools/testing/selftests/kvm/lib/perf_test_util.c
+++ b/tools/testing/selftests/kvm/lib/perf_test_util.c
@@ -16,6 +16,20 @@ struct perf_test_args perf_test_args;
  */
 static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM;
 
+struct vcpu_thread {
+	/* The id of the vCPU. */
+	int vcpu_id;
+
+	/* The pthread backing the vCPU. */
+	pthread_t thread;
+};
+
+/* The vCPU threads involved in this test. */
+static struct vcpu_thread vcpu_threads[KVM_MAX_VCPUS];
+
+/* The function run by each vCPU thread, as provided by the test. */
+static void (*vcpu_thread_fn)(struct perf_test_vcpu_args *);
+
 /*
  * Continuously write to the first 8 bytes of each page in the
  * specified region.
@@ -177,3 +191,35 @@ void perf_test_set_wr_fract(struct kvm_vm *vm, int wr_fract)
 	perf_test_args.wr_fract = wr_fract;
 	sync_global_to_guest(vm, perf_test_args);
 }
+
+static void *vcpu_thread_main(void *data)
+{
+	struct vcpu_thread *vcpu = data;
+
+	vcpu_thread_fn(&perf_test_args.vcpu_args[vcpu->vcpu_id]);
+
+	return NULL;
+}
+
+void perf_test_start_vcpu_threads(int vcpus, void (*vcpu_fn)(struct perf_test_vcpu_args *))
+{
+	int vcpu_id;
+
+	vcpu_thread_fn = vcpu_fn;
+
+	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+		struct vcpu_thread *vcpu = &vcpu_threads[vcpu_id];
+
+		vcpu->vcpu_id = vcpu_id;
+
+		pthread_create(&vcpu->thread, NULL, vcpu_thread_main, vcpu);
+	}
+}
+
+void perf_test_join_vcpu_threads(int vcpus)
+{
+	int vcpu_id;
+
+	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++)
+		pthread_join(vcpu_threads[vcpu_id].thread, NULL);
+}
diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
index df431d0da1ee..5bd0b076f57f 100644
--- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c
+++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
@@ -36,11 +36,9 @@ static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE;
 
 static bool run_vcpus = true;
 
-static void *vcpu_worker(void *data)
+static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args)
 {
 	int ret;
-	struct perf_test_vcpu_args *vcpu_args =
-		(struct perf_test_vcpu_args *)data;
 	int vcpu_id = vcpu_args->vcpu_id;
 	struct kvm_vm *vm = perf_test_args.vm;
 	struct kvm_run *run;
@@ -59,8 +57,6 @@ static void *vcpu_worker(void *data)
 			    "Invalid guest sync status: exit_reason=%s\n",
 			    exit_reason_str(run->exit_reason));
 	}
-
-	return NULL;
 }
 
 struct memslot_antagonist_args {
@@ -100,22 +96,15 @@ struct test_params {
 static void run_test(enum vm_guest_mode mode, void *arg)
 {
 	struct test_params *p = arg;
-	pthread_t *vcpu_threads;
 	struct kvm_vm *vm;
-	int vcpu_id;
 
 	vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1,
 				 VM_MEM_SRC_ANONYMOUS,
 				 p->partition_vcpu_memory_access);
 
-	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
-	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
-
 	pr_info("Finished creating vCPUs\n");
 
-	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++)
-		pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker,
-			       &perf_test_args.vcpu_args[vcpu_id]);
+	perf_test_start_vcpu_threads(nr_vcpus, vcpu_worker);
 
 	pr_info("Started all vCPUs\n");
 
@@ -124,16 +113,11 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 
 	run_vcpus = false;
 
-	/* Wait for the vcpu threads to quit */
-	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++)
-		pthread_join(vcpu_threads[vcpu_id], NULL);
-
+	perf_test_join_vcpu_threads(nr_vcpus);
 	pr_info("All vCPU threads joined\n");
 
 	ucall_uninit(vm);
 	kvm_vm_free(vm);
-
-	free(vcpu_threads);
 }
 
 static void help(char *name)
-- 
cgit v1.2.3


From 89d9a43c1d2d3d703fae25c990a1d98dd178dd17 Mon Sep 17 00:00:00 2001
From: David Matlack <dmatlack@google.com>
Date: Thu, 11 Nov 2021 00:12:56 +0000
Subject: KVM: selftests: Wait for all vCPU to be created before entering guest
 mode

Thread creation requires taking the mmap_sem in write mode, which causes
vCPU threads running in guest mode to block while they are populating
memory. Fix this by waiting for all vCPU threads to be created and start
running before entering guest mode on any one vCPU thread.

This substantially improves the "Populate memory time" when using 1GiB
pages since it allows all vCPUs to zero pages in parallel rather than
blocking because a writer is waiting (which is waiting for another vCPU
that is busy zeroing a 1GiB page).

Before:

  $ ./dirty_log_perf_test -v256 -s anonymous_hugetlb_1gb
  ...
  Populate memory time: 52.811184013s

After:

  $ ./dirty_log_perf_test -v256 -s anonymous_hugetlb_1gb
  ...
  Populate memory time: 10.204573342s

Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20211111001257.1446428-4-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/lib/perf_test_util.c | 26 ++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c
index d646477ed16a..722df3a28791 100644
--- a/tools/testing/selftests/kvm/lib/perf_test_util.c
+++ b/tools/testing/selftests/kvm/lib/perf_test_util.c
@@ -22,6 +22,9 @@ struct vcpu_thread {
 
 	/* The pthread backing the vCPU. */
 	pthread_t thread;
+
+	/* Set to true once the vCPU thread is up and running. */
+	bool running;
 };
 
 /* The vCPU threads involved in this test. */
@@ -30,6 +33,9 @@ static struct vcpu_thread vcpu_threads[KVM_MAX_VCPUS];
 /* The function run by each vCPU thread, as provided by the test. */
 static void (*vcpu_thread_fn)(struct perf_test_vcpu_args *);
 
+/* Set to true once all vCPU threads are up and running. */
+static bool all_vcpu_threads_running;
+
 /*
  * Continuously write to the first 8 bytes of each page in the
  * specified region.
@@ -196,6 +202,17 @@ static void *vcpu_thread_main(void *data)
 {
 	struct vcpu_thread *vcpu = data;
 
+	WRITE_ONCE(vcpu->running, true);
+
+	/*
+	 * Wait for all vCPU threads to be up and running before calling the test-
+	 * provided vCPU thread function. This prevents thread creation (which
+	 * requires taking the mmap_sem in write mode) from interfering with the
+	 * guest faulting in its memory.
+	 */
+	while (!READ_ONCE(all_vcpu_threads_running))
+		;
+
 	vcpu_thread_fn(&perf_test_args.vcpu_args[vcpu->vcpu_id]);
 
 	return NULL;
@@ -206,14 +223,23 @@ void perf_test_start_vcpu_threads(int vcpus, void (*vcpu_fn)(struct perf_test_vc
 	int vcpu_id;
 
 	vcpu_thread_fn = vcpu_fn;
+	WRITE_ONCE(all_vcpu_threads_running, false);
 
 	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
 		struct vcpu_thread *vcpu = &vcpu_threads[vcpu_id];
 
 		vcpu->vcpu_id = vcpu_id;
+		WRITE_ONCE(vcpu->running, false);
 
 		pthread_create(&vcpu->thread, NULL, vcpu_thread_main, vcpu);
 	}
+
+	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+		while (!READ_ONCE(vcpu_threads[vcpu_id].running))
+			;
+	}
+
+	WRITE_ONCE(all_vcpu_threads_running, true);
 }
 
 void perf_test_join_vcpu_threads(int vcpus)
-- 
cgit v1.2.3


From e2bd936581038f3107c45e8ae32309a567b54bf4 Mon Sep 17 00:00:00 2001
From: David Matlack <dmatlack@google.com>
Date: Thu, 11 Nov 2021 00:12:57 +0000
Subject: KVM: selftests: Use perf_test_destroy_vm in
 memslot_modification_stress_test

Change memslot_modification_stress_test to use perf_test_destroy_vm
instead of manually calling ucall_uninit and kvm_vm_free.

No functional change intended.

Signed-off-by: David Matlack <dmatlack@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Message-Id: <20211111001257.1446428-5-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/memslot_modification_stress_test.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
index 5bd0b076f57f..1410d0a9141a 100644
--- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c
+++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
@@ -116,8 +116,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	perf_test_join_vcpu_threads(nr_vcpus);
 	pr_info("All vCPU threads joined\n");
 
-	ucall_uninit(vm);
-	kvm_vm_free(vm);
+	perf_test_destroy_vm(vm);
 }
 
 static void help(char *name)
-- 
cgit v1.2.3


From 1d127effdc1750d1f43de42100185430ea0c90bf Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Fri, 12 Nov 2021 11:33:12 -0500
Subject: selftests: add a test case for mirred egress to ingress

add a selftest that verifies the correct behavior of TC act_mirred egress
to ingress: in particular, it checks if the dst_entry is removed from skb
before redirect egress -> ingress. The correct behavior is: an ICMP 'echo
request' generated by ping will be received and generate a reply the same
way as the one generated by mausezahn.

Suggested-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Cong Wang <cong.wang@bytedance.com>
Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/forwarding/config      |  1 +
 .../testing/selftests/net/forwarding/tc_actions.sh | 47 +++++++++++++++++++++-
 2 files changed, 47 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/forwarding/config b/tools/testing/selftests/net/forwarding/config
index a4bd1b087303..697994a9278b 100644
--- a/tools/testing/selftests/net/forwarding/config
+++ b/tools/testing/selftests/net/forwarding/config
@@ -6,6 +6,7 @@ CONFIG_IPV6_MULTIPLE_TABLES=y
 CONFIG_NET_VRF=m
 CONFIG_BPF_SYSCALL=y
 CONFIG_CGROUP_BPF=y
+CONFIG_NET_ACT_CT=m
 CONFIG_NET_ACT_MIRRED=m
 CONFIG_NET_ACT_MPLS=m
 CONFIG_NET_ACT_VLAN=m
diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh
index d9eca227136b..de19eb6c38f0 100755
--- a/tools/testing/selftests/net/forwarding/tc_actions.sh
+++ b/tools/testing/selftests/net/forwarding/tc_actions.sh
@@ -3,7 +3,7 @@
 
 ALL_TESTS="gact_drop_and_ok_test mirred_egress_redirect_test \
 	mirred_egress_mirror_test matchall_mirred_egress_mirror_test \
-	gact_trap_test"
+	gact_trap_test mirred_egress_to_ingress_test"
 NUM_NETIFS=4
 source tc_common.sh
 source lib.sh
@@ -13,10 +13,12 @@ tcflags="skip_hw"
 h1_create()
 {
 	simple_if_init $h1 192.0.2.1/24
+	tc qdisc add dev $h1 clsact
 }
 
 h1_destroy()
 {
+	tc qdisc del dev $h1 clsact
 	simple_if_fini $h1 192.0.2.1/24
 }
 
@@ -153,6 +155,49 @@ gact_trap_test()
 	log_test "trap ($tcflags)"
 }
 
+mirred_egress_to_ingress_test()
+{
+	RET=0
+
+	tc filter add dev $h1 protocol ip pref 100 handle 100 egress flower \
+		ip_proto icmp src_ip 192.0.2.1 dst_ip 192.0.2.2 type 8 action \
+			ct commit nat src addr 192.0.2.2 pipe \
+			ct clear pipe \
+			ct commit nat dst addr 192.0.2.1 pipe \
+			mirred ingress redirect dev $h1
+
+	tc filter add dev $swp1 protocol ip pref 11 handle 111 ingress flower \
+		ip_proto icmp src_ip 192.0.2.1 dst_ip 192.0.2.2 type 8 action drop
+	tc filter add dev $swp1 protocol ip pref 12 handle 112 ingress flower \
+		ip_proto icmp src_ip 192.0.2.1 dst_ip 192.0.2.2 type 0 action pass
+
+	$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+		-t icmp "ping,id=42,seq=10" -q
+
+	tc_check_packets "dev $h1 egress" 100 1
+	check_err $? "didn't mirror first packet"
+
+	tc_check_packets "dev $swp1 ingress" 111 1
+	check_fail $? "didn't redirect first packet"
+	tc_check_packets "dev $swp1 ingress" 112 1
+	check_err $? "didn't receive reply to first packet"
+
+	ping 192.0.2.2 -I$h1 -c1 -w1 -q 1>/dev/null 2>&1
+
+	tc_check_packets "dev $h1 egress" 100 2
+	check_err $? "didn't mirror second packet"
+	tc_check_packets "dev $swp1 ingress" 111 1
+	check_fail $? "didn't redirect second packet"
+	tc_check_packets "dev $swp1 ingress" 112 2
+	check_err $? "didn't receive reply to second packet"
+
+	tc filter del dev $h1 egress protocol ip pref 100 handle 100 flower
+	tc filter del dev $swp1 ingress protocol ip pref 11 handle 111 flower
+	tc filter del dev $swp1 ingress protocol ip pref 12 handle 112 flower
+
+	log_test "mirred_egress_to_ingress ($tcflags)"
+}
+
 setup_prepare()
 {
 	h1=${NETIFS[p1]}
-- 
cgit v1.2.3


From b768f60bd9791c528a4a4b98659674787b2e7c63 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@kernel.org>
Date: Tue, 16 Nov 2021 12:03:25 -0300
Subject: selftests: KVM: Add /x86_64/sev_migrate_tests to .gitignore

  $ git status
  nothing to commit, working tree clean
  $
  $ make -C tools/testing/selftests/kvm/ > /dev/null 2>&1
  $ git status

  Untracked files:
    (use "git add <file>..." to include in what will be committed)
  	tools/testing/selftests/kvm/x86_64/sev_migrate_tests

  nothing added to commit but untracked files present (use "git add" to track)
  $

Fixes: 6a58150859fdec76 ("selftest: KVM: Add intra host migration tests")
Cc: Brijesh Singh <brijesh.singh@amd.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Marc Orr <marcorr@google.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Gonda <pgonda@google.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Message-Id: <YZPIPfvYgRDCZi/w@kernel.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/.gitignore | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index d4a830139683..3763105029fb 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -23,6 +23,7 @@
 /x86_64/platform_info_test
 /x86_64/set_boot_cpu_id
 /x86_64/set_sregs_test
+/x86_64/sev_migrate_tests
 /x86_64/smm_test
 /x86_64/state_test
 /x86_64/svm_vmcall_test
-- 
cgit v1.2.3


From b075c1d81e7d0e96758877ff9ded30ab87df2b77 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 1 Jul 2021 13:39:15 -0300
Subject: tools headers cpufeatures: Sync with the kernel sources

To pick the changes from:

  eec2113eabd92b7b ("x86/fpu/amx: Define AMX state components and have it used for boot-time checks")

This only causes these perf files to be rebuilt:

  CC       /tmp/build/perf/bench/mem-memcpy-x86-64-asm.o
  CC       /tmp/build/perf/bench/mem-memset-x86-64-asm.o

And addresses this perf build warning:

  Warning: Kernel ABI header at 'tools/arch/x86/include/asm/cpufeatures.h' differs from latest version at 'arch/x86/include/asm/cpufeatures.h'
  diff -u tools/arch/x86/include/asm/cpufeatures.h arch/x86/include/asm/cpufeatures.h

Cc: Borislav Petkov <bp@suse.de>
Cc: Chang S. Bae <chang.seok.bae@intel.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/x86/include/asm/cpufeatures.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'tools')

diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index d0ce5cfd3ac1..d5b5f2ab87a0 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -277,6 +277,7 @@
 #define X86_FEATURE_XSAVEC		(10*32+ 1) /* XSAVEC instruction */
 #define X86_FEATURE_XGETBV1		(10*32+ 2) /* XGETBV with ECX = 1 instruction */
 #define X86_FEATURE_XSAVES		(10*32+ 3) /* XSAVES/XRSTORS instructions */
+#define X86_FEATURE_XFD			(10*32+ 4) /* "" eXtended Feature Disabling */
 
 /*
  * Extended auxiliary flags: Linux defined - for features scattered in various
@@ -298,6 +299,7 @@
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* AVX VNNI instructions */
 #define X86_FEATURE_AVX512_BF16		(12*32+ 5) /* AVX512 BFLOAT16 instructions */
+#define X86_FEATURE_AMX_TILE		(18*32+24) /* AMX tile Support */
 
 /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
 #define X86_FEATURE_CLZERO		(13*32+ 0) /* CLZERO instruction */
-- 
cgit v1.2.3


From 346e91998cba46b64e8ef5f89813f8918c2731e6 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Sun, 9 May 2021 09:39:02 -0300
Subject: tools headers UAPI: Sync linux/kvm.h with the kernel sources

To pick the changes in:

  b56639318bb2be66 ("KVM: SEV: Add support for SEV intra host migration")
  e615e355894e6197 ("KVM: x86: On emulation failure, convey the exit reason, etc. to userspace")
  a9d496d8e08ca1eb ("KVM: x86: Clarify the kvm_run.emulation_failure structure layout")
  c68dc1b577eabd56 ("KVM: x86: Report host tsc and realtime values in KVM_GET_CLOCK")
  dea8ee31a0392775 ("RISC-V: KVM: Add SBI v0.1 support")

That just rebuilds perf, as these patches don't add any new KVM ioctl to
be harvested for the the 'perf trace' ioctl syscall argument
beautifiers.

This is also by now used by tools/testing/selftests/kvm/, a simple test
build succeeded.

This silences this perf build warning:

  Warning: Kernel ABI header at 'tools/include/uapi/linux/kvm.h' differs from latest version at 'include/uapi/linux/kvm.h'
  diff -u tools/include/uapi/linux/kvm.h include/uapi/linux/kvm.h

Cc: Anup Patel <anup@brainfault.org>
Cc: Atish Patra <atish.patra@wdc.com>
Cc: David Edmondson <david.edmondson@oracle.com>
Cc: Oliver Upton <oupton@google.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Gonda <pgonda@google.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/kvm.h | 30 +++++++++++++++++++++++++++---
 1 file changed, 27 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index a067410ebea5..1daa45268de2 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -269,6 +269,7 @@ struct kvm_xen_exit {
 #define KVM_EXIT_AP_RESET_HOLD    32
 #define KVM_EXIT_X86_BUS_LOCK     33
 #define KVM_EXIT_XEN              34
+#define KVM_EXIT_RISCV_SBI        35
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -397,13 +398,23 @@ struct kvm_run {
 		 * "ndata" is correct, that new fields are enumerated in "flags",
 		 * and that each flag enumerates fields that are 64-bit aligned
 		 * and sized (so that ndata+internal.data[] is valid/accurate).
+		 *
+		 * Space beyond the defined fields may be used to store arbitrary
+		 * debug information relating to the emulation failure. It is
+		 * accounted for in "ndata" but the format is unspecified and is
+		 * not represented in "flags". Any such information is *not* ABI!
 		 */
 		struct {
 			__u32 suberror;
 			__u32 ndata;
 			__u64 flags;
-			__u8  insn_size;
-			__u8  insn_bytes[15];
+			union {
+				struct {
+					__u8  insn_size;
+					__u8  insn_bytes[15];
+				};
+			};
+			/* Arbitrary debug data may follow. */
 		} emulation_failure;
 		/* KVM_EXIT_OSI */
 		struct {
@@ -469,6 +480,13 @@ struct kvm_run {
 		} msr;
 		/* KVM_EXIT_XEN */
 		struct kvm_xen_exit xen;
+		/* KVM_EXIT_RISCV_SBI */
+		struct {
+			unsigned long extension_id;
+			unsigned long function_id;
+			unsigned long args[6];
+			unsigned long ret[2];
+		} riscv_sbi;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -1112,6 +1130,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_BINARY_STATS_FD 203
 #define KVM_CAP_EXIT_ON_EMULATION_FAILURE 204
 #define KVM_CAP_ARM_MTE 205
+#define KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM 206
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1223,11 +1242,16 @@ struct kvm_irqfd {
 
 /* Do not use 1, KVM_CHECK_EXTENSION returned it before we had flags.  */
 #define KVM_CLOCK_TSC_STABLE		2
+#define KVM_CLOCK_REALTIME		(1 << 2)
+#define KVM_CLOCK_HOST_TSC		(1 << 3)
 
 struct kvm_clock_data {
 	__u64 clock;
 	__u32 flags;
-	__u32 pad[9];
+	__u32 pad0;
+	__u64 realtime;
+	__u64 host_tsc;
+	__u32 pad[4];
 };
 
 /* For KVM_CAP_SW_TLB */
-- 
cgit v1.2.3


From ccb05590c4325ce50b1c0deedd54d5f24f4f1652 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 16 Nov 2021 13:02:52 -0300
Subject: perf tests wp: Remove unused functions on s390

Fixing these build problems:

  tests/wp.c:24:12: error: 'wp_read' defined but not used [-Werror=unused-function]
   static int wp_read(int fd, long long *count, int size)
              ^
  tests/wp.c:35:13: error: 'get__perf_event_attr' defined but not used [-Werror=unused-function]
   static void get__perf_event_attr(struct perf_event_attr *attr, int wp_type,
               ^
    CC      /tmp/build/perf/util/print_binary.o

Fixes: e47c6ecaae1df54a ("perf test: Convert watch point tests to test cases.")
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Brendan Higgins <brendanhiggins@google.com>
Cc: Daniel Latypov <dlatypov@google.com>
Cc: David Gow <davidgow@google.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Clarke <pc@us.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sohaib Mohamed <sohaib.amhmd@gmail.com>
Cc: Stephane Eranian <eranian@google.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/wp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/tests/wp.c b/tools/perf/tests/wp.c
index 820d942b30c3..9d4c45184e71 100644
--- a/tools/perf/tests/wp.c
+++ b/tools/perf/tests/wp.c
@@ -21,6 +21,7 @@ do {                                            \
 volatile u64 data1;
 volatile u8 data2[3];
 
+#ifndef __s390x__
 static int wp_read(int fd, long long *count, int size)
 {
 	int ret = read(fd, count, size);
@@ -48,7 +49,6 @@ static void get__perf_event_attr(struct perf_event_attr *attr, int wp_type,
 	attr->exclude_hv     = 1;
 }
 
-#ifndef __s390x__
 static int __event(int wp_type, void *wp_addr, unsigned long wp_len)
 {
 	int fd;
-- 
cgit v1.2.3


From 70f9c9b2df1dd12cf40862b2b31c7bf89e311066 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 16 Nov 2021 14:44:17 -0300
Subject: perf tools: Set COMPAT_NEED_REALLOCARRAY for CONFIG_AUXTRACE=1

As it is being used in tools/perf/arch/arm64/util/arm-spe.c and the
COMPAT_NEED_REALLOCARRAY was only being set when CORESIGHT=1 is set.

Fixes: 56c31cdff7c2a640 ("perf arm-spe: Implement find_snapshot callback")
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/all/YZT63mIc7iY01er3@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Makefile.config | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 07e65a061fd3..afd144725a0b 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -1010,6 +1010,9 @@ ifndef NO_AUXTRACE
   ifndef NO_AUXTRACE
     $(call detected,CONFIG_AUXTRACE)
     CFLAGS += -DHAVE_AUXTRACE_SUPPORT
+    ifeq ($(feature-reallocarray), 0)
+      CFLAGS += -DCOMPAT_NEED_REALLOCARRAY
+    endif
   endif
 endif
 
-- 
cgit v1.2.3


From 784e8adda4cdb3e2510742023729851b6c08803c Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Fri, 5 Nov 2021 15:56:15 -0700
Subject: perf sort: Fix the 'weight' sort key behavior

Currently, the 'weight' field in the perf sample has latency information
for some instructions like in memory accesses.  And perf tool has 'weight'
and 'local_weight' sort keys to display the info.

But it's somewhat confusing what it shows exactly.  In my understanding,
'local_weight' shows a weight in a single sample, and (global) 'weight'
shows a sum of the weights in the hist_entry.

For example:

  $ perf mem record -t load dd if=/dev/zero of=/dev/null bs=4k count=1M

  $ perf report --stdio -n -s +local_weight
  ...
  #
  # Overhead  Samples  Command  Shared Object     Symbol                     Local Weight
  # ........  .......  .......  ................  .........................  ............
  #
      21.23%      313  dd       [kernel.vmlinux]  [k] lockref_get_not_zero   32
      12.43%      183  dd       [kernel.vmlinux]  [k] lockref_get_not_zero   35
      11.97%      159  dd       [kernel.vmlinux]  [k] lockref_get_not_zero   36
      10.40%      141  dd       [kernel.vmlinux]  [k] lockref_put_return     32
       7.63%      113  dd       [kernel.vmlinux]  [k] lockref_get_not_zero   33
       6.37%       92  dd       [kernel.vmlinux]  [k] lockref_get_not_zero   34
       6.15%       90  dd       [kernel.vmlinux]  [k] lockref_put_return     33
  ...

So let's look at the 'lockref_get_not_zero' symbols.  The top entry
shows that 313 samples were captured with 'local_weight' 32, so the
total weight should be 313 x 32 = 10016.  But it's not the case:

  $ perf report --stdio -n -s +local_weight,weight -S lockref_get_not_zero
  ...
  #
  # Overhead  Samples  Command  Shared Object     Local Weight  Weight
  # ........  .......  .......  ................  ............  ......
  #
       1.36%        4  dd       [kernel.vmlinux]  36            144
       0.47%        4  dd       [kernel.vmlinux]  37            148
       0.42%        4  dd       [kernel.vmlinux]  32            128
       0.40%        4  dd       [kernel.vmlinux]  34            136
       0.35%        4  dd       [kernel.vmlinux]  36            144
       0.34%        4  dd       [kernel.vmlinux]  35            140
       0.30%        4  dd       [kernel.vmlinux]  36            144
       0.30%        4  dd       [kernel.vmlinux]  34            136
       0.30%        4  dd       [kernel.vmlinux]  32            128
       0.30%        4  dd       [kernel.vmlinux]  32            128
  ...

With the 'weight' sort key, it's divided to 4 samples even with the same
info ('comm', 'dso', 'sym' and 'local_weight').  I don't think this is
what we want.

I found this because of the way it aggregates the 'weight' value.  Since
it's not a period, we should not add them in the he->stat.  Otherwise,
two 32 'weight' entries will create a 64 'weight' entry.

After that, new 32 'weight' samples don't have a matching entry so it'd
create a new entry and make it a 64 'weight' entry again and again.
Later, they will be merged into 128 'weight' entries during the
hists__collapse_resort() with 4 samples, multiple times like above.

Let's keep the weight and display it differently.  For 'local_weight',
it can show the weight as is, and for (global) 'weight' it can display
the number multiplied by the number of samples.

With this change, I can see the expected numbers.

  $ perf report --stdio -n -s +local_weight,weight -S lockref_get_not_zero
  ...
  #
  # Overhead  Samples  Command  Shared Object     Local Weight  Weight
  # ........  .......  .......  ................  ............  .....
  #
      21.23%      313  dd       [kernel.vmlinux]  32            10016
      12.43%      183  dd       [kernel.vmlinux]  35            6405
      11.97%      159  dd       [kernel.vmlinux]  36            5724
       7.63%      113  dd       [kernel.vmlinux]  33            3729
       6.37%       92  dd       [kernel.vmlinux]  34            3128
       4.17%       59  dd       [kernel.vmlinux]  37            2183
       0.08%        1  dd       [kernel.vmlinux]  269           269
       0.08%        1  dd       [kernel.vmlinux]  38            38

Reviewed-by: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20211105225617.151364-1-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/hist.c | 14 +++++---------
 tools/perf/util/sort.c | 24 +++++++-----------------
 tools/perf/util/sort.h |  2 +-
 3 files changed, 13 insertions(+), 27 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 65fe65ba03c2..4e9bd7b589b1 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -290,11 +290,9 @@ static long hist_time(unsigned long htime)
 }
 
 static void he_stat__add_period(struct he_stat *he_stat, u64 period,
-				u64 weight, u64 ins_lat, u64 p_stage_cyc)
+				u64 ins_lat, u64 p_stage_cyc)
 {
-
 	he_stat->period		+= period;
-	he_stat->weight		+= weight;
 	he_stat->nr_events	+= 1;
 	he_stat->ins_lat	+= ins_lat;
 	he_stat->p_stage_cyc	+= p_stage_cyc;
@@ -308,9 +306,8 @@ static void he_stat__add_stat(struct he_stat *dest, struct he_stat *src)
 	dest->period_guest_sys	+= src->period_guest_sys;
 	dest->period_guest_us	+= src->period_guest_us;
 	dest->nr_events		+= src->nr_events;
-	dest->weight		+= src->weight;
 	dest->ins_lat		+= src->ins_lat;
-	dest->p_stage_cyc		+= src->p_stage_cyc;
+	dest->p_stage_cyc	+= src->p_stage_cyc;
 }
 
 static void he_stat__decay(struct he_stat *he_stat)
@@ -598,7 +595,6 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists,
 	struct hist_entry *he;
 	int64_t cmp;
 	u64 period = entry->stat.period;
-	u64 weight = entry->stat.weight;
 	u64 ins_lat = entry->stat.ins_lat;
 	u64 p_stage_cyc = entry->stat.p_stage_cyc;
 	bool leftmost = true;
@@ -619,11 +615,11 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists,
 
 		if (!cmp) {
 			if (sample_self) {
-				he_stat__add_period(&he->stat, period, weight, ins_lat, p_stage_cyc);
+				he_stat__add_period(&he->stat, period, ins_lat, p_stage_cyc);
 				hist_entry__add_callchain_period(he, period);
 			}
 			if (symbol_conf.cumulate_callchain)
-				he_stat__add_period(he->stat_acc, period, weight, ins_lat, p_stage_cyc);
+				he_stat__add_period(he->stat_acc, period, ins_lat, p_stage_cyc);
 
 			/*
 			 * This mem info was allocated from sample__resolve_mem
@@ -733,7 +729,6 @@ __hists__add_entry(struct hists *hists,
 		.stat = {
 			.nr_events = 1,
 			.period	= sample->period,
-			.weight = sample->weight,
 			.ins_lat = sample->ins_lat,
 			.p_stage_cyc = sample->p_stage_cyc,
 		},
@@ -748,6 +743,7 @@ __hists__add_entry(struct hists *hists,
 		.raw_size = sample->raw_size,
 		.ops = ops,
 		.time = hist_time(sample->time),
+		.weight = sample->weight,
 	}, *he = hists__findnew_entry(hists, &entry, al, sample_self);
 
 	if (!hists->has_callchains && he && he->callchain_size != 0)
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 568a88c001c6..903f34fff27e 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1325,45 +1325,35 @@ struct sort_entry sort_mispredict = {
 	.se_width_idx	= HISTC_MISPREDICT,
 };
 
-static u64 he_weight(struct hist_entry *he)
-{
-	return he->stat.nr_events ? he->stat.weight / he->stat.nr_events : 0;
-}
-
 static int64_t
-sort__local_weight_cmp(struct hist_entry *left, struct hist_entry *right)
+sort__weight_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	return he_weight(left) - he_weight(right);
+	return left->weight - right->weight;
 }
 
 static int hist_entry__local_weight_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
-	return repsep_snprintf(bf, size, "%-*llu", width, he_weight(he));
+	return repsep_snprintf(bf, size, "%-*llu", width, he->weight);
 }
 
 struct sort_entry sort_local_weight = {
 	.se_header	= "Local Weight",
-	.se_cmp		= sort__local_weight_cmp,
+	.se_cmp		= sort__weight_cmp,
 	.se_snprintf	= hist_entry__local_weight_snprintf,
 	.se_width_idx	= HISTC_LOCAL_WEIGHT,
 };
 
-static int64_t
-sort__global_weight_cmp(struct hist_entry *left, struct hist_entry *right)
-{
-	return left->stat.weight - right->stat.weight;
-}
-
 static int hist_entry__global_weight_snprintf(struct hist_entry *he, char *bf,
 					      size_t size, unsigned int width)
 {
-	return repsep_snprintf(bf, size, "%-*llu", width, he->stat.weight);
+	return repsep_snprintf(bf, size, "%-*llu", width,
+			       he->weight * he->stat.nr_events);
 }
 
 struct sort_entry sort_global_weight = {
 	.se_header	= "Weight",
-	.se_cmp		= sort__global_weight_cmp,
+	.se_cmp		= sort__weight_cmp,
 	.se_snprintf	= hist_entry__global_weight_snprintf,
 	.se_width_idx	= HISTC_GLOBAL_WEIGHT,
 };
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index b67c469aba79..e18b79916f63 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -49,7 +49,6 @@ struct he_stat {
 	u64			period_us;
 	u64			period_guest_sys;
 	u64			period_guest_us;
-	u64			weight;
 	u64			ins_lat;
 	u64			p_stage_cyc;
 	u32			nr_events;
@@ -109,6 +108,7 @@ struct hist_entry {
 	s32			socket;
 	s32			cpu;
 	u64			code_page_size;
+	u64			weight;
 	u8			cpumode;
 	u8			depth;
 
-- 
cgit v1.2.3


From 4d03c75363eeca861c843319a0e6f4426234ed6c Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Fri, 5 Nov 2021 15:56:16 -0700
Subject: perf sort: Fix the 'ins_lat' sort key behavior

Handle 'ins_lat' (for instruction latency) and 'local_ins_lat' sort keys
with the same rationale as for the 'weight' and 'local_weight', see the
previous fix in this series for a full explanation.

But I couldn't test it actually, so only build tested.

Reviewed-by: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20211105225617.151364-2-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/hist.c | 11 ++++-------
 tools/perf/util/sort.c | 24 +++++++-----------------
 tools/perf/util/sort.h |  2 +-
 3 files changed, 12 insertions(+), 25 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 4e9bd7b589b1..54fe97dd191c 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -290,11 +290,10 @@ static long hist_time(unsigned long htime)
 }
 
 static void he_stat__add_period(struct he_stat *he_stat, u64 period,
-				u64 ins_lat, u64 p_stage_cyc)
+				u64 p_stage_cyc)
 {
 	he_stat->period		+= period;
 	he_stat->nr_events	+= 1;
-	he_stat->ins_lat	+= ins_lat;
 	he_stat->p_stage_cyc	+= p_stage_cyc;
 }
 
@@ -306,7 +305,6 @@ static void he_stat__add_stat(struct he_stat *dest, struct he_stat *src)
 	dest->period_guest_sys	+= src->period_guest_sys;
 	dest->period_guest_us	+= src->period_guest_us;
 	dest->nr_events		+= src->nr_events;
-	dest->ins_lat		+= src->ins_lat;
 	dest->p_stage_cyc	+= src->p_stage_cyc;
 }
 
@@ -595,7 +593,6 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists,
 	struct hist_entry *he;
 	int64_t cmp;
 	u64 period = entry->stat.period;
-	u64 ins_lat = entry->stat.ins_lat;
 	u64 p_stage_cyc = entry->stat.p_stage_cyc;
 	bool leftmost = true;
 
@@ -615,11 +612,11 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists,
 
 		if (!cmp) {
 			if (sample_self) {
-				he_stat__add_period(&he->stat, period, ins_lat, p_stage_cyc);
+				he_stat__add_period(&he->stat, period, p_stage_cyc);
 				hist_entry__add_callchain_period(he, period);
 			}
 			if (symbol_conf.cumulate_callchain)
-				he_stat__add_period(he->stat_acc, period, ins_lat, p_stage_cyc);
+				he_stat__add_period(he->stat_acc, period, p_stage_cyc);
 
 			/*
 			 * This mem info was allocated from sample__resolve_mem
@@ -729,7 +726,6 @@ __hists__add_entry(struct hists *hists,
 		.stat = {
 			.nr_events = 1,
 			.period	= sample->period,
-			.ins_lat = sample->ins_lat,
 			.p_stage_cyc = sample->p_stage_cyc,
 		},
 		.parent = sym_parent,
@@ -744,6 +740,7 @@ __hists__add_entry(struct hists *hists,
 		.ops = ops,
 		.time = hist_time(sample->time),
 		.weight = sample->weight,
+		.ins_lat = sample->ins_lat,
 	}, *he = hists__findnew_entry(hists, &entry, al, sample_self);
 
 	if (!hists->has_callchains && he && he->callchain_size != 0)
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 903f34fff27e..adc0584695d6 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1358,45 +1358,35 @@ struct sort_entry sort_global_weight = {
 	.se_width_idx	= HISTC_GLOBAL_WEIGHT,
 };
 
-static u64 he_ins_lat(struct hist_entry *he)
-{
-		return he->stat.nr_events ? he->stat.ins_lat / he->stat.nr_events : 0;
-}
-
 static int64_t
-sort__local_ins_lat_cmp(struct hist_entry *left, struct hist_entry *right)
+sort__ins_lat_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-		return he_ins_lat(left) - he_ins_lat(right);
+	return left->ins_lat - right->ins_lat;
 }
 
 static int hist_entry__local_ins_lat_snprintf(struct hist_entry *he, char *bf,
 					      size_t size, unsigned int width)
 {
-		return repsep_snprintf(bf, size, "%-*u", width, he_ins_lat(he));
+	return repsep_snprintf(bf, size, "%-*u", width, he->ins_lat);
 }
 
 struct sort_entry sort_local_ins_lat = {
 	.se_header	= "Local INSTR Latency",
-	.se_cmp		= sort__local_ins_lat_cmp,
+	.se_cmp		= sort__ins_lat_cmp,
 	.se_snprintf	= hist_entry__local_ins_lat_snprintf,
 	.se_width_idx	= HISTC_LOCAL_INS_LAT,
 };
 
-static int64_t
-sort__global_ins_lat_cmp(struct hist_entry *left, struct hist_entry *right)
-{
-		return left->stat.ins_lat - right->stat.ins_lat;
-}
-
 static int hist_entry__global_ins_lat_snprintf(struct hist_entry *he, char *bf,
 					       size_t size, unsigned int width)
 {
-		return repsep_snprintf(bf, size, "%-*u", width, he->stat.ins_lat);
+	return repsep_snprintf(bf, size, "%-*u", width,
+			       he->ins_lat * he->stat.nr_events);
 }
 
 struct sort_entry sort_global_ins_lat = {
 	.se_header	= "INSTR Latency",
-	.se_cmp		= sort__global_ins_lat_cmp,
+	.se_cmp		= sort__ins_lat_cmp,
 	.se_snprintf	= hist_entry__global_ins_lat_snprintf,
 	.se_width_idx	= HISTC_GLOBAL_INS_LAT,
 };
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index e18b79916f63..22ae7c6ae398 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -49,7 +49,6 @@ struct he_stat {
 	u64			period_us;
 	u64			period_guest_sys;
 	u64			period_guest_us;
-	u64			ins_lat;
 	u64			p_stage_cyc;
 	u32			nr_events;
 };
@@ -109,6 +108,7 @@ struct hist_entry {
 	s32			cpu;
 	u64			code_page_size;
 	u64			weight;
+	u64			ins_lat;
 	u8			cpumode;
 	u8			depth;
 
-- 
cgit v1.2.3


From db4b284029099224f387d75198e5995df1cb8aef Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Fri, 5 Nov 2021 15:56:17 -0700
Subject: perf sort: Fix the 'p_stage_cyc' sort key behavior

andle 'p_stage_cyc' (for pipeline stage cycles) sort key with the same
rationale as for the 'weight' and 'local_weight', see the fix in this
series for a full explanation.

Not sure it also needs the local and global variants.

But I couldn't test it actually because I don't have the machine.

Reviewed-by: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20211105225617.151364-3-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/hist.c | 12 ++++--------
 tools/perf/util/sort.c |  4 ++--
 tools/perf/util/sort.h |  2 +-
 3 files changed, 7 insertions(+), 11 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 54fe97dd191c..b776465e04ef 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -289,12 +289,10 @@ static long hist_time(unsigned long htime)
 	return htime;
 }
 
-static void he_stat__add_period(struct he_stat *he_stat, u64 period,
-				u64 p_stage_cyc)
+static void he_stat__add_period(struct he_stat *he_stat, u64 period)
 {
 	he_stat->period		+= period;
 	he_stat->nr_events	+= 1;
-	he_stat->p_stage_cyc	+= p_stage_cyc;
 }
 
 static void he_stat__add_stat(struct he_stat *dest, struct he_stat *src)
@@ -305,7 +303,6 @@ static void he_stat__add_stat(struct he_stat *dest, struct he_stat *src)
 	dest->period_guest_sys	+= src->period_guest_sys;
 	dest->period_guest_us	+= src->period_guest_us;
 	dest->nr_events		+= src->nr_events;
-	dest->p_stage_cyc	+= src->p_stage_cyc;
 }
 
 static void he_stat__decay(struct he_stat *he_stat)
@@ -593,7 +590,6 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists,
 	struct hist_entry *he;
 	int64_t cmp;
 	u64 period = entry->stat.period;
-	u64 p_stage_cyc = entry->stat.p_stage_cyc;
 	bool leftmost = true;
 
 	p = &hists->entries_in->rb_root.rb_node;
@@ -612,11 +608,11 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists,
 
 		if (!cmp) {
 			if (sample_self) {
-				he_stat__add_period(&he->stat, period, p_stage_cyc);
+				he_stat__add_period(&he->stat, period);
 				hist_entry__add_callchain_period(he, period);
 			}
 			if (symbol_conf.cumulate_callchain)
-				he_stat__add_period(he->stat_acc, period, p_stage_cyc);
+				he_stat__add_period(he->stat_acc, period);
 
 			/*
 			 * This mem info was allocated from sample__resolve_mem
@@ -726,7 +722,6 @@ __hists__add_entry(struct hists *hists,
 		.stat = {
 			.nr_events = 1,
 			.period	= sample->period,
-			.p_stage_cyc = sample->p_stage_cyc,
 		},
 		.parent = sym_parent,
 		.filtered = symbol__parent_filter(sym_parent) | al->filtered,
@@ -741,6 +736,7 @@ __hists__add_entry(struct hists *hists,
 		.time = hist_time(sample->time),
 		.weight = sample->weight,
 		.ins_lat = sample->ins_lat,
+		.p_stage_cyc = sample->p_stage_cyc,
 	}, *he = hists__findnew_entry(hists, &entry, al, sample_self);
 
 	if (!hists->has_callchains && he && he->callchain_size != 0)
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index adc0584695d6..a111065b484e 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1394,13 +1394,13 @@ struct sort_entry sort_global_ins_lat = {
 static int64_t
 sort__global_p_stage_cyc_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	return left->stat.p_stage_cyc - right->stat.p_stage_cyc;
+	return left->p_stage_cyc - right->p_stage_cyc;
 }
 
 static int hist_entry__p_stage_cyc_snprintf(struct hist_entry *he, char *bf,
 					size_t size, unsigned int width)
 {
-	return repsep_snprintf(bf, size, "%-*u", width, he->stat.p_stage_cyc);
+	return repsep_snprintf(bf, size, "%-*u", width, he->p_stage_cyc);
 }
 
 struct sort_entry sort_p_stage_cyc = {
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 22ae7c6ae398..7b7145501933 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -49,7 +49,6 @@ struct he_stat {
 	u64			period_us;
 	u64			period_guest_sys;
 	u64			period_guest_us;
-	u64			p_stage_cyc;
 	u32			nr_events;
 };
 
@@ -109,6 +108,7 @@ struct hist_entry {
 	u64			code_page_size;
 	u64			weight;
 	u64			ins_lat;
+	u64			p_stage_cyc;
 	u8			cpumode;
 	u8			depth;
 
-- 
cgit v1.2.3


From 162b944598344fd72800d453885979f06ca263f3 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 10 Sep 2021 11:46:54 -0300
Subject: tools headers UAPI: Sync x86's asm/kvm.h with the kernel sources

To pick the changes in:

  828ca89628bfcb1b ("KVM: x86: Expose TSC offset controls to userspace")

That just rebuilds kvm-stat.c on x86, no change in functionality.

This silences these perf build warning:

  Warning: Kernel ABI header at 'tools/arch/x86/include/uapi/asm/kvm.h' differs from latest version at 'arch/x86/include/uapi/asm/kvm.h'
  diff -u tools/arch/x86/include/uapi/asm/kvm.h arch/x86/include/uapi/asm/kvm.h

Cc: Oliver Upton <oupton@google.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/x86/include/uapi/asm/kvm.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'tools')

diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 2ef1f6513c68..5a776a08f78c 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -504,4 +504,8 @@ struct kvm_pmu_event_filter {
 #define KVM_PMU_EVENT_ALLOW 0
 #define KVM_PMU_EVENT_DENY 1
 
+/* for KVM_{GET,SET,HAS}_DEVICE_ATTR */
+#define KVM_VCPU_TSC_CTRL 0 /* control group for the timestamp counter (TSC) */
+#define   KVM_VCPU_TSC_OFFSET 0 /* attribute for the TSC offset */
+
 #endif /* _ASM_X86_KVM_H */
-- 
cgit v1.2.3


From cb5a63feae2d963cac7b687e6598d620bed13507 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Wed, 17 Nov 2021 09:26:09 +0100
Subject: perf test sample-parsing: Fix branch_stack entry endianness check

Commit 10269a2ca2b08cbd ("perf test sample-parsing: Add endian test for
struct branch_flags") broke the test case 27 (Sample parsing) on s390 on
linux-next tree:

  # perf test -Fv 27
  27: Sample parsing
  --- start ---
  parsing failed for sample_type 0x800
  ---- end ----
  Sample parsing: FAILED!
  #

The cause of the failure is a wrong #define BS_EXPECTED_BE statement in
above commit.  Correct this define and the test case runs fine.

Output After:

  # perf test -Fv 27
  27: Sample parsing                                                  :
  --- start ---
  ---- end ----
  Sample parsing: Ok
  #

Fixes: 10269a2ca2b08c ("perf test sample-parsing: Add endian test for struct branch_flags")
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Tested-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Acked-by: Madhavan Srinivasan <maddy@linux.ibm.com>
CC: Sven Schnelle <svens@linux.ibm.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Link: https://lore.kernel.org/r/54077e81-503e-3405-6cb0-6541eb5532cc@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/sample-parsing.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index b669d22f2b13..07f2411b0ad4 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -36,7 +36,7 @@
  * These are based on the input value (213) specified
  * in branch_stack variable.
  */
-#define BS_EXPECTED_BE	0xa00d000000000000
+#define BS_EXPECTED_BE	0xa000d00000000000
 #define BS_EXPECTED_LE	0xd5000000
 #define FLAG(s)	s->branch_stack->entries[i].flags
 
-- 
cgit v1.2.3


From 92723ea0f11d92496687db8c9725248e9d1e5e1d Mon Sep 17 00:00:00 2001
From: Sohaib Mohamed <sohaib.amhmd@gmail.com>
Date: Wed, 10 Nov 2021 04:20:11 +0200
Subject: perf bench: Fix two memory leaks detected with ASan

ASan reports memory leaks while running:

  $ perf bench sched all

Fixes: e27454cc6352c422 ("perf bench: Add sched-messaging.c: Benchmark for scheduler and IPC mechanisms based on hackbench")
Signed-off-by: Sohaib Mohamed <sohaib.amhmd@gmail.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Hitoshi Mitake <h.mitake@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Russel <rusty@rustcorp.com.au>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Pierre Gondois <pierre.gondois@arm.com>
Link: http://lore.kernel.org/lkml/20211110022012.16620-1-sohaib.amhmd@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/bench/sched-messaging.c | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c
index 488f6e6ba1a5..fa0ff4ce2b74 100644
--- a/tools/perf/bench/sched-messaging.c
+++ b/tools/perf/bench/sched-messaging.c
@@ -223,6 +223,8 @@ static unsigned int group(pthread_t *pth,
 		snd_ctx->out_fds[i] = fds[1];
 		if (!thread_mode)
 			close(fds[0]);
+
+		free(ctx);
 	}
 
 	/* Now we have all the fds, fork the senders */
@@ -239,6 +241,8 @@ static unsigned int group(pthread_t *pth,
 		for (i = 0; i < num_fds; i++)
 			close(snd_ctx->out_fds[i]);
 
+	free(snd_ctx);
+
 	/* Return number of children to reap */
 	return num_fds * 2;
 }
-- 
cgit v1.2.3


From 9e1a8d9f683260d50e0a14176d3f7c46a93b2700 Mon Sep 17 00:00:00 2001
From: German Gomez <german.gomez@arm.com>
Date: Fri, 5 Nov 2021 10:41:30 +0000
Subject: perf inject: Fix ARM SPE handling

'perf inject' is currently not working for Arm SPE. When you try to run
'perf inject' and 'perf report' with a perf.data file that contains SPE
traces, the tool reports a "Bad address" error:

  # ./perf record -e arm_spe_0/ts_enable=1,store_filter=1,branch_filter=1,load_filter=1/ -a -- sleep 1
  # ./perf inject -i perf.data -o perf.inject.data --itrace
  # ./perf report -i perf.inject.data --stdio

  0x42c00 [0x8]: failed to process type: 9 [Bad address]
  Error:
  failed to process sample

As far as I know, the issue was first spotted in [1], but 'perf inject'
was not yet injecting the samples. This patch does something similar to
what cs_etm does for injecting the samples [2], but for SPE.

[1] https://patchwork.kernel.org/project/linux-arm-kernel/cover/20210412091006.468557-1-leo.yan@linaro.org/#24117339
[2] https://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git/tree/tools/perf/util/cs-etm.c?h=perf/core&id=133fe2e617e48ca0948983329f43877064ffda3e#n1196

Reviewed-by: James Clark <james.clark@arm.com>
Signed-off-by: German Gomez <german.gomez@arm.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20211105104130.28186-2-german.gomez@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/arm-spe.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index 4748bcfe61de..fccac06b573a 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -51,6 +51,7 @@ struct arm_spe {
 	u8				timeless_decoding;
 	u8				data_queued;
 
+	u64				sample_type;
 	u8				sample_flc;
 	u8				sample_llc;
 	u8				sample_tlb;
@@ -287,6 +288,12 @@ static void arm_spe_prep_sample(struct arm_spe *spe,
 	event->sample.header.size = sizeof(struct perf_event_header);
 }
 
+static int arm_spe__inject_event(union perf_event *event, struct perf_sample *sample, u64 type)
+{
+	event->header.size = perf_event__sample_event_size(sample, type, 0);
+	return perf_event__synthesize_sample(event, type, 0, sample);
+}
+
 static inline int
 arm_spe_deliver_synth_event(struct arm_spe *spe,
 			    struct arm_spe_queue *speq __maybe_unused,
@@ -295,6 +302,12 @@ arm_spe_deliver_synth_event(struct arm_spe *spe,
 {
 	int ret;
 
+	if (spe->synth_opts.inject) {
+		ret = arm_spe__inject_event(event, sample, spe->sample_type);
+		if (ret)
+			return ret;
+	}
+
 	ret = perf_session__deliver_synth_event(spe->session, event, sample);
 	if (ret)
 		pr_err("ARM SPE: failed to deliver event, error %d\n", ret);
@@ -986,6 +999,8 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session)
 	else
 		attr.sample_type |= PERF_SAMPLE_TIME;
 
+	spe->sample_type = attr.sample_type;
+
 	attr.exclude_user = evsel->core.attr.exclude_user;
 	attr.exclude_kernel = evsel->core.attr.exclude_kernel;
 	attr.exclude_hv = evsel->core.attr.exclude_hv;
-- 
cgit v1.2.3


From e8c04ea0fef5731dbcaabac86d65254c227aedf4 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 17 Nov 2021 14:29:31 -0300
Subject: tools build: Fix removal of feature-sync-compare-and-swap feature
 detection
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The patch removing the feature-sync-compare-and-swap feature detection
didn't remove the call to main_test_sync_compare_and_swap(), making the
'test-all' case fail an all the feature tests to be performed
individually:

  $ cat /tmp/build/perf/feature/test-all.make.output
  In file included from test-all.c:18:
  test-libpython-version.c:5:10: error: #error
      5 |         #error
        |          ^~~~~
  test-all.c: In function ‘main’:
  test-all.c:203:9: error: implicit declaration of function ‘main_test_sync_compare_and_swap’ [-Werror=implicit-function-declaration]
    203 |         main_test_sync_compare_and_swap(argc, argv);
        |         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  cc1: all warnings being treated as errors
  $

Fix it, now to figure out what is that test-libpython-version.c
problem...

Fixes: 60fa754b2a5a4e0c ("tools: Remove feature-sync-compare-and-swap feature detection")
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/YZU9Fe0sgkHSXeC2@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/build/feature/test-all.c | 1 -
 1 file changed, 1 deletion(-)

(limited to 'tools')

diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
index 920439527291..0b243ce842be 100644
--- a/tools/build/feature/test-all.c
+++ b/tools/build/feature/test-all.c
@@ -200,7 +200,6 @@ int main(int argc, char *argv[])
 	main_test_timerfd();
 	main_test_stackprotector_all();
 	main_test_libdw_dwarf_unwind();
-	main_test_sync_compare_and_swap(argc, argv);
 	main_test_zlib();
 	main_test_pthread_attr_setaffinity_np();
 	main_test_pthread_barrier();
-- 
cgit v1.2.3


From 8b8dcc3720d57d88faa74e0da2fb419da953ddd0 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 8 Sep 2021 16:09:08 -0300
Subject: tools headers UAPI: Sync MIPS syscall table file changed by new
 futex_waitv syscall

To pick the changes in these csets:

  b3ff2881ba18b852 ("MIPS: syscalls: Wire up futex_waitv syscall")

That add support for this new syscall in tools such as 'perf trace'.

For instance, this is now possible (adapted from the x86_64 test output):

  # perf trace -e futex_waitv
  ^C#
  # perf trace -v -e futex_waitv
  event qualifier tracepoint filter: (common_pid != 807333 && common_pid != 3564) && (id == 449)
  ^C#
  # perf trace -v -e futex* --max-events 10
  event qualifier tracepoint filter: (common_pid != 812168 && common_pid != 3564) && (id == 202 || id == 449)
  mmap size 528384B
           ? (         ): Timer/219310  ... [continued]: futex())                                            = -1 ETIMEDOUT (Connection timed out)
       0.012 ( 0.002 ms): Timer/219310 futex(uaddr: 0x7fd0b152d3c8, op: WAKE|PRIVATE_FLAG, val: 1)           = 0
       0.024 ( 0.060 ms): Timer/219310 futex(uaddr: 0x7fd0b152d420, op: WAIT_BITSET|PRIVATE_FLAG, utime: 0x7fd0b1657840, val3: MATCH_ANY) = 0
       0.086 ( 0.001 ms): Timer/219310 futex(uaddr: 0x7fd0b152d3c8, op: WAKE|PRIVATE_FLAG, val: 1)           = 0
       0.088 (         ): Timer/219310 futex(uaddr: 0x7fd0b152d424, op: WAIT_BITSET|PRIVATE_FLAG, utime: 0x7fd0b1657840, val3: MATCH_ANY) ...
       0.075 ( 0.005 ms): Web Content/219299 futex(uaddr: 0x7fd0b152d420, op: WAKE|PRIVATE_FLAG, val: 1)     = 1
       0.169 ( 0.004 ms): Web Content/219299 futex(uaddr: 0x7fd0b152d424, op: WAKE|PRIVATE_FLAG, val: 1)     = 1
       0.088 ( 0.089 ms): Timer/219310  ... [continued]: futex())                                            = 0
       0.179 ( 0.001 ms): Timer/219310 futex(uaddr: 0x7fd0b152d3c8, op: WAKE|PRIVATE_FLAG, val: 1)           = 0
       0.181 (         ): Timer/219310 futex(uaddr: 0x7fd0b152d420, op: WAIT_BITSET|PRIVATE_FLAG, utime: 0x7fd0b1657840, val3: MATCH_ANY) ...
  #

That is the filter expression attached to the raw_syscalls:sys_{enter,exit}
tracepoints.

  $ grep futex_waitv tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
  449	n64	futex_waitv			sys_futex_waitv
  $

This addresses these perf build warnings:

  Warning: Kernel ABI header at 'tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl' differs from latest version at 'arch/mips/kernel/syscalls/syscall_n64.tbl'
  diff -u tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl arch/mips/kernel/syscalls/syscall_n64.tbl

Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Wang Haojun <jiangliuer01@gmail.com>
Link: https://lore.kernel.org/lkml/YZZRxuIyvSGLZhM4@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
index 1ca7bc337932..e2c481fcede6 100644
--- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
+++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
@@ -363,3 +363,4 @@
 446	n64	landlock_restrict_self		sys_landlock_restrict_self
 # 447 reserved for memfd_secret
 448	n64	process_mrelease		sys_process_mrelease
+449	n64	futex_waitv			sys_futex_waitv
-- 
cgit v1.2.3


From 0ca1f534a776cc7d42f2c33da4732b74ec2790cd Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 17 Nov 2021 23:12:47 -0800
Subject: perf hist: Fix memory leak of a perf_hpp_fmt

perf_hpp__column_unregister() removes an entry from a list but doesn't
free the memory causing a memory leak spotted by leak sanitizer.

Add the free while at the same time reducing the scope of the function
to static.

Signed-off-by: Ian Rogers <irogers@google.com>
Reviewed-by: Kajol Jain <kjain@linux.ibm.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20211118071247.2140392-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/ui/hist.c   | 28 ++++++++++++++--------------
 tools/perf/util/hist.h |  1 -
 2 files changed, 14 insertions(+), 15 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index c1f24d004852..5075ecead5f3 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -535,6 +535,18 @@ struct perf_hpp_list perf_hpp_list = {
 #undef __HPP_SORT_ACC_FN
 #undef __HPP_SORT_RAW_FN
 
+static void fmt_free(struct perf_hpp_fmt *fmt)
+{
+	/*
+	 * At this point fmt should be completely
+	 * unhooked, if not it's a bug.
+	 */
+	BUG_ON(!list_empty(&fmt->list));
+	BUG_ON(!list_empty(&fmt->sort_list));
+
+	if (fmt->free)
+		fmt->free(fmt);
+}
 
 void perf_hpp__init(void)
 {
@@ -598,9 +610,10 @@ void perf_hpp_list__prepend_sort_field(struct perf_hpp_list *list,
 	list_add(&format->sort_list, &list->sorts);
 }
 
-void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
+static void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
 {
 	list_del_init(&format->list);
+	fmt_free(format);
 }
 
 void perf_hpp__cancel_cumulate(void)
@@ -672,19 +685,6 @@ next:
 }
 
 
-static void fmt_free(struct perf_hpp_fmt *fmt)
-{
-	/*
-	 * At this point fmt should be completely
-	 * unhooked, if not it's a bug.
-	 */
-	BUG_ON(!list_empty(&fmt->list));
-	BUG_ON(!list_empty(&fmt->sort_list));
-
-	if (fmt->free)
-		fmt->free(fmt);
-}
-
 void perf_hpp__reset_output_field(struct perf_hpp_list *list)
 {
 	struct perf_hpp_fmt *fmt, *tmp;
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 5343b62476e6..621f35ae1efa 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -369,7 +369,6 @@ enum {
 };
 
 void perf_hpp__init(void);
-void perf_hpp__column_unregister(struct perf_hpp_fmt *format);
 void perf_hpp__cancel_cumulate(void);
 void perf_hpp__setup_output_field(struct perf_hpp_list *list);
 void perf_hpp__reset_output_field(struct perf_hpp_list *list);
-- 
cgit v1.2.3


From d9fc706108c15f8bc2d4ccccf8e50f74830fabd9 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 17 Nov 2021 23:38:04 -0800
Subject: perf report: Fix memory leaks around perf_tip()

perf_tip() may allocate memory or use a literal, this means memory
wasn't freed if allocated. Change the API so that literals aren't used.

At the same time add missing frees for system_path. These issues were
spotted using leak sanitizer.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20211118073804.2149974-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-report.c | 15 +++++++++------
 tools/perf/util/util.c      | 14 +++++++-------
 tools/perf/util/util.h      |  2 +-
 3 files changed, 17 insertions(+), 14 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 8167ebfe776a..8ae400429870 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -619,14 +619,17 @@ static int report__browse_hists(struct report *rep)
 	int ret;
 	struct perf_session *session = rep->session;
 	struct evlist *evlist = session->evlist;
-	const char *help = perf_tip(system_path(TIPDIR));
+	char *help = NULL, *path = NULL;
 
-	if (help == NULL) {
+	path = system_path(TIPDIR);
+	if (perf_tip(&help, path) || help == NULL) {
 		/* fallback for people who don't install perf ;-) */
-		help = perf_tip(DOCDIR);
-		if (help == NULL)
-			help = "Cannot load tips.txt file, please install perf!";
+		free(path);
+		path = system_path(DOCDIR);
+		if (perf_tip(&help, path) || help == NULL)
+			help = strdup("Cannot load tips.txt file, please install perf!");
 	}
+	free(path);
 
 	switch (use_browser) {
 	case 1:
@@ -651,7 +654,7 @@ static int report__browse_hists(struct report *rep)
 		ret = evlist__tty_browse_hists(evlist, rep, help);
 		break;
 	}
-
+	free(help);
 	return ret;
 }
 
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 37a9492edb3e..df3c4671be72 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -379,32 +379,32 @@ fetch_kernel_version(unsigned int *puint, char *str,
 	return 0;
 }
 
-const char *perf_tip(const char *dirpath)
+int perf_tip(char **strp, const char *dirpath)
 {
 	struct strlist *tips;
 	struct str_node *node;
-	char *tip = NULL;
 	struct strlist_config conf = {
 		.dirname = dirpath,
 		.file_only = true,
 	};
+	int ret = 0;
 
+	*strp = NULL;
 	tips = strlist__new("tips.txt", &conf);
 	if (tips == NULL)
-		return errno == ENOENT ? NULL :
-			"Tip: check path of tips.txt or get more memory! ;-p";
+		return -errno;
 
 	if (strlist__nr_entries(tips) == 0)
 		goto out;
 
 	node = strlist__entry(tips, random() % strlist__nr_entries(tips));
-	if (asprintf(&tip, "Tip: %s", node->s) < 0)
-		tip = (char *)"Tip: get more memory! ;-)";
+	if (asprintf(strp, "Tip: %s", node->s) < 0)
+		ret = -ENOMEM;
 
 out:
 	strlist__delete(tips);
 
-	return tip;
+	return ret;
 }
 
 char *perf_exe(char *buf, int len)
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index ad737052e597..9f0d36ba77f2 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -39,7 +39,7 @@ int fetch_kernel_version(unsigned int *puint,
 #define KVER_FMT	"%d.%d.%d"
 #define KVER_PARAM(x)	KVER_VERSION(x), KVER_PATCHLEVEL(x), KVER_SUBLEVEL(x)
 
-const char *perf_tip(const char *dirpath);
+int perf_tip(char **strp, const char *dirpath);
 
 #ifndef HAVE_SCHED_GETCPU_SUPPORT
 int sched_getcpu(void);
-- 
cgit v1.2.3


From b194c9cd09dd98af76beaa32a041af674260d730 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 18 Nov 2021 00:47:49 -0800
Subject: perf evsel: Fix memory leaks relating to unit

unit may have a strdup pointer or be to a literal, consequently memory
assocciated with it isn't freed. Change it so the unit is always strdup
and so the memory can be safely freed.

Fix related issue in perf_event__process_event_update() for name and
own_cpus. Leaks were spotted by leak sanitizer.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20211118084749.2191447-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/event_update.c |  5 ++---
 tools/perf/util/evsel.c         | 18 +++++++++---------
 tools/perf/util/header.c        |  8 +++++---
 tools/perf/util/parse-events.c  |  9 ++++++---
 4 files changed, 22 insertions(+), 18 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/tests/event_update.c b/tools/perf/tests/event_update.c
index fbb68deba59f..d01532d40acb 100644
--- a/tools/perf/tests/event_update.c
+++ b/tools/perf/tests/event_update.c
@@ -88,7 +88,6 @@ static int test__event_update(struct test_suite *test __maybe_unused, int subtes
 	struct evsel *evsel;
 	struct event_name tmp;
 	struct evlist *evlist = evlist__new_default();
-	char *unit = strdup("KRAVA");
 
 	TEST_ASSERT_VAL("failed to get evlist", evlist);
 
@@ -99,7 +98,8 @@ static int test__event_update(struct test_suite *test __maybe_unused, int subtes
 
 	perf_evlist__id_add(&evlist->core, &evsel->core, 0, 0, 123);
 
-	evsel->unit = unit;
+	free((char *)evsel->unit);
+	evsel->unit = strdup("KRAVA");
 
 	TEST_ASSERT_VAL("failed to synthesize attr update unit",
 			!perf_event__synthesize_event_update_unit(NULL, evsel, process_event_unit));
@@ -119,7 +119,6 @@ static int test__event_update(struct test_suite *test __maybe_unused, int subtes
 	TEST_ASSERT_VAL("failed to synthesize attr update cpus",
 			!perf_event__synthesize_event_update_cpus(&tmp.tool, evsel, process_event_cpus));
 
-	free(unit);
 	evlist__delete(evlist);
 	return 0;
 }
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index a59fb2ecb84e..ac0127be0459 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -241,7 +241,7 @@ void evsel__init(struct evsel *evsel,
 {
 	perf_evsel__init(&evsel->core, attr, idx);
 	evsel->tracking	   = !idx;
-	evsel->unit	   = "";
+	evsel->unit	   = strdup("");
 	evsel->scale	   = 1.0;
 	evsel->max_events  = ULONG_MAX;
 	evsel->evlist	   = NULL;
@@ -276,13 +276,8 @@ struct evsel *evsel__new_idx(struct perf_event_attr *attr, int idx)
 	}
 
 	if (evsel__is_clock(evsel)) {
-		/*
-		 * The evsel->unit points to static alias->unit
-		 * so it's ok to use static string in here.
-		 */
-		static const char *unit = "msec";
-
-		evsel->unit = unit;
+		free((char *)evsel->unit);
+		evsel->unit = strdup("msec");
 		evsel->scale = 1e-6;
 	}
 
@@ -420,7 +415,11 @@ struct evsel *evsel__clone(struct evsel *orig)
 
 	evsel->max_events = orig->max_events;
 	evsel->tool_event = orig->tool_event;
-	evsel->unit = orig->unit;
+	free((char *)evsel->unit);
+	evsel->unit = strdup(orig->unit);
+	if (evsel->unit == NULL)
+		goto out_err;
+
 	evsel->scale = orig->scale;
 	evsel->snapshot = orig->snapshot;
 	evsel->per_pkg = orig->per_pkg;
@@ -1441,6 +1440,7 @@ void evsel__exit(struct evsel *evsel)
 	zfree(&evsel->group_name);
 	zfree(&evsel->name);
 	zfree(&evsel->pmu_name);
+	zfree(&evsel->unit);
 	zfree(&evsel->metric_id);
 	evsel__zero_per_pkg(evsel);
 	hashmap__free(evsel->per_pkg_mask);
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index fda8d14c891f..79cce216727e 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -4257,9 +4257,11 @@ int perf_event__process_event_update(struct perf_tool *tool __maybe_unused,
 
 	switch (ev->type) {
 	case PERF_EVENT_UPDATE__UNIT:
+		free((char *)evsel->unit);
 		evsel->unit = strdup(ev->data);
 		break;
 	case PERF_EVENT_UPDATE__NAME:
+		free(evsel->name);
 		evsel->name = strdup(ev->data);
 		break;
 	case PERF_EVENT_UPDATE__SCALE:
@@ -4268,11 +4270,11 @@ int perf_event__process_event_update(struct perf_tool *tool __maybe_unused,
 		break;
 	case PERF_EVENT_UPDATE__CPUS:
 		ev_cpus = (struct perf_record_event_update_cpus *)ev->data;
-
 		map = cpu_map__new_data(&ev_cpus->cpus);
-		if (map)
+		if (map) {
+			perf_cpu_map__put(evsel->core.own_cpus);
 			evsel->core.own_cpus = map;
-		else
+		} else
 			pr_err("failed to get event_update cpus\n");
 	default:
 		break;
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 5bfb6f892489..ba74fdf74af9 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -402,8 +402,10 @@ static int add_event_tool(struct list_head *list, int *idx,
 	if (!evsel)
 		return -ENOMEM;
 	evsel->tool_event = tool_event;
-	if (tool_event == PERF_TOOL_DURATION_TIME)
-		evsel->unit = "ns";
+	if (tool_event == PERF_TOOL_DURATION_TIME) {
+		free((char *)evsel->unit);
+		evsel->unit = strdup("ns");
+	}
 	return 0;
 }
 
@@ -1630,7 +1632,8 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 	if (parse_state->fake_pmu)
 		return 0;
 
-	evsel->unit = info.unit;
+	free((char *)evsel->unit);
+	evsel->unit = strdup(info.unit);
 	evsel->scale = info.scale;
 	evsel->per_pkg = info.per_pkg;
 	evsel->snapshot = info.snapshot;
-- 
cgit v1.2.3


From bdf1565fe03d29777d24e239163d0d53e4af9ce0 Mon Sep 17 00:00:00 2001
From: Li Zhijian <zhijianx.li@intel.com>
Date: Fri, 19 Nov 2021 14:24:56 +0800
Subject: selftests/tc-testing: match any qdisc type

We should not always presume all kernels use pfifo_fast as the default qdisc.

For example, a fq_codel qdisk could have below output:
qdisc fq_codel 0: parent 1:4 limit 10240p flows 1024 quantum 1514 target 5ms interval 100ms memory_limit 32Mb ecn drop_batch 64

Reported-by: kernel test robot <lkp@intel.com>
Suggested-by: Peilin Ye <peilin.ye@bytedance.com>
Signed-off-by: Li Zhijian <zhijianx.li@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json
index 88a20c781e49..c6046096d9db 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json
@@ -15,7 +15,7 @@
 	    "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: mq",
 	    "expExitCode": "0",
 	    "verifyCmd": "$TC qdisc show dev $ETH",
-	    "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-4] bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1",
+	    "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-4]",
 	    "matchCount": "4",
 	    "teardown": [
 		    "echo \"1\" > /sys/bus/netdevsim/del_device"
@@ -37,7 +37,7 @@
 	    "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: mq",
 	    "expExitCode": "0",
 	    "verifyCmd": "$TC qdisc show dev $ETH",
-	    "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-9,a-f][0-9,a-f]{0,2} bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1",
+	    "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-9,a-f][0-9,a-f]{0,2}",
 	    "matchCount": "256",
 	    "teardown": [
 		    "echo \"1\" > /sys/bus/netdevsim/del_device"
@@ -60,7 +60,7 @@
 	    "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: mq",
 	    "expExitCode": "2",
 	    "verifyCmd": "$TC qdisc show dev $ETH",
-	    "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-4] bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1",
+	    "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-4]",
 	    "matchCount": "4",
 	    "teardown": [
 		    "echo \"1\" > /sys/bus/netdevsim/del_device"
@@ -82,7 +82,7 @@
 	    "cmdUnderTest": "$TC qdisc del dev $ETH root handle 1: mq",
 	    "expExitCode": "2",
 	    "verifyCmd": "$TC qdisc show dev $ETH",
-	    "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-4] bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1",
+	    "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-4]",
 	    "matchCount": "0",
 	    "teardown": [
 		    "echo \"1\" > /sys/bus/netdevsim/del_device"
@@ -106,7 +106,7 @@
 	    "cmdUnderTest": "$TC qdisc del dev $ETH root handle 1: mq",
 	    "expExitCode": "2",
 	    "verifyCmd": "$TC qdisc show dev $ETH",
-	    "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-4] bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1",
+	    "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-4]",
 	    "matchCount": "0",
 	    "teardown": [
 		    "echo \"1\" > /sys/bus/netdevsim/del_device"
@@ -128,7 +128,7 @@
 	    "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: mq",
 	    "expExitCode": "2",
 	    "verifyCmd": "$TC qdisc show dev $ETH",
-	    "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-4] bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1",
+	    "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-4]",
 	    "matchCount": "0",
 	    "teardown": [
 		    "echo \"1\" > /sys/bus/netdevsim/del_device"
-- 
cgit v1.2.3


From ac2944abe4d7732f29a79f063c9cae7df2a3e3cc Mon Sep 17 00:00:00 2001
From: Li Zhijian <zhijianx.li@intel.com>
Date: Fri, 19 Nov 2021 14:24:57 +0800
Subject: selftests/tc-testings: Be compatible with newer tc output

old tc(iproute2-5.9.0) output:
 action order 1: bpf action.o:[action-ok] id 60 tag bcf7977d3b93787c jited default-action pipe
newer tc(iproute2-5.14.0) output:
 action order 1: bpf action.o:[action-ok] id 64 name tag bcf7977d3b93787c jited default-action pipe

It can fix below errors:
 # ok 260 f84a - Add cBPF action with invalid bytecode
 # not ok 261 e939 - Add eBPF action with valid object-file
 #       Could not match regex pattern. Verify command output:
 # total acts 0
 #
 #       action order 1: bpf action.o:[action-ok] id 42 name  tag bcf7977d3b93787c jited default-action pipe
 #        index 667 ref 1 bind 0

Signed-off-by: Li Zhijian <zhijianx.li@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
index 503982b8f295..91832400ddbd 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
@@ -68,7 +68,7 @@
         "cmdUnderTest": "$TC action add action bpf object-file $EBPFDIR/action.o section action-ok index 667",
         "expExitCode": "0",
         "verifyCmd": "$TC action get action bpf index 667",
-        "matchPattern": "action order [0-9]*: bpf action.o:\\[action-ok\\] id [0-9]* tag [0-9a-f]{16}( jited)? default-action pipe.*index 667 ref",
+        "matchPattern": "action order [0-9]*: bpf action.o:\\[action-ok\\] id [0-9].* tag [0-9a-f]{16}( jited)? default-action pipe.*index 667 ref",
         "matchCount": "1",
         "teardown": [
             "$TC action flush action bpf"
-- 
cgit v1.2.3


From 02ebe49ab06111a887202959e4d58a3cf252b5ee Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@nvidia.com>
Date: Mon, 22 Nov 2021 17:15:14 +0200
Subject: selftests: net: fib_nexthops: add test for group refcount imbalance
 bug

The new selftest runs a sequence which causes circular refcount
dependency between deleted objects which cannot be released and results
in a netdevice refcount imbalance.

Signed-off-by: Nikolay Aleksandrov <nikolay@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/fib_nexthops.sh | 63 +++++++++++++++++++++++++++++
 1 file changed, 63 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh
index b5a69ad191b0..d444ee6aa3cb 100755
--- a/tools/testing/selftests/net/fib_nexthops.sh
+++ b/tools/testing/selftests/net/fib_nexthops.sh
@@ -629,6 +629,66 @@ ipv6_fcnal()
 	log_test $? 0 "Nexthops removed on admin down"
 }
 
+ipv6_grp_refs()
+{
+	if [ ! -x "$(command -v mausezahn)" ]; then
+		echo "SKIP: Could not run test; need mausezahn tool"
+		return
+	fi
+
+	run_cmd "$IP link set dev veth1 up"
+	run_cmd "$IP link add veth1.10 link veth1 up type vlan id 10"
+	run_cmd "$IP link add veth1.20 link veth1 up type vlan id 20"
+	run_cmd "$IP -6 addr add 2001:db8:91::1/64 dev veth1.10"
+	run_cmd "$IP -6 addr add 2001:db8:92::1/64 dev veth1.20"
+	run_cmd "$IP -6 neigh add 2001:db8:91::2 lladdr 00:11:22:33:44:55 dev veth1.10"
+	run_cmd "$IP -6 neigh add 2001:db8:92::2 lladdr 00:11:22:33:44:55 dev veth1.20"
+	run_cmd "$IP nexthop add id 100 via 2001:db8:91::2 dev veth1.10"
+	run_cmd "$IP nexthop add id 101 via 2001:db8:92::2 dev veth1.20"
+	run_cmd "$IP nexthop add id 102 group 100"
+	run_cmd "$IP route add 2001:db8:101::1/128 nhid 102"
+
+	# create per-cpu dsts through nh 100
+	run_cmd "ip netns exec me mausezahn -6 veth1.10 -B 2001:db8:101::1 -A 2001:db8:91::1 -c 5 -t tcp "dp=1-1023, flags=syn" >/dev/null 2>&1"
+
+	# remove nh 100 from the group to delete the route potentially leaving
+	# a stale per-cpu dst which holds a reference to the nexthop's net
+	# device and to the IPv6 route
+	run_cmd "$IP nexthop replace id 102 group 101"
+	run_cmd "$IP route del 2001:db8:101::1/128"
+
+	# add both nexthops to the group so a reference is taken on them
+	run_cmd "$IP nexthop replace id 102 group 100/101"
+
+	# if the bug described in commit "net: nexthop: release IPv6 per-cpu
+	# dsts when replacing a nexthop group" exists at this point we have
+	# an unlinked IPv6 route (but not freed due to stale dst) with a
+	# reference over the group so we delete the group which will again
+	# only unlink it due to the route reference
+	run_cmd "$IP nexthop del id 102"
+
+	# delete the nexthop with stale dst, since we have an unlinked
+	# group with a ref to it and an unlinked IPv6 route with ref to the
+	# group, the nh will only be unlinked and not freed so the stale dst
+	# remains forever and we get a net device refcount imbalance
+	run_cmd "$IP nexthop del id 100"
+
+	# if a reference was lost this command will hang because the net device
+	# cannot be removed
+	timeout -s KILL 5 ip netns exec me ip link del veth1.10 >/dev/null 2>&1
+
+	# we can't cleanup if the command is hung trying to delete the netdev
+	if [ $? -eq 137 ]; then
+		return 1
+	fi
+
+	# cleanup
+	run_cmd "$IP link del veth1.20"
+	run_cmd "$IP nexthop flush"
+
+	return 0
+}
+
 ipv6_grp_fcnal()
 {
 	local rc
@@ -734,6 +794,9 @@ ipv6_grp_fcnal()
 
 	run_cmd "$IP nexthop add id 108 group 31/24"
 	log_test $? 2 "Nexthop group can not have a blackhole and another nexthop"
+
+	ipv6_grp_refs
+	log_test $? 0 "Nexthop group replace refcounts"
 }
 
 ipv6_res_grp_fcnal()
-- 
cgit v1.2.3


From 710d5835b7ae17c517f5aeaff853c300959c87ec Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 22 Nov 2021 10:48:10 -0800
Subject: tools: sync uapi/linux/if_link.h header

This file has not been updated for a while.

Sync it before BIG TCP patch series.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20211122184810.769159-1-eric.dumazet@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/include/uapi/linux/if_link.h | 293 ++++++++++++++++++++++++++++++++-----
 1 file changed, 259 insertions(+), 34 deletions(-)

(limited to 'tools')

diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index b3610fdd1fee..eebd3894fe89 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -7,24 +7,23 @@
 
 /* This struct should be in sync with struct rtnl_link_stats64 */
 struct rtnl_link_stats {
-	__u32	rx_packets;		/* total packets received	*/
-	__u32	tx_packets;		/* total packets transmitted	*/
-	__u32	rx_bytes;		/* total bytes received 	*/
-	__u32	tx_bytes;		/* total bytes transmitted	*/
-	__u32	rx_errors;		/* bad packets received		*/
-	__u32	tx_errors;		/* packet transmit problems	*/
-	__u32	rx_dropped;		/* no space in linux buffers	*/
-	__u32	tx_dropped;		/* no space available in linux	*/
-	__u32	multicast;		/* multicast packets received	*/
+	__u32	rx_packets;
+	__u32	tx_packets;
+	__u32	rx_bytes;
+	__u32	tx_bytes;
+	__u32	rx_errors;
+	__u32	tx_errors;
+	__u32	rx_dropped;
+	__u32	tx_dropped;
+	__u32	multicast;
 	__u32	collisions;
-
 	/* detailed rx_errors: */
 	__u32	rx_length_errors;
-	__u32	rx_over_errors;		/* receiver ring buff overflow	*/
-	__u32	rx_crc_errors;		/* recved pkt with crc error	*/
-	__u32	rx_frame_errors;	/* recv'd frame alignment error */
-	__u32	rx_fifo_errors;		/* recv'r fifo overrun		*/
-	__u32	rx_missed_errors;	/* receiver missed packet	*/
+	__u32	rx_over_errors;
+	__u32	rx_crc_errors;
+	__u32	rx_frame_errors;
+	__u32	rx_fifo_errors;
+	__u32	rx_missed_errors;
 
 	/* detailed tx_errors */
 	__u32	tx_aborted_errors;
@@ -37,29 +36,201 @@ struct rtnl_link_stats {
 	__u32	rx_compressed;
 	__u32	tx_compressed;
 
-	__u32	rx_nohandler;		/* dropped, no handler found	*/
+	__u32	rx_nohandler;
 };
 
-/* The main device statistics structure */
+/**
+ * struct rtnl_link_stats64 - The main device statistics structure.
+ *
+ * @rx_packets: Number of good packets received by the interface.
+ *   For hardware interfaces counts all good packets received from the device
+ *   by the host, including packets which host had to drop at various stages
+ *   of processing (even in the driver).
+ *
+ * @tx_packets: Number of packets successfully transmitted.
+ *   For hardware interfaces counts packets which host was able to successfully
+ *   hand over to the device, which does not necessarily mean that packets
+ *   had been successfully transmitted out of the device, only that device
+ *   acknowledged it copied them out of host memory.
+ *
+ * @rx_bytes: Number of good received bytes, corresponding to @rx_packets.
+ *
+ *   For IEEE 802.3 devices should count the length of Ethernet Frames
+ *   excluding the FCS.
+ *
+ * @tx_bytes: Number of good transmitted bytes, corresponding to @tx_packets.
+ *
+ *   For IEEE 802.3 devices should count the length of Ethernet Frames
+ *   excluding the FCS.
+ *
+ * @rx_errors: Total number of bad packets received on this network device.
+ *   This counter must include events counted by @rx_length_errors,
+ *   @rx_crc_errors, @rx_frame_errors and other errors not otherwise
+ *   counted.
+ *
+ * @tx_errors: Total number of transmit problems.
+ *   This counter must include events counter by @tx_aborted_errors,
+ *   @tx_carrier_errors, @tx_fifo_errors, @tx_heartbeat_errors,
+ *   @tx_window_errors and other errors not otherwise counted.
+ *
+ * @rx_dropped: Number of packets received but not processed,
+ *   e.g. due to lack of resources or unsupported protocol.
+ *   For hardware interfaces this counter may include packets discarded
+ *   due to L2 address filtering but should not include packets dropped
+ *   by the device due to buffer exhaustion which are counted separately in
+ *   @rx_missed_errors (since procfs folds those two counters together).
+ *
+ * @tx_dropped: Number of packets dropped on their way to transmission,
+ *   e.g. due to lack of resources.
+ *
+ * @multicast: Multicast packets received.
+ *   For hardware interfaces this statistic is commonly calculated
+ *   at the device level (unlike @rx_packets) and therefore may include
+ *   packets which did not reach the host.
+ *
+ *   For IEEE 802.3 devices this counter may be equivalent to:
+ *
+ *    - 30.3.1.1.21 aMulticastFramesReceivedOK
+ *
+ * @collisions: Number of collisions during packet transmissions.
+ *
+ * @rx_length_errors: Number of packets dropped due to invalid length.
+ *   Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter should be equivalent to a sum
+ *   of the following attributes:
+ *
+ *    - 30.3.1.1.23 aInRangeLengthErrors
+ *    - 30.3.1.1.24 aOutOfRangeLengthField
+ *    - 30.3.1.1.25 aFrameTooLongErrors
+ *
+ * @rx_over_errors: Receiver FIFO overflow event counter.
+ *
+ *   Historically the count of overflow events. Such events may be
+ *   reported in the receive descriptors or via interrupts, and may
+ *   not correspond one-to-one with dropped packets.
+ *
+ *   The recommended interpretation for high speed interfaces is -
+ *   number of packets dropped because they did not fit into buffers
+ *   provided by the host, e.g. packets larger than MTU or next buffer
+ *   in the ring was not available for a scatter transfer.
+ *
+ *   Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ *   This statistics was historically used interchangeably with
+ *   @rx_fifo_errors.
+ *
+ *   This statistic corresponds to hardware events and is not commonly used
+ *   on software devices.
+ *
+ * @rx_crc_errors: Number of packets received with a CRC error.
+ *   Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter must be equivalent to:
+ *
+ *    - 30.3.1.1.6 aFrameCheckSequenceErrors
+ *
+ * @rx_frame_errors: Receiver frame alignment errors.
+ *   Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter should be equivalent to:
+ *
+ *    - 30.3.1.1.7 aAlignmentErrors
+ *
+ * @rx_fifo_errors: Receiver FIFO error counter.
+ *
+ *   Historically the count of overflow events. Those events may be
+ *   reported in the receive descriptors or via interrupts, and may
+ *   not correspond one-to-one with dropped packets.
+ *
+ *   This statistics was used interchangeably with @rx_over_errors.
+ *   Not recommended for use in drivers for high speed interfaces.
+ *
+ *   This statistic is used on software devices, e.g. to count software
+ *   packet queue overflow (can) or sequencing errors (GRE).
+ *
+ * @rx_missed_errors: Count of packets missed by the host.
+ *   Folded into the "drop" counter in `/proc/net/dev`.
+ *
+ *   Counts number of packets dropped by the device due to lack
+ *   of buffer space. This usually indicates that the host interface
+ *   is slower than the network interface, or host is not keeping up
+ *   with the receive packet rate.
+ *
+ *   This statistic corresponds to hardware events and is not used
+ *   on software devices.
+ *
+ * @tx_aborted_errors:
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *   For IEEE 802.3 devices capable of half-duplex operation this counter
+ *   must be equivalent to:
+ *
+ *    - 30.3.1.1.11 aFramesAbortedDueToXSColls
+ *
+ *   High speed interfaces may use this counter as a general device
+ *   discard counter.
+ *
+ * @tx_carrier_errors: Number of frame transmission errors due to loss
+ *   of carrier during transmission.
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter must be equivalent to:
+ *
+ *    - 30.3.1.1.13 aCarrierSenseErrors
+ *
+ * @tx_fifo_errors: Number of frame transmission errors due to device
+ *   FIFO underrun / underflow. This condition occurs when the device
+ *   begins transmission of a frame but is unable to deliver the
+ *   entire frame to the transmitter in time for transmission.
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ * @tx_heartbeat_errors: Number of Heartbeat / SQE Test errors for
+ *   old half-duplex Ethernet.
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices possibly equivalent to:
+ *
+ *    - 30.3.2.1.4 aSQETestErrors
+ *
+ * @tx_window_errors: Number of frame transmission errors due
+ *   to late collisions (for Ethernet - after the first 64B of transmission).
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter must be equivalent to:
+ *
+ *    - 30.3.1.1.10 aLateCollisions
+ *
+ * @rx_compressed: Number of correctly received compressed packets.
+ *   This counters is only meaningful for interfaces which support
+ *   packet compression (e.g. CSLIP, PPP).
+ *
+ * @tx_compressed: Number of transmitted compressed packets.
+ *   This counters is only meaningful for interfaces which support
+ *   packet compression (e.g. CSLIP, PPP).
+ *
+ * @rx_nohandler: Number of packets received on the interface
+ *   but dropped by the networking stack because the device is
+ *   not designated to receive packets (e.g. backup link in a bond).
+ */
 struct rtnl_link_stats64 {
-	__u64	rx_packets;		/* total packets received	*/
-	__u64	tx_packets;		/* total packets transmitted	*/
-	__u64	rx_bytes;		/* total bytes received 	*/
-	__u64	tx_bytes;		/* total bytes transmitted	*/
-	__u64	rx_errors;		/* bad packets received		*/
-	__u64	tx_errors;		/* packet transmit problems	*/
-	__u64	rx_dropped;		/* no space in linux buffers	*/
-	__u64	tx_dropped;		/* no space available in linux	*/
-	__u64	multicast;		/* multicast packets received	*/
+	__u64	rx_packets;
+	__u64	tx_packets;
+	__u64	rx_bytes;
+	__u64	tx_bytes;
+	__u64	rx_errors;
+	__u64	tx_errors;
+	__u64	rx_dropped;
+	__u64	tx_dropped;
+	__u64	multicast;
 	__u64	collisions;
 
 	/* detailed rx_errors: */
 	__u64	rx_length_errors;
-	__u64	rx_over_errors;		/* receiver ring buff overflow	*/
-	__u64	rx_crc_errors;		/* recved pkt with crc error	*/
-	__u64	rx_frame_errors;	/* recv'd frame alignment error */
-	__u64	rx_fifo_errors;		/* recv'r fifo overrun		*/
-	__u64	rx_missed_errors;	/* receiver missed packet	*/
+	__u64	rx_over_errors;
+	__u64	rx_crc_errors;
+	__u64	rx_frame_errors;
+	__u64	rx_fifo_errors;
+	__u64	rx_missed_errors;
 
 	/* detailed tx_errors */
 	__u64	tx_aborted_errors;
@@ -71,8 +242,7 @@ struct rtnl_link_stats64 {
 	/* for cslip etc */
 	__u64	rx_compressed;
 	__u64	tx_compressed;
-
-	__u64	rx_nohandler;		/* dropped, no handler found	*/
+	__u64	rx_nohandler;
 };
 
 /* The struct should be in sync with struct ifmap */
@@ -170,12 +340,29 @@ enum {
 	IFLA_PROP_LIST,
 	IFLA_ALT_IFNAME, /* Alternative ifname */
 	IFLA_PERM_ADDRESS,
+	IFLA_PROTO_DOWN_REASON,
+
+	/* device (sysfs) name as parent, used instead
+	 * of IFLA_LINK where there's no parent netdev
+	 */
+	IFLA_PARENT_DEV_NAME,
+	IFLA_PARENT_DEV_BUS_NAME,
+
 	__IFLA_MAX
 };
 
 
 #define IFLA_MAX (__IFLA_MAX - 1)
 
+enum {
+	IFLA_PROTO_DOWN_REASON_UNSPEC,
+	IFLA_PROTO_DOWN_REASON_MASK,	/* u32, mask for reason bits */
+	IFLA_PROTO_DOWN_REASON_VALUE,   /* u32, reason bit value */
+
+	__IFLA_PROTO_DOWN_REASON_CNT,
+	IFLA_PROTO_DOWN_REASON_MAX = __IFLA_PROTO_DOWN_REASON_CNT - 1
+};
+
 /* backwards compatibility for userspace */
 #ifndef __KERNEL__
 #define IFLA_RTA(r)  ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifinfomsg))))
@@ -293,6 +480,7 @@ enum {
 	IFLA_BR_MCAST_MLD_VERSION,
 	IFLA_BR_VLAN_STATS_PER_PORT,
 	IFLA_BR_MULTI_BOOLOPT,
+	IFLA_BR_MCAST_QUERIER_STATE,
 	__IFLA_BR_MAX,
 };
 
@@ -346,6 +534,8 @@ enum {
 	IFLA_BRPORT_BACKUP_PORT,
 	IFLA_BRPORT_MRP_RING_OPEN,
 	IFLA_BRPORT_MRP_IN_OPEN,
+	IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT,
+	IFLA_BRPORT_MCAST_EHT_HOSTS_CNT,
 	__IFLA_BRPORT_MAX
 };
 #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
@@ -433,6 +623,7 @@ enum macvlan_macaddr_mode {
 };
 
 #define MACVLAN_FLAG_NOPROMISC	1
+#define MACVLAN_FLAG_NODST	2 /* skip dst macvlan if matching src macvlan */
 
 /* VRF section */
 enum {
@@ -597,6 +788,18 @@ enum ifla_geneve_df {
 	GENEVE_DF_MAX = __GENEVE_DF_END - 1,
 };
 
+/* Bareudp section  */
+enum {
+	IFLA_BAREUDP_UNSPEC,
+	IFLA_BAREUDP_PORT,
+	IFLA_BAREUDP_ETHERTYPE,
+	IFLA_BAREUDP_SRCPORT_MIN,
+	IFLA_BAREUDP_MULTIPROTO_MODE,
+	__IFLA_BAREUDP_MAX
+};
+
+#define IFLA_BAREUDP_MAX (__IFLA_BAREUDP_MAX - 1)
+
 /* PPP section */
 enum {
 	IFLA_PPP_UNSPEC,
@@ -899,7 +1102,14 @@ enum {
 #define IFLA_IPOIB_MAX (__IFLA_IPOIB_MAX - 1)
 
 
-/* HSR section */
+/* HSR/PRP section, both uses same interface */
+
+/* Different redundancy protocols for hsr device */
+enum {
+	HSR_PROTOCOL_HSR,
+	HSR_PROTOCOL_PRP,
+	HSR_PROTOCOL_MAX,
+};
 
 enum {
 	IFLA_HSR_UNSPEC,
@@ -909,6 +1119,9 @@ enum {
 	IFLA_HSR_SUPERVISION_ADDR,	/* Supervision frame multicast addr */
 	IFLA_HSR_SEQ_NR,
 	IFLA_HSR_VERSION,		/* HSR version */
+	IFLA_HSR_PROTOCOL,		/* Indicate different protocol than
+					 * HSR. For example PRP.
+					 */
 	__IFLA_HSR_MAX,
 };
 
@@ -1033,6 +1246,8 @@ enum {
 #define RMNET_FLAGS_INGRESS_MAP_COMMANDS          (1U << 1)
 #define RMNET_FLAGS_INGRESS_MAP_CKSUMV4           (1U << 2)
 #define RMNET_FLAGS_EGRESS_MAP_CKSUMV4            (1U << 3)
+#define RMNET_FLAGS_INGRESS_MAP_CKSUMV5           (1U << 4)
+#define RMNET_FLAGS_EGRESS_MAP_CKSUMV5            (1U << 5)
 
 enum {
 	IFLA_RMNET_UNSPEC,
@@ -1048,4 +1263,14 @@ struct ifla_rmnet_flags {
 	__u32	mask;
 };
 
+/* MCTP section */
+
+enum {
+	IFLA_MCTP_UNSPEC,
+	IFLA_MCTP_NET,
+	__IFLA_MCTP_MAX,
+};
+
+#define IFLA_MCTP_MAX (__IFLA_MCTP_MAX - 1)
+
 #endif /* _UAPI_LINUX_IF_LINK_H */
-- 
cgit v1.2.3


From 619ca0d0108a5866cca7793bd7e19c5d7a30e750 Mon Sep 17 00:00:00 2001
From: James Prestwood <prestwoj@gmail.com>
Date: Mon, 22 Nov 2021 09:18:06 -0800
Subject: selftests: add arp_ndisc_evict_nocarrier to Makefile

This was previously added in selftests but never added
to the Makefile

Signed-off-by: James Prestwood <prestwoj@gmail.com>
Link: https://lore.kernel.org/r/20211122171806.3529401-1-prestwoj@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/Makefile | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 7615f29831eb..9897fa9ab953 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -34,6 +34,7 @@ TEST_PROGS += srv6_end_dt46_l3vpn_test.sh
 TEST_PROGS += srv6_end_dt4_l3vpn_test.sh
 TEST_PROGS += srv6_end_dt6_l3vpn_test.sh
 TEST_PROGS += vrf_strict_mode_test.sh
+TEST_PROGS += arp_ndisc_evict_nocarrier.sh
 TEST_PROGS_EXTENDED := in_netns.sh setup_loopback.sh setup_veth.sh
 TEST_PROGS_EXTENDED += toeplitz_client.sh toeplitz.sh
 TEST_GEN_FILES =  socket nettest
-- 
cgit v1.2.3


From a125f91fe783a79c9d990fe6e28a3da8d9a0857f Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 24 Nov 2021 15:25:49 -0800
Subject: selftests: tls: add helper for creating sock pairs

We have the same code 3 times, about to add a fourth copy.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/tls.c | 128 +++++++++-----------------------------
 1 file changed, 29 insertions(+), 99 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index e61fc4c32ba2..8fb7cf8c4bfb 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -78,26 +78,21 @@ static void memrnd(void *s, size_t n)
 		*byte++ = rand();
 }
 
-FIXTURE(tls_basic)
-{
-	int fd, cfd;
-	bool notls;
-};
-
-FIXTURE_SETUP(tls_basic)
+static void ulp_sock_pair(struct __test_metadata *_metadata,
+			  int *fd, int *cfd, bool *notls)
 {
 	struct sockaddr_in addr;
 	socklen_t len;
 	int sfd, ret;
 
-	self->notls = false;
+	*notls = false;
 	len = sizeof(addr);
 
 	addr.sin_family = AF_INET;
 	addr.sin_addr.s_addr = htonl(INADDR_ANY);
 	addr.sin_port = 0;
 
-	self->fd = socket(AF_INET, SOCK_STREAM, 0);
+	*fd = socket(AF_INET, SOCK_STREAM, 0);
 	sfd = socket(AF_INET, SOCK_STREAM, 0);
 
 	ret = bind(sfd, &addr, sizeof(addr));
@@ -108,26 +103,37 @@ FIXTURE_SETUP(tls_basic)
 	ret = getsockname(sfd, &addr, &len);
 	ASSERT_EQ(ret, 0);
 
-	ret = connect(self->fd, &addr, sizeof(addr));
+	ret = connect(*fd, &addr, sizeof(addr));
 	ASSERT_EQ(ret, 0);
 
-	self->cfd = accept(sfd, &addr, &len);
-	ASSERT_GE(self->cfd, 0);
+	*cfd = accept(sfd, &addr, &len);
+	ASSERT_GE(*cfd, 0);
 
 	close(sfd);
 
-	ret = setsockopt(self->fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
+	ret = setsockopt(*fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
 	if (ret != 0) {
 		ASSERT_EQ(errno, ENOENT);
-		self->notls = true;
+		*notls = true;
 		printf("Failure setting TCP_ULP, testing without tls\n");
 		return;
 	}
 
-	ret = setsockopt(self->cfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
+	ret = setsockopt(*cfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
 	ASSERT_EQ(ret, 0);
 }
 
+FIXTURE(tls_basic)
+{
+	int fd, cfd;
+	bool notls;
+};
+
+FIXTURE_SETUP(tls_basic)
+{
+	ulp_sock_pair(_metadata, &self->fd, &self->cfd, &self->notls);
+}
+
 FIXTURE_TEARDOWN(tls_basic)
 {
 	close(self->fd);
@@ -199,60 +205,21 @@ FIXTURE_VARIANT_ADD(tls, 13_sm4_ccm)
 FIXTURE_SETUP(tls)
 {
 	struct tls_crypto_info_keys tls12;
-	struct sockaddr_in addr;
-	socklen_t len;
-	int sfd, ret;
-
-	self->notls = false;
-	len = sizeof(addr);
+	int ret;
 
 	tls_crypto_info_init(variant->tls_version, variant->cipher_type,
 			     &tls12);
 
-	addr.sin_family = AF_INET;
-	addr.sin_addr.s_addr = htonl(INADDR_ANY);
-	addr.sin_port = 0;
+	ulp_sock_pair(_metadata, &self->fd, &self->cfd, &self->notls);
 
-	self->fd = socket(AF_INET, SOCK_STREAM, 0);
-	sfd = socket(AF_INET, SOCK_STREAM, 0);
-
-	ret = bind(sfd, &addr, sizeof(addr));
-	ASSERT_EQ(ret, 0);
-	ret = listen(sfd, 10);
-	ASSERT_EQ(ret, 0);
+	if (self->notls)
+		return;
 
-	ret = getsockname(sfd, &addr, &len);
+	ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len);
 	ASSERT_EQ(ret, 0);
 
-	ret = connect(self->fd, &addr, sizeof(addr));
+	ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len);
 	ASSERT_EQ(ret, 0);
-
-	ret = setsockopt(self->fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
-	if (ret != 0) {
-		self->notls = true;
-		printf("Failure setting TCP_ULP, testing without tls\n");
-	}
-
-	if (!self->notls) {
-		ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12,
-				 tls12.len);
-		ASSERT_EQ(ret, 0);
-	}
-
-	self->cfd = accept(sfd, &addr, &len);
-	ASSERT_GE(self->cfd, 0);
-
-	if (!self->notls) {
-		ret = setsockopt(self->cfd, IPPROTO_TCP, TCP_ULP, "tls",
-				 sizeof("tls"));
-		ASSERT_EQ(ret, 0);
-
-		ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12,
-				 tls12.len);
-		ASSERT_EQ(ret, 0);
-	}
-
-	close(sfd);
 }
 
 FIXTURE_TEARDOWN(tls)
@@ -1355,62 +1322,25 @@ TEST(non_established) {
 
 TEST(keysizes) {
 	struct tls12_crypto_info_aes_gcm_256 tls12;
-	struct sockaddr_in addr;
-	int sfd, ret, fd, cfd;
-	socklen_t len;
+	int ret, fd, cfd;
 	bool notls;
 
-	notls = false;
-	len = sizeof(addr);
-
 	memset(&tls12, 0, sizeof(tls12));
 	tls12.info.version = TLS_1_2_VERSION;
 	tls12.info.cipher_type = TLS_CIPHER_AES_GCM_256;
 
-	addr.sin_family = AF_INET;
-	addr.sin_addr.s_addr = htonl(INADDR_ANY);
-	addr.sin_port = 0;
-
-	fd = socket(AF_INET, SOCK_STREAM, 0);
-	sfd = socket(AF_INET, SOCK_STREAM, 0);
-
-	ret = bind(sfd, &addr, sizeof(addr));
-	ASSERT_EQ(ret, 0);
-	ret = listen(sfd, 10);
-	ASSERT_EQ(ret, 0);
-
-	ret = getsockname(sfd, &addr, &len);
-	ASSERT_EQ(ret, 0);
-
-	ret = connect(fd, &addr, sizeof(addr));
-	ASSERT_EQ(ret, 0);
-
-	ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
-	if (ret != 0) {
-		notls = true;
-		printf("Failure setting TCP_ULP, testing without tls\n");
-	}
+	ulp_sock_pair(_metadata, &fd, &cfd, &notls);
 
 	if (!notls) {
 		ret = setsockopt(fd, SOL_TLS, TLS_TX, &tls12,
 				 sizeof(tls12));
 		EXPECT_EQ(ret, 0);
-	}
-
-	cfd = accept(sfd, &addr, &len);
-	ASSERT_GE(cfd, 0);
-
-	if (!notls) {
-		ret = setsockopt(cfd, IPPROTO_TCP, TCP_ULP, "tls",
-				 sizeof("tls"));
-		EXPECT_EQ(ret, 0);
 
 		ret = setsockopt(cfd, SOL_TLS, TLS_RX, &tls12,
 				 sizeof(tls12));
 		EXPECT_EQ(ret, 0);
 	}
 
-	close(sfd);
 	close(fd);
 	close(cfd);
 }
-- 
cgit v1.2.3


From 31180adb0bed7d3e67ae97121dc83f320bbd45be Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 24 Nov 2021 15:25:50 -0800
Subject: selftests: tls: factor out cmsg send/receive

Add helpers for sending and receiving special record types.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/tls.c | 111 ++++++++++++++++++++++++--------------
 1 file changed, 70 insertions(+), 41 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 8fb7cf8c4bfb..642d1d629b28 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -123,6 +123,65 @@ static void ulp_sock_pair(struct __test_metadata *_metadata,
 	ASSERT_EQ(ret, 0);
 }
 
+/* Produce a basic cmsg */
+static int tls_send_cmsg(int fd, unsigned char record_type,
+			 void *data, size_t len, int flags)
+{
+	char cbuf[CMSG_SPACE(sizeof(char))];
+	int cmsg_len = sizeof(char);
+	struct cmsghdr *cmsg;
+	struct msghdr msg;
+	struct iovec vec;
+
+	vec.iov_base = data;
+	vec.iov_len = len;
+	memset(&msg, 0, sizeof(struct msghdr));
+	msg.msg_iov = &vec;
+	msg.msg_iovlen = 1;
+	msg.msg_control = cbuf;
+	msg.msg_controllen = sizeof(cbuf);
+	cmsg = CMSG_FIRSTHDR(&msg);
+	cmsg->cmsg_level = SOL_TLS;
+	/* test sending non-record types. */
+	cmsg->cmsg_type = TLS_SET_RECORD_TYPE;
+	cmsg->cmsg_len = CMSG_LEN(cmsg_len);
+	*CMSG_DATA(cmsg) = record_type;
+	msg.msg_controllen = cmsg->cmsg_len;
+
+	return sendmsg(fd, &msg, flags);
+}
+
+static int tls_recv_cmsg(struct __test_metadata *_metadata,
+			 int fd, unsigned char record_type,
+			 void *data, size_t len, int flags)
+{
+	char cbuf[CMSG_SPACE(sizeof(char))];
+	struct cmsghdr *cmsg;
+	unsigned char ctype;
+	struct msghdr msg;
+	struct iovec vec;
+	int n;
+
+	vec.iov_base = data;
+	vec.iov_len = len;
+	memset(&msg, 0, sizeof(struct msghdr));
+	msg.msg_iov = &vec;
+	msg.msg_iovlen = 1;
+	msg.msg_control = cbuf;
+	msg.msg_controllen = sizeof(cbuf);
+
+	n = recvmsg(fd, &msg, flags);
+
+	cmsg = CMSG_FIRSTHDR(&msg);
+	EXPECT_NE(cmsg, NULL);
+	EXPECT_EQ(cmsg->cmsg_level, SOL_TLS);
+	EXPECT_EQ(cmsg->cmsg_type, TLS_GET_RECORD_TYPE);
+	ctype = *((unsigned char *)CMSG_DATA(cmsg));
+	EXPECT_EQ(ctype, record_type);
+
+	return n;
+}
+
 FIXTURE(tls_basic)
 {
 	int fd, cfd;
@@ -1160,60 +1219,30 @@ TEST_F(tls, mutliproc_sendpage_writers)
 
 TEST_F(tls, control_msg)
 {
-	if (self->notls)
-		return;
-
-	char cbuf[CMSG_SPACE(sizeof(char))];
-	char const *test_str = "test_read";
-	int cmsg_len = sizeof(char);
+	char *test_str = "test_read";
 	char record_type = 100;
-	struct cmsghdr *cmsg;
-	struct msghdr msg;
 	int send_len = 10;
-	struct iovec vec;
 	char buf[10];
 
-	vec.iov_base = (char *)test_str;
-	vec.iov_len = 10;
-	memset(&msg, 0, sizeof(struct msghdr));
-	msg.msg_iov = &vec;
-	msg.msg_iovlen = 1;
-	msg.msg_control = cbuf;
-	msg.msg_controllen = sizeof(cbuf);
-	cmsg = CMSG_FIRSTHDR(&msg);
-	cmsg->cmsg_level = SOL_TLS;
-	/* test sending non-record types. */
-	cmsg->cmsg_type = TLS_SET_RECORD_TYPE;
-	cmsg->cmsg_len = CMSG_LEN(cmsg_len);
-	*CMSG_DATA(cmsg) = record_type;
-	msg.msg_controllen = cmsg->cmsg_len;
+	if (self->notls)
+		SKIP(return, "no TLS support");
 
-	EXPECT_EQ(sendmsg(self->fd, &msg, 0), send_len);
+	EXPECT_EQ(tls_send_cmsg(self->fd, record_type, test_str, send_len, 0),
+		  send_len);
 	/* Should fail because we didn't provide a control message */
 	EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1);
 
-	vec.iov_base = buf;
-	EXPECT_EQ(recvmsg(self->cfd, &msg, MSG_WAITALL | MSG_PEEK), send_len);
-
-	cmsg = CMSG_FIRSTHDR(&msg);
-	EXPECT_NE(cmsg, NULL);
-	EXPECT_EQ(cmsg->cmsg_level, SOL_TLS);
-	EXPECT_EQ(cmsg->cmsg_type, TLS_GET_RECORD_TYPE);
-	record_type = *((unsigned char *)CMSG_DATA(cmsg));
-	EXPECT_EQ(record_type, 100);
+	EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, record_type,
+				buf, sizeof(buf), MSG_WAITALL | MSG_PEEK),
+		  send_len);
 	EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
 
 	/* Recv the message again without MSG_PEEK */
-	record_type = 0;
 	memset(buf, 0, sizeof(buf));
 
-	EXPECT_EQ(recvmsg(self->cfd, &msg, MSG_WAITALL), send_len);
-	cmsg = CMSG_FIRSTHDR(&msg);
-	EXPECT_NE(cmsg, NULL);
-	EXPECT_EQ(cmsg->cmsg_level, SOL_TLS);
-	EXPECT_EQ(cmsg->cmsg_type, TLS_GET_RECORD_TYPE);
-	record_type = *((unsigned char *)CMSG_DATA(cmsg));
-	EXPECT_EQ(record_type, 100);
+	EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, record_type,
+				buf, sizeof(buf), MSG_WAITALL),
+		  send_len);
 	EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
 }
 
-- 
cgit v1.2.3


From ef0fc0b3cc2b8df7f29656a190a13ceb644b0c00 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 24 Nov 2021 15:25:51 -0800
Subject: selftests: tls: add tests for handling of bad records

Test broken records.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/tls.c | 154 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 154 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 642d1d629b28..2108b197d3f6 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -1297,6 +1297,160 @@ TEST_F(tls, shutdown_reuse)
 	EXPECT_EQ(errno, EISCONN);
 }
 
+FIXTURE(tls_err)
+{
+	int fd, cfd;
+	int fd2, cfd2;
+	bool notls;
+};
+
+FIXTURE_VARIANT(tls_err)
+{
+	uint16_t tls_version;
+};
+
+FIXTURE_VARIANT_ADD(tls_err, 12_aes_gcm)
+{
+	.tls_version = TLS_1_2_VERSION,
+};
+
+FIXTURE_VARIANT_ADD(tls_err, 13_aes_gcm)
+{
+	.tls_version = TLS_1_3_VERSION,
+};
+
+FIXTURE_SETUP(tls_err)
+{
+	struct tls_crypto_info_keys tls12;
+	int ret;
+
+	tls_crypto_info_init(variant->tls_version, TLS_CIPHER_AES_GCM_128,
+			     &tls12);
+
+	ulp_sock_pair(_metadata, &self->fd, &self->cfd, &self->notls);
+	ulp_sock_pair(_metadata, &self->fd2, &self->cfd2, &self->notls);
+	if (self->notls)
+		return;
+
+	ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len);
+	ASSERT_EQ(ret, 0);
+
+	ret = setsockopt(self->cfd2, SOL_TLS, TLS_RX, &tls12, tls12.len);
+	ASSERT_EQ(ret, 0);
+}
+
+FIXTURE_TEARDOWN(tls_err)
+{
+	close(self->fd);
+	close(self->cfd);
+	close(self->fd2);
+	close(self->cfd2);
+}
+
+TEST_F(tls_err, bad_rec)
+{
+	char buf[64];
+
+	if (self->notls)
+		SKIP(return, "no TLS support");
+
+	memset(buf, 0x55, sizeof(buf));
+	EXPECT_EQ(send(self->fd2, buf, sizeof(buf), 0), sizeof(buf));
+	EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1);
+	EXPECT_EQ(errno, EMSGSIZE);
+	EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), MSG_DONTWAIT), -1);
+	EXPECT_EQ(errno, EAGAIN);
+}
+
+TEST_F(tls_err, bad_auth)
+{
+	char buf[128];
+	int n;
+
+	if (self->notls)
+		SKIP(return, "no TLS support");
+
+	memrnd(buf, sizeof(buf) / 2);
+	EXPECT_EQ(send(self->fd, buf, sizeof(buf) / 2, 0), sizeof(buf) / 2);
+	n = recv(self->cfd, buf, sizeof(buf), 0);
+	EXPECT_GT(n, sizeof(buf) / 2);
+
+	buf[n - 1]++;
+
+	EXPECT_EQ(send(self->fd2, buf, n, 0), n);
+	EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1);
+	EXPECT_EQ(errno, EBADMSG);
+	EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1);
+	EXPECT_EQ(errno, EBADMSG);
+}
+
+TEST_F(tls_err, bad_in_large_read)
+{
+	char txt[3][64];
+	char cip[3][128];
+	char buf[3 * 128];
+	int i, n;
+
+	if (self->notls)
+		SKIP(return, "no TLS support");
+
+	/* Put 3 records in the sockets */
+	for (i = 0; i < 3; i++) {
+		memrnd(txt[i], sizeof(txt[i]));
+		EXPECT_EQ(send(self->fd, txt[i], sizeof(txt[i]), 0),
+			  sizeof(txt[i]));
+		n = recv(self->cfd, cip[i], sizeof(cip[i]), 0);
+		EXPECT_GT(n, sizeof(txt[i]));
+		/* Break the third message */
+		if (i == 2)
+			cip[2][n - 1]++;
+		EXPECT_EQ(send(self->fd2, cip[i], n, 0), n);
+	}
+
+	/* We should be able to receive the first two messages */
+	EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), sizeof(txt[0]) * 2);
+	EXPECT_EQ(memcmp(buf, txt[0], sizeof(txt[0])), 0);
+	EXPECT_EQ(memcmp(buf + sizeof(txt[0]), txt[1], sizeof(txt[1])), 0);
+	/* Third mesasge is bad */
+	EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1);
+	EXPECT_EQ(errno, EBADMSG);
+	EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1);
+	EXPECT_EQ(errno, EBADMSG);
+}
+
+TEST_F(tls_err, bad_cmsg)
+{
+	char *test_str = "test_read";
+	int send_len = 10;
+	char cip[128];
+	char buf[128];
+	char txt[64];
+	int n;
+
+	if (self->notls)
+		SKIP(return, "no TLS support");
+
+	/* Queue up one data record */
+	memrnd(txt, sizeof(txt));
+	EXPECT_EQ(send(self->fd, txt, sizeof(txt), 0), sizeof(txt));
+	n = recv(self->cfd, cip, sizeof(cip), 0);
+	EXPECT_GT(n, sizeof(txt));
+	EXPECT_EQ(send(self->fd2, cip, n, 0), n);
+
+	EXPECT_EQ(tls_send_cmsg(self->fd, 100, test_str, send_len, 0), 10);
+	n = recv(self->cfd, cip, sizeof(cip), 0);
+	cip[n - 1]++; /* Break it */
+	EXPECT_GT(n, send_len);
+	EXPECT_EQ(send(self->fd2, cip, n, 0), n);
+
+	EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), sizeof(txt));
+	EXPECT_EQ(memcmp(buf, txt, sizeof(txt)), 0);
+	EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1);
+	EXPECT_EQ(errno, EBADMSG);
+	EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1);
+	EXPECT_EQ(errno, EBADMSG);
+}
+
 TEST(non_established) {
 	struct tls12_crypto_info_aes_gcm_256 tls12;
 	struct sockaddr_in addr;
-- 
cgit v1.2.3


From d87d67fd61ef4e7619eb24ab20cba3250a6444e8 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 24 Nov 2021 15:25:53 -0800
Subject: selftests: tls: test splicing cmsgs

Make sure we correctly reject splicing non-data records.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/tls.c | 40 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 40 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 2108b197d3f6..3dfa9d7dd4cc 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -639,6 +639,46 @@ TEST_F(tls, splice_to_pipe)
 	EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
 }
 
+TEST_F(tls, splice_cmsg_to_pipe)
+{
+	char *test_str = "test_read";
+	char record_type = 100;
+	int send_len = 10;
+	char buf[10];
+	int p[2];
+
+	ASSERT_GE(pipe(p), 0);
+	EXPECT_EQ(tls_send_cmsg(self->fd, 100, test_str, send_len, 0), 10);
+	EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, send_len, 0), -1);
+	EXPECT_EQ(errno, EINVAL);
+	EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1);
+	EXPECT_EQ(errno, EIO);
+	EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, record_type,
+				buf, sizeof(buf), MSG_WAITALL),
+		  send_len);
+	EXPECT_EQ(memcmp(test_str, buf, send_len), 0);
+}
+
+TEST_F(tls, splice_dec_cmsg_to_pipe)
+{
+	char *test_str = "test_read";
+	char record_type = 100;
+	int send_len = 10;
+	char buf[10];
+	int p[2];
+
+	ASSERT_GE(pipe(p), 0);
+	EXPECT_EQ(tls_send_cmsg(self->fd, 100, test_str, send_len, 0), 10);
+	EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1);
+	EXPECT_EQ(errno, EIO);
+	EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, send_len, 0), -1);
+	EXPECT_EQ(errno, EINVAL);
+	EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, record_type,
+				buf, sizeof(buf), MSG_WAITALL),
+		  send_len);
+	EXPECT_EQ(memcmp(test_str, buf, send_len), 0);
+}
+
 TEST_F(tls, recvmsg_single)
 {
 	char const *test_str = "test_recvmsg_single";
-- 
cgit v1.2.3


From 274af0f9e2799da22a866139d9bd203cc0baacff Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 24 Nov 2021 15:25:55 -0800
Subject: selftests: tls: test splicing decrypted records

Add tests for half-received and peeked records.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/tls.c | 49 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 49 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 3dfa9d7dd4cc..6e78d7207cc1 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -679,6 +679,55 @@ TEST_F(tls, splice_dec_cmsg_to_pipe)
 	EXPECT_EQ(memcmp(test_str, buf, send_len), 0);
 }
 
+TEST_F(tls, recv_and_splice)
+{
+	int send_len = TLS_PAYLOAD_MAX_LEN;
+	char mem_send[TLS_PAYLOAD_MAX_LEN];
+	char mem_recv[TLS_PAYLOAD_MAX_LEN];
+	int half = send_len / 2;
+	int p[2];
+
+	ASSERT_GE(pipe(p), 0);
+	EXPECT_EQ(send(self->fd, mem_send, send_len, 0), send_len);
+	/* Recv hald of the record, splice the other half */
+	EXPECT_EQ(recv(self->cfd, mem_recv, half, MSG_WAITALL), half);
+	EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, half, SPLICE_F_NONBLOCK),
+		  half);
+	EXPECT_EQ(read(p[0], &mem_recv[half], half), half);
+	EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
+}
+
+TEST_F(tls, peek_and_splice)
+{
+	int send_len = TLS_PAYLOAD_MAX_LEN;
+	char mem_send[TLS_PAYLOAD_MAX_LEN];
+	char mem_recv[TLS_PAYLOAD_MAX_LEN];
+	int chunk = TLS_PAYLOAD_MAX_LEN / 4;
+	int n, i, p[2];
+
+	memrnd(mem_send, sizeof(mem_send));
+
+	ASSERT_GE(pipe(p), 0);
+	for (i = 0; i < 4; i++)
+		EXPECT_EQ(send(self->fd, &mem_send[chunk * i], chunk, 0),
+			  chunk);
+
+	EXPECT_EQ(recv(self->cfd, mem_recv, chunk * 5 / 2,
+		       MSG_WAITALL | MSG_PEEK),
+		  chunk * 5 / 2);
+	EXPECT_EQ(memcmp(mem_send, mem_recv, chunk * 5 / 2), 0);
+
+	n = 0;
+	while (n < send_len) {
+		i = splice(self->cfd, NULL, p[1], NULL, send_len - n, 0);
+		EXPECT_GT(i, 0);
+		n += i;
+	}
+	EXPECT_EQ(n, send_len);
+	EXPECT_EQ(read(p[0], mem_recv, send_len), send_len);
+	EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
+}
+
 TEST_F(tls, recvmsg_single)
 {
 	char const *test_str = "test_recvmsg_single";
-- 
cgit v1.2.3


From f884a3426291b3f368231c0ac0e50a6a061f6aca Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 24 Nov 2021 15:25:57 -0800
Subject: selftests: tls: test for correct proto_ops

Previous patch fixes overriding callbacks incorrectly. Triggering
the crash in sendpage_locked would be more spectacular but it's
hard to get to, so take the easier path of proving this is broken
and call getname. We're currently getting IPv4 socket info on an
IPv6 socket.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/tls.c | 55 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 55 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 6e78d7207cc1..8a22db0cca49 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -1617,4 +1617,59 @@ TEST(keysizes) {
 	close(cfd);
 }
 
+TEST(tls_v6ops) {
+	struct tls_crypto_info_keys tls12;
+	struct sockaddr_in6 addr, addr2;
+	int sfd, ret, fd;
+	socklen_t len, len2;
+
+	tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_GCM_128, &tls12);
+
+	addr.sin6_family = AF_INET6;
+	addr.sin6_addr = in6addr_any;
+	addr.sin6_port = 0;
+
+	fd = socket(AF_INET6, SOCK_STREAM, 0);
+	sfd = socket(AF_INET6, SOCK_STREAM, 0);
+
+	ret = bind(sfd, &addr, sizeof(addr));
+	ASSERT_EQ(ret, 0);
+	ret = listen(sfd, 10);
+	ASSERT_EQ(ret, 0);
+
+	len = sizeof(addr);
+	ret = getsockname(sfd, &addr, &len);
+	ASSERT_EQ(ret, 0);
+
+	ret = connect(fd, &addr, sizeof(addr));
+	ASSERT_EQ(ret, 0);
+
+	len = sizeof(addr);
+	ret = getsockname(fd, &addr, &len);
+	ASSERT_EQ(ret, 0);
+
+	ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
+	if (ret) {
+		ASSERT_EQ(errno, ENOENT);
+		SKIP(return, "no TLS support");
+	}
+	ASSERT_EQ(ret, 0);
+
+	ret = setsockopt(fd, SOL_TLS, TLS_TX, &tls12, tls12.len);
+	ASSERT_EQ(ret, 0);
+
+	ret = setsockopt(fd, SOL_TLS, TLS_RX, &tls12, tls12.len);
+	ASSERT_EQ(ret, 0);
+
+	len2 = sizeof(addr2);
+	ret = getsockname(fd, &addr2, &len2);
+	ASSERT_EQ(ret, 0);
+
+	EXPECT_EQ(len2, len);
+	EXPECT_EQ(memcmp(&addr, &addr2, len), 0);
+
+	close(fd);
+	close(sfd);
+}
+
 TEST_HARNESS_MAIN
-- 
cgit v1.2.3


From 4916ea8b06a594d9d4e0cf5aa434e9ebd56baafb Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Thu, 18 Nov 2021 05:23:20 -0500
Subject: selftests: fix check for circular KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM

KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM leaves the source VM in a dead state,
so migrating back to the original source VM fails the ioctl.  Adjust
the test.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c
index 5ba325cd64bf..a66b9be30239 100644
--- a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c
+++ b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c
@@ -89,7 +89,7 @@ static void test_sev_migrate_from(bool es)
 {
 	struct kvm_vm *src_vm;
 	struct kvm_vm *dst_vms[NR_MIGRATE_TEST_VMS];
-	int i;
+	int i, ret;
 
 	src_vm = sev_vm_create(es);
 	for (i = 0; i < NR_MIGRATE_TEST_VMS; ++i)
@@ -102,7 +102,10 @@ static void test_sev_migrate_from(bool es)
 		sev_migrate_from(dst_vms[i]->fd, dst_vms[i - 1]->fd);
 
 	/* Migrate the guest back to the original VM. */
-	sev_migrate_from(src_vm->fd, dst_vms[NR_MIGRATE_TEST_VMS - 1]->fd);
+	ret = __sev_migrate_from(src_vm->fd, dst_vms[NR_MIGRATE_TEST_VMS - 1]->fd);
+	TEST_ASSERT(ret == -1 && errno == EIO,
+		    "VM that was migrated from should be dead. ret %d, errno: %d\n", ret,
+		    errno);
 
 	kvm_vm_free(src_vm);
 	for (i = 0; i < NR_MIGRATE_TEST_VMS; ++i)
-- 
cgit v1.2.3


From 826bff439ff8dd8670a313c4a8d378fca0d5df3e Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Wed, 17 Nov 2021 10:49:24 -0500
Subject: selftests: sev_migrate_tests: free all VMs

Ensure that the ASID are freed promptly, which becomes more important
when more tests are added to this file.

Cc: Peter Gonda <pgonda@google.com>
Cc: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c
index a66b9be30239..0cd7e2eaa895 100644
--- a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c
+++ b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c
@@ -149,6 +149,8 @@ static void test_sev_migrate_locking(void)
 
 	for (i = 0; i < NR_LOCK_TESTING_THREADS; ++i)
 		pthread_join(pt[i], NULL);
+	for (i = 0; i < NR_LOCK_TESTING_THREADS; ++i)
+		kvm_vm_free(input[i].vm);
 }
 
 static void test_sev_migrate_parameters(void)
@@ -165,7 +167,6 @@ static void test_sev_migrate_parameters(void)
 	sev_ioctl(sev_es_vm_no_vmsa->fd, KVM_SEV_ES_INIT, NULL);
 	vm_vcpu_add(sev_es_vm_no_vmsa, 1);
 
-
 	ret = __sev_migrate_from(sev_vm->fd, sev_es_vm->fd);
 	TEST_ASSERT(
 		ret == -1 && errno == EINVAL,
@@ -194,6 +195,12 @@ static void test_sev_migrate_parameters(void)
 	TEST_ASSERT(ret == -1 && errno == EINVAL,
 		    "Migrations require SEV enabled. ret %d, errno: %d\n", ret,
 		    errno);
+
+	kvm_vm_free(sev_vm);
+	kvm_vm_free(sev_es_vm);
+	kvm_vm_free(sev_es_vm_no_vmsa);
+	kvm_vm_free(vm_no_vcpu);
+	kvm_vm_free(vm_no_sev);
 }
 
 int main(int argc, char *argv[])
-- 
cgit v1.2.3


From 6c1186430a808f97e2052bd5d9eff12c5d5defb0 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Mon, 22 Nov 2021 18:58:17 +0100
Subject: KVM: selftests: Avoid KVM_SET_CPUID2 after KVM_RUN in hyperv_features
 test

hyperv_features's sole purpose is to test access to various Hyper-V MSRs
and hypercalls with different CPUID data. As KVM_SET_CPUID2 after KVM_RUN
is deprecated and soon-to-be forbidden, avoid it by re-creating test VM
for each sub-test.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20211122175818.608220-2-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 .../testing/selftests/kvm/x86_64/hyperv_features.c | 140 +++++++++++----------
 1 file changed, 71 insertions(+), 69 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86_64/hyperv_features.c
index 91d88aaa9899..672915ce73d8 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_features.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_features.c
@@ -165,10 +165,10 @@ static void hv_set_cpuid(struct kvm_vm *vm, struct kvm_cpuid2 *cpuid,
 	vcpu_set_cpuid(vm, VCPU_ID, cpuid);
 }
 
-static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr,
-				   struct kvm_cpuid2 *best)
+static void guest_test_msrs_access(void)
 {
 	struct kvm_run *run;
+	struct kvm_vm *vm;
 	struct ucall uc;
 	int stage = 0, r;
 	struct kvm_cpuid_entry2 feat = {
@@ -180,11 +180,34 @@ static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr,
 	struct kvm_cpuid_entry2 dbg = {
 		.function = HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES
 	};
-	struct kvm_enable_cap cap = {0};
-
-	run = vcpu_state(vm, VCPU_ID);
+	struct kvm_cpuid2 *best;
+	vm_vaddr_t msr_gva;
+	struct kvm_enable_cap cap = {
+		.cap = KVM_CAP_HYPERV_ENFORCE_CPUID,
+		.args = {1}
+	};
+	struct msr_data *msr;
 
 	while (true) {
+		vm = vm_create_default(VCPU_ID, 0, guest_msr);
+
+		msr_gva = vm_vaddr_alloc_page(vm);
+		memset(addr_gva2hva(vm, msr_gva), 0x0, getpagesize());
+		msr = addr_gva2hva(vm, msr_gva);
+
+		vcpu_args_set(vm, VCPU_ID, 1, msr_gva);
+		vcpu_enable_cap(vm, VCPU_ID, &cap);
+
+		vcpu_set_hv_cpuid(vm, VCPU_ID);
+
+		best = kvm_get_supported_hv_cpuid();
+
+		vm_init_descriptor_tables(vm);
+		vcpu_init_descriptor_tables(vm, VCPU_ID);
+		vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler);
+
+		run = vcpu_state(vm, VCPU_ID);
+
 		switch (stage) {
 		case 0:
 			/*
@@ -315,6 +338,7 @@ static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr,
 			 * capability enabled and guest visible CPUID bit unset.
 			 */
 			cap.cap = KVM_CAP_HYPERV_SYNIC2;
+			cap.args[0] = 0;
 			vcpu_enable_cap(vm, VCPU_ID, &cap);
 			break;
 		case 22:
@@ -461,9 +485,9 @@ static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr,
 
 		switch (get_ucall(vm, VCPU_ID, &uc)) {
 		case UCALL_SYNC:
-			TEST_ASSERT(uc.args[1] == stage,
-				    "Unexpected stage: %ld (%d expected)\n",
-				    uc.args[1], stage);
+			TEST_ASSERT(uc.args[1] == 0,
+				    "Unexpected stage: %ld (0 expected)\n",
+				    uc.args[1]);
 			break;
 		case UCALL_ABORT:
 			TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0],
@@ -474,13 +498,14 @@ static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr,
 		}
 
 		stage++;
+		kvm_vm_free(vm);
 	}
 }
 
-static void guest_test_hcalls_access(struct kvm_vm *vm, struct hcall_data *hcall,
-				     void *input, void *output, struct kvm_cpuid2 *best)
+static void guest_test_hcalls_access(void)
 {
 	struct kvm_run *run;
+	struct kvm_vm *vm;
 	struct ucall uc;
 	int stage = 0, r;
 	struct kvm_cpuid_entry2 feat = {
@@ -493,10 +518,38 @@ static void guest_test_hcalls_access(struct kvm_vm *vm, struct hcall_data *hcall
 	struct kvm_cpuid_entry2 dbg = {
 		.function = HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES
 	};
-
-	run = vcpu_state(vm, VCPU_ID);
+	struct kvm_enable_cap cap = {
+		.cap = KVM_CAP_HYPERV_ENFORCE_CPUID,
+		.args = {1}
+	};
+	vm_vaddr_t hcall_page, hcall_params;
+	struct hcall_data *hcall;
+	struct kvm_cpuid2 *best;
 
 	while (true) {
+		vm = vm_create_default(VCPU_ID, 0, guest_hcall);
+
+		vm_init_descriptor_tables(vm);
+		vcpu_init_descriptor_tables(vm, VCPU_ID);
+		vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler);
+
+		/* Hypercall input/output */
+		hcall_page = vm_vaddr_alloc_pages(vm, 2);
+		hcall = addr_gva2hva(vm, hcall_page);
+		memset(addr_gva2hva(vm, hcall_page), 0x0, 2 * getpagesize());
+
+		hcall_params = vm_vaddr_alloc_page(vm);
+		memset(addr_gva2hva(vm, hcall_params), 0x0, getpagesize());
+
+		vcpu_args_set(vm, VCPU_ID, 2, addr_gva2gpa(vm, hcall_page), hcall_params);
+		vcpu_enable_cap(vm, VCPU_ID, &cap);
+
+		vcpu_set_hv_cpuid(vm, VCPU_ID);
+
+		best = kvm_get_supported_hv_cpuid();
+
+		run = vcpu_state(vm, VCPU_ID);
+
 		switch (stage) {
 		case 0:
 			hcall->control = 0xdeadbeef;
@@ -606,9 +659,9 @@ static void guest_test_hcalls_access(struct kvm_vm *vm, struct hcall_data *hcall
 
 		switch (get_ucall(vm, VCPU_ID, &uc)) {
 		case UCALL_SYNC:
-			TEST_ASSERT(uc.args[1] == stage,
-				    "Unexpected stage: %ld (%d expected)\n",
-				    uc.args[1], stage);
+			TEST_ASSERT(uc.args[1] == 0,
+				    "Unexpected stage: %ld (0 expected)\n",
+				    uc.args[1]);
 			break;
 		case UCALL_ABORT:
 			TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0],
@@ -619,66 +672,15 @@ static void guest_test_hcalls_access(struct kvm_vm *vm, struct hcall_data *hcall
 		}
 
 		stage++;
+		kvm_vm_free(vm);
 	}
 }
 
 int main(void)
 {
-	struct kvm_cpuid2 *best;
-	struct kvm_vm *vm;
-	vm_vaddr_t msr_gva, hcall_page, hcall_params;
-	struct kvm_enable_cap cap = {
-		.cap = KVM_CAP_HYPERV_ENFORCE_CPUID,
-		.args = {1}
-	};
-
-	/* Test MSRs */
-	vm = vm_create_default(VCPU_ID, 0, guest_msr);
-
-	msr_gva = vm_vaddr_alloc_page(vm);
-	memset(addr_gva2hva(vm, msr_gva), 0x0, getpagesize());
-	vcpu_args_set(vm, VCPU_ID, 1, msr_gva);
-	vcpu_enable_cap(vm, VCPU_ID, &cap);
-
-	vcpu_set_hv_cpuid(vm, VCPU_ID);
-
-	best = kvm_get_supported_hv_cpuid();
-
-	vm_init_descriptor_tables(vm);
-	vcpu_init_descriptor_tables(vm, VCPU_ID);
-	vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler);
-
 	pr_info("Testing access to Hyper-V specific MSRs\n");
-	guest_test_msrs_access(vm, addr_gva2hva(vm, msr_gva),
-			       best);
-	kvm_vm_free(vm);
-
-	/* Test hypercalls */
-	vm = vm_create_default(VCPU_ID, 0, guest_hcall);
-
-	vm_init_descriptor_tables(vm);
-	vcpu_init_descriptor_tables(vm, VCPU_ID);
-	vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler);
-
-	/* Hypercall input/output */
-	hcall_page = vm_vaddr_alloc_pages(vm, 2);
-	memset(addr_gva2hva(vm, hcall_page), 0x0, 2 * getpagesize());
-
-	hcall_params = vm_vaddr_alloc_page(vm);
-	memset(addr_gva2hva(vm, hcall_params), 0x0, getpagesize());
-
-	vcpu_args_set(vm, VCPU_ID, 2, addr_gva2gpa(vm, hcall_page), hcall_params);
-	vcpu_enable_cap(vm, VCPU_ID, &cap);
-
-	vcpu_set_hv_cpuid(vm, VCPU_ID);
-
-	best = kvm_get_supported_hv_cpuid();
+	guest_test_msrs_access();
 
 	pr_info("Testing access to Hyper-V hypercalls\n");
-	guest_test_hcalls_access(vm, addr_gva2hva(vm, hcall_params),
-				 addr_gva2hva(vm, hcall_page),
-				 addr_gva2hva(vm, hcall_page) + getpagesize(),
-				 best);
-
-	kvm_vm_free(vm);
+	guest_test_hcalls_access();
 }
-- 
cgit v1.2.3


From 908fa88e420f30dde6d80f092795a18ec72ca6d3 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 23 Nov 2021 14:59:53 +0100
Subject: KVM: selftests: Make sure kvm_create_max_vcpus test won't hit
 RLIMIT_NOFILE

With the elevated 'KVM_CAP_MAX_VCPUS' value kvm_create_max_vcpus test
may hit RLIMIT_NOFILE limits:

 # ./kvm_create_max_vcpus
 KVM_CAP_MAX_VCPU_ID: 4096
 KVM_CAP_MAX_VCPUS: 1024
 Testing creating 1024 vCPUs, with IDs 0...1023.
 /dev/kvm not available (errno: 24), skipping test

Adjust RLIMIT_NOFILE limits to make sure KVM_CAP_MAX_VCPUS fds can be
opened. Note, raising hard limit ('rlim_max') requires CAP_SYS_RESOURCE
capability which is generally not needed to run kvm selftests (but without
raising the limit the test is doomed to fail anyway).

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20211123135953.667434-1-vkuznets@redhat.com>
[Skip the test if the hard limit can be raised. - Paolo]
Reviewed-by: Sean Christopherson <seanjc@google.com>
Tested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/kvm_create_max_vcpus.c | 30 ++++++++++++++++++++++
 1 file changed, 30 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/kvm_create_max_vcpus.c b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c
index f968dfd4ee88..aed9dc3ca1e9 100644
--- a/tools/testing/selftests/kvm/kvm_create_max_vcpus.c
+++ b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c
@@ -12,6 +12,7 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
+#include <sys/resource.h>
 
 #include "test_util.h"
 
@@ -40,10 +41,39 @@ int main(int argc, char *argv[])
 {
 	int kvm_max_vcpu_id = kvm_check_cap(KVM_CAP_MAX_VCPU_ID);
 	int kvm_max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS);
+	/*
+	 * Number of file descriptors reqired, KVM_CAP_MAX_VCPUS for vCPU fds +
+	 * an arbitrary number for everything else.
+	 */
+	int nr_fds_wanted = kvm_max_vcpus + 100;
+	struct rlimit rl;
 
 	pr_info("KVM_CAP_MAX_VCPU_ID: %d\n", kvm_max_vcpu_id);
 	pr_info("KVM_CAP_MAX_VCPUS: %d\n", kvm_max_vcpus);
 
+	/*
+	 * Check that we're allowed to open nr_fds_wanted file descriptors and
+	 * try raising the limits if needed.
+	 */
+	TEST_ASSERT(!getrlimit(RLIMIT_NOFILE, &rl), "getrlimit() failed!");
+
+	if (rl.rlim_cur < nr_fds_wanted) {
+		rl.rlim_cur = nr_fds_wanted;
+		if (rl.rlim_max < nr_fds_wanted) {
+			int old_rlim_max = rl.rlim_max;
+			rl.rlim_max = nr_fds_wanted;
+
+			int r = setrlimit(RLIMIT_NOFILE, &rl);
+			if (r < 0) {
+				printf("RLIMIT_NOFILE hard limit is too low (%d, wanted %d)\n",
+				       old_rlim_max, nr_fds_wanted);
+				exit(KSFT_SKIP);
+			}
+		} else {
+			TEST_ASSERT(!setrlimit(RLIMIT_NOFILE, &rl), "setrlimit() failed!");
+		}
+	}
+
 	/*
 	 * Upstream KVM prior to 4.8 does not support KVM_CAP_MAX_VCPU_ID.
 	 * Userspace is supposed to use KVM_CAP_MAX_VCPUS as the maximum ID
-- 
cgit v1.2.3


From 03ff1b1def73f817e196bf96ab36ac259490bd7c Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Mon, 29 Nov 2021 10:39:21 -0500
Subject: wireguard: selftests: increase default dmesg log size

The selftests currently parse the kernel log at the end to track
potential memory leaks. With these tests now reading off the end of the
buffer, due to recent optimizations, some creation messages were lost,
making the tests think that there was a free without an alloc. Fix this
by increasing the kernel log size.

Fixes: 24b70eeeb4f4 ("wireguard: use synchronize_net rather than synchronize_rcu")
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/wireguard/qemu/kernel.config | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/wireguard/qemu/kernel.config b/tools/testing/selftests/wireguard/qemu/kernel.config
index 74db83a0aedd..a9b5a520a1d2 100644
--- a/tools/testing/selftests/wireguard/qemu/kernel.config
+++ b/tools/testing/selftests/wireguard/qemu/kernel.config
@@ -66,6 +66,7 @@ CONFIG_PROC_SYSCTL=y
 CONFIG_SYSFS=y
 CONFIG_TMPFS=y
 CONFIG_CONSOLE_LOGLEVEL_DEFAULT=15
+CONFIG_LOG_BUF_SHIFT=18
 CONFIG_PRINTK_TIME=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_LEGACY_VSYSCALL_NONE=y
-- 
cgit v1.2.3


From 782c72af567fc2ef09bd7615d0307f24de72c7e0 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Mon, 29 Nov 2021 10:39:22 -0500
Subject: wireguard: selftests: actually test for routing loops

We previously removed the restriction on looping to self, and then added
a test to make sure the kernel didn't blow up during a routing loop. The
kernel didn't blow up, thankfully, but on certain architectures where
skb fragmentation is easier, such as ppc64, the skbs weren't actually
being discarded after a few rounds through. But the test wasn't catching
this. So actually test explicitly for massive increases in tx to see if
we have a routing loop. Note that the actual loop problem will need to
be addressed in a different commit.

Fixes: b673e24aad36 ("wireguard: socket: remove errant restriction on looping to self")
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/wireguard/netns.sh | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh
index ebc4ee0fe179..2e5c1630885e 100755
--- a/tools/testing/selftests/wireguard/netns.sh
+++ b/tools/testing/selftests/wireguard/netns.sh
@@ -276,7 +276,11 @@ n0 ping -W 1 -c 1 192.168.241.2
 n1 wg set wg0 peer "$pub2" endpoint 192.168.241.2:7
 ip2 link del wg0
 ip2 link del wg1
-! n0 ping -W 1 -c 10 -f 192.168.241.2 || false # Should not crash kernel
+read _ _ tx_bytes_before < <(n0 wg show wg1 transfer)
+! n0 ping -W 1 -c 10 -f 192.168.241.2 || false
+sleep 1
+read _ _ tx_bytes_after < <(n0 wg show wg1 transfer)
+(( tx_bytes_after - tx_bytes_before < 70000 ))
 
 ip0 link del wg1
 ip1 link del wg0
-- 
cgit v1.2.3


From 7e938beb8321d34f040557b8915b228af125f73c Mon Sep 17 00:00:00 2001
From: Li Zhijian <lizhijian@cn.fujitsu.com>
Date: Mon, 29 Nov 2021 10:39:24 -0500
Subject: wireguard: selftests: rename DEBUG_PI_LIST to DEBUG_PLIST

DEBUG_PI_LIST was renamed to DEBUG_PLIST since 8e18faeac3 ("lib/plist:
rename DEBUG_PI_LIST to DEBUG_PLIST").

Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
Fixes: 8e18faeac3e4 ("lib/plist: rename DEBUG_PI_LIST to DEBUG_PLIST")
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/wireguard/qemu/debug.config | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/wireguard/qemu/debug.config b/tools/testing/selftests/wireguard/qemu/debug.config
index fe07d97df9fa..2b321b8a96cf 100644
--- a/tools/testing/selftests/wireguard/qemu/debug.config
+++ b/tools/testing/selftests/wireguard/qemu/debug.config
@@ -47,7 +47,7 @@ CONFIG_DEBUG_ATOMIC_SLEEP=y
 CONFIG_TRACE_IRQFLAGS=y
 CONFIG_DEBUG_BUGVERBOSE=y
 CONFIG_DEBUG_LIST=y
-CONFIG_DEBUG_PI_LIST=y
+CONFIG_DEBUG_PLIST=y
 CONFIG_PROVE_RCU=y
 CONFIG_SPARSE_RCU_POINTER=y
 CONFIG_RCU_CPU_STALL_TIMEOUT=21
-- 
cgit v1.2.3


From 20ae1d6aa159eb91a9bf09ff92ccaa94dbea92c2 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Mon, 29 Nov 2021 10:39:25 -0500
Subject: wireguard: device: reset peer src endpoint when netns exits
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Each peer's endpoint contains a dst_cache entry that takes a reference
to another netdev. When the containing namespace exits, we take down the
socket and prevent future sockets from being created (by setting
creating_net to NULL), which removes that potential reference on the
netns. However, it doesn't release references to the netns that a netdev
cached in dst_cache might be taking, so the netns still might fail to
exit. Since the socket is gimped anyway, we can simply clear all the
dst_caches (by way of clearing the endpoint src), which will release all
references.

However, the current dst_cache_reset function only releases those
references lazily. But it turns out that all of our usages of
wg_socket_clear_peer_endpoint_src are called from contexts that are not
exactly high-speed or bottle-necked. For example, when there's
connection difficulty, or when userspace is reconfiguring the interface.
And in particular for this patch, when the netns is exiting. So for
those cases, it makes more sense to call dst_release immediately. For
that, we add a small helper function to dst_cache.

This patch also adds a test to netns.sh from Hangbin Liu to ensure this
doesn't regress.

Tested-by: Hangbin Liu <liuhangbin@gmail.com>
Reported-by: Xiumei Mu <xmu@redhat.com>
Cc: Toke Høiland-Jørgensen <toke@redhat.com>
Cc: Paolo Abeni <pabeni@redhat.com>
Fixes: 900575aa33a3 ("wireguard: device: avoid circular netns references")
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/wireguard/netns.sh | 24 +++++++++++++++++++++++-
 1 file changed, 23 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh
index 2e5c1630885e..8a9461aa0878 100755
--- a/tools/testing/selftests/wireguard/netns.sh
+++ b/tools/testing/selftests/wireguard/netns.sh
@@ -613,6 +613,28 @@ ip0 link set wg0 up
 kill $ncat_pid
 ip0 link del wg0
 
+# Ensure that dst_cache references don't outlive netns lifetime
+ip1 link add dev wg0 type wireguard
+ip2 link add dev wg0 type wireguard
+configure_peers
+ip1 link add veth1 type veth peer name veth2
+ip1 link set veth2 netns $netns2
+ip1 addr add fd00:aa::1/64 dev veth1
+ip2 addr add fd00:aa::2/64 dev veth2
+ip1 link set veth1 up
+ip2 link set veth2 up
+waitiface $netns1 veth1
+waitiface $netns2 veth2
+ip1 -6 route add default dev veth1 via fd00:aa::2
+ip2 -6 route add default dev veth2 via fd00:aa::1
+n1 wg set wg0 peer "$pub2" endpoint [fd00:aa::2]:2
+n2 wg set wg0 peer "$pub1" endpoint [fd00:aa::1]:1
+n1 ping6 -c 1 fd00::2
+pp ip netns delete $netns1
+pp ip netns delete $netns2
+pp ip netns add $netns1
+pp ip netns add $netns2
+
 # Ensure there aren't circular reference loops
 ip1 link add wg1 type wireguard
 ip2 link add wg2 type wireguard
@@ -631,7 +653,7 @@ while read -t 0.1 -r line 2>/dev/null || [[ $? -ne 142 ]]; do
 done < /dev/kmsg
 alldeleted=1
 for object in "${!objects[@]}"; do
-	if [[ ${objects["$object"]} != *createddestroyed ]]; then
+	if [[ ${objects["$object"]} != *createddestroyed && ${objects["$object"]} != *createdcreateddestroyeddestroyed ]]; then
 		echo "Error: $object: merely ${objects["$object"]}" >&3
 		alldeleted=0
 	fi
-- 
cgit v1.2.3


From 81835ee113e92683160030fe3328f3c3187a92c2 Mon Sep 17 00:00:00 2001
From: "Maciej S. Szmigiero" <maciej.szmigiero@oracle.com>
Date: Fri, 26 Nov 2021 16:28:31 +0100
Subject: KVM: selftests: page_table_test: fix calculation of
 guest_test_phys_mem

A kvm_page_table_test run with its default settings fails on VMX due to
memory region add failure:
> ==== Test Assertion Failure ====
>  lib/kvm_util.c:952: ret == 0
>  pid=10538 tid=10538 errno=17 - File exists
>     1  0x00000000004057d1: vm_userspace_mem_region_add at kvm_util.c:947
>     2  0x0000000000401ee9: pre_init_before_test at kvm_page_table_test.c:302
>     3   (inlined by) run_test at kvm_page_table_test.c:374
>     4  0x0000000000409754: for_each_guest_mode at guest_modes.c:53
>     5  0x0000000000401860: main at kvm_page_table_test.c:500
>     6  0x00007f82ae2d8554: ?? ??:0
>     7  0x0000000000401894: _start at ??:?
>  KVM_SET_USER_MEMORY_REGION IOCTL failed,
>  rc: -1 errno: 17
>  slot: 1 flags: 0x0
>  guest_phys_addr: 0xc0000000 size: 0x40000000

This is because the memory range that this test is trying to add
(0x0c0000000 - 0x100000000) conflicts with LAPIC mapping at 0x0fee00000.

Looking at the code it seems that guest_test_*phys*_mem variable gets
mistakenly overwritten with guest_test_*virt*_mem while trying to adjust
the former for alignment.
With the correct variable adjusted this test runs successfully.

Signed-off-by: Maciej S. Szmigiero <maciej.szmigiero@oracle.com>
Message-Id: <52e487458c3172923549bbcf9dfccfbe6faea60b.1637940473.git.maciej.szmigiero@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/kvm_page_table_test.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c
index 3836322add00..ba1fdc3dcf4a 100644
--- a/tools/testing/selftests/kvm/kvm_page_table_test.c
+++ b/tools/testing/selftests/kvm/kvm_page_table_test.c
@@ -280,7 +280,7 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg)
 #ifdef __s390x__
 	alignment = max(0x100000, alignment);
 #endif
-	guest_test_phys_mem = align_down(guest_test_virt_mem, alignment);
+	guest_test_phys_mem = align_down(guest_test_phys_mem, alignment);
 
 	/* Set up the shared data structure test_args */
 	test_args.vm = vm;
-- 
cgit v1.2.3


From dc79c9f4eb6b4f4584ba0f6f334b907283ed4b6c Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Mon, 22 Nov 2021 19:50:32 -0500
Subject: selftests: sev_migrate_tests: add tests for
 KVM_CAP_VM_COPY_ENC_CONTEXT_FROM

I am putting the tests in sev_migrate_tests because the failure conditions are
very similar and some of the setup code can be reused, too.

The tests cover both successful creation of a mirror VM, and error
conditions.

Cc: Peter Gonda <pgonda@google.com>
Cc: Sean Christopherson <seanjc@google.com>
Message-Id: <20211123005036.2954379-9-pbonzini@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 .../selftests/kvm/x86_64/sev_migrate_tests.c       | 112 +++++++++++++++++++--
 1 file changed, 105 insertions(+), 7 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c
index 0cd7e2eaa895..d265cea5de85 100644
--- a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c
+++ b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c
@@ -54,12 +54,15 @@ static struct kvm_vm *sev_vm_create(bool es)
 	return vm;
 }
 
-static struct kvm_vm *__vm_create(void)
+static struct kvm_vm *aux_vm_create(bool with_vcpus)
 {
 	struct kvm_vm *vm;
 	int i;
 
 	vm = vm_create(VM_MODE_DEFAULT, 0, O_RDWR);
+	if (!with_vcpus)
+		return vm;
+
 	for (i = 0; i < NR_MIGRATE_TEST_VCPUS; ++i)
 		vm_vcpu_add(vm, i);
 
@@ -93,7 +96,7 @@ static void test_sev_migrate_from(bool es)
 
 	src_vm = sev_vm_create(es);
 	for (i = 0; i < NR_MIGRATE_TEST_VMS; ++i)
-		dst_vms[i] = __vm_create();
+		dst_vms[i] = aux_vm_create(true);
 
 	/* Initial migration from the src to the first dst. */
 	sev_migrate_from(dst_vms[0]->fd, src_vm->fd);
@@ -162,7 +165,7 @@ static void test_sev_migrate_parameters(void)
 	sev_vm = sev_vm_create(/* es= */ false);
 	sev_es_vm = sev_vm_create(/* es= */ true);
 	vm_no_vcpu = vm_create(VM_MODE_DEFAULT, 0, O_RDWR);
-	vm_no_sev = __vm_create();
+	vm_no_sev = aux_vm_create(true);
 	sev_es_vm_no_vmsa = vm_create(VM_MODE_DEFAULT, 0, O_RDWR);
 	sev_ioctl(sev_es_vm_no_vmsa->fd, KVM_SEV_ES_INIT, NULL);
 	vm_vcpu_add(sev_es_vm_no_vmsa, 1);
@@ -203,11 +206,106 @@ static void test_sev_migrate_parameters(void)
 	kvm_vm_free(vm_no_sev);
 }
 
+static int __sev_mirror_create(int dst_fd, int src_fd)
+{
+	struct kvm_enable_cap cap = {
+		.cap = KVM_CAP_VM_COPY_ENC_CONTEXT_FROM,
+		.args = { src_fd }
+	};
+
+	return ioctl(dst_fd, KVM_ENABLE_CAP, &cap);
+}
+
+
+static void sev_mirror_create(int dst_fd, int src_fd)
+{
+	int ret;
+
+	ret = __sev_mirror_create(dst_fd, src_fd);
+	TEST_ASSERT(!ret, "Copying context failed, ret: %d, errno: %d\n", ret, errno);
+}
+
+static void test_sev_mirror(bool es)
+{
+	struct kvm_vm *src_vm, *dst_vm;
+	struct kvm_sev_launch_start start = {
+		.policy = es ? SEV_POLICY_ES : 0
+	};
+	int i;
+
+	src_vm = sev_vm_create(es);
+	dst_vm = aux_vm_create(false);
+
+	sev_mirror_create(dst_vm->fd, src_vm->fd);
+
+	/* Check that we can complete creation of the mirror VM.  */
+	for (i = 0; i < NR_MIGRATE_TEST_VCPUS; ++i)
+		vm_vcpu_add(dst_vm, i);
+	sev_ioctl(dst_vm->fd, KVM_SEV_LAUNCH_START, &start);
+	if (es)
+		sev_ioctl(dst_vm->fd, KVM_SEV_LAUNCH_UPDATE_VMSA, NULL);
+
+	kvm_vm_free(src_vm);
+	kvm_vm_free(dst_vm);
+}
+
+static void test_sev_mirror_parameters(void)
+{
+	struct kvm_vm *sev_vm, *sev_es_vm, *vm_no_vcpu, *vm_with_vcpu;
+	int ret;
+
+	sev_vm = sev_vm_create(/* es= */ false);
+	sev_es_vm = sev_vm_create(/* es= */ true);
+	vm_with_vcpu = aux_vm_create(true);
+	vm_no_vcpu = aux_vm_create(false);
+
+	ret = __sev_mirror_create(sev_vm->fd, sev_vm->fd);
+	TEST_ASSERT(
+		ret == -1 && errno == EINVAL,
+		"Should not be able copy context to self. ret: %d, errno: %d\n",
+		ret, errno);
+
+	ret = __sev_mirror_create(sev_vm->fd, sev_es_vm->fd);
+	TEST_ASSERT(
+		ret == -1 && errno == EINVAL,
+		"Should not be able copy context to SEV enabled VM. ret: %d, errno: %d\n",
+		ret, errno);
+
+	ret = __sev_mirror_create(sev_es_vm->fd, sev_vm->fd);
+	TEST_ASSERT(
+		ret == -1 && errno == EINVAL,
+		"Should not be able copy context to SEV-ES enabled VM. ret: %d, errno: %d\n",
+		ret, errno);
+
+	ret = __sev_mirror_create(vm_no_vcpu->fd, vm_with_vcpu->fd);
+	TEST_ASSERT(ret == -1 && errno == EINVAL,
+		    "Copy context requires SEV enabled. ret %d, errno: %d\n", ret,
+		    errno);
+
+	ret = __sev_mirror_create(vm_with_vcpu->fd, sev_vm->fd);
+	TEST_ASSERT(
+		ret == -1 && errno == EINVAL,
+		"SEV copy context requires no vCPUS on the destination. ret: %d, errno: %d\n",
+		ret, errno);
+
+	kvm_vm_free(sev_vm);
+	kvm_vm_free(sev_es_vm);
+	kvm_vm_free(vm_with_vcpu);
+	kvm_vm_free(vm_no_vcpu);
+}
+
 int main(int argc, char *argv[])
 {
-	test_sev_migrate_from(/* es= */ false);
-	test_sev_migrate_from(/* es= */ true);
-	test_sev_migrate_locking();
-	test_sev_migrate_parameters();
+	if (kvm_check_cap(KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM)) {
+		test_sev_migrate_from(/* es= */ false);
+		test_sev_migrate_from(/* es= */ true);
+		test_sev_migrate_locking();
+		test_sev_migrate_parameters();
+	}
+	if (kvm_check_cap(KVM_CAP_VM_COPY_ENC_CONTEXT_FROM)) {
+		test_sev_mirror(/* es= */ false);
+		test_sev_mirror(/* es= */ true);
+		test_sev_mirror_parameters();
+	}
 	return 0;
 }
-- 
cgit v1.2.3


From 17d44a96f000fe1040d4ba1c34e458c63be6b7ce Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Mon, 22 Nov 2021 19:50:34 -0500
Subject: KVM: SEV: Prohibit migration of a VM that has mirrors

VMs that mirror an encryption context rely on the owner to keep the
ASID allocated.  Performing a KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM
would cause a dangling ASID:

1. copy context from A to B (gets ref to A)
2. move context from A to L (moves ASID from A to L)
3. close L (releases ASID from L, B still references it)

The right way to do the handoff instead is to create a fresh mirror VM
on the destination first:

1. copy context from A to B (gets ref to A)
[later] 2. close B (releases ref to A)
3. move context from A to L (moves ASID from A to L)
4. copy context from L to M

So, catch the situation by adding a count of how many VMs are
mirroring this one's encryption context.

Fixes: 0b020f5af092 ("KVM: SEV: Add support for SEV-ES intra host migration")
Message-Id: <20211123005036.2954379-11-pbonzini@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 .../selftests/kvm/x86_64/sev_migrate_tests.c       | 37 ++++++++++++++++++++++
 1 file changed, 37 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c
index d265cea5de85..29b18d565cf4 100644
--- a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c
+++ b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c
@@ -294,6 +294,41 @@ static void test_sev_mirror_parameters(void)
 	kvm_vm_free(vm_no_vcpu);
 }
 
+static void test_sev_move_copy(void)
+{
+	struct kvm_vm *dst_vm, *sev_vm, *mirror_vm, *dst_mirror_vm;
+	int ret;
+
+	sev_vm = sev_vm_create(/* es= */ false);
+	dst_vm = aux_vm_create(true);
+	mirror_vm = aux_vm_create(false);
+	dst_mirror_vm = aux_vm_create(false);
+
+	sev_mirror_create(mirror_vm->fd, sev_vm->fd);
+	ret = __sev_migrate_from(dst_vm->fd, sev_vm->fd);
+	TEST_ASSERT(ret == -1 && errno == EBUSY,
+		    "Cannot migrate VM that has mirrors. ret %d, errno: %d\n", ret,
+		    errno);
+
+	/* The mirror itself can be migrated.  */
+	sev_migrate_from(dst_mirror_vm->fd, mirror_vm->fd);
+	ret = __sev_migrate_from(dst_vm->fd, sev_vm->fd);
+	TEST_ASSERT(ret == -1 && errno == EBUSY,
+		    "Cannot migrate VM that has mirrors. ret %d, errno: %d\n", ret,
+		    errno);
+
+	/*
+	 * mirror_vm is not a mirror anymore, dst_mirror_vm is.  Thus,
+	 * the owner can be copied as soon as dst_mirror_vm is gone.
+	 */
+	kvm_vm_free(dst_mirror_vm);
+	sev_migrate_from(dst_vm->fd, sev_vm->fd);
+
+	kvm_vm_free(mirror_vm);
+	kvm_vm_free(dst_vm);
+	kvm_vm_free(sev_vm);
+}
+
 int main(int argc, char *argv[])
 {
 	if (kvm_check_cap(KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM)) {
@@ -301,6 +336,8 @@ int main(int argc, char *argv[])
 		test_sev_migrate_from(/* es= */ true);
 		test_sev_migrate_locking();
 		test_sev_migrate_parameters();
+		if (kvm_check_cap(KVM_CAP_VM_COPY_ENC_CONTEXT_FROM))
+			test_sev_move_copy();
 	}
 	if (kvm_check_cap(KVM_CAP_VM_COPY_ENC_CONTEXT_FROM)) {
 		test_sev_mirror(/* es= */ false);
-- 
cgit v1.2.3


From d6e6a27d960f9f07aef0b979c49c6736ede28f75 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Tue, 30 Nov 2021 14:13:16 +0000
Subject: tools: Fix math.h breakage

Commit 98e1385ef24b ("include/linux/radix-tree.h: replace kernel.h with
the necessary inclusions") broke the radix tree test suite in two
different ways; first by including math.h which didn't exist in the
tools directory, and second by removing an implicit include of
spinlock.h before lockdep.h.  Fix both issues.

Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Acked-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/include/linux/kernel.h             | 22 +---------------------
 tools/include/linux/math.h               | 25 +++++++++++++++++++++++++
 tools/testing/radix-tree/linux/lockdep.h |  3 +++
 3 files changed, 29 insertions(+), 21 deletions(-)
 create mode 100644 tools/include/linux/math.h

(limited to 'tools')

diff --git a/tools/include/linux/kernel.h b/tools/include/linux/kernel.h
index a7e54a08fb54..3e8df500cfbd 100644
--- a/tools/include/linux/kernel.h
+++ b/tools/include/linux/kernel.h
@@ -7,6 +7,7 @@
 #include <assert.h>
 #include <linux/build_bug.h>
 #include <linux/compiler.h>
+#include <linux/math.h>
 #include <endian.h>
 #include <byteswap.h>
 
@@ -14,8 +15,6 @@
 #define UINT_MAX	(~0U)
 #endif
 
-#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d))
-
 #define PERF_ALIGN(x, a)	__PERF_ALIGN_MASK(x, (typeof(x))(a)-1)
 #define __PERF_ALIGN_MASK(x, mask)	(((x)+(mask))&~(mask))
 
@@ -52,15 +51,6 @@
 	_min1 < _min2 ? _min1 : _min2; })
 #endif
 
-#ifndef roundup
-#define roundup(x, y) (                                \
-{                                                      \
-	const typeof(y) __y = y;		       \
-	(((x) + (__y - 1)) / __y) * __y;	       \
-}                                                      \
-)
-#endif
-
 #ifndef BUG_ON
 #ifdef NDEBUG
 #define BUG_ON(cond) do { if (cond) {} } while (0)
@@ -104,16 +94,6 @@ int scnprintf_pad(char * buf, size_t size, const char * fmt, ...);
 
 #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]) + __must_be_array(arr))
 
-/*
- * This looks more complex than it should be. But we need to
- * get the type for the ~ right in round_down (it needs to be
- * as wide as the result!), and we want to evaluate the macro
- * arguments just once each.
- */
-#define __round_mask(x, y) ((__typeof__(x))((y)-1))
-#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1)
-#define round_down(x, y) ((x) & ~__round_mask(x, y))
-
 #define current_gfp_context(k) 0
 #define synchronize_rcu()
 
diff --git a/tools/include/linux/math.h b/tools/include/linux/math.h
new file mode 100644
index 000000000000..4e7af99ec9eb
--- /dev/null
+++ b/tools/include/linux/math.h
@@ -0,0 +1,25 @@
+#ifndef _TOOLS_MATH_H
+#define _TOOLS_MATH_H
+
+/*
+ * This looks more complex than it should be. But we need to
+ * get the type for the ~ right in round_down (it needs to be
+ * as wide as the result!), and we want to evaluate the macro
+ * arguments just once each.
+ */
+#define __round_mask(x, y) ((__typeof__(x))((y)-1))
+#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1)
+#define round_down(x, y) ((x) & ~__round_mask(x, y))
+
+#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d))
+
+#ifndef roundup
+#define roundup(x, y) (                                \
+{                                                      \
+	const typeof(y) __y = y;		       \
+	(((x) + (__y - 1)) / __y) * __y;	       \
+}                                                      \
+)
+#endif
+
+#endif
diff --git a/tools/testing/radix-tree/linux/lockdep.h b/tools/testing/radix-tree/linux/lockdep.h
index 565fccdfe6e9..016cff473cfc 100644
--- a/tools/testing/radix-tree/linux/lockdep.h
+++ b/tools/testing/radix-tree/linux/lockdep.h
@@ -1,5 +1,8 @@
 #ifndef _LINUX_LOCKDEP_H
 #define _LINUX_LOCKDEP_H
+
+#include <linux/spinlock.h>
+
 struct lock_class_key {
 	unsigned int a;
 };
-- 
cgit v1.2.3


From a05431b22be819d75db72ca3d44381d18a37b092 Mon Sep 17 00:00:00 2001
From: Li Zhijian <lizhijian@cn.fujitsu.com>
Date: Thu, 2 Dec 2021 10:28:41 +0800
Subject: selftests: net: Correct case name

ipv6_addr_bind/ipv4_addr_bind are function names. Previously, bind test
would not be run by default due to the wrong case names

Fixes: 34d0302ab861 ("selftests: Add ipv6 address bind tests to fcnal-test")
Fixes: 75b2b2b3db4c ("selftests: Add ipv4 address bind tests to fcnal-test")
Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/fcnal-test.sh | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh
index 3313566ce906..7f5b265fcb90 100755
--- a/tools/testing/selftests/net/fcnal-test.sh
+++ b/tools/testing/selftests/net/fcnal-test.sh
@@ -4002,8 +4002,8 @@ EOF
 ################################################################################
 # main
 
-TESTS_IPV4="ipv4_ping ipv4_tcp ipv4_udp ipv4_addr_bind ipv4_runtime ipv4_netfilter"
-TESTS_IPV6="ipv6_ping ipv6_tcp ipv6_udp ipv6_addr_bind ipv6_runtime ipv6_netfilter"
+TESTS_IPV4="ipv4_ping ipv4_tcp ipv4_udp ipv4_bind ipv4_runtime ipv4_netfilter"
+TESTS_IPV6="ipv6_ping ipv6_tcp ipv6_udp ipv6_bind ipv6_runtime ipv6_netfilter"
 TESTS_OTHER="use_cases"
 
 PAUSE_ON_FAIL=no
-- 
cgit v1.2.3


From 3345193f6f3cc24791c245d4ba2c38502f1cf684 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Mon, 22 Nov 2021 20:17:42 +0530
Subject: tools/resolve_btfids: Skip unresolved symbol warning for empty BTF
 sets

resolve_btfids prints a warning when it finds an unresolved symbol,
(id == 0) in id_patch. This can be the case for BTF sets that are empty
(due to disabled config options), hence printing warnings for certain
builds, most recently seen in [0].

The reason behind this is because id->cnt aliases id->id in btf_id
struct, leading to empty set showing up as ID 0 when we get to id_patch,
which triggers the warning. Since sets are an exception here, accomodate
by reusing hole in btf_id for bool is_set member, setting it to true for
BTF set when setting id->cnt, and use that to skip extraneous warning.

  [0]: https://lore.kernel.org/all/1b99ae14-abb4-d18f-cc6a-d7e523b25542@gmail.com

Before:

; ./tools/bpf/resolve_btfids/resolve_btfids -v -b vmlinux net/ipv4/tcp_cubic.ko
adding symbol tcp_cubic_kfunc_ids
WARN: resolve_btfids: unresolved symbol tcp_cubic_kfunc_ids
patching addr     0: ID       0 [tcp_cubic_kfunc_ids]
sorting  addr     4: cnt      0 [tcp_cubic_kfunc_ids]
update ok for net/ipv4/tcp_cubic.ko

After:

; ./tools/bpf/resolve_btfids/resolve_btfids -v -b vmlinux net/ipv4/tcp_cubic.ko
adding symbol tcp_cubic_kfunc_ids
patching addr     0: ID       0 [tcp_cubic_kfunc_ids]
sorting  addr     4: cnt      0 [tcp_cubic_kfunc_ids]
update ok for net/ipv4/tcp_cubic.ko

Fixes: 0e32dfc80bae ("bpf: Enable TCP congestion control kfunc from modules")
Reported-by: Pavel Skripkin <paskripkin@gmail.com>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20211122144742.477787-4-memxor@gmail.com
---
 tools/bpf/resolve_btfids/main.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c
index a59cb0ee609c..73409e27be01 100644
--- a/tools/bpf/resolve_btfids/main.c
+++ b/tools/bpf/resolve_btfids/main.c
@@ -83,6 +83,7 @@ struct btf_id {
 		int	 cnt;
 	};
 	int		 addr_cnt;
+	bool		 is_set;
 	Elf64_Addr	 addr[ADDR_CNT];
 };
 
@@ -451,8 +452,10 @@ static int symbols_collect(struct object *obj)
 			 * in symbol's size, together with 'cnt' field hence
 			 * that - 1.
 			 */
-			if (id)
+			if (id) {
 				id->cnt = sym.st_size / sizeof(int) - 1;
+				id->is_set = true;
+			}
 		} else {
 			pr_err("FAILED unsupported prefix %s\n", prefix);
 			return -1;
@@ -568,9 +571,8 @@ static int id_patch(struct object *obj, struct btf_id *id)
 	int *ptr = data->d_buf;
 	int i;
 
-	if (!id->id) {
+	if (!id->id && !id->is_set)
 		pr_err("WARN: resolve_btfids: unresolved symbol %s\n", id->name);
-	}
 
 	for (i = 0; i < id->addr_cnt; i++) {
 		unsigned long addr = id->addr[i];
-- 
cgit v1.2.3


From f6071e5e3961eeb5300bd0901c9e128598730ae3 Mon Sep 17 00:00:00 2001
From: Peilin Ye <peilin.ye@bytedance.com>
Date: Tue, 30 Nov 2021 16:47:20 -0800
Subject: selftests/fib_tests: Rework fib_rp_filter_test()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently rp_filter tests in fib_tests.sh:fib_rp_filter_test() are
failing.  ping sockets are bound to dummy1 using the "-I" option
(SO_BINDTODEVICE), but socket lookup is failing when receiving ping
replies, since the routing table thinks they belong to dummy0.

For example, suppose ping is using a SOCK_RAW socket for ICMP messages.
When receiving ping replies, in __raw_v4_lookup(), sk->sk_bound_dev_if
is 3 (dummy1), but dif (skb_rtable(skb)->rt_iif) says 2 (dummy0), so the
raw_sk_bound_dev_eq() check fails.  Similar things happen in
ping_lookup() for SOCK_DGRAM sockets.

These tests used to pass due to a bug [1] in iputils, where "ping -I"
actually did not bind ICMP message sockets to device.  The bug has been
fixed by iputils commit f455fee41c07 ("ping: also bind the ICMP socket
to the specific device") in 2016, which is why our rp_filter tests
started to fail.  See [2] .

Fixing the tests while keeping everything in one netns turns out to be
nontrivial.  Rework the tests and build the following topology:

 ┌─────────────────────────────┐    ┌─────────────────────────────┐
 │  network namespace 1 (ns1)  │    │  network namespace 2 (ns2)  │
 │                             │    │                             │
 │  ┌────┐     ┌─────┐         │    │  ┌─────┐            ┌────┐  │
 │  │ lo │<───>│veth1│<────────┼────┼─>│veth2│<──────────>│ lo │  │
 │  └────┘     ├─────┴──────┐  │    │  ├─────┴──────┐     └────┘  │
 │             │192.0.2.1/24│  │    │  │192.0.2.1/24│             │
 │             └────────────┘  │    │  └────────────┘             │
 └─────────────────────────────┘    └─────────────────────────────┘

Consider sending an ICMP_ECHO packet A in ns2.  Both source and
destination IP addresses are 192.0.2.1, and we use strict mode rp_filter
in both ns1 and ns2:

  1. A is routed to lo since its destination IP address is one of ns2's
     local addresses (veth2);
  2. A is redirected from lo's egress to veth2's egress using mirred;
  3. A arrives at veth1's ingress in ns1;
  4. A is redirected from veth1's ingress to lo's ingress, again, using
     mirred;
  5. In __fib_validate_source(), fib_info_nh_uses_dev() returns false,
     since A was received on lo, but reverse path lookup says veth1;
  6. However A is not dropped since we have relaxed this check for lo in
     commit 66f8209547cc ("fib: relax source validation check for loopback
     packets");

Making sure A is not dropped here in this corner case is the whole point
of having this test.

  7. As A reaches the ICMP layer, an ICMP_ECHOREPLY packet, B, is
     generated;
  8. Similarly, B is redirected from lo's egress to veth1's egress (in
     ns1), then redirected once again from veth2's ingress to lo's
     ingress (in ns2), using mirred.

Also test "ping 127.0.0.1" from ns2.  It does not trigger the relaxed
check in __fib_validate_source(), but just to make sure the topology
works with loopback addresses.

Tested with ping from iputils 20210722-41-gf9fb573:

$ ./fib_tests.sh -t rp_filter

IPv4 rp_filter tests
    TEST: rp_filter passes local packets		[ OK ]
    TEST: rp_filter passes loopback packets		[ OK ]

[1] https://github.com/iputils/iputils/issues/55
[2] https://github.com/iputils/iputils/commit/f455fee41c077d4b700a473b2f5b3487b8febc1d

Reported-by: Hangbin Liu <liuhangbin@gmail.com>
Fixes: adb701d6cfa4 ("selftests: add a test case for rp_filter")
Reviewed-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Peilin Ye <peilin.ye@bytedance.com>
Acked-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20211201004720.6357-1-yepeilin.cs@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/fib_tests.sh | 59 ++++++++++++++++++++++++++------
 1 file changed, 49 insertions(+), 10 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 5abe92d55b69..996af1ae3d3d 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -444,24 +444,63 @@ fib_rp_filter_test()
 	setup
 
 	set -e
+	ip netns add ns2
+	ip netns set ns2 auto
+
+	ip -netns ns2 link set dev lo up
+
+	$IP link add name veth1 type veth peer name veth2
+	$IP link set dev veth2 netns ns2
+	$IP address add 192.0.2.1/24 dev veth1
+	ip -netns ns2 address add 192.0.2.1/24 dev veth2
+	$IP link set dev veth1 up
+	ip -netns ns2 link set dev veth2 up
+
 	$IP link set dev lo address 52:54:00:6a:c7:5e
-	$IP link set dummy0 address 52:54:00:6a:c7:5e
-	$IP link add dummy1 type dummy
-	$IP link set dummy1 address 52:54:00:6a:c7:5e
-	$IP link set dev dummy1 up
+	$IP link set dev veth1 address 52:54:00:6a:c7:5e
+	ip -netns ns2 link set dev lo address 52:54:00:6a:c7:5e
+	ip -netns ns2 link set dev veth2 address 52:54:00:6a:c7:5e
+
+	# 1. (ns2) redirect lo's egress to veth2's egress
+	ip netns exec ns2 tc qdisc add dev lo parent root handle 1: fq_codel
+	ip netns exec ns2 tc filter add dev lo parent 1: protocol arp basic \
+		action mirred egress redirect dev veth2
+	ip netns exec ns2 tc filter add dev lo parent 1: protocol ip basic \
+		action mirred egress redirect dev veth2
+
+	# 2. (ns1) redirect veth1's ingress to lo's ingress
+	$NS_EXEC tc qdisc add dev veth1 ingress
+	$NS_EXEC tc filter add dev veth1 ingress protocol arp basic \
+		action mirred ingress redirect dev lo
+	$NS_EXEC tc filter add dev veth1 ingress protocol ip basic \
+		action mirred ingress redirect dev lo
+
+	# 3. (ns1) redirect lo's egress to veth1's egress
+	$NS_EXEC tc qdisc add dev lo parent root handle 1: fq_codel
+	$NS_EXEC tc filter add dev lo parent 1: protocol arp basic \
+		action mirred egress redirect dev veth1
+	$NS_EXEC tc filter add dev lo parent 1: protocol ip basic \
+		action mirred egress redirect dev veth1
+
+	# 4. (ns2) redirect veth2's ingress to lo's ingress
+	ip netns exec ns2 tc qdisc add dev veth2 ingress
+	ip netns exec ns2 tc filter add dev veth2 ingress protocol arp basic \
+		action mirred ingress redirect dev lo
+	ip netns exec ns2 tc filter add dev veth2 ingress protocol ip basic \
+		action mirred ingress redirect dev lo
+
 	$NS_EXEC sysctl -qw net.ipv4.conf.all.rp_filter=1
 	$NS_EXEC sysctl -qw net.ipv4.conf.all.accept_local=1
 	$NS_EXEC sysctl -qw net.ipv4.conf.all.route_localnet=1
-
-	$NS_EXEC tc qd add dev dummy1 parent root handle 1: fq_codel
-	$NS_EXEC tc filter add dev dummy1 parent 1: protocol arp basic action mirred egress redirect dev lo
-	$NS_EXEC tc filter add dev dummy1 parent 1: protocol ip basic action mirred egress redirect dev lo
+	ip netns exec ns2 sysctl -qw net.ipv4.conf.all.rp_filter=1
+	ip netns exec ns2 sysctl -qw net.ipv4.conf.all.accept_local=1
+	ip netns exec ns2 sysctl -qw net.ipv4.conf.all.route_localnet=1
 	set +e
 
-	run_cmd "ip netns exec ns1 ping -I dummy1 -w1 -c1 198.51.100.1"
+	run_cmd "ip netns exec ns2 ping -w1 -c1 192.0.2.1"
 	log_test $? 0 "rp_filter passes local packets"
 
-	run_cmd "ip netns exec ns1 ping -I dummy1 -w1 -c1 127.0.0.1"
+	run_cmd "ip netns exec ns2 ping -w1 -c1 127.0.0.1"
 	log_test $? 0 "rp_filter passes loopback packets"
 
 	cleanup
-- 
cgit v1.2.3


From 988f01683c7f2bf9f8fe2bae1cf4010fcd1baaf5 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 2 Dec 2021 21:45:34 +0100
Subject: objtool: Fix pv_ops noinstr validation

Boris reported that in one of his randconfig builds, objtool got
infinitely stuck. Turns out there's trivial list corruption in the
pv_ops tracking when a function is both in a static table and in a code
assignment.

Avoid re-adding function to the pv_ops[] lists when they're already on
it.

Fixes: db2b0c5d7b6f ("objtool: Support pv_opsindirect calls for noinstr")
Reported-by: Borislav Petkov <bp@alien8.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Tested-by: Borislav Petkov <bp@alien8.de>
Link: https://lkml.kernel.org/r/20211202204534.GA16608@worktop.programming.kicks-ass.net
---
 tools/objtool/elf.c     | 1 +
 tools/objtool/objtool.c | 4 ++++
 2 files changed, 5 insertions(+)

(limited to 'tools')

diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index 81a4c543ff7e..4b384c907027 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -375,6 +375,7 @@ static int read_symbols(struct elf *elf)
 			return -1;
 		}
 		memset(sym, 0, sizeof(*sym));
+		INIT_LIST_HEAD(&sym->pv_target);
 		sym->alias = sym;
 
 		sym->idx = i;
diff --git a/tools/objtool/objtool.c b/tools/objtool/objtool.c
index c90c7084e45a..bdf699f6552b 100644
--- a/tools/objtool/objtool.c
+++ b/tools/objtool/objtool.c
@@ -153,6 +153,10 @@ void objtool_pv_add(struct objtool_file *f, int idx, struct symbol *func)
 	    !strcmp(func->name, "_paravirt_ident_64"))
 		return;
 
+	/* already added this function */
+	if (!list_empty(&func->pv_target))
+		return;
+
 	list_add(&func->pv_target, &f->pv_ops[idx].targets);
 	f->pv_ops[idx].clean = false;
 }
-- 
cgit v1.2.3


From 96f3896780153214040a6747974bebc1355307c0 Mon Sep 17 00:00:00 2001
From: Li Zhijian <zhijianx.li@intel.com>
Date: Fri, 3 Dec 2021 10:53:21 +0800
Subject: selftests/tc-testing: add exit code

Mark the summary result as FAIL to prevent from confusing the selftest
framework if some of them are failed.

Previously, the selftest framework always treats it as *ok* even though
some of them are failed actually. That's because the script tdc.sh always
return 0.

 # All test results:
 #
 # 1..97
 # ok 1 83be - Create FQ-PIE with invalid number of flows
 # ok 2 8b6e - Create RED with no flags
[...snip]
 # ok 6 5f15 - Create RED with flags ECN, harddrop
 # ok 7 53e8 - Create RED with flags ECN, nodrop
 # ok 8 d091 - Fail to create RED with only nodrop flag
 # ok 9 af8e - Create RED with flags ECN, nodrop, harddrop
 # not ok 10 ce7d - Add mq Qdisc to multi-queue device (4 queues)
 #       Could not match regex pattern. Verify command output:
 # qdisc mq 1: root
 # qdisc fq_codel 0: parent 1:4 limit 10240p flows 1024 quantum 1514 target 5ms interval 100ms memory_limit 32Mb ecn drop_batch 64
 # qdisc fq_codel 0: parent 1:3 limit 10240p flows 1024 quantum 1514 target 5ms interval 100ms memory_limit 32Mb ecn drop_batch 64
[...snip]
 # ok 96 6979 - Change quantum of a strict ETS band
 # ok 97 9a7d - Change ETS strict band without quantum
 #
 #
 #
 #
 ok 1 selftests: tc-testing: tdc.sh <<< summary result

CC: Philip Li <philip.li@intel.com>
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Li Zhijian <zhijianx.li@intel.com>
Acked-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/tc-testing/tdc.py | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py
index a3e43189d940..ee22e3447ec7 100755
--- a/tools/testing/selftests/tc-testing/tdc.py
+++ b/tools/testing/selftests/tc-testing/tdc.py
@@ -716,6 +716,7 @@ def set_operation_mode(pm, parser, args, remaining):
         list_test_cases(alltests)
         exit(0)
 
+    exit_code = 0 # KSFT_PASS
     if len(alltests):
         req_plugins = pm.get_required_plugins(alltests)
         try:
@@ -724,6 +725,8 @@ def set_operation_mode(pm, parser, args, remaining):
             print('The following plugins were not found:')
             print('{}'.format(pde.missing_pg))
         catresults = test_runner(pm, args, alltests)
+        if catresults.count_failures() != 0:
+            exit_code = 1 # KSFT_FAIL
         if args.format == 'none':
             print('Test results output suppression requested\n')
         else:
@@ -748,6 +751,8 @@ def set_operation_mode(pm, parser, args, remaining):
                         gid=int(os.getenv('SUDO_GID')))
     else:
         print('No tests found\n')
+        exit_code = 4 # KSFT_SKIP
+    exit(exit_code)
 
 def main():
     """
@@ -767,8 +772,5 @@ def main():
 
     set_operation_mode(pm, parser, args, remaining)
 
-    exit(0)
-
-
 if __name__ == "__main__":
     main()
-- 
cgit v1.2.3


From a8c9505c53c5f1f0aba572a4c70e2d91ad08434e Mon Sep 17 00:00:00 2001
From: Li Zhijian <zhijianx.li@intel.com>
Date: Fri, 3 Dec 2021 10:53:22 +0800
Subject: selftests/tc-testing: add missing config

qdiscs/fq_pie requires CONFIG_NET_SCH_FQ_PIE, otherwise tc will fail
to create a fq_pie qdisc.

It fixes following issue:
 # not ok 57 83be - Create FQ-PIE with invalid number of flows
 #       Command exited with 2, expected 0
 # Error: Specified qdisc not found.

Signed-off-by: Li Zhijian <zhijianx.li@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/tc-testing/config | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/tc-testing/config b/tools/testing/selftests/tc-testing/config
index b71828df5a6d..b1cd7efa4512 100644
--- a/tools/testing/selftests/tc-testing/config
+++ b/tools/testing/selftests/tc-testing/config
@@ -60,6 +60,7 @@ CONFIG_NET_IFE_SKBTCINDEX=m
 CONFIG_NET_SCH_FIFO=y
 CONFIG_NET_SCH_ETS=m
 CONFIG_NET_SCH_RED=m
+CONFIG_NET_SCH_FQ_PIE=m
 
 #
 ## Network testing
-- 
cgit v1.2.3


From db925bca33a9f0029a9891defd926a4856dd5c87 Mon Sep 17 00:00:00 2001
From: Li Zhijian <zhijianx.li@intel.com>
Date: Fri, 3 Dec 2021 10:53:23 +0800
Subject: selftests/tc-testing: Fix cannot create
 /sys/bus/netdevsim/new_device: Directory nonexistent

Install netdevsim to provide /sys/bus/netdevsim/new_device interface.

It helps to fix:
 # ok 97 9a7d - Change ETS strict band without quantum # skipped - skipped - previous setup failed 11 ce7d
 #
 #
 # -----> prepare stage *** Could not execute: "echo "1 1 4" > /sys/bus/netdevsim/new_device"
 #
 # -----> prepare stage *** Error message: "/bin/sh: 1: cannot create /sys/bus/netdevsim/new_device: Directory nonexistent
 # "
 #
 # -----> prepare stage *** Aborting test run.
 #
 #
 # <_io.BufferedReader name=5> *** stdout ***
 #

Signed-off-by: Li Zhijian <zhijianx.li@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/tc-testing/config | 1 +
 tools/testing/selftests/tc-testing/tdc.sh | 1 +
 2 files changed, 2 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/tc-testing/config b/tools/testing/selftests/tc-testing/config
index b1cd7efa4512..a3239d5e40c7 100644
--- a/tools/testing/selftests/tc-testing/config
+++ b/tools/testing/selftests/tc-testing/config
@@ -61,6 +61,7 @@ CONFIG_NET_SCH_FIFO=y
 CONFIG_NET_SCH_ETS=m
 CONFIG_NET_SCH_RED=m
 CONFIG_NET_SCH_FQ_PIE=m
+CONFIG_NETDEVSIM=m
 
 #
 ## Network testing
diff --git a/tools/testing/selftests/tc-testing/tdc.sh b/tools/testing/selftests/tc-testing/tdc.sh
index 7fe38c76db44..afb0cd86fa3d 100755
--- a/tools/testing/selftests/tc-testing/tdc.sh
+++ b/tools/testing/selftests/tc-testing/tdc.sh
@@ -1,5 +1,6 @@
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
 
+modprobe netdevsim
 ./tdc.py -c actions --nobuildebpf
 ./tdc.py -c qdisc
-- 
cgit v1.2.3


From 0f8a3b48f91b8dc1f3eff06b77a63a17183fccbd Mon Sep 17 00:00:00 2001
From: Li Zhijian <zhijianx.li@intel.com>
Date: Fri, 3 Dec 2021 10:32:13 +0800
Subject: selftests: net/fcnal-test.sh: add exit code

Previously, the selftest framework always treats it as *ok* even though
some of them are failed actually. That's because the script always
returns 0.

It supports PASS/FAIL/SKIP exit code now.

CC: Philip Li <philip.li@intel.com>
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Li Zhijian <zhijianx.li@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/fcnal-test.sh | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh
index 7f5b265fcb90..a1da013d847b 100755
--- a/tools/testing/selftests/net/fcnal-test.sh
+++ b/tools/testing/selftests/net/fcnal-test.sh
@@ -4077,3 +4077,11 @@ cleanup 2>/dev/null
 
 printf "\nTests passed: %3d\n" ${nsuccess}
 printf "Tests failed: %3d\n"   ${nfail}
+
+if [ $nfail -ne 0 ]; then
+	exit 1 # KSFT_FAIL
+elif [ $nsuccess -eq 0 ]; then
+	exit $ksft_skip
+fi
+
+exit 0 # KSFT_PASS
-- 
cgit v1.2.3


From 2fa7d94afc1afbb4d702760c058dc2d7ed30f226 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@nvidia.com>
Date: Tue, 30 Nov 2021 20:16:07 +0200
Subject: bpf: Fix the off-by-two error in range markings

The first commit cited below attempts to fix the off-by-one error that
appeared in some comparisons with an open range. Due to this error,
arithmetically equivalent pieces of code could get different verdicts
from the verifier, for example (pseudocode):

  // 1. Passes the verifier:
  if (data + 8 > data_end)
      return early
  read *(u64 *)data, i.e. [data; data+7]

  // 2. Rejected by the verifier (should still pass):
  if (data + 7 >= data_end)
      return early
  read *(u64 *)data, i.e. [data; data+7]

The attempted fix, however, shifts the range by one in a wrong
direction, so the bug not only remains, but also such piece of code
starts failing in the verifier:

  // 3. Rejected by the verifier, but the check is stricter than in #1.
  if (data + 8 >= data_end)
      return early
  read *(u64 *)data, i.e. [data; data+7]

The change performed by that fix converted an off-by-one bug into
off-by-two. The second commit cited below added the BPF selftests
written to ensure than code chunks like #3 are rejected, however,
they should be accepted.

This commit fixes the off-by-two error by adjusting new_range in the
right direction and fixes the tests by changing the range into the
one that should actually fail.

Fixes: fb2a311a31d3 ("bpf: fix off by one for range markings with L{T, E} patterns")
Fixes: b37242c773b2 ("bpf: add test cases to bpf selftests to cover all access tests")
Signed-off-by: Maxim Mikityanskiy <maximmi@nvidia.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20211130181607.593149-1-maximmi@nvidia.com
---
 .../bpf/verifier/xdp_direct_packet_access.c        | 32 +++++++++++-----------
 1 file changed, 16 insertions(+), 16 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/verifier/xdp_direct_packet_access.c b/tools/testing/selftests/bpf/verifier/xdp_direct_packet_access.c
index bfb97383e6b5..de172a5b8754 100644
--- a/tools/testing/selftests/bpf/verifier/xdp_direct_packet_access.c
+++ b/tools/testing/selftests/bpf/verifier/xdp_direct_packet_access.c
@@ -112,10 +112,10 @@
 	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
 		    offsetof(struct xdp_md, data_end)),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
 	BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
 	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
@@ -167,10 +167,10 @@
 	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
 		    offsetof(struct xdp_md, data_end)),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
 	BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
 	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
@@ -274,9 +274,9 @@
 	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
 		    offsetof(struct xdp_md, data_end)),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
 	BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
@@ -437,9 +437,9 @@
 	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
 		    offsetof(struct xdp_md, data_end)),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
 	BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
@@ -544,10 +544,10 @@
 		    offsetof(struct xdp_md, data_meta)),
 	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
 	BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
 	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
@@ -599,10 +599,10 @@
 		    offsetof(struct xdp_md, data_meta)),
 	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
 	BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
 	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
@@ -706,9 +706,9 @@
 		    offsetof(struct xdp_md, data_meta)),
 	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
 	BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
@@ -869,9 +869,9 @@
 		    offsetof(struct xdp_md, data_meta)),
 	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
 	BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
-- 
cgit v1.2.3


From 3f8d6577163f9903d4af5e5c0f90eb42944a8851 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Mon, 22 Nov 2021 10:11:05 -0300
Subject: Revert "perf bench: Fix two memory leaks detected with ASan"

This: This reverts commit 92723ea0f11d92496687db8c9725248e9d1e5e1d.

  # perf test 91
  91: perf stat --bpf-counters test           :RRRRRRRRRRRRR FAILED!
  # perf test 91
  91: perf stat --bpf-counters test           :RRRRRRRRRRRRR FAILED!
  # perf test 91
  91: perf stat --bpf-counters test           :RRRRRRRRRRRR FAILED!
  # perf test 91
  91: perf stat --bpf-counters test           :RRRRRRRRRRRRRRRRRR Ok
  # perf test 91
  91: perf stat --bpf-counters test           :RRRRRRRRR FAILED!
  # perf test 91
  91: perf stat --bpf-counters test           :RRRRRRRRRRR Ok
  # perf test 91
  91: perf stat --bpf-counters test           :RRRRRRRRRRRRRRR Ok

yep, it seems the perf bench is broken so the counts won't correlated if
I revert this one:

  92723ea0f11d perf bench: Fix two memory leaks detected with ASan

it works for me again.. it seems to break -t option

   [root@dell-r440-01 perf]# ./perf bench sched messaging -g 1 -l 100 -t
   # Running 'sched/messaging' benchmark:
   RRRperf: CLIENT: ready write: Bad file descriptor
   Rperf: SENDER: write: Bad file descriptor

Reported-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Sohaib Mohamed <sohaib.amhmd@gmail.com>
Cc: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/lkml/YZev7KClb%2Fud43Lc@krava/
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/bench/sched-messaging.c | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c
index fa0ff4ce2b74..488f6e6ba1a5 100644
--- a/tools/perf/bench/sched-messaging.c
+++ b/tools/perf/bench/sched-messaging.c
@@ -223,8 +223,6 @@ static unsigned int group(pthread_t *pth,
 		snd_ctx->out_fds[i] = fds[1];
 		if (!thread_mode)
 			close(fds[0]);
-
-		free(ctx);
 	}
 
 	/* Now we have all the fds, fork the senders */
@@ -241,8 +239,6 @@ static unsigned int group(pthread_t *pth,
 		for (i = 0; i < num_fds; i++)
 			close(snd_ctx->out_fds[i]);
 
-	free(snd_ctx);
-
 	/* Return number of children to reap */
 	return num_fds * 2;
 }
-- 
cgit v1.2.3


From 71a16df164b23210d4dcaf35c70825f47d7c5599 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 8 Sep 2021 16:09:08 -0300
Subject: tools headers UAPI: Sync s390 syscall table file changed by new
 futex_waitv syscall

To pick the changes in these csets:

  6c122360cf2f4c5a ("s390: wire up sys_futex_waitv system call")

That add support for this new syscall in tools such as 'perf trace'.

For instance, this is now possible (adapted from the x86_64 test output):

  # perf trace -e futex_waitv
  ^C#
  # perf trace -v -e futex_waitv
  event qualifier tracepoint filter: (common_pid != 807333 && common_pid != 3564) && (id == 449)
  ^C#
  # perf trace -v -e futex* --max-events 10
  event qualifier tracepoint filter: (common_pid != 812168 && common_pid != 3564) && (id == 238 || id == 449)
           ? (         ): Timer/219310  ... [continued]: futex())                                            = -1 ETIMEDOUT (Connection timed out)
       0.012 ( 0.002 ms): Timer/219310 futex(uaddr: 0x7fd0b152d3c8, op: WAKE|PRIVATE_FLAG, val: 1)           = 0
       0.024 ( 0.060 ms): Timer/219310 futex(uaddr: 0x7fd0b152d420, op: WAIT_BITSET|PRIVATE_FLAG, utime: 0x7fd0b1657840, val3: MATCH_ANY) = 0
       0.086 ( 0.001 ms): Timer/219310 futex(uaddr: 0x7fd0b152d3c8, op: WAKE|PRIVATE_FLAG, val: 1)           = 0
       0.088 (         ): Timer/219310 futex(uaddr: 0x7fd0b152d424, op: WAIT_BITSET|PRIVATE_FLAG, utime: 0x7fd0b1657840, val3: MATCH_ANY) ...
       0.075 ( 0.005 ms): Web Content/219299 futex(uaddr: 0x7fd0b152d420, op: WAKE|PRIVATE_FLAG, val: 1)     = 1
       0.169 ( 0.004 ms): Web Content/219299 futex(uaddr: 0x7fd0b152d424, op: WAKE|PRIVATE_FLAG, val: 1)     = 1
       0.088 ( 0.089 ms): Timer/219310  ... [continued]: futex())                                            = 0
       0.179 ( 0.001 ms): Timer/219310 futex(uaddr: 0x7fd0b152d3c8, op: WAKE|PRIVATE_FLAG, val: 1)           = 0
       0.181 (         ): Timer/219310 futex(uaddr: 0x7fd0b152d420, op: WAIT_BITSET|PRIVATE_FLAG, utime: 0x7fd0b1657840, val3: MATCH_ANY) ...
  #

That is the filter expression attached to the raw_syscalls:sys_{enter,exit}
tracepoints.

  $ grep futex tools/perf/arch/s390/entry/syscalls/syscall.tbl
  238  common	futex			sys_futex			sys_futex_time32
  422	32	futex_time64		-				sys_futex
  449  common	futex_waitv		sys_futex_waitv			sys_futex_waitv
  $

This addresses this perf build warnings:

  Warning: Kernel ABI header at 'tools/perf/arch/s390/entry/syscalls/syscall.tbl' differs from latest version at 'arch/s390/kernel/syscalls/syscall.tbl'
  diff -u tools/perf/arch/s390/entry/syscalls/syscall.tbl arch/s390/kernel/syscalls/syscall.tbl

Acked-by: Heiko Carstens <hca@linux.ibm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>,
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Link: https://lore.kernel.org/lkml/YZ%2F2qRW%2FTScYTP1U@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/s390/entry/syscalls/syscall.tbl | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
index df5261e5cfe1..ed9c5c2eafad 100644
--- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -451,3 +451,4 @@
 446  common	landlock_restrict_self	sys_landlock_restrict_self	sys_landlock_restrict_self
 # 447 reserved for memfd_secret
 448  common	process_mrelease	sys_process_mrelease		sys_process_mrelease
+449  common	futex_waitv		sys_futex_waitv			sys_futex_waitv
-- 
cgit v1.2.3


From c29d9792607e67ed8a3f6e9db0d96836d885a8c5 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Thu, 25 Nov 2021 09:14:57 +0200
Subject: perf inject: Fix itrace space allowed for new attributes

The space allowed for new attributes can be too small if existing header
information is large. That can happen, for example, if there are very
many CPUs, due to having an event ID per CPU per event being stored in the
header information.

Fix by adding the existing header.data_offset. Also increase the extra
space allowed to 8KiB and align to a 4KiB boundary for neatness.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lore.kernel.org/lkml/20211125071457.2066863-1-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-inject.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index bc5259db5fd9..b9d6306cc14e 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -820,7 +820,7 @@ static int __cmd_inject(struct perf_inject *inject)
 		inject->tool.ordered_events = true;
 		inject->tool.ordering_requires_timestamps = true;
 		/* Allow space in the header for new attributes */
-		output_data_offset = 4096;
+		output_data_offset = roundup(8192 + session->header.data_offset, 4096);
 		if (inject->strip)
 			strip_init(inject);
 	}
-- 
cgit v1.2.3


From cba43fcf7aaf8369f80aac26cc2c50232c065a9e Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 8 Sep 2021 16:09:08 -0300
Subject: tools headers UAPI: Sync powerpc syscall table file changed by new
 futex_waitv syscall
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To pick the changes in this cset:

  a0eb2da92b715d0c ("futex: Wireup futex_waitv syscall")

That add support for this new syscall in tools such as 'perf trace'.

For instance, this is now possible (adapted from the x86_64 test output):

  # perf trace -e futex_waitv
  ^C#
  # perf trace -v -e futex_waitv
  event qualifier tracepoint filter: (common_pid != 807333 && common_pid != 3564) && (id == 449)
  ^C#
  # perf trace -v -e futex* --max-events 10
  event qualifier tracepoint filter: (common_pid != 812168 && common_pid != 3564) && (id == 221 || id == 449)
  mmap size 528384B
           ? (         ): Timer/219310  ... [continued]: futex())                                            = -1 ETIMEDOUT (Connection timed out)
       0.012 ( 0.002 ms): Timer/219310 futex(uaddr: 0x7fd0b152d3c8, op: WAKE|PRIVATE_FLAG, val: 1)           = 0
       0.024 ( 0.060 ms): Timer/219310 futex(uaddr: 0x7fd0b152d420, op: WAIT_BITSET|PRIVATE_FLAG, utime: 0x7fd0b1657840, val3: MATCH_ANY) = 0
       0.086 ( 0.001 ms): Timer/219310 futex(uaddr: 0x7fd0b152d3c8, op: WAKE|PRIVATE_FLAG, val: 1)           = 0
       0.088 (         ): Timer/219310 futex(uaddr: 0x7fd0b152d424, op: WAIT_BITSET|PRIVATE_FLAG, utime: 0x7fd0b1657840, val3: MATCH_ANY) ...
       0.075 ( 0.005 ms): Web Content/219299 futex(uaddr: 0x7fd0b152d420, op: WAKE|PRIVATE_FLAG, val: 1)     = 1
       0.169 ( 0.004 ms): Web Content/219299 futex(uaddr: 0x7fd0b152d424, op: WAKE|PRIVATE_FLAG, val: 1)     = 1
       0.088 ( 0.089 ms): Timer/219310  ... [continued]: futex())                                            = 0
       0.179 ( 0.001 ms): Timer/219310 futex(uaddr: 0x7fd0b152d3c8, op: WAKE|PRIVATE_FLAG, val: 1)           = 0
       0.181 (         ): Timer/219310 futex(uaddr: 0x7fd0b152d420, op: WAIT_BITSET|PRIVATE_FLAG, utime: 0x7fd0b1657840, val3: MATCH_ANY) ...
  #

That is the filter expression attached to the raw_syscalls:sys_{enter,exit}
tracepoints.

  $ grep futex tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
  221	32	futex				sys_futex_time32
  221	64	futex				sys_futex
  221	spu	futex				sys_futex
  422	32	futex_time64			sys_futex			sys_futex
  449	common  futex_waitv                     sys_futex_waitv
  $

This addresses this perf build warnings:

  Warning: Kernel ABI header at 'tools/perf/arch/powerpc/entry/syscalls/syscall.tbl' differs from latest version at 'arch/powerpc/kernel/syscalls/syscall.tbl'
  diff -u tools/perf/arch/powerpc/entry/syscalls/syscall.tbl arch/powerpc/kernel/syscalls/syscall.tbl

Reviewed-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Tested-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>,
Cc: André Almeida <andrealmeid@collabora.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/YZ%2F1OU9mJuyS2HMa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/powerpc/entry/syscalls/syscall.tbl | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index 7bef917cc84e..15109af9d075 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -528,3 +528,4 @@
 446	common	landlock_restrict_self		sys_landlock_restrict_self
 # 447 reserved for memfd_secret
 448	common	process_mrelease		sys_process_mrelease
+449	common  futex_waitv                     sys_futex_waitv
-- 
cgit v1.2.3


From 4ffbe87e2d5b53bcb0213d8650bbe70bf942de6a Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 23 Nov 2021 16:12:29 -0800
Subject: perf tools: Fix SMT detection fast read path

sysfs__read_int() returns 0 on success, and so the fast read path was
always failing.

Fixes: bb629484d924118e ("perf tools: Simplify checking if SMT is active.")
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Konstantin Khlebnikov <koct9i@gmail.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Clarke <pc@us.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20211124001231.3277836-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/smt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/util/smt.c b/tools/perf/util/smt.c
index 20bacd5972ad..34f1b1b1176c 100644
--- a/tools/perf/util/smt.c
+++ b/tools/perf/util/smt.c
@@ -15,7 +15,7 @@ int smt_on(void)
 	if (cached)
 		return cached_result;
 
-	if (sysfs__read_int("devices/system/cpu/smt/active", &cached_result) > 0)
+	if (sysfs__read_int("devices/system/cpu/smt/active", &cached_result) >= 0)
 		goto done;
 
 	ncpu = sysconf(_SC_NPROCESSORS_CONF);
-- 
cgit v1.2.3


From 3d1d57debee2d342a47615707588b96658fabb85 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 30 Nov 2021 10:12:41 -0300
Subject: tools build: Remove needless libpython-version feature check that
 breaks test-all fast path
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since 66dfdff03d196e51 ("perf tools: Add Python 3 support") we don't use
the tools/build/feature/test-libpython-version.c version in any Makefile
feature check:

  $ find tools/ -type f | xargs grep feature-libpython-version
  $

The only place where this was used was removed in 66dfdff03d196e51:

  -        ifneq ($(feature-libpython-version), 1)
  -          $(warning Python 3 is not yet supported; please set)
  -          $(warning PYTHON and/or PYTHON_CONFIG appropriately.)
  -          $(warning If you also have Python 2 installed, then)
  -          $(warning try something like:)
  -          $(warning $(and ,))
  -          $(warning $(and ,)  make PYTHON=python2)
  -          $(warning $(and ,))
  -          $(warning Otherwise, disable Python support entirely:)
  -          $(warning $(and ,))
  -          $(warning $(and ,)  make NO_LIBPYTHON=1)
  -          $(warning $(and ,))
  -          $(error   $(and ,))
  -        else
  -          LDFLAGS += $(PYTHON_EMBED_LDFLAGS)
  -          EXTLIBS += $(PYTHON_EMBED_LIBADD)
  -          LANG_BINDINGS += $(obj-perf)python/perf.so
  -          $(call detected,CONFIG_LIBPYTHON)
  -        endif

And nowadays we either build with PYTHON=python3 or just install the
python3 devel packages and perf will build against it.

But the leftover feature-libpython-version check made the fast path
feature detection to break in all cases except when python2 devel files
were installed:

  $ rpm -qa | grep python.*devel
  python3-devel-3.9.7-1.fc34.x86_64
  $ rm -rf /tmp/build/perf ; mkdir -p /tmp/build/perf ;
  $ make -C tools/perf O=/tmp/build/perf install-bin
  make: Entering directory '/var/home/acme/git/perf/tools/perf'
    BUILD:   Doing 'make -j32' parallel build
    HOSTCC  /tmp/build/perf/fixdep.o
  <SNIP>
  $ cat /tmp/build/perf/feature/test-all.make.output
  In file included from test-all.c:18:
  test-libpython-version.c:5:10: error: #error
      5 |         #error
        |          ^~~~~
  $ ldd ~/bin/perf | grep python
	libpython3.9.so.1.0 => /lib64/libpython3.9.so.1.0 (0x00007fda6dbcf000)
  $

As python3 is the norm these days, fix this by just removing the unused
feature-libpython-version feature check, making the test-all fast path
to work with the common case.

With this:

  $ rm -rf /tmp/build/perf ; mkdir -p /tmp/build/perf ;
  $ make -C tools/perf O=/tmp/build/perf install-bin |& head
  make: Entering directory '/var/home/acme/git/perf/tools/perf'
    BUILD:   Doing 'make -j32' parallel build
    HOSTCC  /tmp/build/perf/fixdep.o
    HOSTLD  /tmp/build/perf/fixdep-in.o
    LINK    /tmp/build/perf/fixdep

  Auto-detecting system features:
  ...                         dwarf: [ on  ]
  ...            dwarf_getlocations: [ on  ]
  ...                         glibc: [ on  ]
  $ ldd ~/bin/perf | grep python
	libpython3.9.so.1.0 => /lib64/libpython3.9.so.1.0 (0x00007f58800b0000)
  $ cat /tmp/build/perf/feature/test-all.make.output
  $

Reviewed-by: James Clark <james.clark@arm.com>
Fixes: 66dfdff03d196e51 ("perf tools: Add Python 3 support")
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jaroslav Škarvada <jskarvad@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/YaYmeeC6CS2b8OSz@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/build/Makefile.feature                 |  1 -
 tools/build/feature/Makefile                 |  4 ----
 tools/build/feature/test-all.c               |  5 -----
 tools/build/feature/test-libpython-version.c | 11 -----------
 tools/perf/Makefile.config                   |  2 --
 5 files changed, 23 deletions(-)
 delete mode 100644 tools/build/feature/test-libpython-version.c

(limited to 'tools')

diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 45a9a59828c3..ae61f464043a 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -48,7 +48,6 @@ FEATURE_TESTS_BASIC :=                  \
         numa_num_possible_cpus          \
         libperl                         \
         libpython                       \
-        libpython-version               \
         libslang                        \
         libslang-include-subdir         \
         libtraceevent                   \
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 0a3244ad9673..1480910c792e 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -32,7 +32,6 @@ FILES=                                          \
          test-numa_num_possible_cpus.bin        \
          test-libperl.bin                       \
          test-libpython.bin                     \
-         test-libpython-version.bin             \
          test-libslang.bin                      \
          test-libslang-include-subdir.bin       \
          test-libtraceevent.bin                 \
@@ -227,9 +226,6 @@ $(OUTPUT)test-libperl.bin:
 $(OUTPUT)test-libpython.bin:
 	$(BUILD) $(FLAGS_PYTHON_EMBED)
 
-$(OUTPUT)test-libpython-version.bin:
-	$(BUILD)
-
 $(OUTPUT)test-libbfd.bin:
 	$(BUILD) -DPACKAGE='"perf"' -lbfd -ldl
 
diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
index 0b243ce842be..5ffafb967b6e 100644
--- a/tools/build/feature/test-all.c
+++ b/tools/build/feature/test-all.c
@@ -14,10 +14,6 @@
 # include "test-libpython.c"
 #undef main
 
-#define main main_test_libpython_version
-# include "test-libpython-version.c"
-#undef main
-
 #define main main_test_libperl
 # include "test-libperl.c"
 #undef main
@@ -177,7 +173,6 @@
 int main(int argc, char *argv[])
 {
 	main_test_libpython();
-	main_test_libpython_version();
 	main_test_libperl();
 	main_test_hello();
 	main_test_libelf();
diff --git a/tools/build/feature/test-libpython-version.c b/tools/build/feature/test-libpython-version.c
deleted file mode 100644
index 47714b942d4d..000000000000
--- a/tools/build/feature/test-libpython-version.c
+++ /dev/null
@@ -1,11 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <Python.h>
-
-#if PY_VERSION_HEX >= 0x03000000
-	#error
-#endif
-
-int main(void)
-{
-	return 0;
-}
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index afd144725a0b..3df74cf5651a 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -271,8 +271,6 @@ endif
 
 FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS)
 FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS)
-FEATURE_CHECK_CFLAGS-libpython-version := $(PYTHON_EMBED_CCOPTS)
-FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS)
 
 FEATURE_CHECK_LDFLAGS-libaio = -lrt
 
-- 
cgit v1.2.3


From 6c481031c9f71e2b0ff9c49d21116a38ca671746 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Mon, 29 Nov 2021 12:23:39 +0100
Subject: perf test: Fix 'Simple expression parser' test on arch without CPU
 die topology info

Some platforms do not have CPU die support, for example s390.

Commit
Cc: Ian Rogers <irogers@google.com>
Fixes: fdf1e29b6118c18f ("perf expr: Add metric literals for topology.")
fails on s390:

  # perf test -Fv 7
    ...
  # FAILED tests/expr.c:173 #num_dies >= #num_packages
    ---- end ----
    Simple expression parser: FAILED!
  #

Investigating this issue leads to these functions:

 build_cpu_topology()
   +--> has_die_topology(void)
        {
           struct utsname uts;

           if (uname(&uts) < 0)
                  return false;
           if (strncmp(uts.machine, "x86_64", 6))
                  return false;
           ....
        }

which always returns false on s390. The caller build_cpu_topology()
checks has_die_topology() return value. On false the the struct
cpu_topology::die_cpu_list is not contructed and has zero entries. This
leads to the failing comparison: #num_dies >= #num_packages.  s390 of
course has a positive number of packages.

Fix this and check if the function build_cpu_topology() did build up
a die_cpus_list. The number of entries in this list should be larger
than 0. If the number of list element is zero, the die_cpus_list has
not been created and the check in function test__expr():

    TEST_ASSERT_VAL("#num_dies >= #num_packages", \
		    num_dies >= num_packages)

always fails.

Output after:

  # perf test -Fv 7
   7: Simple expression parser                                        :
   --- start ---
   division by zero
   syntax error
   ---- end ----
   Simple expression parser: Ok
  #

Fixes: fdf1e29b6118c18f ("perf expr: Add metric literals for topology.")
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Link: http://lore.kernel.org/lkml/20211129112339.3003036-1-tmricht@linux.ibm.com
[ Added comment in the added 'if (num_dies)' line about architectures not having die topology ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/expr.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c
index c895de481fe1..d54c5371c6a6 100644
--- a/tools/perf/tests/expr.c
+++ b/tools/perf/tests/expr.c
@@ -169,7 +169,9 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u
 	TEST_ASSERT_VAL("#num_dies", expr__parse(&num_dies, ctx, "#num_dies") == 0);
 	TEST_ASSERT_VAL("#num_cores >= #num_dies", num_cores >= num_dies);
 	TEST_ASSERT_VAL("#num_packages", expr__parse(&num_packages, ctx, "#num_packages") == 0);
-	TEST_ASSERT_VAL("#num_dies >= #num_packages", num_dies >= num_packages);
+
+	if (num_dies) // Some platforms do not have CPU die support, for example s390
+		TEST_ASSERT_VAL("#num_dies >= #num_packages", num_dies >= num_packages);
 
 	/*
 	 * Source count returns the number of events aggregating in a leader
-- 
cgit v1.2.3


From 1aa79e57730980dfbabd44e7c0a12fbb56064cb6 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Sun, 28 Nov 2021 00:58:10 -0800
Subject: perf test: Reset shadow counts before loading

Otherwise load counting is an average. Without this change
duration_time in test_memory_bandwidth will alter its value if an
earlier test contains duration_time.

This patch fixes an issue that's introduced in the proposed patch:
https://lore.kernel.org/lkml/20211124015226.3317994-1-irogers@google.com/
in perf test "Parse and process metrics".

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Clarke <pc@us.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20211128085810.4027314-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/parse-metric.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c
index 574b7e4efd3a..07b6f4ec024f 100644
--- a/tools/perf/tests/parse-metric.c
+++ b/tools/perf/tests/parse-metric.c
@@ -109,6 +109,7 @@ static void load_runtime_stat(struct runtime_stat *st, struct evlist *evlist,
 	struct evsel *evsel;
 	u64 count;
 
+	perf_stat__reset_shadow_stats();
 	evlist__for_each_entry(evlist, evsel) {
 		count = find_value(evsel->name, vals);
 		perf_stat__update_shadow_stats(evsel, count, 0, st);
-- 
cgit v1.2.3


From 4747395082abc67c700a75e4cf3b796e79c7cf3a Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 18 Nov 2021 12:17:30 -0800
Subject: perf header: Fix memory leaks when processing feature headers

These leaks were found with leak sanitizer running "perf pipe recording
and injection test".

In pipe mode feat_fd may hold onto an events struct that needs freeing.

When string features are processed they may overwrite an already created
string, so free this before the overwrite.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20211118201730.2302927-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/header.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 79cce216727e..e3c1a532d059 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2321,6 +2321,7 @@ out:
 #define FEAT_PROCESS_STR_FUN(__feat, __feat_env) \
 static int process_##__feat(struct feat_fd *ff, void *data __maybe_unused) \
 {\
+	free(ff->ph->env.__feat_env);		     \
 	ff->ph->env.__feat_env = do_read_string(ff); \
 	return ff->ph->env.__feat_env ? 0 : -ENOMEM; \
 }
@@ -4124,6 +4125,7 @@ int perf_event__process_feature(struct perf_session *session,
 	struct perf_record_header_feature *fe = (struct perf_record_header_feature *)event;
 	int type = fe->header.type;
 	u64 feat = fe->feat_id;
+	int ret = 0;
 
 	if (type < 0 || type >= PERF_RECORD_HEADER_MAX) {
 		pr_warning("invalid record type %d in pipe-mode\n", type);
@@ -4141,11 +4143,13 @@ int perf_event__process_feature(struct perf_session *session,
 	ff.size = event->header.size - sizeof(*fe);
 	ff.ph = &session->header;
 
-	if (feat_ops[feat].process(&ff, NULL))
-		return -1;
+	if (feat_ops[feat].process(&ff, NULL)) {
+		ret = -1;
+		goto out;
+	}
 
 	if (!feat_ops[feat].print || !tool->show_feat_hdr)
-		return 0;
+		goto out;
 
 	if (!feat_ops[feat].full_only ||
 	    tool->show_feat_hdr >= SHOW_FEAT_HEADER_FULL_INFO) {
@@ -4154,8 +4158,9 @@ int perf_event__process_feature(struct perf_session *session,
 		fprintf(stdout, "# %s info available, use -I to display\n",
 			feat_ops[feat].name);
 	}
-
-	return 0;
+out:
+	free_event_desc(ff.events);
+	return ret;
 }
 
 size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp)
-- 
cgit v1.2.3


From f7c4e85bccea960203e5872553957511df86913e Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Fri, 3 Dec 2021 19:32:34 +0000
Subject: perf bpf: Fix building perf with BUILD_BPF_SKEL=1 by default in more
 distros

Arnaldo reported that building all his containers with BUILD_BPF_SKEL=1
to then make this the default he found problems in some distros where
the system linux/bpf.h file was being used and lacked this:

   util/bpf_skel/bperf_leader.bpf.c:13:20: error: use of undeclared identifier 'BPF_F_PRESERVE_ELEMS'
           __uint(map_flags, BPF_F_PRESERVE_ELEMS);

So use instead the vmlinux.h file generated by bpftool from BTF info.

This fixed these as well, getting the build back working on debian:11,
debian:experimental and ubuntu:21.10:

  In file included from In file included from util/bpf_skel/bperf_leader.bpf.cutil/bpf_skel/bpf_prog_profiler.bpf.c::33:
  :
  In file included from In file included from /usr/include/linux/bpf.h/usr/include/linux/bpf.h::1111:
  :
  /usr/include/linux/types.h/usr/include/linux/types.h::55::1010:: In file included from  util/bpf_skel/bperf_follower.bpf.c:3fatal errorfatal error:
  : : In file included from /usr/include/linux/bpf.h:'asm/types.h' file not found11'asm/types.h' file not found:

  /usr/include/linux/types.h:5:10: fatal error: 'asm/types.h' file not found
  #include <asm/types.h>#include <asm/types.h>

           ^~~~~~~~~~~~~         ^~~~~~~~~~~~~

  #include <asm/types.h>
           ^~~~~~~~~~~~~
  1 error generated.

Reported-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Song Liu <song@kernel.org>
Tested-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lore.kernel.org/lkml/CF175681-8101-43D1-ABDB-449E644BE986@fb.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/bpf_skel/bperf_follower.bpf.c    | 3 +--
 tools/perf/util/bpf_skel/bperf_leader.bpf.c      | 3 +--
 tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c | 2 +-
 3 files changed, 3 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/util/bpf_skel/bperf_follower.bpf.c b/tools/perf/util/bpf_skel/bperf_follower.bpf.c
index b8fa3cb2da23..4a6acfde1493 100644
--- a/tools/perf/util/bpf_skel/bperf_follower.bpf.c
+++ b/tools/perf/util/bpf_skel/bperf_follower.bpf.c
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 // Copyright (c) 2021 Facebook
-#include <linux/bpf.h>
-#include <linux/perf_event.h>
+#include "vmlinux.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 #include "bperf.h"
diff --git a/tools/perf/util/bpf_skel/bperf_leader.bpf.c b/tools/perf/util/bpf_skel/bperf_leader.bpf.c
index 4f70d1459e86..40d962b05863 100644
--- a/tools/perf/util/bpf_skel/bperf_leader.bpf.c
+++ b/tools/perf/util/bpf_skel/bperf_leader.bpf.c
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 // Copyright (c) 2021 Facebook
-#include <linux/bpf.h>
-#include <linux/perf_event.h>
+#include "vmlinux.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 #include "bperf.h"
diff --git a/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c b/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c
index ab12b4c4ece2..97037d3b3d9f 100644
--- a/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c
+++ b/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 // Copyright (c) 2020 Facebook
-#include <linux/bpf.h>
+#include "vmlinux.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
-- 
cgit v1.2.3


From 5a897531e00243cebbcc4dbe4ab06cd559ccf53f Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Fri, 3 Dec 2021 15:14:41 -0800
Subject: perf bpf_skel: Do not use typedef to avoid error on old clang

When building bpf_skel with clang-10, typedef causes confusions like:

  libbpf: map 'prev_readings': unexpected def kind var.

Fix this by removing the typedef.

Fixes: 7fac83aaf2eecc9e ("perf stat: Introduce 'bperf' to share hardware PMCs with BPF")
Reported-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Song Liu <songliubraving@fb.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lore.kernel.org/lkml/BEF5C312-4331-4A60-AEC0-AD7617CB2BC4@fb.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/bpf_skel/bperf.h              | 14 --------------
 tools/perf/util/bpf_skel/bperf_follower.bpf.c | 16 +++++++++++++---
 tools/perf/util/bpf_skel/bperf_leader.bpf.c   | 16 +++++++++++++---
 3 files changed, 26 insertions(+), 20 deletions(-)
 delete mode 100644 tools/perf/util/bpf_skel/bperf.h

(limited to 'tools')

diff --git a/tools/perf/util/bpf_skel/bperf.h b/tools/perf/util/bpf_skel/bperf.h
deleted file mode 100644
index 186a5551ddb9..000000000000
--- a/tools/perf/util/bpf_skel/bperf.h
+++ /dev/null
@@ -1,14 +0,0 @@
-// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
-// Copyright (c) 2021 Facebook
-
-#ifndef __BPERF_STAT_H
-#define __BPERF_STAT_H
-
-typedef struct {
-	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
-	__uint(key_size, sizeof(__u32));
-	__uint(value_size, sizeof(struct bpf_perf_event_value));
-	__uint(max_entries, 1);
-} reading_map;
-
-#endif /* __BPERF_STAT_H */
diff --git a/tools/perf/util/bpf_skel/bperf_follower.bpf.c b/tools/perf/util/bpf_skel/bperf_follower.bpf.c
index 4a6acfde1493..f193998530d4 100644
--- a/tools/perf/util/bpf_skel/bperf_follower.bpf.c
+++ b/tools/perf/util/bpf_skel/bperf_follower.bpf.c
@@ -3,11 +3,21 @@
 #include "vmlinux.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
-#include "bperf.h"
 #include "bperf_u.h"
 
-reading_map diff_readings SEC(".maps");
-reading_map accum_readings SEC(".maps");
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(struct bpf_perf_event_value));
+	__uint(max_entries, 1);
+} diff_readings SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(struct bpf_perf_event_value));
+	__uint(max_entries, 1);
+} accum_readings SEC(".maps");
 
 struct {
 	__uint(type, BPF_MAP_TYPE_HASH);
diff --git a/tools/perf/util/bpf_skel/bperf_leader.bpf.c b/tools/perf/util/bpf_skel/bperf_leader.bpf.c
index 40d962b05863..e2a2d4cd7779 100644
--- a/tools/perf/util/bpf_skel/bperf_leader.bpf.c
+++ b/tools/perf/util/bpf_skel/bperf_leader.bpf.c
@@ -3,7 +3,6 @@
 #include "vmlinux.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
-#include "bperf.h"
 
 struct {
 	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
@@ -12,8 +11,19 @@ struct {
 	__uint(map_flags, BPF_F_PRESERVE_ELEMS);
 } events SEC(".maps");
 
-reading_map prev_readings SEC(".maps");
-reading_map diff_readings SEC(".maps");
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(struct bpf_perf_event_value));
+	__uint(max_entries, 1);
+} prev_readings SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(struct bpf_perf_event_value));
+	__uint(max_entries, 1);
+} diff_readings SEC(".maps");
 
 SEC("raw_tp/sched_switch")
 int BPF_PROG(on_switch)
-- 
cgit v1.2.3


From d43b75fbc23f0ac1ef9c14a5a166d3ccb761a451 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Fri, 26 Nov 2021 15:36:12 +0100
Subject: vrf: don't run conntrack on vrf with !dflt qdisc

After the below patch, the conntrack attached to skb is set to "notrack" in
the context of vrf device, for locally generated packets.
But this is true only when the default qdisc is set to the vrf device. When
changing the qdisc, notrack is not set anymore.
In fact, there is a shortcut in the vrf driver, when the default qdisc is
set, see commit dcdd43c41e60 ("net: vrf: performance improvements for
IPv4") for more details.

This patch ensures that the behavior is always the same, whatever the qdisc
is.

To demonstrate the difference, a new test is added in conntrack_vrf.sh.

Fixes: 8c9c296adfae ("vrf: run conntrack only in context of lower/physdev for locally generated packets")
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Acked-by: Florian Westphal <fw@strlen.de>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 tools/testing/selftests/netfilter/conntrack_vrf.sh | 30 +++++++++++++++++++---
 1 file changed, 26 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/netfilter/conntrack_vrf.sh b/tools/testing/selftests/netfilter/conntrack_vrf.sh
index 91f3ef0f1192..8b5ea9234588 100755
--- a/tools/testing/selftests/netfilter/conntrack_vrf.sh
+++ b/tools/testing/selftests/netfilter/conntrack_vrf.sh
@@ -150,11 +150,27 @@ EOF
 # oifname is the vrf device.
 test_masquerade_vrf()
 {
+	local qdisc=$1
+
+	if [ "$qdisc" != "default" ]; then
+		tc -net $ns0 qdisc add dev tvrf root $qdisc
+	fi
+
 	ip netns exec $ns0 conntrack -F 2>/dev/null
 
 ip netns exec $ns0 nft -f - <<EOF
 flush ruleset
 table ip nat {
+	chain rawout {
+		type filter hook output priority raw;
+
+		oif tvrf ct state untracked counter
+	}
+	chain postrouting2 {
+		type filter hook postrouting priority mangle;
+
+		oif tvrf ct state untracked counter
+	}
 	chain postrouting {
 		type nat hook postrouting priority 0;
 		# NB: masquerade should always be combined with 'oif(name) bla',
@@ -171,13 +187,18 @@ EOF
 	fi
 
 	# must also check that nat table was evaluated on second (lower device) iteration.
-	ip netns exec $ns0 nft list table ip nat |grep -q 'counter packets 2'
+	ip netns exec $ns0 nft list table ip nat |grep -q 'counter packets 2' &&
+	ip netns exec $ns0 nft list table ip nat |grep -q 'untracked counter packets [1-9]'
 	if [ $? -eq 0 ]; then
-		echo "PASS: iperf3 connect with masquerade + sport rewrite on vrf device"
+		echo "PASS: iperf3 connect with masquerade + sport rewrite on vrf device ($qdisc qdisc)"
 	else
-		echo "FAIL: vrf masq rule has unexpected counter value"
+		echo "FAIL: vrf rules have unexpected counter value"
 		ret=1
 	fi
+
+	if [ "$qdisc" != "default" ]; then
+		tc -net $ns0 qdisc del dev tvrf root
+	fi
 }
 
 # add masq rule that gets evaluated w. outif set to veth device.
@@ -213,7 +234,8 @@ EOF
 }
 
 test_ct_zone_in
-test_masquerade_vrf
+test_masquerade_vrf "default"
+test_masquerade_vrf "pfifo"
 test_masquerade_veth
 
 exit $ret
-- 
cgit v1.2.3


From 0de53b0ffb5b22b52c1e0bd4d9e18cbbce5801d0 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Sat, 27 Nov 2021 11:33:38 +0100
Subject: selftests: netfilter: Add correctness test for mac,net set type

The existing net,mac test didn't cover the issue recently reported
by Nikita Yushchenko, where MAC addresses wouldn't match if given
as first field of a concatenated set with AVX2 and 8-bit groups,
because there's a different code path covering the lookup of six
8-bit groups (MAC addresses) if that's the first field.

Add a similar mac,net test, with MAC address and IPv4 address
swapped in the set specification.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 .../selftests/netfilter/nft_concat_range.sh        | 24 +++++++++++++++++++---
 1 file changed, 21 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/netfilter/nft_concat_range.sh b/tools/testing/selftests/netfilter/nft_concat_range.sh
index 5a4938d6dcf2..ed61f6cab60f 100755
--- a/tools/testing/selftests/netfilter/nft_concat_range.sh
+++ b/tools/testing/selftests/netfilter/nft_concat_range.sh
@@ -23,8 +23,8 @@ TESTS="reported_issues correctness concurrency timeout"
 
 # Set types, defined by TYPE_ variables below
 TYPES="net_port port_net net6_port port_proto net6_port_mac net6_port_mac_proto
-       net_port_net net_mac net_mac_icmp net6_mac_icmp net6_port_net6_port
-       net_port_mac_proto_net"
+       net_port_net net_mac mac_net net_mac_icmp net6_mac_icmp
+       net6_port_net6_port net_port_mac_proto_net"
 
 # Reported bugs, also described by TYPE_ variables below
 BUGS="flush_remove_add"
@@ -277,6 +277,23 @@ perf_entries	1000
 perf_proto	ipv4
 "
 
+TYPE_mac_net="
+display		mac,net
+type_spec	ether_addr . ipv4_addr
+chain_spec	ether saddr . ip saddr
+dst		 
+src		mac addr4
+start		1
+count		5
+src_delta	2000
+tools		sendip nc bash
+proto		udp
+
+race_repeat	0
+
+perf_duration	0
+"
+
 TYPE_net_mac_icmp="
 display		net,mac - ICMP
 type_spec	ipv4_addr . ether_addr
@@ -984,7 +1001,8 @@ format() {
 		fi
 	done
 	for f in ${src}; do
-		__expr="${__expr} . "
+		[ "${__expr}" != "{ " ] && __expr="${__expr} . "
+
 		__start="$(eval format_"${f}" "${srcstart}")"
 		__end="$(eval format_"${f}" "${srcend}")"
 
-- 
cgit v1.2.3


From d46cea0e6933da93c5373a46e3dc7e5d0e56bedb Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 3 Dec 2021 15:33:23 +0100
Subject: selftests: netfilter: switch zone stress to socat

centos9 has nmap-ncat which doesn't like the '-q' option, use socat.
While at it, mark test skipped if needed tools are missing.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 tools/testing/selftests/netfilter/nft_zones_many.sh | 19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/netfilter/nft_zones_many.sh b/tools/testing/selftests/netfilter/nft_zones_many.sh
index ac646376eb01..04633119b29a 100755
--- a/tools/testing/selftests/netfilter/nft_zones_many.sh
+++ b/tools/testing/selftests/netfilter/nft_zones_many.sh
@@ -18,11 +18,17 @@ cleanup()
 	ip netns del $ns
 }
 
-ip netns add $ns
-if [ $? -ne 0 ];then
-	echo "SKIP: Could not create net namespace $gw"
-	exit $ksft_skip
-fi
+checktool (){
+	if ! $1 > /dev/null 2>&1; then
+		echo "SKIP: Could not $2"
+		exit $ksft_skip
+	fi
+}
+
+checktool "nft --version" "run test without nft tool"
+checktool "ip -Version" "run test without ip tool"
+checktool "socat -V" "run test without socat tool"
+checktool "ip netns add $ns" "create net namespace"
 
 trap cleanup EXIT
 
@@ -71,7 +77,8 @@ EOF
 		local start=$(date +%s%3N)
 		i=$((i + 10000))
 		j=$((j + 1))
-		dd if=/dev/zero of=/dev/stdout bs=8k count=10000 2>/dev/null | ip netns exec "$ns" nc -w 1 -q 1 -u -p 12345 127.0.0.1 12345 > /dev/null
+		# nft rule in output places each packet in a different zone.
+		dd if=/dev/zero of=/dev/stdout bs=8k count=10000 2>/dev/null | ip netns exec "$ns" socat STDIN UDP:127.0.0.1:12345,sourceport=12345
 		if [ $? -ne 0 ] ;then
 			ret=1
 			break
-- 
cgit v1.2.3


From d76c51f976ed1095dcd8c5c85ec9d8fed77a3e05 Mon Sep 17 00:00:00 2001
From: Vadim Fedorenko <vfedorenko@novek.ru>
Date: Tue, 7 Dec 2021 00:39:31 +0300
Subject: selftests: tls: add missing AES-CCM cipher tests

Add tests for TLSv1.2 and TLSv1.3 with AES-CCM cipher.

Signed-off-by: Vadim Fedorenko <vfedorenko@novek.ru>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/tls.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 8a22db0cca49..fb1bb402ee10 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -31,6 +31,7 @@ struct tls_crypto_info_keys {
 		struct tls12_crypto_info_chacha20_poly1305 chacha20;
 		struct tls12_crypto_info_sm4_gcm sm4gcm;
 		struct tls12_crypto_info_sm4_ccm sm4ccm;
+		struct tls12_crypto_info_aes_ccm_128 aesccm128;
 	};
 	size_t len;
 };
@@ -61,6 +62,11 @@ static void tls_crypto_info_init(uint16_t tls_version, uint16_t cipher_type,
 		tls12->sm4ccm.info.version = tls_version;
 		tls12->sm4ccm.info.cipher_type = cipher_type;
 		break;
+	case TLS_CIPHER_AES_CCM_128:
+		tls12->len = sizeof(struct tls12_crypto_info_aes_ccm_128);
+		tls12->aesccm128.info.version = tls_version;
+		tls12->aesccm128.info.cipher_type = cipher_type;
+		break;
 	default:
 		break;
 	}
@@ -261,6 +267,18 @@ FIXTURE_VARIANT_ADD(tls, 13_sm4_ccm)
 	.cipher_type = TLS_CIPHER_SM4_CCM,
 };
 
+FIXTURE_VARIANT_ADD(tls, 12_aes_ccm)
+{
+	.tls_version = TLS_1_2_VERSION,
+	.cipher_type = TLS_CIPHER_AES_CCM_128,
+};
+
+FIXTURE_VARIANT_ADD(tls, 13_aes_ccm)
+{
+	.tls_version = TLS_1_3_VERSION,
+	.cipher_type = TLS_CIPHER_AES_CCM_128,
+};
+
 FIXTURE_SETUP(tls)
 {
 	struct tls_crypto_info_keys tls12;
-- 
cgit v1.2.3


From 13bf99ab2130783e2b1988ef415585e3af7df97b Mon Sep 17 00:00:00 2001
From: Vadim Fedorenko <vfedorenko@novek.ru>
Date: Tue, 7 Dec 2021 00:39:32 +0300
Subject: selftests: tls: add missing AES256-GCM cipher

Add tests for TLSv1.2 and TLSv1.3 with AES256-GCM cipher

Signed-off-by: Vadim Fedorenko <vfedorenko@novek.ru>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/tls.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index fb1bb402ee10..6e468e0f42f7 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -32,6 +32,7 @@ struct tls_crypto_info_keys {
 		struct tls12_crypto_info_sm4_gcm sm4gcm;
 		struct tls12_crypto_info_sm4_ccm sm4ccm;
 		struct tls12_crypto_info_aes_ccm_128 aesccm128;
+		struct tls12_crypto_info_aes_gcm_256 aesgcm256;
 	};
 	size_t len;
 };
@@ -67,6 +68,11 @@ static void tls_crypto_info_init(uint16_t tls_version, uint16_t cipher_type,
 		tls12->aesccm128.info.version = tls_version;
 		tls12->aesccm128.info.cipher_type = cipher_type;
 		break;
+	case TLS_CIPHER_AES_GCM_256:
+		tls12->len = sizeof(struct tls12_crypto_info_aes_gcm_256);
+		tls12->aesgcm256.info.version = tls_version;
+		tls12->aesgcm256.info.cipher_type = cipher_type;
+		break;
 	default:
 		break;
 	}
@@ -279,6 +285,18 @@ FIXTURE_VARIANT_ADD(tls, 13_aes_ccm)
 	.cipher_type = TLS_CIPHER_AES_CCM_128,
 };
 
+FIXTURE_VARIANT_ADD(tls, 12_aes_gcm_256)
+{
+	.tls_version = TLS_1_2_VERSION,
+	.cipher_type = TLS_CIPHER_AES_GCM_256,
+};
+
+FIXTURE_VARIANT_ADD(tls, 13_aes_gcm_256)
+{
+	.tls_version = TLS_1_3_VERSION,
+	.cipher_type = TLS_CIPHER_AES_GCM_256,
+};
+
 FIXTURE_SETUP(tls)
 {
 	struct tls_crypto_info_keys tls12;
-- 
cgit v1.2.3


From 11f8cb8903ba4e8ba900fa4e4ab29d0fb4c9ef5d Mon Sep 17 00:00:00 2001
From: Chen Yu <yu.c.chen@intel.com>
Date: Tue, 23 Nov 2021 21:23:30 +0800
Subject: ACPI: tools: Fix compilation when output directory is not present

Compiling the ACPI tools when output directory parameter is specified,
but the output directory is not present, triggers the following error:

make O=/data/test/tmp/ -C tools/power/acpi/

make: Entering directory '/data/src/kernel/linux/tools/power/acpi'
  DESCEND tools/acpidbg
make[1]: Entering directory '/data/src/kernel/linux/tools/power/acpi/tools/acpidbg'
  MKDIR    include
  CP       include
  CC       tools/acpidbg/acpidbg.o
Assembler messages:
Fatal error: can't create /data/test/tmp/tools/power/acpi/tools/acpidbg/acpidbg.o: No such file or directory
make[1]: *** [../../Makefile.rules:24: /data/test/tmp/tools/power/acpi/tools/acpidbg/acpidbg.o] Error 1
make[1]: Leaving directory '/data/src/kernel/linux/tools/power/acpi/tools/acpidbg'
make: *** [Makefile:18: acpidbg] Error 2
make: Leaving directory '/data/src/kernel/linux/tools/power/acpi'

which occurs because the output directory has not been created yet.

Fix this issue by creating the output directory before compiling.

Reported-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Signed-off-by: Chen Yu <yu.c.chen@intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
[ rjw: New subject, changelog edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 tools/power/acpi/Makefile.config | 1 +
 tools/power/acpi/Makefile.rules  | 1 +
 2 files changed, 2 insertions(+)

(limited to 'tools')

diff --git a/tools/power/acpi/Makefile.config b/tools/power/acpi/Makefile.config
index 331f6d30f472..cd7106876a5f 100644
--- a/tools/power/acpi/Makefile.config
+++ b/tools/power/acpi/Makefile.config
@@ -69,6 +69,7 @@ KERNEL_INCLUDE := $(OUTPUT)include
 ACPICA_INCLUDE := $(srctree)/../../../drivers/acpi/acpica
 CFLAGS += -D_LINUX -I$(KERNEL_INCLUDE) -I$(ACPICA_INCLUDE)
 CFLAGS += $(WARNINGS)
+MKDIR = mkdir
 
 ifeq ($(strip $(V)),false)
 	QUIET=@
diff --git a/tools/power/acpi/Makefile.rules b/tools/power/acpi/Makefile.rules
index 2a6c170b57cd..1d7616f5d0ae 100644
--- a/tools/power/acpi/Makefile.rules
+++ b/tools/power/acpi/Makefile.rules
@@ -21,6 +21,7 @@ $(KERNEL_INCLUDE):
 
 $(objdir)%.o: %.c $(KERNEL_INCLUDE)
 	$(ECHO) "  CC      " $(subst $(OUTPUT),,$@)
+	$(QUIET) $(MKDIR) -p $(objdir) 2>/dev/null
 	$(QUIET) $(CC) -c $(CFLAGS) -o $@ $<
 
 all: $(OUTPUT)$(TOOL)
-- 
cgit v1.2.3


From b560b21f71eb4ef9dfc7c8ec1d0e4d7f9aa54b51 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@nvidia.com>
Date: Tue, 7 Dec 2021 10:15:21 +0200
Subject: bpf: Add selftests to cover packet access corner cases

This commit adds BPF verifier selftests that cover all corner cases by
packet boundary checks. Specifically, 8-byte packet reads are tested at
the beginning of data and at the beginning of data_meta, using all kinds
of boundary checks (all comparison operators: <, >, <=, >=; both
permutations of operands: data + length compared to end, end compared to
data + length). For each case there are three tests:

1. Length is just enough for an 8-byte read. Length is either 7 or 8,
   depending on the comparison.

2. Length is increased by 1 - should still pass the verifier. These
   cases are useful, because they failed before commit 2fa7d94afc1a
   ("bpf: Fix the off-by-two error in range markings").

3. Length is decreased by 1 - should be rejected by the verifier.

Some existing tests are just renamed to avoid duplication.

Signed-off-by: Maxim Mikityanskiy <maximmi@nvidia.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20211207081521.41923-1-maximmi@nvidia.com
---
 .../bpf/verifier/xdp_direct_packet_access.c        | 600 ++++++++++++++++++++-
 1 file changed, 584 insertions(+), 16 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/verifier/xdp_direct_packet_access.c b/tools/testing/selftests/bpf/verifier/xdp_direct_packet_access.c
index de172a5b8754..b4ec228eb95d 100644
--- a/tools/testing/selftests/bpf/verifier/xdp_direct_packet_access.c
+++ b/tools/testing/selftests/bpf/verifier/xdp_direct_packet_access.c
@@ -35,7 +35,7 @@
 	.prog_type = BPF_PROG_TYPE_XDP,
 },
 {
-	"XDP pkt read, pkt_data' > pkt_end, good access",
+	"XDP pkt read, pkt_data' > pkt_end, corner case, good access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
 	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
@@ -87,6 +87,41 @@
 	.prog_type = BPF_PROG_TYPE_XDP,
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
+{
+	"XDP pkt read, pkt_data' > pkt_end, corner case +1, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct xdp_md, data_end)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9),
+	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_data' > pkt_end, corner case -1, bad access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct xdp_md, data_end)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.errstr = "R1 offset is outside of the packet",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
 {
 	"XDP pkt read, pkt_end > pkt_data', good access",
 	.insns = {
@@ -106,7 +141,7 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
-	"XDP pkt read, pkt_end > pkt_data', bad access 1",
+	"XDP pkt read, pkt_end > pkt_data', corner case -1, bad access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
 	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
@@ -142,6 +177,42 @@
 	.prog_type = BPF_PROG_TYPE_XDP,
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
+{
+	"XDP pkt read, pkt_end > pkt_data', corner case, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct xdp_md, data_end)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+	BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_end > pkt_data', corner case +1, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct xdp_md, data_end)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+	BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
 {
 	"XDP pkt read, pkt_data' < pkt_end, good access",
 	.insns = {
@@ -161,7 +232,7 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
-	"XDP pkt read, pkt_data' < pkt_end, bad access 1",
+	"XDP pkt read, pkt_data' < pkt_end, corner case -1, bad access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
 	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
@@ -198,7 +269,43 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
-	"XDP pkt read, pkt_end < pkt_data', good access",
+	"XDP pkt read, pkt_data' < pkt_end, corner case, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct xdp_md, data_end)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+	BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_data' < pkt_end, corner case +1, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct xdp_md, data_end)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+	BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_end < pkt_data', corner case, good access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
 	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
@@ -250,6 +357,41 @@
 	.prog_type = BPF_PROG_TYPE_XDP,
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
+{
+	"XDP pkt read, pkt_end < pkt_data', corner case +1, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct xdp_md, data_end)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9),
+	BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_end < pkt_data', corner case -1, bad access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct xdp_md, data_end)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+	BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.errstr = "R1 offset is outside of the packet",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
 {
 	"XDP pkt read, pkt_data' >= pkt_end, good access",
 	.insns = {
@@ -268,7 +410,7 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
-	"XDP pkt read, pkt_data' >= pkt_end, bad access 1",
+	"XDP pkt read, pkt_data' >= pkt_end, corner case -1, bad access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
 	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
@@ -304,7 +446,41 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
-	"XDP pkt read, pkt_end >= pkt_data', good access",
+	"XDP pkt read, pkt_data' >= pkt_end, corner case, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct xdp_md, data_end)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+	BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_data' >= pkt_end, corner case +1, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct xdp_md, data_end)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+	BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_end >= pkt_data', corner case, good access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
 	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
@@ -359,7 +535,44 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
-	"XDP pkt read, pkt_data' <= pkt_end, good access",
+	"XDP pkt read, pkt_end >= pkt_data', corner case +1, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct xdp_md, data_end)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9),
+	BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_end >= pkt_data', corner case -1, bad access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct xdp_md, data_end)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+	BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.errstr = "R1 offset is outside of the packet",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_data' <= pkt_end, corner case, good access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
 	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
@@ -413,6 +626,43 @@
 	.prog_type = BPF_PROG_TYPE_XDP,
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
+{
+	"XDP pkt read, pkt_data' <= pkt_end, corner case +1, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct xdp_md, data_end)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9),
+	BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_data' <= pkt_end, corner case -1, bad access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct xdp_md, data_end)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+	BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.errstr = "R1 offset is outside of the packet",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
 {
 	"XDP pkt read, pkt_end <= pkt_data', good access",
 	.insns = {
@@ -431,7 +681,7 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
-	"XDP pkt read, pkt_end <= pkt_data', bad access 1",
+	"XDP pkt read, pkt_end <= pkt_data', corner case -1, bad access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
 	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
@@ -467,7 +717,41 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
-	"XDP pkt read, pkt_meta' > pkt_data, good access",
+	"XDP pkt read, pkt_end <= pkt_data', corner case, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct xdp_md, data_end)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+	BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_end <= pkt_data', corner case +1, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct xdp_md, data_end)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+	BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_meta' > pkt_data, corner case, good access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
 		    offsetof(struct xdp_md, data_meta)),
@@ -519,6 +803,41 @@
 	.prog_type = BPF_PROG_TYPE_XDP,
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
+{
+	"XDP pkt read, pkt_meta' > pkt_data, corner case +1, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct xdp_md, data_meta)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9),
+	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_meta' > pkt_data, corner case -1, bad access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct xdp_md, data_meta)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.errstr = "R1 offset is outside of the packet",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
 {
 	"XDP pkt read, pkt_data > pkt_meta', good access",
 	.insns = {
@@ -538,7 +857,7 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
-	"XDP pkt read, pkt_data > pkt_meta', bad access 1",
+	"XDP pkt read, pkt_data > pkt_meta', corner case -1, bad access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
 		    offsetof(struct xdp_md, data_meta)),
@@ -574,6 +893,42 @@
 	.prog_type = BPF_PROG_TYPE_XDP,
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
+{
+	"XDP pkt read, pkt_data > pkt_meta', corner case, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct xdp_md, data_meta)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+	BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_data > pkt_meta', corner case +1, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct xdp_md, data_meta)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+	BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
 {
 	"XDP pkt read, pkt_meta' < pkt_data, good access",
 	.insns = {
@@ -593,7 +948,7 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
-	"XDP pkt read, pkt_meta' < pkt_data, bad access 1",
+	"XDP pkt read, pkt_meta' < pkt_data, corner case -1, bad access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
 		    offsetof(struct xdp_md, data_meta)),
@@ -630,7 +985,43 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
-	"XDP pkt read, pkt_data < pkt_meta', good access",
+	"XDP pkt read, pkt_meta' < pkt_data, corner case, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct xdp_md, data_meta)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+	BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_meta' < pkt_data, corner case +1, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct xdp_md, data_meta)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+	BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_data < pkt_meta', corner case, good access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
 		    offsetof(struct xdp_md, data_meta)),
@@ -682,6 +1073,41 @@
 	.prog_type = BPF_PROG_TYPE_XDP,
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
+{
+	"XDP pkt read, pkt_data < pkt_meta', corner case +1, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct xdp_md, data_meta)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9),
+	BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_data < pkt_meta', corner case -1, bad access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct xdp_md, data_meta)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+	BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.errstr = "R1 offset is outside of the packet",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
 {
 	"XDP pkt read, pkt_meta' >= pkt_data, good access",
 	.insns = {
@@ -700,7 +1126,7 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
-	"XDP pkt read, pkt_meta' >= pkt_data, bad access 1",
+	"XDP pkt read, pkt_meta' >= pkt_data, corner case -1, bad access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
 		    offsetof(struct xdp_md, data_meta)),
@@ -736,7 +1162,41 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
-	"XDP pkt read, pkt_data >= pkt_meta', good access",
+	"XDP pkt read, pkt_meta' >= pkt_data, corner case, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct xdp_md, data_meta)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+	BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_meta' >= pkt_data, corner case +1, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct xdp_md, data_meta)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+	BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_data >= pkt_meta', corner case, good access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
 		    offsetof(struct xdp_md, data_meta)),
@@ -791,7 +1251,44 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
-	"XDP pkt read, pkt_meta' <= pkt_data, good access",
+	"XDP pkt read, pkt_data >= pkt_meta', corner case +1, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct xdp_md, data_meta)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9),
+	BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_data >= pkt_meta', corner case -1, bad access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct xdp_md, data_meta)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+	BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.errstr = "R1 offset is outside of the packet",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_meta' <= pkt_data, corner case, good access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
 		    offsetof(struct xdp_md, data_meta)),
@@ -845,6 +1342,43 @@
 	.prog_type = BPF_PROG_TYPE_XDP,
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
+{
+	"XDP pkt read, pkt_meta' <= pkt_data, corner case +1, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct xdp_md, data_meta)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9),
+	BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_meta' <= pkt_data, corner case -1, bad access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct xdp_md, data_meta)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+	BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.errstr = "R1 offset is outside of the packet",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
 {
 	"XDP pkt read, pkt_data <= pkt_meta', good access",
 	.insns = {
@@ -863,7 +1397,7 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
-	"XDP pkt read, pkt_data <= pkt_meta', bad access 1",
+	"XDP pkt read, pkt_data <= pkt_meta', corner case -1, bad access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
 		    offsetof(struct xdp_md, data_meta)),
@@ -898,3 +1432,37 @@
 	.prog_type = BPF_PROG_TYPE_XDP,
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
+{
+	"XDP pkt read, pkt_data <= pkt_meta', corner case, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct xdp_md, data_meta)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+	BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_data <= pkt_meta', corner case +1, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct xdp_md, data_meta)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+	BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
-- 
cgit v1.2.3


From 3a49cc22d31eccceb856f468be0646faa2d4643f Mon Sep 17 00:00:00 2001
From: Sasha Levin <sashal@kernel.org>
Date: Thu, 9 Dec 2021 11:51:13 -0500
Subject: tools/lib/lockdep: drop leftover liblockdep headers

Clean up remaining headers that are specific to liblockdep but lived in
the shared header directory.  These are all unused after the liblockdep
code was removed in commit 7246f4dcaccc ("tools/lib/lockdep: drop
liblockdep").

Note that there are still headers that were originally created for
liblockdep, that still have liblockdep references, but they are used by
other tools/ code at this point.

Signed-off-by: Sasha Levin <sashal@kernel.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/include/linux/debug_locks.h | 14 --------
 tools/include/linux/hardirq.h     | 12 -------
 tools/include/linux/irqflags.h    | 39 ---------------------
 tools/include/linux/lockdep.h     | 72 ---------------------------------------
 tools/include/linux/proc_fs.h     |  4 ---
 tools/include/linux/spinlock.h    |  2 --
 tools/include/linux/stacktrace.h  | 33 ------------------
 7 files changed, 176 deletions(-)
 delete mode 100644 tools/include/linux/debug_locks.h
 delete mode 100644 tools/include/linux/hardirq.h
 delete mode 100644 tools/include/linux/irqflags.h
 delete mode 100644 tools/include/linux/lockdep.h
 delete mode 100644 tools/include/linux/proc_fs.h
 delete mode 100644 tools/include/linux/stacktrace.h

(limited to 'tools')

diff --git a/tools/include/linux/debug_locks.h b/tools/include/linux/debug_locks.h
deleted file mode 100644
index 72d595ce764a..000000000000
--- a/tools/include/linux/debug_locks.h
+++ /dev/null
@@ -1,14 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LIBLOCKDEP_DEBUG_LOCKS_H_
-#define _LIBLOCKDEP_DEBUG_LOCKS_H_
-
-#include <stddef.h>
-#include <linux/compiler.h>
-#include <asm/bug.h>
-
-#define DEBUG_LOCKS_WARN_ON(x) WARN_ON(x)
-
-extern bool debug_locks;
-extern bool debug_locks_silent;
-
-#endif
diff --git a/tools/include/linux/hardirq.h b/tools/include/linux/hardirq.h
deleted file mode 100644
index b25580b6a9be..000000000000
--- a/tools/include/linux/hardirq.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LIBLOCKDEP_LINUX_HARDIRQ_H_
-#define _LIBLOCKDEP_LINUX_HARDIRQ_H_
-
-#define SOFTIRQ_BITS	0UL
-#define HARDIRQ_BITS	0UL
-#define SOFTIRQ_SHIFT	0UL
-#define HARDIRQ_SHIFT	0UL
-#define hardirq_count()	0UL
-#define softirq_count()	0UL
-
-#endif
diff --git a/tools/include/linux/irqflags.h b/tools/include/linux/irqflags.h
deleted file mode 100644
index 501262aee8ff..000000000000
--- a/tools/include/linux/irqflags.h
+++ /dev/null
@@ -1,39 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LIBLOCKDEP_LINUX_TRACE_IRQFLAGS_H_
-#define _LIBLOCKDEP_LINUX_TRACE_IRQFLAGS_H_
-
-# define lockdep_hardirq_context()	0
-# define lockdep_softirq_context(p)	0
-# define lockdep_hardirqs_enabled()	0
-# define lockdep_softirqs_enabled(p)	0
-# define lockdep_hardirq_enter()	do { } while (0)
-# define lockdep_hardirq_exit()		do { } while (0)
-# define lockdep_softirq_enter()	do { } while (0)
-# define lockdep_softirq_exit()		do { } while (0)
-# define INIT_TRACE_IRQFLAGS
-
-# define stop_critical_timings() do { } while (0)
-# define start_critical_timings() do { } while (0)
-
-#define raw_local_irq_disable() do { } while (0)
-#define raw_local_irq_enable() do { } while (0)
-#define raw_local_irq_save(flags) ((flags) = 0)
-#define raw_local_irq_restore(flags) ((void)(flags))
-#define raw_local_save_flags(flags) ((flags) = 0)
-#define raw_irqs_disabled_flags(flags) ((void)(flags))
-#define raw_irqs_disabled() 0
-#define raw_safe_halt()
-
-#define local_irq_enable() do { } while (0)
-#define local_irq_disable() do { } while (0)
-#define local_irq_save(flags) ((flags) = 0)
-#define local_irq_restore(flags) ((void)(flags))
-#define local_save_flags(flags)	((flags) = 0)
-#define irqs_disabled() (1)
-#define irqs_disabled_flags(flags) ((void)(flags), 0)
-#define safe_halt() do { } while (0)
-
-#define trace_lock_release(x, y)
-#define trace_lock_acquire(a, b, c, d, e, f, g)
-
-#endif
diff --git a/tools/include/linux/lockdep.h b/tools/include/linux/lockdep.h
deleted file mode 100644
index e56997288f2b..000000000000
--- a/tools/include/linux/lockdep.h
+++ /dev/null
@@ -1,72 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LIBLOCKDEP_LOCKDEP_H_
-#define _LIBLOCKDEP_LOCKDEP_H_
-
-#include <sys/prctl.h>
-#include <sys/syscall.h>
-#include <string.h>
-#include <limits.h>
-#include <linux/utsname.h>
-#include <linux/compiler.h>
-#include <linux/export.h>
-#include <linux/kern_levels.h>
-#include <linux/err.h>
-#include <linux/rcu.h>
-#include <linux/list.h>
-#include <linux/hardirq.h>
-#include <unistd.h>
-
-#define MAX_LOCK_DEPTH 63UL
-
-#define asmlinkage
-#define __visible
-
-#include "../../../include/linux/lockdep.h"
-
-struct task_struct {
-	u64 curr_chain_key;
-	int lockdep_depth;
-	unsigned int lockdep_recursion;
-	struct held_lock held_locks[MAX_LOCK_DEPTH];
-	gfp_t lockdep_reclaim_gfp;
-	int pid;
-	int state;
-	char comm[17];
-};
-
-#define TASK_RUNNING 0
-
-extern struct task_struct *__curr(void);
-
-#define current (__curr())
-
-static inline int debug_locks_off(void)
-{
-	return 1;
-}
-
-#define task_pid_nr(tsk) ((tsk)->pid)
-
-#define KSYM_NAME_LEN 128
-#define printk(...) dprintf(STDOUT_FILENO, __VA_ARGS__)
-#define pr_err(format, ...) fprintf (stderr, format, ## __VA_ARGS__)
-#define pr_warn pr_err
-#define pr_cont pr_err
-
-#define list_del_rcu list_del
-
-#define atomic_t unsigned long
-#define atomic_inc(x) ((*(x))++)
-
-#define print_tainted() ""
-#define static_obj(x) 1
-
-#define debug_show_all_locks()
-extern void debug_check_no_locks_held(void);
-
-static __used bool __is_kernel_percpu_address(unsigned long addr, void *can_addr)
-{
-	return false;
-}
-
-#endif
diff --git a/tools/include/linux/proc_fs.h b/tools/include/linux/proc_fs.h
deleted file mode 100644
index 8b3b03b64fda..000000000000
--- a/tools/include/linux/proc_fs.h
+++ /dev/null
@@ -1,4 +0,0 @@
-#ifndef _TOOLS_INCLUDE_LINUX_PROC_FS_H
-#define _TOOLS_INCLUDE_LINUX_PROC_FS_H
-
-#endif /* _TOOLS_INCLUDE_LINUX_PROC_FS_H */
diff --git a/tools/include/linux/spinlock.h b/tools/include/linux/spinlock.h
index c934572d935c..622266b197d0 100644
--- a/tools/include/linux/spinlock.h
+++ b/tools/include/linux/spinlock.h
@@ -37,6 +37,4 @@ static inline bool arch_spin_is_locked(arch_spinlock_t *mutex)
 	return true;
 }
 
-#include <linux/lockdep.h>
-
 #endif
diff --git a/tools/include/linux/stacktrace.h b/tools/include/linux/stacktrace.h
deleted file mode 100644
index ae343ac35bfa..000000000000
--- a/tools/include/linux/stacktrace.h
+++ /dev/null
@@ -1,33 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LIBLOCKDEP_LINUX_STACKTRACE_H_
-#define _LIBLOCKDEP_LINUX_STACKTRACE_H_
-
-#include <execinfo.h>
-
-struct stack_trace {
-	unsigned int nr_entries, max_entries;
-	unsigned long *entries;
-	int skip;
-};
-
-static inline void print_stack_trace(struct stack_trace *trace, int spaces)
-{
-	backtrace_symbols_fd((void **)trace->entries, trace->nr_entries, 1);
-}
-
-#define save_stack_trace(trace)	\
-	((trace)->nr_entries =	\
-		backtrace((void **)(trace)->entries, (trace)->max_entries))
-
-static inline int dump_stack(void)
-{
-	void *array[64];
-	size_t size;
-
-	size = backtrace(array, 64);
-	backtrace_symbols_fd(array, size, 1);
-
-	return 0;
-}
-
-#endif
-- 
cgit v1.2.3


From ee3a4f666207b5a9d3d4bc7f45c9d59f2aeb3a0d Mon Sep 17 00:00:00 2001
From: "Maciej S. Szmigiero" <maciej.szmigiero@oracle.com>
Date: Fri, 3 Dec 2021 00:10:13 +0100
Subject: KVM: x86: selftests: svm_int_ctl_test: fix intercept calculation

INTERCEPT_x are bit positions, but the code was using the raw value of
INTERCEPT_VINTR (4) instead of BIT(INTERCEPT_VINTR).
This resulted in masking of bit 2 - that is, SMI instead of VINTR.

Signed-off-by: Maciej S. Szmigiero <maciej.szmigiero@oracle.com>
Message-Id: <49b9571d25588870db5380b0be1a41df4bbaaf93.1638486479.git.maciej.szmigiero@oracle.com>
---
 tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c b/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c
index df04f56ce859..30a81038df46 100644
--- a/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c
+++ b/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c
@@ -75,7 +75,7 @@ static void l1_guest_code(struct svm_test_data *svm)
 	vmcb->control.int_ctl &= ~V_INTR_MASKING_MASK;
 
 	/* No intercepts for real and virtual interrupts */
-	vmcb->control.intercept &= ~(1ULL << INTERCEPT_INTR | INTERCEPT_VINTR);
+	vmcb->control.intercept &= ~(BIT(INTERCEPT_INTR) | BIT(INTERCEPT_VINTR));
 
 	/* Make a virtual interrupt VINTR_IRQ_NUMBER pending */
 	vmcb->control.int_ctl |= V_IRQ_MASK | (0x1 << V_INTR_PRIO_SHIFT);
-- 
cgit v1.2.3


From c8cc43c1eae2910ac96daa4216e0fb3391ad0504 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Thu, 5 Aug 2021 06:54:23 -0400
Subject: selftests: KVM: avoid failures due to reserved HyperTransport region

AMD proceessors define an address range that is reserved by HyperTransport
and causes a failure if used for guest physical addresses.  Avoid
selftests failures by reserving those guest physical addresses; the
rules are:

- On parts with <40 bits, its fully hidden from software.

- Before Fam17h, it was always 12G just below 1T, even if there was more
RAM above this location.  In this case we just not use any RAM above 1T.

- On Fam17h and later, it is variable based on SME, and is either just
below 2^48 (no encryption) or 2^43 (encryption).

Fixes: ef4c9f4f6546 ("KVM: selftests: Fix 32-bit truncation of vm_get_max_gfn()")
Cc: stable@vger.kernel.org
Cc: David Matlack <dmatlack@google.com>
Reported-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210805105423.412878-1-pbonzini@redhat.com>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Tested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/include/kvm_util.h     |  9 +++
 tools/testing/selftests/kvm/lib/kvm_util.c         |  2 +-
 tools/testing/selftests/kvm/lib/x86_64/processor.c | 68 ++++++++++++++++++++++
 3 files changed, 78 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 6a1a37f30494..da2b702da71a 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -71,6 +71,15 @@ enum vm_guest_mode {
 
 #endif
 
+#if defined(__x86_64__)
+unsigned long vm_compute_max_gfn(struct kvm_vm *vm);
+#else
+static inline unsigned long vm_compute_max_gfn(struct kvm_vm *vm)
+{
+	return ((1ULL << vm->pa_bits) >> vm->page_shift) - 1;
+}
+#endif
+
 #define MIN_PAGE_SIZE		(1U << MIN_PAGE_SHIFT)
 #define PTES_PER_MIN_PAGE	ptes_per_page(MIN_PAGE_SIZE)
 
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 8f2e0bb1ef96..daf6fdb217a7 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -302,7 +302,7 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 		(1ULL << (vm->va_bits - 1)) >> vm->page_shift);
 
 	/* Limit physical addresses to PA-bits. */
-	vm->max_gfn = ((1ULL << vm->pa_bits) >> vm->page_shift) - 1;
+	vm->max_gfn = vm_compute_max_gfn(vm);
 
 	/* Allocate and setup memory for guest. */
 	vm->vpages_mapped = sparsebit_alloc();
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index 82c39db91369..eef7b34756d5 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -1431,3 +1431,71 @@ struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vm *vm, uint32_t vcpui
 
 	return cpuid;
 }
+
+#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx 0x68747541
+#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx 0x444d4163
+#define X86EMUL_CPUID_VENDOR_AuthenticAMD_edx 0x69746e65
+
+static inline unsigned x86_family(unsigned int eax)
+{
+        unsigned int x86;
+
+        x86 = (eax >> 8) & 0xf;
+
+        if (x86 == 0xf)
+                x86 += (eax >> 20) & 0xff;
+
+        return x86;
+}
+
+unsigned long vm_compute_max_gfn(struct kvm_vm *vm)
+{
+	const unsigned long num_ht_pages = 12 << (30 - vm->page_shift); /* 12 GiB */
+	unsigned long ht_gfn, max_gfn, max_pfn;
+	uint32_t eax, ebx, ecx, edx, max_ext_leaf;
+
+	max_gfn = (1ULL << (vm->pa_bits - vm->page_shift)) - 1;
+
+	/* Avoid reserved HyperTransport region on AMD processors.  */
+	eax = ecx = 0;
+	cpuid(&eax, &ebx, &ecx, &edx);
+	if (ebx != X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx ||
+	    ecx != X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx ||
+	    edx != X86EMUL_CPUID_VENDOR_AuthenticAMD_edx)
+		return max_gfn;
+
+	/* On parts with <40 physical address bits, the area is fully hidden */
+	if (vm->pa_bits < 40)
+		return max_gfn;
+
+	/* Before family 17h, the HyperTransport area is just below 1T.  */
+	ht_gfn = (1 << 28) - num_ht_pages;
+	eax = 1;
+	cpuid(&eax, &ebx, &ecx, &edx);
+	if (x86_family(eax) < 0x17)
+		goto done;
+
+	/*
+	 * Otherwise it's at the top of the physical address space, possibly
+	 * reduced due to SME by bits 11:6 of CPUID[0x8000001f].EBX.  Use
+	 * the old conservative value if MAXPHYADDR is not enumerated.
+	 */
+	eax = 0x80000000;
+	cpuid(&eax, &ebx, &ecx, &edx);
+	max_ext_leaf = eax;
+	if (max_ext_leaf < 0x80000008)
+		goto done;
+
+	eax = 0x80000008;
+	cpuid(&eax, &ebx, &ecx, &edx);
+	max_pfn = (1ULL << ((eax & 0xff) - vm->page_shift)) - 1;
+	if (max_ext_leaf >= 0x8000001f) {
+		eax = 0x8000001f;
+		cpuid(&eax, &ebx, &ecx, &edx);
+		max_pfn >>= (ebx >> 6) & 0x3f;
+	}
+
+	ht_gfn = max_pfn - num_ht_pages;
+done:
+	return min(max_gfn, ht_gfn - 1);
+}
-- 
cgit v1.2.3


From 10e7a099bfd860a2b77ea8aaac661f52c16dd865 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Mon, 25 Oct 2021 13:13:11 -0700
Subject: selftests: KVM: Add test to verify KVM doesn't explode on "bad" I/O

Add an x86 selftest to verify that KVM doesn't WARN or otherwise explode
if userspace modifies RCX during a userspace exit to handle string I/O.
This is a regression test for a user-triggerable WARN introduced by
commit 3b27de271839 ("KVM: x86: split the two parts of emulator_pio_in").

Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20211025201311.1881846-3-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/.gitignore             |   1 +
 tools/testing/selftests/kvm/Makefile               |   1 +
 .../selftests/kvm/x86_64/userspace_io_test.c       | 114 +++++++++++++++++++++
 3 files changed, 116 insertions(+)
 create mode 100644 tools/testing/selftests/kvm/x86_64/userspace_io_test.c

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 3763105029fb..00814c0f87a6 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -30,6 +30,7 @@
 /x86_64/svm_int_ctl_test
 /x86_64/sync_regs_test
 /x86_64/tsc_msrs_test
+/x86_64/userspace_io_test
 /x86_64/userspace_msr_exit_test
 /x86_64/vmx_apic_access_test
 /x86_64/vmx_close_while_nested_test
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index c4e34717826a..f307c9f61981 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -59,6 +59,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/vmx_preemption_timer_test
 TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test
 TEST_GEN_PROGS_x86_64 += x86_64/svm_int_ctl_test
 TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test
+TEST_GEN_PROGS_x86_64 += x86_64/userspace_io_test
 TEST_GEN_PROGS_x86_64 += x86_64/userspace_msr_exit_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_apic_access_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test
diff --git a/tools/testing/selftests/kvm/x86_64/userspace_io_test.c b/tools/testing/selftests/kvm/x86_64/userspace_io_test.c
new file mode 100644
index 000000000000..e4bef2e05686
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/userspace_io_test.c
@@ -0,0 +1,114 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+
+#include "kvm_util.h"
+#include "processor.h"
+
+#define VCPU_ID			1
+
+static void guest_ins_port80(uint8_t *buffer, unsigned int count)
+{
+	unsigned long end;
+
+	if (count == 2)
+		end = (unsigned long)buffer + 1;
+	else
+		end = (unsigned long)buffer + 8192;
+
+	asm volatile("cld; rep; insb" : "+D"(buffer), "+c"(count) : "d"(0x80) : "memory");
+	GUEST_ASSERT_1(count == 0, count);
+	GUEST_ASSERT_2((unsigned long)buffer == end, buffer, end);
+}
+
+static void guest_code(void)
+{
+	uint8_t buffer[8192];
+	int i;
+
+	/*
+	 * Special case tests.  main() will adjust RCX 2 => 1 and 3 => 8192 to
+	 * test that KVM doesn't explode when userspace modifies the "count" on
+	 * a userspace I/O exit.  KVM isn't required to play nice with the I/O
+	 * itself as KVM doesn't support manipulating the count, it just needs
+	 * to not explode or overflow a buffer.
+	 */
+	guest_ins_port80(buffer, 2);
+	guest_ins_port80(buffer, 3);
+
+	/* Verify KVM fills the buffer correctly when not stuffing RCX. */
+	memset(buffer, 0, sizeof(buffer));
+	guest_ins_port80(buffer, 8192);
+	for (i = 0; i < 8192; i++)
+		GUEST_ASSERT_2(buffer[i] == 0xaa, i, buffer[i]);
+
+	GUEST_DONE();
+}
+
+int main(int argc, char *argv[])
+{
+	struct kvm_regs regs;
+	struct kvm_run *run;
+	struct kvm_vm *vm;
+	struct ucall uc;
+	int rc;
+
+	/* Tell stdout not to buffer its content */
+	setbuf(stdout, NULL);
+
+	/* Create VM */
+	vm = vm_create_default(VCPU_ID, 0, guest_code);
+	run = vcpu_state(vm, VCPU_ID);
+
+	memset(&regs, 0, sizeof(regs));
+
+	while (1) {
+		rc = _vcpu_run(vm, VCPU_ID);
+
+		TEST_ASSERT(rc == 0, "vcpu_run failed: %d\n", rc);
+		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+			    "Unexpected exit reason: %u (%s),\n",
+			    run->exit_reason,
+			    exit_reason_str(run->exit_reason));
+
+		if (get_ucall(vm, VCPU_ID, &uc))
+			break;
+
+		TEST_ASSERT(run->io.port == 0x80,
+			    "Expected I/O at port 0x80, got port 0x%x\n", run->io.port);
+
+		/*
+		 * Modify the rep string count in RCX: 2 => 1 and 3 => 8192.
+		 * Note, this abuses KVM's batching of rep string I/O to avoid
+		 * getting stuck in an infinite loop.  That behavior isn't in
+		 * scope from a testing perspective as it's not ABI in any way,
+		 * i.e. it really is abusing internal KVM knowledge.
+		 */
+		vcpu_regs_get(vm, VCPU_ID, &regs);
+		if (regs.rcx == 2)
+			regs.rcx = 1;
+		if (regs.rcx == 3)
+			regs.rcx = 8192;
+		memset((void *)run + run->io.data_offset, 0xaa, 4096);
+		vcpu_regs_set(vm, VCPU_ID, &regs);
+	}
+
+	switch (uc.cmd) {
+	case UCALL_DONE:
+		break;
+	case UCALL_ABORT:
+		TEST_FAIL("%s at %s:%ld : argN+1 = 0x%lx, argN+2 = 0x%lx",
+			  (const char *)uc.args[0], __FILE__, uc.args[1],
+			  uc.args[2], uc.args[3]);
+	default:
+		TEST_FAIL("Unknown ucall %lu", uc.cmd);
+	}
+
+	kvm_vm_free(vm);
+	return 0;
+}
-- 
cgit v1.2.3


From 964e17016cf99902c79a5de095cc5e57e7d58248 Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Fri, 10 Dec 2021 14:46:46 -0800
Subject: selftests/damon: skip test if DAMON is running

Testing the DAMON debugfs files while DAMON is running makes no sense,
as any write to the debugfs files will fail.  This commit makes the test
be skipped in this case.

Link: https://lkml.kernel.org/r/20211201150440.1088-8-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: Brendan Higgins <brendanhiggins@google.com>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/testing/selftests/damon/debugfs_attrs.sh | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/damon/debugfs_attrs.sh b/tools/testing/selftests/damon/debugfs_attrs.sh
index 196b6640bf37..fc80380c59f0 100644
--- a/tools/testing/selftests/damon/debugfs_attrs.sh
+++ b/tools/testing/selftests/damon/debugfs_attrs.sh
@@ -44,6 +44,15 @@ test_content() {
 
 source ./_chk_dependency.sh
 
+ksft_skip=4
+
+damon_onoff="$DBGFS/monitor_on"
+if [ $(cat "$damon_onoff") = "on" ]
+then
+	echo "monitoring is on"
+	exit $ksft_skip
+fi
+
 # Test attrs file
 # ===============
 
-- 
cgit v1.2.3


From c6980e30af356e85699f37142ae435a6aa483ceb Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Fri, 10 Dec 2021 14:46:49 -0800
Subject: selftests/damon: test DAMON enabling with empty target_ids case

DAMON debugfs didn't check empty targets when starting monitoring, and
the issue is fixed with commit b5ca3e83ddb0 ("mm/damon/dbgfs: add
adaptive_targets list check before enable monitor_on").  To avoid future
regression, this commit adds a test case for that in DAMON selftests.

Link: https://lkml.kernel.org/r/20211201150440.1088-9-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: Brendan Higgins <brendanhiggins@google.com>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/testing/selftests/damon/debugfs_attrs.sh | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/damon/debugfs_attrs.sh b/tools/testing/selftests/damon/debugfs_attrs.sh
index fc80380c59f0..d0916373f310 100644
--- a/tools/testing/selftests/damon/debugfs_attrs.sh
+++ b/tools/testing/selftests/damon/debugfs_attrs.sh
@@ -94,4 +94,13 @@ test_write_succ "$file" "" "$orig_content" "empty input"
 test_content "$file" "$orig_content" "" "empty input written"
 echo "$orig_content" > "$file"
 
+# Test empty targets case
+# =======================
+
+orig_target_ids=$(cat "$DBGFS/target_ids")
+echo "" > "$DBGFS/target_ids"
+orig_monitor_on=$(cat "$DBGFS/monitor_on")
+test_write_fail "$DBGFS/monitor_on" "on" "orig_monitor_on" "empty target ids"
+echo "$orig_target_ids" > "$DBGFS/target_ids"
+
 echo "PASS"
-- 
cgit v1.2.3


From d85570c655cc2c257b7da37a6d1fa4c59443c055 Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Fri, 10 Dec 2021 14:46:52 -0800
Subject: selftests/damon: test wrong DAMOS condition ranges input

A patch titled "mm/damon/schemes: add the validity judgment of
thresholds"[1] makes DAMON debugfs interface to validate DAMON scheme
inputs.  This commit adds a test case for the validation logic in DAMON
selftests.

[1] https://lore.kernel.org/linux-mm/d78360e52158d786fcbf20bc62c96785742e76d3.1637239568.git.xhao@linux.alibaba.com/

Link: https://lkml.kernel.org/r/20211201150440.1088-10-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: Brendan Higgins <brendanhiggins@google.com>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/testing/selftests/damon/debugfs_attrs.sh | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/damon/debugfs_attrs.sh b/tools/testing/selftests/damon/debugfs_attrs.sh
index d0916373f310..1ef118617167 100644
--- a/tools/testing/selftests/damon/debugfs_attrs.sh
+++ b/tools/testing/selftests/damon/debugfs_attrs.sh
@@ -77,6 +77,8 @@ test_write_succ "$file" "1 2 3 4 5 6 4 0 0 0 1 2 3 1 100 3 2 1" \
 test_write_fail "$file" "1 2
 3 4 5 6 3 0 0 0 1 2 3 1 100 3 2 1" "$orig_content" "multi lines"
 test_write_succ "$file" "" "$orig_content" "disabling"
+test_write_fail "$file" "2 1 2 1 10 1 3 10 1 1 1 1 1 1 1 1 2 3" \
+	"$orig_content" "wrong condition ranges"
 echo "$orig_content" > "$file"
 
 # Test target_ids file
-- 
cgit v1.2.3


From b4a002889d24979295ed3c2bf1d5fcfb3901026a Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Fri, 10 Dec 2021 14:46:55 -0800
Subject: selftests/damon: test debugfs file reads/writes with huge count

DAMON debugfs interface users were able to trigger warning by writing
some files with arbitrarily large 'count' parameter.  The issue is fixed
with commit db7a347b26fe ("mm/damon/dbgfs: use '__GFP_NOWARN' for
user-specified size buffer allocation").  This commit adds a test case
for the issue in DAMON selftests to avoid future regressions.

Link: https://lkml.kernel.org/r/20211201150440.1088-11-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: Brendan Higgins <brendanhiggins@google.com>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/testing/selftests/damon/.gitignore           |  2 ++
 tools/testing/selftests/damon/Makefile             |  2 ++
 tools/testing/selftests/damon/debugfs_attrs.sh     | 18 ++++++++++
 .../selftests/damon/huge_count_read_write.c        | 39 ++++++++++++++++++++++
 4 files changed, 61 insertions(+)
 create mode 100644 tools/testing/selftests/damon/.gitignore
 create mode 100644 tools/testing/selftests/damon/huge_count_read_write.c

(limited to 'tools')

diff --git a/tools/testing/selftests/damon/.gitignore b/tools/testing/selftests/damon/.gitignore
new file mode 100644
index 000000000000..c6c2965a6607
--- /dev/null
+++ b/tools/testing/selftests/damon/.gitignore
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+huge_count_read_write
diff --git a/tools/testing/selftests/damon/Makefile b/tools/testing/selftests/damon/Makefile
index 8a3f2cd9fec0..f0aa954b5d13 100644
--- a/tools/testing/selftests/damon/Makefile
+++ b/tools/testing/selftests/damon/Makefile
@@ -1,6 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
 # Makefile for damon selftests
 
+TEST_GEN_FILES += huge_count_read_write
+
 TEST_FILES = _chk_dependency.sh
 TEST_PROGS = debugfs_attrs.sh
 
diff --git a/tools/testing/selftests/damon/debugfs_attrs.sh b/tools/testing/selftests/damon/debugfs_attrs.sh
index 1ef118617167..23a7b48ca7d3 100644
--- a/tools/testing/selftests/damon/debugfs_attrs.sh
+++ b/tools/testing/selftests/damon/debugfs_attrs.sh
@@ -105,4 +105,22 @@ orig_monitor_on=$(cat "$DBGFS/monitor_on")
 test_write_fail "$DBGFS/monitor_on" "on" "orig_monitor_on" "empty target ids"
 echo "$orig_target_ids" > "$DBGFS/target_ids"
 
+# Test huge count read write
+# ==========================
+
+dmesg -C
+
+for file in "$DBGFS/"*
+do
+	./huge_count_read_write "$file"
+done
+
+if dmesg | grep -q WARNING
+then
+	dmesg
+	exit 1
+else
+	exit 0
+fi
+
 echo "PASS"
diff --git a/tools/testing/selftests/damon/huge_count_read_write.c b/tools/testing/selftests/damon/huge_count_read_write.c
new file mode 100644
index 000000000000..ad7a6b4cf338
--- /dev/null
+++ b/tools/testing/selftests/damon/huge_count_read_write.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Author: SeongJae Park <sj@kernel.org>
+ */
+
+#include <fcntl.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <stdio.h>
+
+void write_read_with_huge_count(char *file)
+{
+	int filedesc = open(file, O_RDWR);
+	char buf[25];
+	int ret;
+
+	printf("%s %s\n", __func__, file);
+	if (filedesc < 0) {
+		fprintf(stderr, "failed opening %s\n", file);
+		exit(1);
+	}
+
+	write(filedesc, "", 0xfffffffful);
+	perror("after write: ");
+	ret = read(filedesc, buf, 0xfffffffful);
+	perror("after read: ");
+	close(filedesc);
+}
+
+int main(int argc, char *argv[])
+{
+	if (argc != 2) {
+		fprintf(stderr, "Usage: %s <file>\n", argv[0]);
+		exit(1);
+	}
+	write_read_with_huge_count(argv[1]);
+
+	return 0;
+}
-- 
cgit v1.2.3


From 9ab3b0c8ef629f60ef25cb7634ad305315ae94d1 Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Fri, 10 Dec 2021 14:46:59 -0800
Subject: selftests/damon: split test cases

Currently, the single test program, debugfs.sh, contains all test cases
for DAMON.  When one of the cases fails, finding which case is failed
from the test log is not so easy, and all remaining tests will be
skipped.  To improve the situation, this commit splits the single
program into small test programs having their own names.

Link: https://lkml.kernel.org/r/20211201150440.1088-12-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: Brendan Higgins <brendanhiggins@google.com>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/testing/selftests/damon/Makefile             |   5 +-
 tools/testing/selftests/damon/_debugfs_common.sh   |  52 ++++++++++
 tools/testing/selftests/damon/debugfs_attrs.sh     | 111 +--------------------
 .../selftests/damon/debugfs_empty_targets.sh       |  13 +++
 .../damon/debugfs_huge_count_read_write.sh         |  22 ++++
 tools/testing/selftests/damon/debugfs_schemes.sh   |  19 ++++
 .../testing/selftests/damon/debugfs_target_ids.sh  |  19 ++++
 7 files changed, 129 insertions(+), 112 deletions(-)
 create mode 100644 tools/testing/selftests/damon/_debugfs_common.sh
 create mode 100644 tools/testing/selftests/damon/debugfs_empty_targets.sh
 create mode 100644 tools/testing/selftests/damon/debugfs_huge_count_read_write.sh
 create mode 100644 tools/testing/selftests/damon/debugfs_schemes.sh
 create mode 100644 tools/testing/selftests/damon/debugfs_target_ids.sh

(limited to 'tools')

diff --git a/tools/testing/selftests/damon/Makefile b/tools/testing/selftests/damon/Makefile
index f0aa954b5d13..937d36ae9a69 100644
--- a/tools/testing/selftests/damon/Makefile
+++ b/tools/testing/selftests/damon/Makefile
@@ -3,7 +3,8 @@
 
 TEST_GEN_FILES += huge_count_read_write
 
-TEST_FILES = _chk_dependency.sh
-TEST_PROGS = debugfs_attrs.sh
+TEST_FILES = _chk_dependency.sh _debugfs_common.sh
+TEST_PROGS = debugfs_attrs.sh debugfs_schemes.sh debugfs_target_ids.sh
+TEST_PROGS += debugfs_empty_targets.sh debugfs_huge_count_read_write.sh
 
 include ../lib.mk
diff --git a/tools/testing/selftests/damon/_debugfs_common.sh b/tools/testing/selftests/damon/_debugfs_common.sh
new file mode 100644
index 000000000000..48989d4813ae
--- /dev/null
+++ b/tools/testing/selftests/damon/_debugfs_common.sh
@@ -0,0 +1,52 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+test_write_result() {
+	file=$1
+	content=$2
+	orig_content=$3
+	expect_reason=$4
+	expected=$5
+
+	echo "$content" > "$file"
+	if [ $? -ne "$expected" ]
+	then
+		echo "writing $content to $file doesn't return $expected"
+		echo "expected because: $expect_reason"
+		echo "$orig_content" > "$file"
+		exit 1
+	fi
+}
+
+test_write_succ() {
+	test_write_result "$1" "$2" "$3" "$4" 0
+}
+
+test_write_fail() {
+	test_write_result "$1" "$2" "$3" "$4" 1
+}
+
+test_content() {
+	file=$1
+	orig_content=$2
+	expected=$3
+	expect_reason=$4
+
+	content=$(cat "$file")
+	if [ "$content" != "$expected" ]
+	then
+		echo "reading $file expected $expected but $content"
+		echo "expected because: $expect_reason"
+		echo "$orig_content" > "$file"
+		exit 1
+	fi
+}
+
+source ./_chk_dependency.sh
+
+damon_onoff="$DBGFS/monitor_on"
+if [ $(cat "$damon_onoff") = "on" ]
+then
+	echo "monitoring is on"
+	exit $ksft_skip
+fi
diff --git a/tools/testing/selftests/damon/debugfs_attrs.sh b/tools/testing/selftests/damon/debugfs_attrs.sh
index 23a7b48ca7d3..902e312bca89 100644
--- a/tools/testing/selftests/damon/debugfs_attrs.sh
+++ b/tools/testing/selftests/damon/debugfs_attrs.sh
@@ -1,57 +1,7 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
-test_write_result() {
-	file=$1
-	content=$2
-	orig_content=$3
-	expect_reason=$4
-	expected=$5
-
-	echo "$content" > "$file"
-	if [ $? -ne "$expected" ]
-	then
-		echo "writing $content to $file doesn't return $expected"
-		echo "expected because: $expect_reason"
-		echo "$orig_content" > "$file"
-		exit 1
-	fi
-}
-
-test_write_succ() {
-	test_write_result "$1" "$2" "$3" "$4" 0
-}
-
-test_write_fail() {
-	test_write_result "$1" "$2" "$3" "$4" 1
-}
-
-test_content() {
-	file=$1
-	orig_content=$2
-	expected=$3
-	expect_reason=$4
-
-	content=$(cat "$file")
-	if [ "$content" != "$expected" ]
-	then
-		echo "reading $file expected $expected but $content"
-		echo "expected because: $expect_reason"
-		echo "$orig_content" > "$file"
-		exit 1
-	fi
-}
-
-source ./_chk_dependency.sh
-
-ksft_skip=4
-
-damon_onoff="$DBGFS/monitor_on"
-if [ $(cat "$damon_onoff") = "on" ]
-then
-	echo "monitoring is on"
-	exit $ksft_skip
-fi
+source _debugfs_common.sh
 
 # Test attrs file
 # ===============
@@ -65,62 +15,3 @@ test_write_fail "$file" "1 2 3 5 4" "$orig_content" \
 	"min_nr_regions > max_nr_regions"
 test_content "$file" "$orig_content" "1 2 3 4 5" "successfully written"
 echo "$orig_content" > "$file"
-
-# Test schemes file
-# =================
-
-file="$DBGFS/schemes"
-orig_content=$(cat "$file")
-
-test_write_succ "$file" "1 2 3 4 5 6 4 0 0 0 1 2 3 1 100 3 2 1" \
-	"$orig_content" "valid input"
-test_write_fail "$file" "1 2
-3 4 5 6 3 0 0 0 1 2 3 1 100 3 2 1" "$orig_content" "multi lines"
-test_write_succ "$file" "" "$orig_content" "disabling"
-test_write_fail "$file" "2 1 2 1 10 1 3 10 1 1 1 1 1 1 1 1 2 3" \
-	"$orig_content" "wrong condition ranges"
-echo "$orig_content" > "$file"
-
-# Test target_ids file
-# ====================
-
-file="$DBGFS/target_ids"
-orig_content=$(cat "$file")
-
-test_write_succ "$file" "1 2 3 4" "$orig_content" "valid input"
-test_write_succ "$file" "1 2 abc 4" "$orig_content" "still valid input"
-test_content "$file" "$orig_content" "1 2" "non-integer was there"
-test_write_succ "$file" "abc 2 3" "$orig_content" "the file allows wrong input"
-test_content "$file" "$orig_content" "" "wrong input written"
-test_write_succ "$file" "" "$orig_content" "empty input"
-test_content "$file" "$orig_content" "" "empty input written"
-echo "$orig_content" > "$file"
-
-# Test empty targets case
-# =======================
-
-orig_target_ids=$(cat "$DBGFS/target_ids")
-echo "" > "$DBGFS/target_ids"
-orig_monitor_on=$(cat "$DBGFS/monitor_on")
-test_write_fail "$DBGFS/monitor_on" "on" "orig_monitor_on" "empty target ids"
-echo "$orig_target_ids" > "$DBGFS/target_ids"
-
-# Test huge count read write
-# ==========================
-
-dmesg -C
-
-for file in "$DBGFS/"*
-do
-	./huge_count_read_write "$file"
-done
-
-if dmesg | grep -q WARNING
-then
-	dmesg
-	exit 1
-else
-	exit 0
-fi
-
-echo "PASS"
diff --git a/tools/testing/selftests/damon/debugfs_empty_targets.sh b/tools/testing/selftests/damon/debugfs_empty_targets.sh
new file mode 100644
index 000000000000..87aff8083822
--- /dev/null
+++ b/tools/testing/selftests/damon/debugfs_empty_targets.sh
@@ -0,0 +1,13 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source _debugfs_common.sh
+
+# Test empty targets case
+# =======================
+
+orig_target_ids=$(cat "$DBGFS/target_ids")
+echo "" > "$DBGFS/target_ids"
+orig_monitor_on=$(cat "$DBGFS/monitor_on")
+test_write_fail "$DBGFS/monitor_on" "on" "orig_monitor_on" "empty target ids"
+echo "$orig_target_ids" > "$DBGFS/target_ids"
diff --git a/tools/testing/selftests/damon/debugfs_huge_count_read_write.sh b/tools/testing/selftests/damon/debugfs_huge_count_read_write.sh
new file mode 100644
index 000000000000..922cadac2950
--- /dev/null
+++ b/tools/testing/selftests/damon/debugfs_huge_count_read_write.sh
@@ -0,0 +1,22 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source _debugfs_common.sh
+
+# Test huge count read write
+# ==========================
+
+dmesg -C
+
+for file in "$DBGFS/"*
+do
+	./huge_count_read_write "$file"
+done
+
+if dmesg | grep -q WARNING
+then
+	dmesg
+	exit 1
+else
+	exit 0
+fi
diff --git a/tools/testing/selftests/damon/debugfs_schemes.sh b/tools/testing/selftests/damon/debugfs_schemes.sh
new file mode 100644
index 000000000000..5b39ab44731c
--- /dev/null
+++ b/tools/testing/selftests/damon/debugfs_schemes.sh
@@ -0,0 +1,19 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source _debugfs_common.sh
+
+# Test schemes file
+# =================
+
+file="$DBGFS/schemes"
+orig_content=$(cat "$file")
+
+test_write_succ "$file" "1 2 3 4 5 6 4 0 0 0 1 2 3 1 100 3 2 1" \
+	"$orig_content" "valid input"
+test_write_fail "$file" "1 2
+3 4 5 6 3 0 0 0 1 2 3 1 100 3 2 1" "$orig_content" "multi lines"
+test_write_succ "$file" "" "$orig_content" "disabling"
+test_write_fail "$file" "2 1 2 1 10 1 3 10 1 1 1 1 1 1 1 1 2 3" \
+	"$orig_content" "wrong condition ranges"
+echo "$orig_content" > "$file"
diff --git a/tools/testing/selftests/damon/debugfs_target_ids.sh b/tools/testing/selftests/damon/debugfs_target_ids.sh
new file mode 100644
index 000000000000..49aeabdb0aae
--- /dev/null
+++ b/tools/testing/selftests/damon/debugfs_target_ids.sh
@@ -0,0 +1,19 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source _debugfs_common.sh
+
+# Test target_ids file
+# ====================
+
+file="$DBGFS/target_ids"
+orig_content=$(cat "$file")
+
+test_write_succ "$file" "1 2 3 4" "$orig_content" "valid input"
+test_write_succ "$file" "1 2 abc 4" "$orig_content" "still valid input"
+test_content "$file" "$orig_content" "1 2" "non-integer was there"
+test_write_succ "$file" "abc 2 3" "$orig_content" "the file allows wrong input"
+test_content "$file" "$orig_content" "" "wrong input written"
+test_write_succ "$file" "" "$orig_content" "empty input"
+test_content "$file" "$orig_content" "" "empty input written"
+echo "$orig_content" > "$file"
-- 
cgit v1.2.3


From c897899752478d4c905c56f2b54b99ba82b34e13 Mon Sep 17 00:00:00 2001
From: German Gomez <german.gomez@arm.com>
Date: Wed, 1 Dec 2021 12:33:29 +0000
Subject: perf tools: Prevent out-of-bounds access to registers

The size of the cache of register values is arch-dependant
(PERF_REGS_MAX). This has the potential of causing an out-of-bounds
access in the function "perf_reg_value" if the local architecture
contains less registers than the one the perf.data file was recorded on.

Since the maximum number of registers is bound by the bitmask "u64
cache_mask", and the size of the cache when running under x86 systems is
64 already, fix the size to 64 and add a range-check to the function
"perf_reg_value" to prevent out-of-bounds access.

Reported-by: Alexandre Truong <alexandre.truong@arm.com>
Reviewed-by: Kajol Jain <kjain@linux.ibm.com>
Signed-off-by: German Gomez <german.gomez@arm.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-csky@vger.kernel.org
Cc: linux-riscv@lists.infradead.org
Link: https://lore.kernel.org/r/20211201123334.679131-2-german.gomez@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/event.h     | 5 ++++-
 tools/perf/util/perf_regs.c | 3 +++
 2 files changed, 7 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 95ffed66369c..c59331eea1d9 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -44,13 +44,16 @@ struct perf_event_attr;
 /* perf sample has 16 bits size limit */
 #define PERF_SAMPLE_MAX_SIZE (1 << 16)
 
+/* number of register is bound by the number of bits in regs_dump::mask (64) */
+#define PERF_SAMPLE_REGS_CACHE_SIZE (8 * sizeof(u64))
+
 struct regs_dump {
 	u64 abi;
 	u64 mask;
 	u64 *regs;
 
 	/* Cached values/mask filled by first register access. */
-	u64 cache_regs[PERF_REGS_MAX];
+	u64 cache_regs[PERF_SAMPLE_REGS_CACHE_SIZE];
 	u64 cache_mask;
 };
 
diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c
index 5ee47ae1509c..06a7461ba864 100644
--- a/tools/perf/util/perf_regs.c
+++ b/tools/perf/util/perf_regs.c
@@ -25,6 +25,9 @@ int perf_reg_value(u64 *valp, struct regs_dump *regs, int id)
 	int i, idx = 0;
 	u64 mask = regs->mask;
 
+	if ((u64)id >= PERF_SAMPLE_REGS_CACHE_SIZE)
+		return -EINVAL;
+
 	if (regs->cache_mask & (1ULL << id))
 		goto out;
 
-- 
cgit v1.2.3


From 057ae59f5a1d924511beb1b09f395bdb316cfd03 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 10 Dec 2021 18:22:57 +0200
Subject: perf intel-pt: Fix some PGE (packet generation enable/control flow
 packets) usage

Packet generation enable (PGE) refers to whether control flow (COFI)
packets are being produced.

PGE may be false even when branch-tracing is enabled, due to being
out-of-context, or outside a filter address range.  Fix some missing PGE
usage.

Fixes: 7c1b16ba0e26e6 ("perf intel-pt: Add support for decoding FUP/TIP only")
Fixes: 839598176b0554 ("perf intel-pt: Allow decoding with branch tracing disabled")
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: stable@vger.kernel.org # v5.15+
Link: https://lore.kernel.org/r/20211210162303.2288710-2-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/intel-pt-decoder/intel-pt-decoder.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index 5f83937bf8f3..6f6f163161a9 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -2678,6 +2678,7 @@ static int intel_pt_hop_trace(struct intel_pt_decoder *decoder, bool *no_tip, in
 		return HOP_IGNORE;
 
 	case INTEL_PT_TIP_PGD:
+		decoder->pge = false;
 		if (!decoder->packet.count) {
 			intel_pt_set_nr(decoder);
 			return HOP_IGNORE;
@@ -2707,7 +2708,7 @@ static int intel_pt_hop_trace(struct intel_pt_decoder *decoder, bool *no_tip, in
 		intel_pt_set_ip(decoder);
 		if (intel_pt_fup_event(decoder))
 			return HOP_RETURN;
-		if (!decoder->branch_enable)
+		if (!decoder->branch_enable || !decoder->pge)
 			*no_tip = true;
 		if (*no_tip) {
 			decoder->state.type = INTEL_PT_INSTRUCTION;
@@ -2897,7 +2898,7 @@ static bool intel_pt_psb_with_fup(struct intel_pt_decoder *decoder, int *err)
 {
 	struct intel_pt_psb_info data = { .fup = false };
 
-	if (!decoder->branch_enable || !decoder->pge)
+	if (!decoder->branch_enable)
 		return false;
 
 	intel_pt_pkt_lookahead(decoder, intel_pt_psb_lookahead_cb, &data);
@@ -2999,7 +3000,7 @@ next:
 				break;
 			}
 			intel_pt_set_last_ip(decoder);
-			if (!decoder->branch_enable) {
+			if (!decoder->branch_enable || !decoder->pge) {
 				decoder->ip = decoder->last_ip;
 				if (intel_pt_fup_event(decoder))
 					return 0;
-- 
cgit v1.2.3


From ad106a26aef3a95ac7ca88d033b431661ba346ce Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 10 Dec 2021 18:22:58 +0200
Subject: perf intel-pt: Fix sync state when a PSB (synchronization) packet is
 found

When syncing, it may be that branch packet generation is not enabled at
that point, in which case there will not immediately be a control-flow
packet, so some packets before a control flow packet turns up, get
ignored.  However, the decoder is in sync as soon as a PSB is found, so
the state should be set accordingly.

Fixes: f4aa081949e7b6 ("perf tools: Add Intel PT decoder")
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: stable@vger.kernel.org # v5.15+
Link: https://lore.kernel.org/r/20211210162303.2288710-3-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/intel-pt-decoder/intel-pt-decoder.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index 6f6f163161a9..bddf98123dc3 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -3608,7 +3608,7 @@ static int intel_pt_sync(struct intel_pt_decoder *decoder)
 	}
 
 	decoder->have_last_ip = true;
-	decoder->pkt_state = INTEL_PT_STATE_NO_IP;
+	decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
 
 	err = intel_pt_walk_psb(decoder);
 	if (err)
-- 
cgit v1.2.3


From 4c761d805bb2d2ead1b9baaba75496152b394c80 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 10 Dec 2021 18:22:59 +0200
Subject: perf intel-pt: Fix intel_pt_fup_event() assumptions about setting
 state type

intel_pt_fup_event() assumes it can overwrite the state type if there has
been an FUP event, but this is an unnecessary and unexpected constraint on
callers.

Fix by touching only the state type flags that are affected by an FUP
event.

Fixes: a472e65fc490a ("perf intel-pt: Add decoder support for ptwrite and power event packets")
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: stable@vger.kernel.org # v5.15+
Link: https://lore.kernel.org/r/20211210162303.2288710-4-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../perf/util/intel-pt-decoder/intel-pt-decoder.c  | 32 +++++++++-------------
 1 file changed, 13 insertions(+), 19 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index bddf98123dc3..16fbbf07e367 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -1205,61 +1205,55 @@ out_no_progress:
 
 static bool intel_pt_fup_event(struct intel_pt_decoder *decoder)
 {
+	enum intel_pt_sample_type type = decoder->state.type;
 	bool ret = false;
 
+	decoder->state.type &= ~INTEL_PT_BRANCH;
+
 	if (decoder->set_fup_tx_flags) {
 		decoder->set_fup_tx_flags = false;
 		decoder->tx_flags = decoder->fup_tx_flags;
-		decoder->state.type = INTEL_PT_TRANSACTION;
+		decoder->state.type |= INTEL_PT_TRANSACTION;
 		if (decoder->fup_tx_flags & INTEL_PT_ABORT_TX)
 			decoder->state.type |= INTEL_PT_BRANCH;
-		decoder->state.from_ip = decoder->ip;
-		decoder->state.to_ip = 0;
 		decoder->state.flags = decoder->fup_tx_flags;
-		return true;
+		ret = true;
 	}
 	if (decoder->set_fup_ptw) {
 		decoder->set_fup_ptw = false;
-		decoder->state.type = INTEL_PT_PTW;
+		decoder->state.type |= INTEL_PT_PTW;
 		decoder->state.flags |= INTEL_PT_FUP_IP;
-		decoder->state.from_ip = decoder->ip;
-		decoder->state.to_ip = 0;
 		decoder->state.ptw_payload = decoder->fup_ptw_payload;
-		return true;
+		ret = true;
 	}
 	if (decoder->set_fup_mwait) {
 		decoder->set_fup_mwait = false;
-		decoder->state.type = INTEL_PT_MWAIT_OP;
-		decoder->state.from_ip = decoder->ip;
-		decoder->state.to_ip = 0;
+		decoder->state.type |= INTEL_PT_MWAIT_OP;
 		decoder->state.mwait_payload = decoder->fup_mwait_payload;
 		ret = true;
 	}
 	if (decoder->set_fup_pwre) {
 		decoder->set_fup_pwre = false;
 		decoder->state.type |= INTEL_PT_PWR_ENTRY;
-		decoder->state.type &= ~INTEL_PT_BRANCH;
-		decoder->state.from_ip = decoder->ip;
-		decoder->state.to_ip = 0;
 		decoder->state.pwre_payload = decoder->fup_pwre_payload;
 		ret = true;
 	}
 	if (decoder->set_fup_exstop) {
 		decoder->set_fup_exstop = false;
 		decoder->state.type |= INTEL_PT_EX_STOP;
-		decoder->state.type &= ~INTEL_PT_BRANCH;
 		decoder->state.flags |= INTEL_PT_FUP_IP;
-		decoder->state.from_ip = decoder->ip;
-		decoder->state.to_ip = 0;
 		ret = true;
 	}
 	if (decoder->set_fup_bep) {
 		decoder->set_fup_bep = false;
 		decoder->state.type |= INTEL_PT_BLK_ITEMS;
-		decoder->state.type &= ~INTEL_PT_BRANCH;
+		ret = true;
+	}
+	if (ret) {
 		decoder->state.from_ip = decoder->ip;
 		decoder->state.to_ip = 0;
-		ret = true;
+	} else {
+		decoder->state.type = type;
 	}
 	return ret;
 }
-- 
cgit v1.2.3


From c79ee2b2160909889df67c8801352d3e69d43a1a Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 10 Dec 2021 18:23:00 +0200
Subject: perf intel-pt: Fix state setting when receiving overflow (OVF) packet

An overflow (OVF packet) is treated as an error because it represents a
loss of trace data, but there is no loss of synchronization, so the packet
state should be INTEL_PT_STATE_IN_SYNC not INTEL_PT_STATE_ERR_RESYNC.

To support that, some additional variables must be reset, and the FUP
packet that may follow OVF is treated as an FUP event.

Fixes: f4aa081949e7b6 ("perf tools: Add Intel PT decoder")
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: stable@vger.kernel.org # v5.15+
Link: https://lore.kernel.org/r/20211210162303.2288710-5-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../perf/util/intel-pt-decoder/intel-pt-decoder.c  | 32 +++++++++++++++++++---
 1 file changed, 28 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index 16fbbf07e367..845b0ca866a4 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -1249,6 +1249,20 @@ static bool intel_pt_fup_event(struct intel_pt_decoder *decoder)
 		decoder->state.type |= INTEL_PT_BLK_ITEMS;
 		ret = true;
 	}
+	if (decoder->overflow) {
+		decoder->overflow = false;
+		if (!ret && !decoder->pge) {
+			if (decoder->hop) {
+				decoder->state.type = 0;
+				decoder->pkt_state = INTEL_PT_STATE_RESAMPLE;
+			}
+			decoder->pge = true;
+			decoder->state.type |= INTEL_PT_BRANCH | INTEL_PT_TRACE_BEGIN;
+			decoder->state.from_ip = 0;
+			decoder->state.to_ip = decoder->ip;
+			return true;
+		}
+	}
 	if (ret) {
 		decoder->state.from_ip = decoder->ip;
 		decoder->state.to_ip = 0;
@@ -1602,7 +1616,16 @@ static int intel_pt_overflow(struct intel_pt_decoder *decoder)
 	intel_pt_clear_tx_flags(decoder);
 	intel_pt_set_nr(decoder);
 	decoder->timestamp_insn_cnt = 0;
-	decoder->pkt_state = INTEL_PT_STATE_ERR_RESYNC;
+	decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
+	decoder->state.from_ip = decoder->ip;
+	decoder->ip = 0;
+	decoder->pge = false;
+	decoder->set_fup_tx_flags = false;
+	decoder->set_fup_ptw = false;
+	decoder->set_fup_mwait = false;
+	decoder->set_fup_pwre = false;
+	decoder->set_fup_exstop = false;
+	decoder->set_fup_bep = false;
 	decoder->overflow = true;
 	return -EOVERFLOW;
 }
@@ -2957,6 +2980,7 @@ next:
 
 		case INTEL_PT_TIP_PGE: {
 			decoder->pge = true;
+			decoder->overflow = false;
 			intel_pt_mtc_cyc_cnt_pge(decoder);
 			intel_pt_set_nr(decoder);
 			if (decoder->packet.count == 0) {
@@ -3462,10 +3486,10 @@ static int intel_pt_sync_ip(struct intel_pt_decoder *decoder)
 	decoder->set_fup_pwre = false;
 	decoder->set_fup_exstop = false;
 	decoder->set_fup_bep = false;
+	decoder->overflow = false;
 
 	if (!decoder->branch_enable) {
 		decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
-		decoder->overflow = false;
 		decoder->state.type = 0; /* Do not have a sample */
 		return 0;
 	}
@@ -3480,7 +3504,6 @@ static int intel_pt_sync_ip(struct intel_pt_decoder *decoder)
 		decoder->pkt_state = INTEL_PT_STATE_RESAMPLE;
 	else
 		decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
-	decoder->overflow = false;
 
 	decoder->state.from_ip = 0;
 	decoder->state.to_ip = decoder->ip;
@@ -3699,7 +3722,8 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder)
 
 	if (err) {
 		decoder->state.err = intel_pt_ext_err(err);
-		decoder->state.from_ip = decoder->ip;
+		if (err != -EOVERFLOW)
+			decoder->state.from_ip = decoder->ip;
 		intel_pt_update_sample_time(decoder);
 		decoder->sample_tot_cyc_cnt = decoder->tot_cyc_cnt;
 		intel_pt_set_nr(decoder);
-- 
cgit v1.2.3


From a32e6c5da599dbf49e60622a4dfb5b9b40ece029 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 10 Dec 2021 18:23:01 +0200
Subject: perf intel-pt: Fix next 'err' value, walking trace

Code after label 'next:' in intel_pt_walk_trace() assumes 'err' is zero,
but it may not be, if arrived at via a 'goto'. Ensure it is zero.

Fixes: 7c1b16ba0e26e6 ("perf intel-pt: Add support for decoding FUP/TIP only")
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: stable@vger.kernel.org # v5.15+
Link: https://lore.kernel.org/r/20211210162303.2288710-6-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/intel-pt-decoder/intel-pt-decoder.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index 845b0ca866a4..75b504aed7f4 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -2942,6 +2942,7 @@ static int intel_pt_walk_trace(struct intel_pt_decoder *decoder)
 		if (err)
 			return err;
 next:
+		err = 0;
 		if (decoder->cyc_threshold) {
 			if (decoder->sample_cyc && last_packet_type != INTEL_PT_CYC)
 				decoder->sample_cyc = false;
-- 
cgit v1.2.3


From a882cc94971093e146ffa1163b140ad956236754 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 10 Dec 2021 18:23:02 +0200
Subject: perf intel-pt: Fix missing 'instruction' events with 'q' option

FUP packets contain IP information, which makes them also an 'instruction'
event in 'hop' mode i.e. the itrace 'q' option.  That wasn't happening, so
restructure the logic so that FUP events are added along with appropriate
'instruction' and 'branch' events.

Fixes: 7c1b16ba0e26e6 ("perf intel-pt: Add support for decoding FUP/TIP only")
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: stable@vger.kernel.org # v5.15+
Link: https://lore.kernel.org/r/20211210162303.2288710-7-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/intel-pt-decoder/intel-pt-decoder.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index 75b504aed7f4..0e013c2d9eb4 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -2683,6 +2683,8 @@ static int intel_pt_scan_for_psb(struct intel_pt_decoder *decoder);
 /* Hop mode: Ignore TNT, do not walk code, but get ip from FUPs and TIPs */
 static int intel_pt_hop_trace(struct intel_pt_decoder *decoder, bool *no_tip, int *err)
 {
+	*err = 0;
+
 	/* Leap from PSB to PSB, getting ip from FUP within PSB+ */
 	if (decoder->leap && !decoder->in_psb && decoder->packet.type != INTEL_PT_PSB) {
 		*err = intel_pt_scan_for_psb(decoder);
@@ -2723,18 +2725,21 @@ static int intel_pt_hop_trace(struct intel_pt_decoder *decoder, bool *no_tip, in
 		if (!decoder->packet.count)
 			return HOP_IGNORE;
 		intel_pt_set_ip(decoder);
-		if (intel_pt_fup_event(decoder))
-			return HOP_RETURN;
+		if (decoder->set_fup_mwait || decoder->set_fup_pwre)
+			*no_tip = true;
 		if (!decoder->branch_enable || !decoder->pge)
 			*no_tip = true;
 		if (*no_tip) {
 			decoder->state.type = INTEL_PT_INSTRUCTION;
 			decoder->state.from_ip = decoder->ip;
 			decoder->state.to_ip = 0;
+			intel_pt_fup_event(decoder);
 			return HOP_RETURN;
 		}
+		intel_pt_fup_event(decoder);
+		decoder->state.type |= INTEL_PT_INSTRUCTION | INTEL_PT_BRANCH;
 		*err = intel_pt_walk_fup_tip(decoder);
-		if (!*err)
+		if (!*err && decoder->state.to_ip)
 			decoder->pkt_state = INTEL_PT_STATE_RESAMPLE;
 		return HOP_RETURN;
 
-- 
cgit v1.2.3


From 6665b8e4836caa8023cbc7e53733acd234969c8c Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 10 Dec 2021 18:23:03 +0200
Subject: perf intel-pt: Fix error timestamp setting on the decoder error path

An error timestamp shows the last known timestamp for the queue, but this
is not updated on the error path. Fix by setting it.

Fixes: f4aa081949e7b6 ("perf tools: Add Intel PT decoder")
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: stable@vger.kernel.org # v5.15+
Link: https://lore.kernel.org/r/20211210162303.2288710-8-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/intel-pt.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 556a893508da..10c3187e4c5a 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -2565,6 +2565,7 @@ static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp)
 				ptq->sync_switch = false;
 				intel_pt_next_tid(pt, ptq);
 			}
+			ptq->timestamp = state->est_timestamp;
 			if (pt->synth_opts.errors) {
 				err = intel_ptq_synth_error(ptq, state);
 				if (err)
-- 
cgit v1.2.3


From 9937e8daab29d9e20de6b7bc56c76db7a4eeda69 Mon Sep 17 00:00:00 2001
From: Miaoqian Lin <linmq006@gmail.com>
Date: Sat, 11 Dec 2021 05:38:53 +0000
Subject: perf python: Fix NULL vs IS_ERR_OR_NULL() checking

The function trace_event__tp_format_id may return ERR_PTR(-ENOMEM).  Use
IS_ERR_OR_NULL to check tp_format.

Signed-off-by: Miaoqian Lin <linmq006@gmail.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Song Liu <song@kernel.org>
Link: http://lore.kernel.org/lkml/20211211053856.19827-1-linmq006@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/python.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 563a9ba8954f..7f782a31bda3 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -461,7 +461,7 @@ get_tracepoint_field(struct pyrf_event *pevent, PyObject *attr_name)
 		struct tep_event *tp_format;
 
 		tp_format = trace_event__tp_format_id(evsel->core.attr.config);
-		if (!tp_format)
+		if (IS_ERR_OR_NULL(tp_format))
 			return NULL;
 
 		evsel->tp_format = tp_format;
-- 
cgit v1.2.3